Articles | Volume 30, issue 16
https://doi.org/10.5194/hess-30-5373-2026
© Author(s) 2026. This work is distributed under
the Creative Commons Attribution 4.0 License.
the Creative Commons Attribution 4.0 License.
https://doi.org/10.5194/hess-30-5373-2026
© Author(s) 2026. This work is distributed under
the Creative Commons Attribution 4.0 License.
the Creative Commons Attribution 4.0 License.
Research article
| Highlight paper
| 
25 Aug 2026
Research article | Highlight paper |
| 25 Aug 2026
| 25 Aug 2026
Learning evaporative fraction with memory
Wenli Zhao
CORRESPONDING AUTHOR
Max Planck Institute for Biogeochemistry, Jena, Germany
Columbia University, New York, USA
ELLIS Jena Unit, Jena, Germany
Alexander J. Winkler
Max Planck Institute for Biogeochemistry, Jena, Germany
ELLIS Jena Unit, Jena, Germany
Markus Reichstein
Max Planck Institute for Biogeochemistry, Jena, Germany
ELLIS Jena Unit, Jena, Germany
Rene Orth
Max Planck Institute for Biogeochemistry, Jena, Germany
Faculty of Environment and Natural Resources, University of Freiburg, Freiburg, Germany
Pierre Gentine
Columbia University, New York, USA
Related authors
Wenli Zhao, Alexander J. Winkler, Markus Reichstein, Rene Orth, and Pierre Gentine
EGUsphere, https://doi.org/10.5194/egusphere-2025-365, https://doi.org/10.5194/egusphere-2025-365, 2025
Preprint archived
Short summary
Short summary
We developed a machine learning model that accounts for the memory effects of soil moisture and vegetation to predict Evaporative Fraction (EF) without relying on soil moisture as a direct input. The model accurately predicts EF during dry periods for the unseen sites, highlighting the key of meteorological memory effects. The learned memory effect related to rooting depth and soil water holding capacity could potentially serve as proxies for assessing the plant water stress.
Siyuan Wang, Hui Yang, Sujan Koirala, Maurizio Santoro, Anna Candotti, Ulrich Weber, Ranit De, Claire Robin, Felix Cremer, Matthias Forkel, Markus Reichstein, and Nuno Carvalhais
Earth Syst. Sci. Data, 18, 5895–5913, https://doi.org/10.5194/essd-18-5895-2026, https://doi.org/10.5194/essd-18-5895-2026, 2026
Short summary
Short summary
Forest disturbances are difficult to predict in models because they occur randomly. We discovered that the long-term rules of disturbance known as
regimeleave a unique footprint in a forest's spatial biomass patterns. We trained a model on millions of computer simulations to learn this link. By applying this model to detailed satellite biomass, we could read these patterns to infer the disturbance regime globally, helping make climate projections more accurate.
Xueyan Cheng, Chunhui Zhan, Martin G. De Kauwe, Anke Hildebrandt, and Rene Orth
Biogeosciences, 23, 5117–5131, https://doi.org/10.5194/bg-23-5117-2026, https://doi.org/10.5194/bg-23-5117-2026, 2026
Short summary
Short summary
Using long-term satellite greenness data and a machine-learning attribution approach, we assessed vegetation responses to wet and dry soil moisture extremes and identified their dominant drivers. Dry extremes caused widespread negative greenness anomalies mainly controlled by pre-extreme conditions and seasonal timing, while wet extremes showed more heterogeneous responses additionally shaped by climate and topography, highlighting contrasting ecosystem sensitivity to hydrological extremes.
Raf Antwerpen, Marco Tedesco, Pierre Gentine, Willem Jan van de Berg, and Xavier Fettweis
The Cryosphere, 20, 3131–3149, https://doi.org/10.5194/tc-20-3131-2026, https://doi.org/10.5194/tc-20-3131-2026, 2026
Short summary
Short summary
We study why Greenland ice melts faster by improving how ice brightness is represented. This is important because it controls how much sunlight is absorbed by the ice. Using satellite data and a new transparent machine learning method trained with climate model information, we capture how the shape of the ice sheet, temperature, and meltwater change ice brightness. Our approach outperforms existing climate models and can reduce uncertainty in future sea level rise projections.
Zavud Baghirov, Markus Reichstein, Basil Kraft, Bernhard Ahrens, Marco Körner, and Martin Jung
Geosci. Model Dev., 19, 4467–4496, https://doi.org/10.5194/gmd-19-4467-2026, https://doi.org/10.5194/gmd-19-4467-2026, 2026
Short summary
Short summary
We introduce a new global model that links how water and carbon move through land ecosystems. By combining process knowledge with artificial intelligence that learns from observations, we model daily changes in vegetation, water and carbon cycle processes. This model outperforms both purely data-driven and traditional process models, especially in dry and tropical regions. This advance could improve current understanding of water–carbon cycle relationships.
Hao Huang, Junguo Liu, Aifang Chen, Melissa Ruiz-Vásquez, and René Orth
Earth Syst. Sci. Data, 18, 3109–3124, https://doi.org/10.5194/essd-18-3109-2026, https://doi.org/10.5194/essd-18-3109-2026, 2026
Short summary
Short summary
Hydrological research benefits from a growing number and diversity of datasets. However, the consistency across the increasing suite of datasets is unclear, limiting the comparability of findings derived from different datasets and variables. We find overall low consistency of numerous state-of-the-art precipitation, evapotranspiration, runoff, and soil moisture datasets in terms of the water balance. Meanwhile, the water balance consistency varies across space, sources, variables, and time.
Jincheng Wu, Philippe Ciais, Yuanyuan Huang, Jianing Fang, Pierre Gentine, Yidi Xu, Daniel Goll, Fayong Liu, Xiaomeng Du, Rui Ma, Nan Meng, Mengjie Han, Jinlong Zang, Runda Jiang, and Wei Li
EGUsphere, https://doi.org/10.5194/egusphere-2026-2241, https://doi.org/10.5194/egusphere-2026-2241, 2026
Short summary
Short summary
Predicting land carbon sinks remains a challenge because carbon allocation and turnover are poorly constrained in terrestrial biosphere models. We used a differentiable framework to jointly assimilate daily satellite data and long-term boreal forest growth trajectories. This approach significantly reduced biomass simulation errors. We found that boreal forests sustain biomass through long carbon residence times rather than high allocation rates, making them highly vulnerable to warming.
Olivia Hau, Matthias Forkel, Wolfgang Buermann, Johanna Kranz, Mirco Migliavacca, Ulrich Weber, and Alexander Josef Winkler
EGUsphere, https://doi.org/10.5194/egusphere-2026-910, https://doi.org/10.5194/egusphere-2026-910, 2026
Short summary
Short summary
Shifts in spring and autumn growth due to climate warming change how plants reflect sunlight and release heat and moisture into the air, modulating surface warming. The strength of these effects and their regional variability remain poorly understood. Using satellite and climate data, we show that earlier spring growth increases moisture release, especially in forests, while autumn changes are smaller and less consistent. Impacts on land-atmosphere interactions vary by ecosystem and data source.
Samuel Upton, Markus Reichstein, Wouter Peters, Santiago Botía, Jacob A. Nelson, Sophia Walther, Martin Jung, Fabian Gans, László Haszpra, and Ana Bastos
Atmos. Chem. Phys., 26, 2561–2595, https://doi.org/10.5194/acp-26-2561-2026, https://doi.org/10.5194/acp-26-2561-2026, 2026
Short summary
Short summary
We create a hybrid ecosystem-level carbon flux model using both eddy-covariance observations and observations of the atmospheric mole fraction of CO2 at three tall-tower observatories. Our study uses an atmospheric transport model (STILT) to connect the atmospheric signal to the ecosystem-level model. We show that this inclusion of atmospheric information meaningfully improves the model's representation of the interannual variability of the global net flux of CO2.
Mazen Nakad, Mahmoud Mbarak, Jihad Karaki, Tehreem Qureshi, Matteo Detto, Benjamin I. Cook, Marcos Longo, Géraldine Derroire, Xiangtao Xu, Jeremy Lichstein, Zong-Liang Yang, Pierre Gentine, and Ensheng Weng
EGUsphere, https://doi.org/10.5194/egusphere-2026-145, https://doi.org/10.5194/egusphere-2026-145, 2026
Short summary
Short summary
Because long-term drought and heat experiments are hard to run in tropical forests, we used a computer model to test how less rain and warmer, drier air affect forest growth and water loss at three sites. Forest productivity stayed stable until rainfall dropped below a threshold, but warmer air reduced carbon uptake even when soils were moist. Persistent heat and drought caused far larger declines than brief pulses, raising risks for future carbon storage.
Daju Wang, Ruowen Yang, Lei Cai, Pierre Gentine, César Terrer, Shuli Niu, Mirco Migliavacca, Wenping Yuan, Ryunosuke Tateno, Junlan Xiao, Josep Peñuelas, Caixian Tang, Yongshuo H. Fu, and Weiyu Shi
EGUsphere, https://doi.org/10.5194/egusphere-2026-296, https://doi.org/10.5194/egusphere-2026-296, 2026
This preprint is open for discussion and under review for Biogeosciences (BG).
Short summary
Short summary
Soil respiration is a major CO2 source, yet its response to vary nitrogen addition levels remains unclear. Using global data from 226 sites, we found moderate N addition has negligible or slightly positive effects, whereas high N addition consistently suppresses total and microbial respiration. These findings were incorporated into the CLM5 model, improving predictions of soil respiration and carbon storage. Our work elucidates how N deposition alters soil carbon processes and climate feedbacks.
Na Li, Sebastian Sippel, Nora Linscheid, Miguel D. Mahecha, Markus Reichstein, and Ana Bastos
Biogeosciences, 23, 767–792, https://doi.org/10.5194/bg-23-767-2026, https://doi.org/10.5194/bg-23-767-2026, 2026
Short summary
Short summary
We study when anthropogenic signal becomes detectable in the global land carbon sink, which has risen since the 1950s due to CO₂ fertilization and mid- to high-latitude warming. The signal emerges earlier at the global than at regional scales. Future scenarios (2016–2100) take longer to detect than the historical period (1851–2014) because the signal is weaker relative to larger natural variability. Removing circulation-induced variability with dynamical adjustment shortens the detection time.
Victor Brovkin, Benjamin M. Sanderson, Noel G. Brizuela, Tomohiro Hajima, Tatiana Ilyina, Chris D. Jones, Charles Koven, David Lawrence, Peter Lawrence, Hongmei Li, Spencer Liddcoat, Anastasia Romanou, Roland Séférian, Lori T. Sentman, Abigail L. S. Swann, Jerry Tjiputra, Tilo Ziehn, and Alexander J. Winkler
Earth Syst. Dynam., 16, 2021–2034, https://doi.org/10.5194/esd-16-2021-2025, https://doi.org/10.5194/esd-16-2021-2025, 2025
Short summary
Short summary
Idealized experiments with Earth system models provide a basis for understanding the response of the carbon cycle to emissions. We show that most models exhibit a quasi-linear relationship between cumulative carbon uptake on land and in the ocean and hypothesize that this relationship does not depend on emission pathways. We reduce the coupled system to only one differential equation, which represents a powerful simplification of the Earth system dynamics as a function of fossil fuel emissions.
Josephin Kroll, Ruth Stephan, Andrew F. Feldman, Diego G. Miralles, and Rene Orth
EGUsphere, https://doi.org/10.5194/egusphere-2025-4391, https://doi.org/10.5194/egusphere-2025-4391, 2025
Short summary
Short summary
In this study, we investigate contributors to and trends in the co-occurrence of heat and dryness. We find radiation, representing the atmospheric forcing, inducing high temperatures during dryness. For the persistence of heat, evaporation as the land contribution and the consequent effect on sensible heat flux becomes more important. While the co-occurrence of high temperatures and dryness shows a strong increase over 1980–2010, the atmospheric and land contributions show no clear trend.
Basil Kraft, Jacob A. Nelson, Sophia Walther, Fabian Gans, Ulrich Weber, Gregory Duveiller, Markus Reichstein, Weijie Zhang, Marc Rußwurm, Devis Tuia, Marco Körner, Zayd Hamdi, and Martin Jung
Biogeosciences, 22, 3965–3987, https://doi.org/10.5194/bg-22-3965-2025, https://doi.org/10.5194/bg-22-3965-2025, 2025
Short summary
Short summary
This study evaluates machine learning approaches for upscaling evapotranspiration from the site to the global scale. Sequential models capture temporal dynamics better, especially with precipitation data, but all models show biases in data-scarce regions. Improved upscaling requires richer training data, informed covariate selection, and physical constraints to enhance robustness and reduce extrapolation errors.
Theertha Kariyathan, Ana Bastos, Markus Reichstein, Wouter Peters, and Julia Marshall
Atmos. Chem. Phys., 25, 7863–7878, https://doi.org/10.5194/acp-25-7863-2025, https://doi.org/10.5194/acp-25-7863-2025, 2025
Short summary
Short summary
The carbon uptake period (CUP) is the time period when land absorbs more CO2 than it emits. While atmospheric CO2 mole fraction measurements can be used to assess CUP changes, atmospheric transport and asynchronous timing across regions reduce the accuracy of the estimates. Forward model experiments show that only ~ 50 % of prescribed shifts in CUP timing applied to surface fluxes (ΔCUPNEE) are captured in simulated CO2 mole fraction data at monitoring sites like the Barrow Atmospheric Baseline Observatory.
Laura Nadolski, Tarek S. El-Madany, Jacob Nelson, Arnaud Carrara, Gerardo Moreno, Richard Nair, Yunpeng Luo, Anke Hildebrandt, Victor Rolo, Markus Reichstein, and Sung-Ching Lee
Biogeosciences, 22, 2935–2958, https://doi.org/10.5194/bg-22-2935-2025, https://doi.org/10.5194/bg-22-2935-2025, 2025
Short summary
Short summary
Semi-arid ecosystems are crucial for Earth's carbon balance and are sensitive to changes in nitrogen (N) and phosphorus (P) levels. Their carbon dynamics are complex and not fully understood. We studied how long-term nutrient changes affect carbon exchange. In summer, the addition of N+P changed plant composition and productivity. In transitional seasons, carbon exchange was less weather-dependent with N. The addition of N and N+P increases carbon-exchange variability, driven by grass greenness.
Yigit Uckan, Melissa Ruiz-Vásquez, Kelley De Polt, and René Orth
Earth Syst. Dynam., 16, 869–889, https://doi.org/10.5194/esd-16-869-2025, https://doi.org/10.5194/esd-16-869-2025, 2025
Short summary
Short summary
We analyze drivers of hot temperature extremes, focusing on both atmospheric and land-surface factors. Using observation-based data and an analogue-based approach, we find that geopotential height at 500 hPa is the most significant driver worldwide at daily and weekly timescales. Surface net radiation and evaporative fraction play relevant roles at the daily scale and wind at the weekly timescale. The driver influence varies by region, related to differences in climate regimes and land cover.
Friedrich J. Bohn, Ana Bastos, Romina Martin, Anja Rammig, Niak Sian Koh, Giles B. Sioen, Bram Buscher, Louise Carver, Fabrice DeClerck, Moritz Drupp, Robert Fletcher, Matthew Forrest, Alexandros Gasparatos, Alex Godoy-Faúndez, Gregor Hagedorn, Martin C. Hänsel, Jessica Hetzer, Thomas Hickler, Cornelia B. Krug, Stasja Koot, Xiuzhen Li, Amy Luers, Shelby Matevich, H. Damon Matthews, Ina C. Meier, Mirco Migliavacca, Awaz Mohamed, Sungmin O, David Obura, Ben Orlove, Rene Orth, Laura Pereira, Markus Reichstein, Lerato Thakholi, Peter H. Verburg, and Yuki Yoshida
Biogeosciences, 22, 2425–2460, https://doi.org/10.5194/bg-22-2425-2025, https://doi.org/10.5194/bg-22-2425-2025, 2025
Short summary
Short summary
An interdisciplinary collaboration of 36 international researchers from 35 institutions highlights recent findings in biosphere research. Within eight themes, they discuss issues arising from climate change and other anthropogenic stressors and highlight the co-benefits of nature-based solutions and ecosystem services. Based on an analysis of these eight topics, we have synthesized four overarching insights.
Zavud Baghirov, Martin Jung, Markus Reichstein, Marco Körner, and Basil Kraft
Geosci. Model Dev., 18, 2921–2943, https://doi.org/10.5194/gmd-18-2921-2025, https://doi.org/10.5194/gmd-18-2921-2025, 2025
Short summary
Short summary
We use an innovative approach to studying the Earth's water cycle by integrating advanced machine learning techniques with a traditional water cycle model. Our model is designed to learn from observational data, with a particular emphasis on understanding the influence of vegetation on water movement. By closely aligning with real-world observations, our model offers new possibilities for enhancing our understanding of the water cycle and its interactions with vegetation.
Marleen Pallandt, Marion Schrumpf, Holger Lange, Markus Reichstein, Lin Yu, and Bernhard Ahrens
Biogeosciences, 22, 1907–1928, https://doi.org/10.5194/bg-22-1907-2025, https://doi.org/10.5194/bg-22-1907-2025, 2025
Short summary
Short summary
As soils warm due to climate change, soil organic carbon (SOC) decomposes faster due to increased microbial activity, given sufficient available moisture. We modelled the microbial decomposition of plant litter and residue at different depths and found that deep soil layers are more sensitive than topsoils. Warming causes SOC loss, but its extent depends on the litter type and its temperature sensitivity, which can either counteract or amplify losses. Droughts may also counteract warming-induced SOC losses.
Mitra Cattry, Wenli Zhao, Juan Nathaniel, Jinghao Qiu, Yao Zhang, and Pierre Gentine
EGUsphere, https://doi.org/10.5194/egusphere-2024-3726, https://doi.org/10.5194/egusphere-2024-3726, 2025
Preprint archived
Short summary
Short summary
Climate change alters Mediterranean biota, affecting how they absorb and store carbon. These associated impacts arise from short- and long-term effects of rainfall, temperature, and other atmospheric forcings, which existing tools struggle to capture. This study presents a memory-integrated model combining high- and low-resolution data to track daily ecosystem responses. By analyzing past conditions, we show how earlier conditions shape plant carbon uptake and improve predictions.
Wenli Zhao, Alexander J. Winkler, Markus Reichstein, Rene Orth, and Pierre Gentine
EGUsphere, https://doi.org/10.5194/egusphere-2025-365, https://doi.org/10.5194/egusphere-2025-365, 2025
Preprint archived
Short summary
Short summary
We developed a machine learning model that accounts for the memory effects of soil moisture and vegetation to predict Evaporative Fraction (EF) without relying on soil moisture as a direct input. The model accurately predicts EF during dry periods for the unseen sites, highlighting the key of meteorological memory effects. The learned memory effect related to rooting depth and soil water holding capacity could potentially serve as proxies for assessing the plant water stress.
Jacob A. Nelson, Sophia Walther, Fabian Gans, Basil Kraft, Ulrich Weber, Kimberly Novick, Nina Buchmann, Mirco Migliavacca, Georg Wohlfahrt, Ladislav Šigut, Andreas Ibrom, Dario Papale, Mathias Göckede, Gregory Duveiller, Alexander Knohl, Lukas Hörtnagl, Russell L. Scott, Jiří Dušek, Weijie Zhang, Zayd Mahmoud Hamdi, Markus Reichstein, Sergio Aranda-Barranco, Jonas Ardö, Maarten Op de Beeck, Dave Billesbach, David Bowling, Rosvel Bracho, Christian Brümmer, Gustau Camps-Valls, Shiping Chen, Jamie Rose Cleverly, Ankur Desai, Gang Dong, Tarek S. El-Madany, Eugenie Susanne Euskirchen, Iris Feigenwinter, Marta Galvagno, Giacomo A. Gerosa, Bert Gielen, Ignacio Goded, Sarah Goslee, Christopher Michael Gough, Bernard Heinesch, Kazuhito Ichii, Marcin Antoni Jackowicz-Korczynski, Anne Klosterhalfen, Sara Knox, Hideki Kobayashi, Kukka-Maaria Kohonen, Mika Korkiakoski, Ivan Mammarella, Mana Gharun, Riccardo Marzuoli, Roser Matamala, Stefan Metzger, Leonardo Montagnani, Giacomo Nicolini, Thomas O'Halloran, Jean-Marc Ourcival, Matthias Peichl, Elise Pendall, Borja Ruiz Reverter, Marilyn Roland, Simone Sabbatini, Torsten Sachs, Marius Schmidt, Christopher R. Schwalm, Ankit Shekhar, Richard Silberstein, Maria Lucia Silveira, Donatella Spano, Torbern Tagesson, Gianluca Tramontana, Carlo Trotta, Fabio Turco, Timo Vesala, Caroline Vincke, Domenico Vitale, Enrique R. Vivoni, Yi Wang, William Woodgate, Enrico A. Yepez, Junhui Zhang, Donatella Zona, and Martin Jung
Biogeosciences, 21, 5079–5115, https://doi.org/10.5194/bg-21-5079-2024, https://doi.org/10.5194/bg-21-5079-2024, 2024
Short summary
Short summary
The movement of water, carbon, and energy from the Earth's surface to the atmosphere, or flux, is an important process to understand because it impacts our lives. Here, we outline a method called FLUXCOM-X to estimate global water and CO2 fluxes based on direct measurements from sites around the world. We go on to demonstrate how these new estimates of net CO2 uptake/loss, gross CO2 uptake, total water evaporation, and transpiration from plants compare to previous and independent estimates.
Guohua Liu, Mirco Migliavacca, Christian Reimers, Basil Kraft, Markus Reichstein, Andrew D. Richardson, Lisa Wingate, Nicolas Delpierre, Hui Yang, and Alexander J. Winkler
Geosci. Model Dev., 17, 6683–6701, https://doi.org/10.5194/gmd-17-6683-2024, https://doi.org/10.5194/gmd-17-6683-2024, 2024
Short summary
Short summary
Our study employs long short-term memory (LSTM) networks to model canopy greenness and phenology, integrating meteorological memory effects. The LSTM model outperforms traditional methods, enhancing accuracy in predicting greenness dynamics and phenological transitions across plant functional types. Highlighting the importance of multi-variate meteorological memory effects, our research pioneers unlock the secrets of vegetation phenology responses to climate change with deep learning techniques.
Jasper M. C. Denissen, Adriaan J. Teuling, Sujan Koirala, Markus Reichstein, Gianpaolo Balsamo, Martha M. Vogel, Xin Yu, and René Orth
Earth Syst. Dynam., 15, 717–734, https://doi.org/10.5194/esd-15-717-2024, https://doi.org/10.5194/esd-15-717-2024, 2024
Short summary
Short summary
Heat extremes have severe implications for human health and ecosystems. Heat extremes are mostly introduced by large-scale atmospheric circulation but can be modulated by vegetation. Vegetation with access to water uses solar energy to evaporate water into the atmosphere. Under dry conditions, water may not be available, suppressing evaporation and heating the atmosphere. Using climate projections, we show that regionally less water is available for vegetation, intensifying future heat extremes.
Bjorn Stevens, Stefan Adami, Tariq Ali, Hartwig Anzt, Zafer Aslan, Sabine Attinger, Jaana Bäck, Johanna Baehr, Peter Bauer, Natacha Bernier, Bob Bishop, Hendryk Bockelmann, Sandrine Bony, Guy Brasseur, David N. Bresch, Sean Breyer, Gilbert Brunet, Pier Luigi Buttigieg, Junji Cao, Christelle Castet, Yafang Cheng, Ayantika Dey Choudhury, Deborah Coen, Susanne Crewell, Atish Dabholkar, Qing Dai, Francisco Doblas-Reyes, Dale Durran, Ayoub El Gaidi, Charlie Ewen, Eleftheria Exarchou, Veronika Eyring, Florencia Falkinhoff, David Farrell, Piers M. Forster, Ariane Frassoni, Claudia Frauen, Oliver Fuhrer, Shahzad Gani, Edwin Gerber, Debra Goldfarb, Jens Grieger, Nicolas Gruber, Wilco Hazeleger, Rolf Herken, Chris Hewitt, Torsten Hoefler, Huang-Hsiung Hsu, Daniela Jacob, Alexandra Jahn, Christian Jakob, Thomas Jung, Christopher Kadow, In-Sik Kang, Sarah Kang, Karthik Kashinath, Katharina Kleinen-von Königslöw, Daniel Klocke, Uta Kloenne, Milan Klöwer, Chihiro Kodama, Stefan Kollet, Tobias Kölling, Jenni Kontkanen, Steve Kopp, Michal Koran, Markku Kulmala, Hanna Lappalainen, Fakhria Latifi, Bryan Lawrence, June Yi Lee, Quentin Lejeun, Christian Lessig, Chao Li, Thomas Lippert, Jürg Luterbacher, Pekka Manninen, Jochem Marotzke, Satoshi Matsouoka, Charlotte Merchant, Peter Messmer, Gero Michel, Kristel Michielsen, Tomoki Miyakawa, Jens Müller, Ramsha Munir, Sandeep Narayanasetti, Ousmane Ndiaye, Carlos Nobre, Achim Oberg, Riko Oki, Tuba Özkan-Haller, Tim Palmer, Stan Posey, Andreas Prein, Odessa Primus, Mike Pritchard, Julie Pullen, Dian Putrasahan, Johannes Quaas, Krishnan Raghavan, Venkatachalam Ramaswamy, Markus Rapp, Florian Rauser, Markus Reichstein, Aromar Revi, Sonakshi Saluja, Masaki Satoh, Vera Schemann, Sebastian Schemm, Christina Schnadt Poberaj, Thomas Schulthess, Cath Senior, Jagadish Shukla, Manmeet Singh, Julia Slingo, Adam Sobel, Silvina Solman, Jenna Spitzer, Philip Stier, Thomas Stocker, Sarah Strock, Hang Su, Petteri Taalas, John Taylor, Susann Tegtmeier, Georg Teutsch, Adrian Tompkins, Uwe Ulbrich, Pier-Luigi Vidale, Chien-Ming Wu, Hao Xu, Najibullah Zaki, Laure Zanna, Tianjun Zhou, and Florian Ziemen
Earth Syst. Sci. Data, 16, 2113–2122, https://doi.org/10.5194/essd-16-2113-2024, https://doi.org/10.5194/essd-16-2113-2024, 2024
Short summary
Short summary
To manage Earth in the Anthropocene, new tools, new institutions, and new forms of international cooperation will be required. Earth Virtualization Engines is proposed as an international federation of centers of excellence to empower all people to respond to the immense and urgent challenges posed by climate change.
Sinikka J. Paulus, Rene Orth, Sung-Ching Lee, Anke Hildebrandt, Martin Jung, Jacob A. Nelson, Tarek Sebastian El-Madany, Arnaud Carrara, Gerardo Moreno, Matthias Mauder, Jannis Groh, Alexander Graf, Markus Reichstein, and Mirco Migliavacca
Biogeosciences, 21, 2051–2085, https://doi.org/10.5194/bg-21-2051-2024, https://doi.org/10.5194/bg-21-2051-2024, 2024
Short summary
Short summary
Porous materials are known to reversibly trap water from the air, even at low humidity. However, this behavior is poorly understood for soils. In this analysis, we test whether eddy covariance is able to measure the so-called adsorption of atmospheric water vapor by soils. We find that this flux occurs frequently during dry nights in a Mediterranean ecosystem, while EC detects downwardly directed vapor fluxes. These results can help to map moisture uptake globally.
Martin Jung, Jacob Nelson, Mirco Migliavacca, Tarek El-Madany, Dario Papale, Markus Reichstein, Sophia Walther, and Thomas Wutzler
Biogeosciences, 21, 1827–1846, https://doi.org/10.5194/bg-21-1827-2024, https://doi.org/10.5194/bg-21-1827-2024, 2024
Short summary
Short summary
We present a methodology to detect inconsistencies in perhaps the most important data source for measurements of ecosystem–atmosphere carbon, water, and energy fluxes. We expect that the derived consistency flags will be relevant for data users and will help in improving our understanding of and our ability to model ecosystem–climate interactions.
Prajwal Khanal, Anne J. Hoek Van Dijke, Timo Schaffhauser, Wantong Li, Sinikka J. Paulus, Chunhui Zhan, and René Orth
Biogeosciences, 21, 1533–1547, https://doi.org/10.5194/bg-21-1533-2024, https://doi.org/10.5194/bg-21-1533-2024, 2024
Short summary
Short summary
Water availability is essential for vegetation functioning, but the depth of vegetation water uptake is largely unknown due to sparse ground measurements. This study correlates vegetation growth with soil moisture availability globally to infer vegetation water uptake depth using only satellite-based data. We find that the vegetation water uptake depth varies across climate regimes and vegetation types and also changes during dry months at a global scale.
Samuel Upton, Markus Reichstein, Fabian Gans, Wouter Peters, Basil Kraft, and Ana Bastos
Atmos. Chem. Phys., 24, 2555–2582, https://doi.org/10.5194/acp-24-2555-2024, https://doi.org/10.5194/acp-24-2555-2024, 2024
Short summary
Short summary
Data-driven eddy-covariance upscaled estimates of the global land–atmosphere net CO2 exchange (NEE) show important mismatches with regional and global estimates based on atmospheric information. To address this, we create a model with a dual constraint based on bottom-up eddy-covariance data and top-down atmospheric inversion data. Our model overcomes shortcomings of each approach, producing improved NEE estimates from local to global scale, helping to reduce uncertainty in the carbon budget.
Jiabo Yin, Louise J. Slater, Abdou Khouakhi, Le Yu, Pan Liu, Fupeng Li, Yadu Pokhrel, and Pierre Gentine
Earth Syst. Sci. Data, 15, 5597–5615, https://doi.org/10.5194/essd-15-5597-2023, https://doi.org/10.5194/essd-15-5597-2023, 2023
Short summary
Short summary
This study presents long-term (i.e., 1940–2022) and high-resolution (i.e., 0.25°) monthly time series of TWS anomalies over the global land surface. The reconstruction is achieved by using a set of machine learning models with a large number of predictors, including climatic and hydrological variables, land use/land cover data, and vegetation indicators (e.g., leaf area index). Our proposed GTWS-MLrec performs overall as well as, or is more reliable than, previous TWS datasets.
Richard Nair, Yunpeng Luo, Tarek El-Madany, Victor Rolo, Javier Pacheco-Labrador, Silvia Caldararu, Kendalynn A. Morris, Marion Schrumpf, Arnaud Carrara, Gerardo Moreno, Markus Reichstein, and Mirco Migliavacca
EGUsphere, https://doi.org/10.5194/egusphere-2023-2434, https://doi.org/10.5194/egusphere-2023-2434, 2023
Preprint archived
Short summary
Short summary
We studied a Mediterranean ecosystem to understand carbon uptake efficiency and its controls. These ecosystems face potential nitrogen-phosphorus imbalances due to pollution. Analysing six years of carbon data, we assessed controls at different timeframes. This is crucial for predicting such vulnerable regions. Our findings revealed N limitation on C uptake, not N:P imbalance, and strong influence of water availability. whether drought or wetness promoted net C uptake depended on timescale.
Theertha Kariyathan, Ana Bastos, Julia Marshall, Wouter Peters, Pieter Tans, and Markus Reichstein
Atmos. Meas. Tech., 16, 3299–3312, https://doi.org/10.5194/amt-16-3299-2023, https://doi.org/10.5194/amt-16-3299-2023, 2023
Short summary
Short summary
The timing and duration of the carbon uptake period (CUP) are sensitive to the occurrence of major phenological events, which are influenced by recent climate change. This study presents an ensemble-based approach for quantifying the timing and duration of the CUP and their uncertainty when derived from atmospheric CO2 measurements with noise and gaps. The CUP metrics derived with the approach are more robust and have less uncertainty than when estimated with the conventional methods.
Jatan Buch, A. Park Williams, Caroline S. Juang, Winslow D. Hansen, and Pierre Gentine
Geosci. Model Dev., 16, 3407–3433, https://doi.org/10.5194/gmd-16-3407-2023, https://doi.org/10.5194/gmd-16-3407-2023, 2023
Short summary
Short summary
We leverage machine learning techniques to construct a statistical model of grid-scale fire frequencies and sizes using climate, vegetation, and human predictors. Our model reproduces the observed trends in fire activity across multiple regions and timescales. We provide uncertainty estimates to inform resource allocation plans for fuel treatment and fire management. Altogether the accuracy and efficiency of our model make it ideal for coupled use with large-scale dynamical vegetation models.
Hoontaek Lee, Martin Jung, Nuno Carvalhais, Tina Trautmann, Basil Kraft, Markus Reichstein, Matthias Forkel, and Sujan Koirala
Hydrol. Earth Syst. Sci., 27, 1531–1563, https://doi.org/10.5194/hess-27-1531-2023, https://doi.org/10.5194/hess-27-1531-2023, 2023
Short summary
Short summary
We spatially attribute the variance in global terrestrial water storage (TWS) interannual variability (IAV) and its modeling error with two data-driven hydrological models. We find error hotspot regions that show a disproportionately large significance in the global mismatch and the association of the error regions with a smaller-scale lateral convergence of water. Our findings imply that TWS IAV modeling can be efficiently improved by focusing on model representations for the error hotspots.
Robert Vautard, Geert Jan van Oldenborgh, Rémy Bonnet, Sihan Li, Yoann Robin, Sarah Kew, Sjoukje Philip, Jean-Michel Soubeyroux, Brigitte Dubuisson, Nicolas Viovy, Markus Reichstein, Friederike Otto, and Iñaki Garcia de Cortazar-Atauri
Nat. Hazards Earth Syst. Sci., 23, 1045–1058, https://doi.org/10.5194/nhess-23-1045-2023, https://doi.org/10.5194/nhess-23-1045-2023, 2023
Short summary
Short summary
A deep frost occurred in early April 2021, inducing severe damages in grapevine and fruit trees in France. We found that such extreme frosts occurring after the start of the growing season such as those of April 2021 are currently about 2°C colder [0.5 °C to 3.3 °C] in observations than in preindustrial climate. This observed intensification of growing-period frosts is attributable, at least in part, to human-caused climate change, making the 2021 event 50 % more likely [10 %–110 %].
Manal Lam'barki, Wantong Li, Sungmin O, Chunhui Zhan, and Rene Orth
Hydrol. Earth Syst. Sci. Discuss., https://doi.org/10.5194/hess-2022-404, https://doi.org/10.5194/hess-2022-404, 2022
Manuscript not accepted for further review
Short summary
Short summary
We investigate the main drivers of high river flows in near-natural European catchments. While there are a lot of previous research in this area, the understanding of the relative relevance of high flow drivers other than precipitation is understudied. We find that the secondary drivers of high river flows are very diverse and become more relevant for more extreme events. This illustrates the necessity of flood management by considering a multitude of drivers in the context of climate change.
Sinikka Jasmin Paulus, Tarek Sebastian El-Madany, René Orth, Anke Hildebrandt, Thomas Wutzler, Arnaud Carrara, Gerardo Moreno, Oscar Perez-Priego, Olaf Kolle, Markus Reichstein, and Mirco Migliavacca
Hydrol. Earth Syst. Sci., 26, 6263–6287, https://doi.org/10.5194/hess-26-6263-2022, https://doi.org/10.5194/hess-26-6263-2022, 2022
Short summary
Short summary
In this study, we analyze small inputs of water to ecosystems such as fog, dew, and adsorption of vapor. To measure them, we use a scaling system and later test our attribution of different water fluxes to weight changes. We found that they occur frequently during 1 year in a dry summer ecosystem. In each season, a different flux seems dominant, but they all mainly occur during the night. Therefore, they could be important for the biosphere because rain is unevenly distributed over the year.
Na Li, Sebastian Sippel, Alexander J. Winkler, Miguel D. Mahecha, Markus Reichstein, and Ana Bastos
Earth Syst. Dynam., 13, 1505–1533, https://doi.org/10.5194/esd-13-1505-2022, https://doi.org/10.5194/esd-13-1505-2022, 2022
Short summary
Short summary
Quantifying the imprint of large-scale atmospheric circulation dynamics and associated carbon cycle responses is key to improving our understanding of carbon cycle dynamics. Using a statistical model that relies on spatiotemporal sea level pressure as a proxy for large-scale atmospheric circulation, we quantify the fraction of interannual variability in atmospheric CO2 growth rate and the land CO2 sink that are driven by atmospheric circulation variability.
Melissa Ruiz-Vásquez, Sungmin O, Alexander Brenning, Randal D. Koster, Gianpaolo Balsamo, Ulrich Weber, Gabriele Arduini, Ana Bastos, Markus Reichstein, and René Orth
Earth Syst. Dynam., 13, 1451–1471, https://doi.org/10.5194/esd-13-1451-2022, https://doi.org/10.5194/esd-13-1451-2022, 2022
Short summary
Short summary
Subseasonal forecasts facilitate early warning of extreme events; however their predictability sources are not fully explored. We find that global temperature forecast errors in many regions are related to climate variables such as solar radiation and precipitation, as well as land surface variables such as soil moisture and evaporative fraction. A better representation of these variables in the forecasting and data assimilation systems can support the accuracy of temperature forecasts.
Xin Yu, René Orth, Markus Reichstein, Michael Bahn, Anne Klosterhalfen, Alexander Knohl, Franziska Koebsch, Mirco Migliavacca, Martina Mund, Jacob A. Nelson, Benjamin D. Stocker, Sophia Walther, and Ana Bastos
Biogeosciences, 19, 4315–4329, https://doi.org/10.5194/bg-19-4315-2022, https://doi.org/10.5194/bg-19-4315-2022, 2022
Short summary
Short summary
Identifying drought legacy effects is challenging because they are superimposed on variability driven by climate conditions in the recovery period. We develop a residual-based approach to quantify legacies on gross primary productivity (GPP) from eddy covariance data. The GPP reduction due to legacy effects is comparable to the concurrent effects at two sites in Germany, which reveals the importance of legacy effects. Our novel methodology can be used to quantify drought legacies elsewhere.
Philip J. Ward, James Daniell, Melanie Duncan, Anna Dunne, Cédric Hananel, Stefan Hochrainer-Stigler, Annegien Tijssen, Silvia Torresan, Roxana Ciurean, Joel C. Gill, Jana Sillmann, Anaïs Couasnon, Elco Koks, Noemi Padrón-Fumero, Sharon Tatman, Marianne Tronstad Lund, Adewole Adesiyun, Jeroen C. J. H. Aerts, Alexander Alabaster, Bernard Bulder, Carlos Campillo Torres, Andrea Critto, Raúl Hernández-Martín, Marta Machado, Jaroslav Mysiak, Rene Orth, Irene Palomino Antolín, Eva-Cristina Petrescu, Markus Reichstein, Timothy Tiggeloven, Anne F. Van Loon, Hung Vuong Pham, and Marleen C. de Ruiter
Nat. Hazards Earth Syst. Sci., 22, 1487–1497, https://doi.org/10.5194/nhess-22-1487-2022, https://doi.org/10.5194/nhess-22-1487-2022, 2022
Short summary
Short summary
The majority of natural-hazard risk research focuses on single hazards (a flood, a drought, a volcanic eruption, an earthquake, etc.). In the international research and policy community it is recognised that risk management could benefit from a more systemic approach. In this perspective paper, we argue for an approach that addresses multi-hazard, multi-risk management through the lens of sustainability challenges that cut across sectors, regions, and hazards.
Basil Kraft, Martin Jung, Marco Körner, Sujan Koirala, and Markus Reichstein
Hydrol. Earth Syst. Sci., 26, 1579–1614, https://doi.org/10.5194/hess-26-1579-2022, https://doi.org/10.5194/hess-26-1579-2022, 2022
Short summary
Short summary
We present a physics-aware machine learning model of the global hydrological cycle. As the model uses neural networks under the hood, the simulations of the water cycle are learned from data, and yet they are informed and constrained by physical knowledge. The simulated patterns lie within the range of existing hydrological models and are plausible. The hybrid modeling approach has the potential to tackle key environmental questions from a novel perspective.
Josephin Kroll, Jasper M. C. Denissen, Mirco Migliavacca, Wantong Li, Anke Hildebrandt, and Rene Orth
Biogeosciences, 19, 477–489, https://doi.org/10.5194/bg-19-477-2022, https://doi.org/10.5194/bg-19-477-2022, 2022
Short summary
Short summary
Plant growth relies on having access to energy (solar radiation) and water (soil moisture). This energy and water availability is impacted by weather extremes, like heat waves and droughts, which will occur more frequently in response to climate change. In this context, we analysed global satellite data to detect in which regions extreme plant growth is controlled by energy or water. We find that extreme plant growth is associated with temperature- or soil-moisture-related extremes.
Ana Bastos, René Orth, Markus Reichstein, Philippe Ciais, Nicolas Viovy, Sönke Zaehle, Peter Anthoni, Almut Arneth, Pierre Gentine, Emilie Joetzjer, Sebastian Lienert, Tammas Loughran, Patrick C. McGuire, Sungmin O, Julia Pongratz, and Stephen Sitch
Earth Syst. Dynam., 12, 1015–1035, https://doi.org/10.5194/esd-12-1015-2021, https://doi.org/10.5194/esd-12-1015-2021, 2021
Short summary
Short summary
Temperate biomes in Europe are not prone to recurrent dry and hot conditions in summer. However, these conditions may become more frequent in the coming decades. Because stress conditions can leave legacies for many years, this may result in reduced ecosystem resilience under recurrent stress. We assess vegetation vulnerability to the hot and dry summers in 2018 and 2019 in Europe and find the important role of inter-annual legacy effects from 2018 in modulating the impacts of the 2019 event.
Alexander J. Winkler, Ranga B. Myneni, Alexis Hannart, Stephen Sitch, Vanessa Haverd, Danica Lombardozzi, Vivek K. Arora, Julia Pongratz, Julia E. M. S. Nabel, Daniel S. Goll, Etsushi Kato, Hanqin Tian, Almut Arneth, Pierre Friedlingstein, Atul K. Jain, Sönke Zaehle, and Victor Brovkin
Biogeosciences, 18, 4985–5010, https://doi.org/10.5194/bg-18-4985-2021, https://doi.org/10.5194/bg-18-4985-2021, 2021
Short summary
Short summary
Satellite observations since the early 1980s show that Earth's greening trend is slowing down and that browning clusters have been emerging, especially in the last 2 decades. A collection of model simulations in conjunction with causal theory points at climatic changes as a key driver of vegetation changes in natural ecosystems. Most models underestimate the observed vegetation browning, especially in tropical rainforests, which could be due to an excessive CO2 fertilization effect in models.
Cited articles
Abatzoglou, J. T., Dobrowski, S. Z., Parks, S. A., and Hegewisch, K. C.: TerraClimate, a high-resolution global dataset of monthly climate and climatic water balance from 1958–2015, Sci. Data, 5, 170191, https://doi.org/10.1038/sdata.2017.191, 2018.
Barnes, E. A., Toms, B., Hurrell, J. W., Ebert-Uphoff, I., Anderson, C., and Anderson, D.: Indicator Patterns of Forced Change Learned by an Artificial Neural Network, https://doi.org/10.1029/2020MS002195, 2020.
Bastiaanssen, W. G. M., Pelgrum, H., Droogers, P., De Bruin, H. A. R., and Menenti, M.: Area-average estimates of evaporation, wetness indicators and top soil moisture during two golden days in EFEDA, Agr. Forest Meteorol., 87, 119–137, https://doi.org/10.1016/S0168-1923(97)00020-8, 1997.
Besnard, S., Carvalhais, N., Arain, M. A., Black, A., Brede, B., Buchmann, N., Chen, J., Clevers, J. G. P. W., Dutrieux, L. P., Gans, F., Herold, M., Jung, M., Kosugi, Y., Knohl, A., Law, B. E., Paul-Limoges, E., Lohila, A., Merbold, L., Roupsard, O., Valentini, R., Wolf, S., Zhang, X., and Reichstein, M.: Memory effects of climate and vegetation affecting net ecosystem CO2 fluxes in global forests, PLOS ONE, 14, e0211510, https://doi.org/10.1371/journal.pone.0211510, 2019.
Biegel, S., Schindler, K., and Stocker, B. D.: Unrecognised water limitation is a main source of uncertainty for models of terrestrial photosynthesis, Biogeosciences, 22, 7455–7481, https://doi.org/10.5194/bg-22-7455-2025, 2025.
Canarini, A., Schmidt, H., Fuchslueger, L., Martin, V., Herbold, C. W., Zezula, D., Gündler, P., Hasibeder, R., Jecmenica, M., Bahn, M., and Richter, A.: Ecological memory of recurrent drought modifies soil processes via changes in soil microbial community, Nat. Commun., 12, 5308, https://doi.org/10.1038/s41467-021-25675-4, 2021.
Chen, S., Stark, S. C., Nobre, A. D., Cuartas, L. A., de Jesus Amore, D., Restrepo-Coupe, N., Smith, M. N., Chitra-Tarak, R., Ko, H., Nelson, B. W., and Saleska, S. R.: Amazon forest biogeography predicts resilience and vulnerability to drought, Nature, 631, 111–117, https://doi.org/10.1038/s41586-024-07568-w, 2024.
Chen, Y., Xue, Y., and Hu, Y.: How multiple factors control evapotranspiration in North America evergreen needleleaf forests, Sci. Total Environ., 622–623, 1217–1224, https://doi.org/10.1016/j.scitotenv.2017.12.038, 2018.
Collins, D. B. G. and Bras, R. L.: Plant rooting strategies in water‐limited ecosystems, Water Resour. Res., 43, 2006WR005541, https://doi.org/10.1029/2006WR005541, 2007.
Dietterich, T. G.: Ensemble Methods in Machine Learning, in: Multiple Classifier Systems, edited by: Kittler, J. and Roli, F., Lecture Notes in Computer Science, vol. 1857, Springer, Berlin, Heidelberg, 1–15, https://doi.org/10.1007/3-540-45014-9_1, 2000.
Dralle, D. N., Jesse Hahm, W., Rempe, D. M., Karst, N., Anderegg, L. D. L., Thompson, S. E., Dawson, T. E., and Dietrich, W. E.: Plants as sensors: vegetation response to rainfall predicts root-zone water storage capacity in Mediterranean-type climates, Environ. Res. Lett., 15, 104074, https://doi.org/10.1088/1748-9326/abb10b, 2020.
Gunning, D. and Aha, D. W.: DARPA’s Explainable Artificial Intelligence (XAI) Program, AI Mag., 40, 44–58, https://doi.org/10.1609/aimag.v40i2.2850, 2019.
ElGhawi, R., Kraft, B., Reimers, C., Reichstein, M., Körner, M., Gentine, P., and Winkler, A. J.: Hybrid modeling of evapotranspiration: inferring stomatal and aerodynamic resistances using combined physics-based and machine learning, Environ. Res. Lett., 18, 034039, https://doi.org/10.1088/1748-9326/acbbe0, 2023.
Erion, G., Janizek, J. D., Sturmfels, P., Lundberg, S. M., and Lee, S.-I.: Improving performance of deep learning models with axiomatic attribution priors and expected gradients, Nat. Mach. Intell., 3, 620–631, https://doi.org/10.1038/s42256-021-00343-w, 2021.
Fan, Y., Miguez-Macho, G., Jobbágy, E. G., Jackson, R. B., and Otero-Casal, C.: Hydrologic regulation of plant rooting depth, Proc. Natl. Acad. Sci. USA, 114, 10572–10577, https://doi.org/10.1073/pnas.1712381114, 2017.
Fang, K. and Shen, C.: Near-real-time forecast of satellite-based soil moisture using long short-term memory with an adaptive data integration kernel, J. Hydrometeorol., 21, 399–413, 2020.
Feng, D., Fang, K., and Shen, C.: Enhancing Streamflow Forecast and Extracting Insights Using Long-Short Term Memory Networks With Data Integration at Continental Scales, Water Resour. Res., 56, e2019WR026793, https://doi.org/10.1029/2019WR026793, 2020.
Foken, T.: The energy balance closure problem: An overview, Ecol. Appl., 18, 1351–1367, 2008.
Fu, Z., Ciais, P., Wigneron, J.-P., Gentine, P., Feldman, A. F., Makowski, D., Viovy, N., Kemanian, A. R., Goll, D. S., Stoy, P. C., Prentice, I. C., Yakir, D., Liu, L., Ma, H., Li, X., Huang, Y., Yu, K., Zhu, P., Li, X., Zhu, Z., Lian, J., and Smith, W. K.: Global critical soil moisture thresholds of plant water stress, Nat. Commun., 15, 4826, https://doi.org/10.1038/s41467-024-49244-7, 2024.
Gentine, P., Entekhabi, D., Chehbouni, A., Boulet, G., and Duchemin, B.: Analysis of evaporative fraction diurnal behaviour, Agr. Forest Meteorol., 143, 13–29, https://doi.org/10.1016/j.agrformet.2006.11.002, 2007.
Gentine, P., Entekhabi, D., and Polcher, J.: The Diurnal Behavior of Evaporative Fraction in the Soil–Vegetation–Atmospheric Boundary Layer Continuum, J. Hydrometeorol., 12, 1530–1546, https://doi.org/10.1175/2011JHM1261.1, 2011.
Giardina, F., Gentine, P., Konings, A. G., Seneviratne, S. I., and Stocker, B. D.: Diagnosing evapotranspiration responses to water deficit across biomes using deep learning, New Phytologist, 240, 968–983, https://doi.org/10.1111/nph.19197, 2023.
Guérin, M., Von Arx, G., Martin-Benito, D., Andreu-Hayles, L., Griffin, K. L., McDowell, N. G., Pockman, W., and Gentine, P.: Distinct xylem responses to acute vs prolonged drought in pine trees, Tree Physiol., 40, 605–620, https://doi.org/10.1093/treephys/tpz144, 2020.
Gunning, D. and Aha, D. W.: DARPA’s Explainable Artificial Intelligence (XAI) Program, AI Mag., 40, 44–58, https://doi.org/10.1609/aimag.v40i2.2850, 2019.
He, B., Liu, J., Guo, L., Wu, X., Xie, X., Zhang, Y., Chen, C., Zhong, Z., and Chen, Z.: Recovery of Ecosystem Carbon and Energy Fluxes From the 2003 Drought in Europe and the 2012 Drought in the United States, Geophys. Res. Lett., 45, 4879–4888, https://doi.org/10.1029/2018GL077518, 2018.
Hochreiter, S. and Schmidhuber, J.: Long Short-Term Memory, Neural Comput., 9, 1735–1780, https://doi.org/10.1162/neco.1997.9.8.1735, 1997.
Hollinger, D. and Richardson, A.: Uncertainty in eddy covariance measurements and its application to physiological models, Tree Physiol., 25, 873–885, 2005.
Hossain, M. L., Li, J., Hoffmann, S., and Beierkuhnlein, C.: Biodiversity showed positive effects on resistance but mixed effects on resilience to climatic extremes in a long-term grassland experiment, Sci. Total Environ., 827, 154322, https://doi.org/10.1016/j.scitotenv.2022.154322, 2022.
Ichii, K., Wang, W., Hashimoto, H., Yang, F., Votava, P., Michaelis, A. R., and Nemani, R. R.: Refinement of rooting depths using satellite-based evapotranspiration seasonality for ecosystem modeling in California, Ag. Forest Meteorol., 149, 1907–1918, https://doi.org/10.1016/j.agrformet.2009.06.019, 2009.
Jiang, S., Zheng, Y., and Solomatine, D.: Improving AI System Awareness of Geoscience Knowledge: Symbiotic Integration of Physical Approaches and Deep Learning, Geophys. Res. Lett., 47, https://doi.org/10.1029/2020GL088229, 2020.
Jiang, S., Bevacqua, E., and Zscheischler, J.: River flooding mechanisms and their changes in Europe revealed by explainable machine learning, Hydrol. Earth Syst. Sci., 26, 6339–6359, https://doi.org/10.5194/hess-26-6339-2022, 2022a.
Jiang, S., Zheng, Y., Wang, C., and Babovic, V.: Uncovering Flooding Mechanisms Across the Contiguous United States Through Interpretive Deep Learning on Representative Catchments, Water Resou. Res., 58, e2021WR030185, https://doi.org/10.1029/2021WR030185, 2022b.
Jung, M., Koirala, S., Weber, U., Ichii, K., Gans, F., Camps-Valls, G., Papale, D., Schwalm, C., Tramontana, G., and Reichstein, M.: The FLUXCOM ensemble of global land-atmosphere energy fluxes, Sci. Data, 6, 74, https://doi.org/10.1038/s41597-019-0076-8, 2019.
Kannenberg, S. A., Schwalm, C. R., and Anderegg, W. R. L.: Ghosts of the past: how drought legacy effects shape forest functioning and carbon cycling, Ecol. Lette., 23, 891–901, https://doi.org/10.1111/ele.13485, 2020.
Kingma, D. P. and Ba, J.: Adam: A Method for Stochastic Optimization, International Conference on Learning Representations (ICLR), San Diego, CA, USA, https://doi.org/10.48550/arXiv.1412.6980, 2015.
Konings, A. G. and Gentine, P.: Global variations in ecosystem-scale isohydricity, Global Change Biol., 23, 891–905, https://doi.org/10.1111/gcb.13389, 2017.
Kraft, B., Jung, M., Körner, M., Requena Mesa, C., Cortés, J., and Reichstein, M.: Identifying Dynamic Memory Effects on Vegetation State Using Recurrent Neural Networks, Front. Big Data, 2, 31, https://doi.org/10.3389/fdata.2019.00031, 2019.
Kraft, B., Jung, M., Körner, M., Koirala, S., and Reichstein, M.: Towards hybrid modeling of the global hydrological cycle, Hydrol. Earth Syst. Sci., 26, 1579–1614, https://doi.org/10.5194/hess-26-1579-2022, 2022.
Kraft, B., Nelson, J. A., Walther, S., Gans, F., Weber, U., Duveiller, G., Reichstein, M., Zhang, W., Rußwurm, M., Tuia, D., Körner, M., Hamdi, Z., and Jung, M.: On the added value of sequential deep learning for the upscaling of evapotranspiration, Biogeosciences, 22, 3965–3987, https://doi.org/10.5194/bg-22-3965-2025, 2025.
Labe, Z. M. and Barnes, E. A.: Detecting Climate Signals Using Explainable AI With Single‐Forcing Large Ensembles, J. Adv. Model. Earth Syst., 13, e2021MS002464, https://doi.org/10.1029/2021MS002464, 2021.
Lees, T., Reece, S., Kratzert, F., Klotz, D., Gauch, M., De Bruijn, J., Kumar Sahu, R., Greve, P., Slater, L., and Dadson, S. J.: Hydrological concept formation inside long short-term memory (LSTM) networks, Hydrol. Earth Syst. Sci., 26, 3079–3101, https://doi.org/10.5194/hess-26-3079-2022, 2022.
Lhomme, J.-P. and Elguero, E.: Examination of evaporative fraction diurnal behaviour using a soil-vegetation model coupled with a mixed-layer model, Hydrol. Earth Syst. Sci., 3, 259–270, https://doi.org/10.5194/hess-3-259-1999, 1999.
Li, Q., Zhu, Y., Shangguan, W., Wang, X., Li, L., and Yu, F.: An attention-aware LSTM model for soil moisture and soil temperature prediction, Geoderma, 409, 115651, https://doi.org/10.1016/j.geoderma.2021.115651, 2022.
Lian, X., Zhao, W., and Gentine, P.: Recent global decline in rainfall interception loss due to altered rainfall regimes, Nat. Commun., 13, 7642, https://doi.org/10.1038/s41467-022-35414-y, 2022.
Liu, X., Chen, F., Barlage, M., and Niyogi, D.: Implementing Dynamic Rooting Depth for Improved Simulation of Soil Moisture and Land Surface Feedbacks in Noah‐MP‐Crop, J. Adv. Model. Earth Sy., 12, https://doi.org/10.1029/2019MS001786, 2020.
Loveland, T. R., Reed, B. C., Brown, J. F., Ohlen, D. O., Zhu, Z., Yang, L., and Merchant, J. W.: Development of a global land cover characteristics database and IGBP DISCover from 1 km AVHRR data, Int.J. Remote Sens., 21, 1303–1330, 2000.
Marqués, L., Peltier, D. M. P., Camarero, J. J., Zavala, M. A., Madrigal-González, J., Sangüesa-Barreda, G., and Ogle, K.: Disentangling the Legacies of Climate and Management on Tree Growth, Ecosystems, 25, 215–235, https://doi.org/10.1007/s10021-021-00650-8, 2022.
McColl, K. A., Wang, W., Peng, B., Akbar, R., Short Gianotti, D. J., Lu, H., Pan, M., and Entekhabi, D.: Global characterization of surface soil moisture drydowns, Geophys. Res. Lett., 44, 3682–3690, https://doi.org/10.1002/2017GL072819, 2017.
Molnar, C.: Interpretable Machine Learning: A Guide for Making Black Box Models Explainable, self-published by Christoph Molnar, ISBN 9780244768522, https://christophm.github.io/interpretable-ml-book/ (last access: 22 August 2026), 2019.
Montero, D., Mahecha, M. D., Martinuzzi, F., Aybar, C., Klosterhalfen, A., Knohl, A., Koebsch, F., Anaya, J., and Wieneke, S.: Recurrent Neural Networks for Modelling Gross Primary Production, in: IGARSS 2024–2024 IEEE International Geoscience and Remote Sensing Symposium, arXiv:2404.12745 [cs], 4214–4217, https://doi.org/10.1109/IGARSS53475.2024.10640715, 2024.
Murdoch, W. J., Singh, C., Kumbier, K., Abbasi-Asl, R., and Yu, B.: Definitions, methods, and applications in interpretable machine learning, P. Natl. Acad. Sci. USA, 116, 22071–22080, https://doi.org/10.1073/pnas.1900654116, 2019.
Nakagawa, R., Chau, M., Calzaretta, J., Keenan, T., Vahabi, P., Todeschini, A., Bassiouni, M., and Kang, Y.: Upscaling Global Hourly GPP with Temporal Fusion Transformer (TFT), https://doi.org/10.48550/arXiv.2306.13815, 23 June 2023.
Nelson, J. A., Walther, S., Gans, F., Kraft, B., Weber, U., Novick, K., Buchmann, N., Migliavacca, M., Wohlfahrt, G., Šigut, L., Ibrom, A., Papale, D., Göckede, M., Duveiller, G., Knohl, A., Hörtnagl, L., Scott, R. L., Dušek, J., Zhang, W., Hamdi, Z. M., Reichstein, M., Aranda-Barranco, S., Ardö, J., Op de Beeck, M., Billesbach, D., Bowling, D., Bracho, R., Brümmer, C., Camps-Valls, G., Chen, S., Cleverly, J. R., Desai, A., Dong, G., El-Madany, T. S., Euskirchen, E. S., Feigenwinter, I., Galvagno, M., Gerosa, G. A., Gielen, B., Goded, I., Goslee, S., Gough, C. M., Heinesch, B., Ichii, K., Jackowicz-Korczynski, M. A., Klosterhalfen, A., Knox, S., Kobayashi, H., Kohonen, K.-M., Korkiakoski, M., Mammarella, I., Gharun, M., Marzuoli, R., Matamala, R., Metzger, S., Montagnani, L., Nicolini, G., O'Halloran, T., Ourcival, J.-M., Peichl, M., Pendall, E., Ruiz Reverter, B., Roland, M., Sabbatini, S., Sachs, T., Schmidt, M., Schwalm, C. R., Shekhar, A., Silberstein, R., Silveira, M. L., Spano, D., Tagesson, T., Tramontana, G., Trotta, C., Turco, F., Vesala, T., Vincke, C., Vitale, D., Vivoni, E. R., Wang, Y., Woodgate, W., Yepez, E. A., Zhang, J., Zona, D., and Jung, M.: X-BASE: the first terrestrial carbon and water flux products from an extended data-driven scaling framework, FLUXCOM-X, Biogeosciences, 21, 5079–5115, https://doi.org/10.5194/bg-21-5079-2024, 2024.
Nutini, F., Boschetti, M., Candiani, G., Bocchi, S., and Brivio, P.: Evaporative Fraction as an Indicator of Moisture Condition and Water Stress Status in Semi-Arid Rangeland Ecosystems, Remote Sens., 6, 6300–6323, https://doi.org/10.3390/rs6076300, 2014.
Olson, D. M., Dinerstein, E., Wikramanayake, E. D., Burgess, N. D., Powell, G. V. N., Underwood, E. C., D'Amico, J. A., Itoua, I., Strand, H. E., Morrison, J. C., Loucks, C. J., Allnutt, T. F., Ricketts, T. H., Kura, Y., Lamoreux, J. F., Wettengel, W. W., Hedao, P., and Kassem, K. R.: Terrestrial Ecoregions of the World: A New Map of Life on Earth, BioScience, 51, 933–938, https://doi.org/10.1641/0006-3568(2001)051[0933:TEOTWA]2.0.CO;2, 2001.
Pan, S., Pan, N., Tian, H., Friedlingstein, P., Sitch, S., Shi, H., Arora, V. K., Haverd, V., Jain, A. K., Kato, E., Lienert, S., Lombardozzi, D., Nabel, J. E. M. S., Ottlé, C., Poulter, B., Zaehle, S., and Running, S. W.: Evaluation of global terrestrial evapotranspiration using state-of-the-art approaches in remote sensing, machine learning and land surface modeling, Hydrol. Earth Syst. Sci., 24, 1485–1509, https://doi.org/10.5194/hess-24-1485-2020, 2020.
Piedallu, C., Gégout, J.-C., Bruand, A., and Seynave, I.: Mapping soil water holding capacity over large areas to predict potential production of forest stands, Geoderma, 160, 355–366, https://doi.org/10.1016/j.geoderma.2010.10.004, 2011.
Poggio, L., de Sousa, L. M., Batjes, N. H., Heuvelink, G. B. M., Kempen, B., Ribeiro, E., and Rossiter, D.: SoilGrids 2.0: producing soil information for the globe with quantified spatial uncertainty, SOIL, 7, 217–240, https://doi.org/10.5194/soil-7-217-2021, 2021.
Qiu, J., Zhang, Y., Cai, M., Keenan, T. F., Zhang, H., Gentine, P., Luo, X., Cattry, M., Zhou, S., and Piao, S.: Large contribution of antecedent climate to ecosystem productivity anomalies during extreme events, Nat. Geosci., 1–8, https://doi.org/10.1038/s41561-025-01856-4, 2025.
Reichstein, M., Falge, E., Baldocchi, D., Papale, D., Aubinet, M., Berbigier, P., Bernhofer, C., Buchmann, N., Gilmanov, T., Granier, A., Grünwald, T., Havránková, K., Ilvesniemi, H., Janouš, D., Knohl, A., Laurila, T., Lohila, A., Loustau, D., Matteucci, G., Meyers, T., Miglietta, F., Ourcival, J.-M., Pumpanen, J., Rambal, S., Rotenberg, E., Sanz, M., Tenhunen, J., Seufert, G., Vaccari, F., Vesala, T., Yakir, D., and Valentini, R.: On the separation of net ecosystem exchange into assimilation and ecosystem respiration: review and improved algorithm, Global Change Biol., 11, 1424–1439, https://doi.org/10.1111/j.1365-2486.2005.001002.x, 2005.
Reichstein, M., Camps-Valls, G., Stevens, B., Jung, M., Denzler, J., Carvalhais, N., and Prabhat, fnm: Deep learning and process understanding for data-driven Earth Syst. Sci., Nature, 566, 195–204, 2019.
Reichstein, M., Ahrens, B., Kraft, B., Camps-Valls, G., Carvalhais, N., Gans, F., Gentine, P., and Winkler, A. J.: Combining system modeling and machine learning into hybrid ecosystem modeling, in: Knowledge Guided Machine Learning, Chapman and Hall/CRC, 327–352, https://doi.org/10.1201/9781003143376-14, 2022.
Richardson, A. D., Hollinger, D. Y., Burba, G. G., Davis, K. J., Flanagan, L. B., Katul, G. G., Munger, J. W., Ricciuto, D. M., Stoy, P. C., and Suyker, A. E.: A multi-site analysis of random error in tower-based measurements of carbon and energy fluxes, Agr. Forest Meteorol., 136, 1–18, 2006.
Schwalm, C. R., Williams, C. A., Schaefer, K., Arneth, A., Bonal, D., Buchmann, N., Chen, J., Law, B. E., Lindroth, A., Luyssaert, S., Reichstein, M., and Richardson, A. D.: Assimilation exceeds respiration sensitivity to drought: A FLUXNET synthesis, Global Change Biol., 16, 657–670, https://doi.org/10.1111/j.1365-2486.2009.01991.x, 2010.
Seyfried, M. S. and Wilcox, B. P.: Soil water storage and rooting depth: key factors controlling recharge on rangelands, Hydrol. Process., 20, 3261–3275, https://doi.org/10.1002/hyp.6331, 2006.
Shen, W., Jenerette, G. D., Hui, D., and Scott, R. L.: Precipitation legacy effects on dryland ecosystem carbon fluxes: direction, magnitude and biogeochemical carryovers, Biogeosciences, 13, 425–439, https://doi.org/10.5194/bg-13-425-2016, 2016.
Shwetha, P. and Varija, K.: Soil Water Retention Curve from Saturated Hydraulic Conductivity for Sandy Loam and Loamy Sand Textured Soils, Aquat. Pr., 4, 1142–1149, https://doi.org/10.1016/j.aqpro.2015.02.145, 2015.
Staacke, T., Mueller-Roeber, B., and Balazadeh, S.: Stress resilience in plants: the complex interplay between heat stress memory and resetting, New Phytol., 245, 2402–2421, https://doi.org/10.1111/nph.20377, 2025.
Stocker, B. D., Wang, H., Smith, N. G., Harrison, S. P., Keenan, T. F., Sandoval, D., Davis, T., and Prentice, I. C.: P-model v1.0: an optimality-based light use efficiency model for simulating ecosystem gross primary production, Geosci. Model Dev., 13, 1545–1581, https://doi.org/10.5194/gmd-13-1545-2020, 2020.
Stocker, B. D., Tumber-Dávila, S. J., Konings, A. G., Anderson, M. C., Hain, C., and Jackson, R. B.: Global patterns of water storage in the rooting zones of vegetation, Nat. Geosci., https://doi.org/10.1038/s41561-023-01125-2, 2023.
Sundararajan, M., Taly, A., and Yan, Q.: Axiomatic Attribution for Deep Networks, http://arxiv.org/abs/1703.01365, last access: 12 June 2017.
Teegavarapu, R. S. V.: Chapter 2 – Changes and Trends in Precipitation Extremes and Characteristics: Links to Climate Variability and Change, in: Trends and Changes in Hydroclimatic Variables, edited by: Teegavarapu, R., Elsevier, 91–148, https://doi.org/10.1016/B978-0-12-810985-4.00002-5, 2019.
Teuling, A. J., Seneviratne, S. I., Williams, C., and Troch, P. A.: Observed timescales of evapotranspiration response to soil moisture, Geophys. Res. Lett., 33, https://doi.org/10.1029/2006GL028178, 2006.
Toms, B. A., Barnes, E. A., and Ebert-Uphoff, I.: Physically Interpretable Neural Networks for the Geosciences: Applications to Earth System Variability, J. Adv. Model. Earth Syst., 12, e2019MS002002, https://doi.org/10.1029/2019MS002002, 2020.
Tumber-Dávila, S. J., Schenk, H. J., Du, E., and Jackson, R. B.: Plant sizes and shapes above- and belowground and their interactions with climate, New Phytol., 235, 1032–1056, https://doi.org/10.1111/nph.18031, 2022.
Verheijen, F. G. A., Zhuravel, A., Silva, F. C., Amaro, A., Ben-Hur, M., and Keizer, J. J.: The influence of biochar particle size and concentration on bulk density and maximum water holding capacity of sandy vs sandy loam soil in a column experiment, Geoderma, 347, 194–202, https://doi.org/10.1016/j.geoderma.2019.03.044, 2019.
Vuichard, N. and Papale, D.: Filling the gaps in meteorological continuous data measured at FLUXNET sites with ERA-Interim reanalysis, Earth Syst. Sci. Data, 7, 157–171, https://doi.org/10.5194/essd-7-157-2015, 2015.
Wang, K., Li, Z., and Cribb, M.: Estimation of evaporative fraction from a combination of day and night land surface temperatures and NDVI: A new method to determine the Priestley–Taylor parameter, Remote Sens. Environ., 102, 293–305, https://doi.org/10.1016/j.rse.2006.02.007, 2006.
Warm Winter 2020 Team and ICOS Ecosystem Thematic Centre: Warm Winter 2020 ecosystem eddy covariance flux product for 73 stations in FLUXNET-Archive format – release 2022-1, version 1.0, ICOS Carbon Portal [data set], https://doi.org/10.18160/2G60-ZHAK, 2022.
Williams, I. N. and Torn, M. S.: Vegetation controls on surface heat flux partitioning, and land-atmosphere coupling, Geophys. Res. Lett., 42, 9416–9424, https://doi.org/10.1002/2015GL066305, 2015.
Wilson, K., Goldstein, A., Falge, E., Aubinet, M., Baldocchi, D., Berbigier, P., Bernhofer, C., Ceulemans, R., Dolman, H., Field, C., Grelle, A., Ibrom, A., Law, B. E., Kowalski, A., Meyers, T., Moncrieff, J., Monson, R., Oechel, W., Tenhunen, J., Valentini, R., and Verma, S.: Energy balance closure at FLUXNET sites, Agr. Forest Meteorol., 113, 223–243, https://doi.org/10.1016/S0168-1923(02)00109-0, 2002.
Xiao, L., Wu, X., Zhao, S., and Zhou, J.: Memory effects of vegetation after extreme weather events under various geological conditions in a typical karst watershed in southwestern China, Agr. Forest Meteorol., 345, 109840, https://doi.org/10.1016/j.agrformet.2023.109840, 2024.
Yang, W., Shabanov, N., Huang, D., Wang, W., Dickinson, R., Nemani, R., Knyazikhin, Y., and Myneni, R.: Analysis of leaf area index products from combination of MODIS Terra and Aqua data, Remote Sens. Environ., 104, 297–312, 2006.
Ying, H., Zhang, H., Zhao, J., Shan, Y., Zhang, Z., Guo, X., Wu, R., and Deng, G.: Effects of spring and summer extreme climate events on the autumn phenology of different vegetation types of Inner Mongolia, China, from 1982 to 2015, Ecol. Indic., 111, 105974, https://doi.org/10.1016/j.ecolind.2019.105974, 2020.
Zenone, T., Vitale, L., Famulari, D., and Magliulo, V.: Application of machine learning techniques to simulate the evaporative fraction and its relationship with environmental variables in corn crops, Ecol. Process., 11, 54, https://doi.org/10.1186/s13717-022-00400-1, 2022.
Zhang, Y., Keenan, T. F., and Zhou, S.: Exacerbated drought impacts on global ecosystems due to structural overshoot, Nat. Ecol. Evol., 5, 1490–1498, https://doi.org/10.1038/s41559-021-01551-8, 2021.
Zhao, W.: Representative analysis and plotting scripts for Learning Evaporative Fraction with Memory, Zenodo [computer software], https://doi.org/10.5281/zenodo.21960468, 2026.
Zhao, W. L., Gentine, P., Reichstein, M., Zhang, Y., Zhou, S., Wen, Y., Lin, C., Li, X., and Qiu, G. Y.: Physics‐Constrained Machine Learning of Evapotranspiration, Geophys. Res. Lett., 46, 14496–14507, https://doi.org/10.1029/2019GL085291, 2019.
Zhao, W., Winkler, A. J., Reichstein, M., Orth, R., and Gentine, P.: Learning Evaporative Fraction with Memory (video abstract), TIB AV-Portal [video supplement], https://doi.org/10.5446/73776, 2026.
Editorial statement
This study proposes a novel framework for predicting evaporative fraction (EF) by explicitly incorporating meteorological memory into machine learning models. By demonstrating that long short-term memory (LSTM) networks substantially outperform conventional approaches across a range of ecosystems, the study reveals that vegetation responses to water availability are fundamentally governed by temporal dependencies that are often neglected in current modeling frameworks. This work provides new process-level understanding of land–atmosphere interactions.
This study proposes a novel framework for predicting evaporative fraction (EF) by explicitly...
Short summary
We used explainable machine learning that incorporates memory effects to study how plants respond to weather and drought. Using data from 90 sites worldwide, we show that memory plays a key role in regulating plant water stress. Forests and savannas rely on longer past conditions than grasslands, reflecting differences in rooting depth and water use. These insights improve our ability to anticipate ecosystem vulnerability as droughts intensify.
We used explainable machine learning that incorporates memory effects to study how plants...
