Articles | Volume 28, issue 4
https://doi.org/10.5194/hess-28-917-2024
© Author(s) 2024. 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-28-917-2024
© Author(s) 2024. This work is distributed under
the Creative Commons Attribution 4.0 License.
the Creative Commons Attribution 4.0 License.
Research article
| 
27 Feb 2024
Research article |
| 27 Feb 2024
| 27 Feb 2024
A comprehensive study of deep learning for soil moisture prediction
Yanling Wang
State Key Laboratory of Water Resources Engineering and Management, Wuhan University, Wuhan, China
Liangsheng Shi
CORRESPONDING AUTHOR
State Key Laboratory of Water Resources Engineering and Management, Wuhan University, Wuhan, China
Yaan Hu
State Key Laboratory of Hydrology, Water Resources and Hydraulic Engineering, Nanjing Hydraulic Research Institute, Nanjing, China
Xiaolong Hu
State Key Laboratory of Water Resources Engineering and Management, Wuhan University, Wuhan, China
Wenxiang Song
State Key Laboratory of Water Resources Engineering and Management, Wuhan University, Wuhan, China
Lijun Wang
State Key Laboratory of Water Resources Engineering and Management, Wuhan University, Wuhan, China
Related authors
No articles found.
Yakun Wang, Xiaolong Hu, Lijun Wang, Jinmin Li, Lin Lin, Kai Huang, and Liangsheng Shi
Hydrol. Earth Syst. Sci., 27, 2661–2680, https://doi.org/10.5194/hess-27-2661-2023, https://doi.org/10.5194/hess-27-2661-2023, 2023
Short summary
Short summary
To avoid overloaded monitoring cost from redundant measurements, this study proposed a non-parametric data worth analysis framework to assess the worth of future soil moisture data regarding the model-free unsaturated flow models before data gathering. Results indicated that (1) the method can quantify the data worth of alternative monitoring schemes to obtain the optimal one, and (2) high-quality and representative small data could be a better choice than unfiltered big data.
Ronny Meier, Edouard L. Davin, Gordon B. Bonan, David M. Lawrence, Xiaolong Hu, Gregory Duveiller, Catherine Prigent, and Sonia I. Seneviratne
Geosci. Model Dev., 15, 2365–2393, https://doi.org/10.5194/gmd-15-2365-2022, https://doi.org/10.5194/gmd-15-2365-2022, 2022
Short summary
Short summary
We revise the roughness of the land surface in the CESM climate model. Guided by observational data, we increase the surface roughness of forests and decrease that of bare soil, snow, ice, and crops. These modifications alter simulated temperatures and wind speeds at and above the land surface considerably, in particular over desert regions. The revised model represents the diurnal variability of the land surface temperature better compared to satellite observations over most regions.
Danyang Yu, Jinzhong Yang, Liangsheng Shi, Qiuru Zhang, Kai Huang, Yuanhao Fang, and Yuanyuan Zha
Hydrol. Earth Syst. Sci., 23, 2897–2914, https://doi.org/10.5194/hess-23-2897-2019, https://doi.org/10.5194/hess-23-2897-2019, 2019
Jicai Zeng, Jinzhong Yang, Yuanyuan Zha, and Liangsheng Shi
Hydrol. Earth Syst. Sci., 23, 637–655, https://doi.org/10.5194/hess-23-637-2019, https://doi.org/10.5194/hess-23-637-2019, 2019
Short summary
Short summary
Accurately capturing the soil-water–groundwater interaction is vital for all disciplines related to subsurface flow but is difficult when undergoing significant nonlinearity in the modeling system. A new soil-water flow package is developed to solve the switching-form Richards’ equation. A multi-scale water balance analysis joins unsaturated–saturated models at separated scales. The whole system is solved efficiently with an iterative feedback coupling scheme.
Related subject area
Subject: Vadose Zone Hydrology | Techniques and Approaches: Modelling approaches
Modeling 2D gravity-driven flow in unsaturated porous media for different infiltration rates
Mesoscale permeability variations estimated from natural airflows in the decorated Cosquer Cave (southeastern France)
Identification of parameter importance for benzene transport in the unsaturated zone using global sensitivity analysis
Evapotranspiration prediction for European forest sites does not improve with assimilation of in situ soil water content data
Quantifying the potential of using SMAP soil moisture variability to predict subsurface water dynamics
Modelling groundwater recharge, actual evaporation, and transpiration in semi-arid sites of the Lake Chad basin: the role of soil and vegetation in groundwater recharge
Predicting soil hydraulic properties for binary mixtures – concept and application for constructed Technosols
Application of an improved distributed hydrological model based on the soil–gravel structure in the Niyang River basin, Qinghai–Tibet Plateau
Assessment of the interactions between soil–biosphere–atmosphere (ISBA) land surface model soil hydrology, using four closed-form soil water relationships and several lysimeters
Soil–vegetation–water interactions controlling solute flow and chemical weathering in volcanic ash soils of the high Andes
Estimating vadose zone water fluxes from soil water monitoring data: a comprehensive field study in Austria
Semi-continuum modeling of unsaturated porous media flow to explain Bauters' paradox
Effects of dynamic changes of desiccation cracks on preferential flow: experimental investigation and numerical modeling
Numerical assessment of morphological and hydraulic properties of moss, lichen and peat from a permafrost peatland
A robust upwind mixed hybrid finite element method for transport in variably saturated porous media
Stepping beyond perfectly mixed conditions in soil hydrological modelling using a Lagrangian approach
Using machine learning to predict optimal electromagnetic induction instrument configurations for characterizing the shallow subsurface
Gravity as a tool to improve the hydrologic mass budget in karstic areas
A scaling procedure for straightforward computation of sorptivity
From hydraulic root architecture models to macroscopic representations of root hydraulics in soil water flow and land surface models
Simulated or measured soil moisture: which one is adding more value to regional landslide early warning?
Interaction of soil water and groundwater during the freezing–thawing cycle: field observations and numerical modeling
Assessing the dynamics of soil salinity with time-lapse inversion of electromagnetic data guided by hydrological modelling
Simulation of reactive solute transport in the critical zone: a Lagrangian model for transient flow and preferential transport
Investigating the impact of exit effects on solute transport in macroporous media
Comparison of root water uptake models in simulating CO2 and H2O fluxes and growth of wheat
Understanding the mass, momentum, and energy transfer in the frozen soil with three levels of model complexities
A field-validated surrogate crop model for predicting root-zone moisture and salt content in regions with shallow groundwater
Characterizing uncertainty in the hydraulic parameters of oil sands mine reclamation covers and its influence on water balance predictions
Simulating preferential soil water flow and tracer transport using the Lagrangian Soil Water and Solute Transport Model
Assessment of simulated soil moisture from WRF Noah, Noah-MP, and CLM land surface schemes for landslide hazard application
Efficient estimation of effective hydraulic properties of stratal undulating surface layer using time-lapse multi-channel GPR
Partitioning snowmelt and rainfall in the critical zone: effects of climate type and soil properties
A unique vadose zone model for shallow aquifers: the Hetao irrigation district, China
Modelling of shallow water table dynamics using conceptual and physically based integrated surface-water–groundwater hydrologic models
Capturing soil-water and groundwater interactions with an iterative feedback coupling scheme: new HYDRUS package for MODFLOW
Caffeine vs. carbamazepine as indicators of wastewater pollution in a karst aquifer
Predicting the soil water retention curve from the particle size distribution based on a pore space geometry containing slit-shaped spaces
Technical note: Saturated hydraulic conductivity and textural heterogeneity of soils
Water ages in the critical zone of long-term experimental sites in northern latitudes
Ecohydrological particle model based on representative domains
Impact of capillary rise and recirculation on simulated crop yields
Soil hydraulic material properties and layered architecture from time-lapse GPR
Root growth, water uptake, and sap flow of winter wheat in response to different soil water conditions
Using lagged dependence to identify (de)coupled surface and subsurface soil moisture values
Shallow water table effects on water, sediment, and pesticide transport in vegetative filter strips – Part 1: nonuniform infiltration and soil water redistribution
Shallow water table effects on water, sediment, and pesticide transport in vegetative filter strips – Part 2: model coupling, application, factor importance, and uncertainty
A pore-size classification for peat bogs derived from unsaturated hydraulic properties
Monitoring and modeling infiltration–recharge dynamics of managed aquifer recharge with desalinated seawater
Effect of unrepresented model errors on estimated soil hydraulic material properties
Jakub Kmec and Miloslav Šír
Hydrol. Earth Syst. Sci., 28, 4947–4970, https://doi.org/10.5194/hess-28-4947-2024, https://doi.org/10.5194/hess-28-4947-2024, 2024
Short summary
Short summary
The most mysterious part of the hydrological cycle is the infiltration of water into porous soil. In this process, water enters the soil, some of it is retained in the soil or evaporates, and the remaining water continues to move below and through the rock environment. The physical description of infiltration, specifically the dependence of the infiltration rate on the flow, shows very unusual features that are beyond the normal human experience. Our paper is devoted to their elucidation.
Hugo Pellet, Bruno Arfib, Pierre Henry, Stéphanie Touron, and Ghislain Gassier
Hydrol. Earth Syst. Sci., 28, 4035–4057, https://doi.org/10.5194/hess-28-4035-2024, https://doi.org/10.5194/hess-28-4035-2024, 2024
Short summary
Short summary
Conservation of decorated caves is highly dependent on airflows and is correlated with rock formation permeability. We present the first conceptual model of flows around the Paleolithic decorated Cosquer coastal cave (southeastern France), quantify air permeability, and show how its variation affects water levels inside the cave. This study highlights that airflows may change in karst unsaturated zones in response to changes in the water cycle and may thus be affected by climate change.
Meirav Cohen, Nimrod Schwartz, and Ravid Rosenzweig
Hydrol. Earth Syst. Sci., 28, 1585–1604, https://doi.org/10.5194/hess-28-1585-2024, https://doi.org/10.5194/hess-28-1585-2024, 2024
Short summary
Short summary
Contamination from fuel constituents poses a major threat to groundwater. However, studies devoted to identification of the driving parameters for fuel derivative transport in soils are scarce, and none have dealt with heterogeneous layered media. Here, we performed global sensitivity analysis (GSA) on a model of benzene transport to groundwater. The results identified the parameters controlling benzene transport in soils and showed that GSA is as an important tool for transport model analysis.
Lukas Strebel, Heye Bogena, Harry Vereecken, Mie Andreasen, Sergio Aranda-Barranco, and Harrie-Jan Hendricks Franssen
Hydrol. Earth Syst. Sci., 28, 1001–1026, https://doi.org/10.5194/hess-28-1001-2024, https://doi.org/10.5194/hess-28-1001-2024, 2024
Short summary
Short summary
We present results from using soil water content measurements from 13 European forest sites in a state-of-the-art land surface model. We use data assimilation to perform a combination of observed and modeled soil water content and show the improvements in the representation of soil water content. However, we also look at the impact on evapotranspiration and see no corresponding improvements.
Aruna Kumar Nayak, Xiaoyong Xu, Steven K. Frey, Omar Khader, Andre R. Erler, David R. Lapen, Hazen A. J. Russell, and Edward A. Sudicky
Hydrol. Earth Syst. Sci. Discuss., https://doi.org/10.5194/hess-2023-309, https://doi.org/10.5194/hess-2023-309, 2024
Revised manuscript accepted for HESS
Short summary
Short summary
Satellite remote sensing measures only the near-surface soil water content. This study demonstrates that satellite-based near-surface soil water variability is a strong reflection of deeper subsurface water fluctuation and quantifies the response time differences between dynamics of satellite near-surface soil water and water in deeper subsurface. Result support the use of satellite near-surface soil water measurements as indicators and/or predictors of water resources in deeper subsurface.
Christoph Neukum, Angela Morales-Santos, Melanie Ronelngar, Aminu Bala, and Sara Vassolo
Hydrol. Earth Syst. Sci., 27, 3601–3619, https://doi.org/10.5194/hess-27-3601-2023, https://doi.org/10.5194/hess-27-3601-2023, 2023
Short summary
Short summary
A generalized approach that requires limited field data and well-established models is tested for assessing groundwater recharge in the southern Lake Chad basin. E and T coefficients are estimated with the FAO-dual Kc concept at six locations. Measured soil water content and chloride concentrations along vertical soil profiles together with different scenarios for E and T partitioning and a Bayesian calibration approach are used to simulate water flow and chloride transport using Hydrus-1D.
Moreen Willaredt, Thomas Nehls, and Andre Peters
Hydrol. Earth Syst. Sci., 27, 3125–3142, https://doi.org/10.5194/hess-27-3125-2023, https://doi.org/10.5194/hess-27-3125-2023, 2023
Short summary
Short summary
This study proposes a model to predict soil hydraulic properties (SHPs) of constructed Technosols for urban greening. The SHPs are determined by the Technosol composition and describe their capacity to store and supply water to plants. The model predicts SHPs of any binary mixture based on the SHPs of its two pure components, facilitating simulations of flow and transport processes before production. This can help create Technosols designed for efficient urban greening and water management.
Pengxiang Wang, Zuhao Zhou, Jiajia Liu, Chongyu Xu, Kang Wang, Yangli Liu, Jia Li, Yuqing Li, Yangwen Jia, and Hao Wang
Hydrol. Earth Syst. Sci., 27, 2681–2701, https://doi.org/10.5194/hess-27-2681-2023, https://doi.org/10.5194/hess-27-2681-2023, 2023
Short summary
Short summary
Considering the impact of the special geological and climatic conditions of the Qinghai–Tibet Plateau on the hydrological cycle, this study established the WEP-QTP hydrological model. The snow cover and gravel layers affected the temporal and spatial changes in frozen soil and improved the regulation of groundwater on the flow process. Ignoring he influence of special underlying surface conditions has a great impact on the hydrological forecast and water resource utilization in this area.
Antoine Sobaga, Bertrand Decharme, Florence Habets, Christine Delire, Noële Enjelvin, Paul-Olivier Redon, Pierre Faure-Catteloin, and Patrick Le Moigne
Hydrol. Earth Syst. Sci., 27, 2437–2461, https://doi.org/10.5194/hess-27-2437-2023, https://doi.org/10.5194/hess-27-2437-2023, 2023
Short summary
Short summary
Seven instrumented lysimeters are used to assess the simulation of the soil water dynamic in one land surface model. Four water potential and hydraulic conductivity closed-form equations, including one mixed form, are evaluated. One form is more relevant for simulating drainage, especially during intense drainage events. The soil profile heterogeneity of one parameter of the closed-form equations is shown to be important.
Sebastián Páez-Bimos, Armando Molina, Marlon Calispa, Pierre Delmelle, Braulio Lahuatte, Marcos Villacís, Teresa Muñoz, and Veerle Vanacker
Hydrol. Earth Syst. Sci., 27, 1507–1529, https://doi.org/10.5194/hess-27-1507-2023, https://doi.org/10.5194/hess-27-1507-2023, 2023
Short summary
Short summary
This study analyzes how vegetation influences soil hydrology, water fluxes, and chemical weathering rates in the high Andes. There are clear differences in the A horizon. The extent of soil chemical weathering varies depending on vegetation type. This difference is attributed mainly to the water fluxes. Our findings reveal that vegetation can modify soil properties in the uppermost horizon, altering the water balance, solutes, and chemical weathering throughout the entire soil profile.
Marleen Schübl, Giuseppe Brunetti, Gabriele Fuchs, and Christine Stumpp
Hydrol. Earth Syst. Sci., 27, 1431–1455, https://doi.org/10.5194/hess-27-1431-2023, https://doi.org/10.5194/hess-27-1431-2023, 2023
Short summary
Short summary
Estimating groundwater recharge through the unsaturated zone is a difficult task that is fundamentally associated with uncertainties. One of the few methods available is inverse modeling based on soil water measurements. Here, we used a nested sampling algorithm within a Bayesian probabilistic framework to assess model uncertainties at 14 sites in Austria. Further, we analyzed simulated recharge rates to identify factors influencing groundwater recharge rates and their temporal variability.
Jakub Kmec, Miloslav Šír, Tomáš Fürst, and Rostislav Vodák
Hydrol. Earth Syst. Sci., 27, 1279–1300, https://doi.org/10.5194/hess-27-1279-2023, https://doi.org/10.5194/hess-27-1279-2023, 2023
Short summary
Short summary
When rain falls on the ground, most of the water subsequently flows through the soil. The movement of water through the partially wet soil layer is surprisingly complicated. For decades, no mathematical model has been able to capture this process in its entire complexity. Here, we present a model that aims to solve this long-standing problem. In this paper, we show that the model correctly reproduces the transition between diffusion and preferential flow regimes.
Yi Luo, Jiaming Zhang, Zhi Zhou, Juan P. Aguilar-Lopez, Roberto Greco, and Thom Bogaard
Hydrol. Earth Syst. Sci., 27, 783–808, https://doi.org/10.5194/hess-27-783-2023, https://doi.org/10.5194/hess-27-783-2023, 2023
Short summary
Short summary
This paper describes an experiment and modeling of the hydrological response of desiccation cracks under long-term wetting–drying cycles. We developed a new dynamic dual-permeability model to quantify the dynamic evolution of desiccation cracks and associated preferential flow and moisture distribution. Compared to other models, the dynamic dual-permeability model could describe the experimental data much better, but it also provided an improved description of the underlying physics.
Simon Cazaurang, Manuel Marcoux, Oleg S. Pokrovsky, Sergey V. Loiko, Artem G. Lim, Stéphane Audry, Liudmila S. Shirokova, and Laurent Orgogozo
Hydrol. Earth Syst. Sci., 27, 431–451, https://doi.org/10.5194/hess-27-431-2023, https://doi.org/10.5194/hess-27-431-2023, 2023
Short summary
Short summary
Moss, lichen and peat samples are reconstructed using X-ray tomography. Most samples can be cut down to a representative volume based on porosity. However, only homogeneous samples could be reduced to a representative volume based on hydraulic conductivity. For heterogeneous samples, a devoted pore network model is computed. The studied samples are mostly highly porous and water-conductive. These results must be put into perspective with compressibility phenomena occurring in field tests.
Anis Younes, Hussein Hoteit, Rainer Helmig, and Marwan Fahs
Hydrol. Earth Syst. Sci., 26, 5227–5239, https://doi.org/10.5194/hess-26-5227-2022, https://doi.org/10.5194/hess-26-5227-2022, 2022
Short summary
Short summary
Despite its advantages for the simulation of flow in heterogeneous and fractured porous media, the mixed hybrid finite element method has been rarely used for transport as it suffers from strong unphysical oscillations. We develop here a new upwind scheme for the mixed hybrid finite element that can avoid oscillations. Numerical examples confirm the robustness of this new scheme for the simulation of contaminant transport in both saturated and unsaturated conditions.
Alexander Sternagel, Ralf Loritz, Brian Berkowitz, and Erwin Zehe
Hydrol. Earth Syst. Sci., 26, 1615–1629, https://doi.org/10.5194/hess-26-1615-2022, https://doi.org/10.5194/hess-26-1615-2022, 2022
Short summary
Short summary
We present a (physically based) Lagrangian approach to simulate diffusive mixing processes on the pore scale beyond perfectly mixed conditions. Results show the feasibility of the approach for reproducing measured mixing times and concentrations of isotopes over pore sizes and that typical shapes of breakthrough curves (normally associated with non-uniform transport in heterogeneous soils) may also occur as a result of imperfect subscale mixing in a macroscopically homogeneous soil matrix.
Kim Madsen van't Veen, Ty Paul Andrew Ferré, Bo Vangsø Iversen, and Christen Duus Børgesen
Hydrol. Earth Syst. Sci., 26, 55–70, https://doi.org/10.5194/hess-26-55-2022, https://doi.org/10.5194/hess-26-55-2022, 2022
Short summary
Short summary
Geophysical instruments are often used in hydrological surveys. A geophysical model that couples electrical conductivity in the subsurface layers with measurements from an electromagnetic induction instrument was combined with a machine learning algorithm. The study reveals that this combination can estimate the identifiability of electrical conductivity in a layered soil and provide insight into the best way to configure the instrument for a specific field site.
Tommaso Pivetta, Carla Braitenberg, Franci Gabrovšek, Gerald Gabriel, and Bruno Meurers
Hydrol. Earth Syst. Sci., 25, 6001–6021, https://doi.org/10.5194/hess-25-6001-2021, https://doi.org/10.5194/hess-25-6001-2021, 2021
Short summary
Short summary
Gravimetry offers a valid complement to classical hydrologic measurements in order to characterize karstic systems in which the recharge process causes fast accumulation of large water volumes in the voids of the epi-phreatic system. In this contribution we show an innovative integration of gravimetric and hydrologic observations to constrain a hydrodynamic model of the Škocjan Caves (Slovenia). We demonstrate how the inclusion of gravity observations improves the water mass budget estimates.
Laurent Lassabatere, Pierre-Emmanuel Peyneau, Deniz Yilmaz, Joseph Pollacco, Jesús Fernández-Gálvez, Borja Latorre, David Moret-Fernández, Simone Di Prima, Mehdi Rahmati, Ryan D. Stewart, Majdi Abou Najm, Claude Hammecker, and Rafael Angulo-Jaramillo
Hydrol. Earth Syst. Sci., 25, 5083–5104, https://doi.org/10.5194/hess-25-5083-2021, https://doi.org/10.5194/hess-25-5083-2021, 2021
Short summary
Short summary
Soil sorptivity is a crucial parameter for the modeling of water infiltration into soils. The standard equation used to compute sorptivity from the soil water retention curve, the unsaturated hydraulic conductivity, and initial and final water contents may lead to erroneous estimates due to its complexity. This study proposes a new straightforward scaling procedure for estimations of sorptivity for four famous and commonly used hydraulic models.
Jan Vanderborght, Valentin Couvreur, Felicien Meunier, Andrea Schnepf, Harry Vereecken, Martin Bouda, and Mathieu Javaux
Hydrol. Earth Syst. Sci., 25, 4835–4860, https://doi.org/10.5194/hess-25-4835-2021, https://doi.org/10.5194/hess-25-4835-2021, 2021
Short summary
Short summary
Root water uptake is an important process in the terrestrial water cycle. How this process depends on soil water content, root distributions, and root properties is a soil–root hydraulic problem. We compare different approaches to implementing root hydraulics in macroscopic soil water flow and land surface models.
Adrian Wicki, Per-Erik Jansson, Peter Lehmann, Christian Hauck, and Manfred Stähli
Hydrol. Earth Syst. Sci., 25, 4585–4610, https://doi.org/10.5194/hess-25-4585-2021, https://doi.org/10.5194/hess-25-4585-2021, 2021
Short summary
Short summary
Soil moisture information was shown to be valuable for landslide prediction. Soil moisture was simulated at 133 sites in Switzerland, and the temporal variability was compared to the regional occurrence of landslides. We found that simulated soil moisture is a good predictor for landslides, and that the forecast goodness is similar to using in situ measurements. This encourages the use of models for complementing existing soil moisture monitoring networks for regional landslide early warning.
Hong-Yu Xie, Xiao-Wei Jiang, Shu-Cong Tan, Li Wan, Xu-Sheng Wang, Si-Hai Liang, and Yijian Zeng
Hydrol. Earth Syst. Sci., 25, 4243–4257, https://doi.org/10.5194/hess-25-4243-2021, https://doi.org/10.5194/hess-25-4243-2021, 2021
Short summary
Short summary
Freezing-induced groundwater migration and water table decline are widely observed, but quantitative understanding of these processes is lacking. By considering wintertime atmospheric conditions and occurrence of lateral groundwater inflow, a model coupling soil water and groundwater reproduced field observations of soil temperature, soil water content, and groundwater level well. The model results led to a clear understanding of the balance of the water budget during the freezing–thawing cycle.
Mohammad Farzamian, Dario Autovino, Angelo Basile, Roberto De Mascellis, Giovanna Dragonetti, Fernando Monteiro Santos, Andrew Binley, and Antonio Coppola
Hydrol. Earth Syst. Sci., 25, 1509–1527, https://doi.org/10.5194/hess-25-1509-2021, https://doi.org/10.5194/hess-25-1509-2021, 2021
Short summary
Short summary
Soil salinity is a serious threat in numerous arid and semi-arid areas of the world. Given this threat, efficient field assessment methods are needed to monitor the dynamics of soil salinity in salt-affected lands efficiently. We demonstrate that rapid and non-invasive geophysical measurements modelled by advanced numerical analysis of the signals and coupled with hydrological modelling can provide valuable information to assess the spatio-temporal variability in soil salinity over large areas.
Alexander Sternagel, Ralf Loritz, Julian Klaus, Brian Berkowitz, and Erwin Zehe
Hydrol. Earth Syst. Sci., 25, 1483–1508, https://doi.org/10.5194/hess-25-1483-2021, https://doi.org/10.5194/hess-25-1483-2021, 2021
Short summary
Short summary
The key innovation of the study is a method to simulate reactive solute transport in the vadose zone within a Lagrangian framework. We extend the LAST-Model with a method to account for non-linear sorption and first-order degradation processes during unsaturated transport of reactive substances in the matrix and macropores. Model evaluations using bromide and pesticide data from irrigation experiments under different flow conditions on various timescales show the feasibility of the method.
Jérôme Raimbault, Pierre-Emmanuel Peyneau, Denis Courtier-Murias, Thomas Bigot, Jaime Gil Roca, Béatrice Béchet, and Laurent Lassabatère
Hydrol. Earth Syst. Sci., 25, 671–683, https://doi.org/10.5194/hess-25-671-2021, https://doi.org/10.5194/hess-25-671-2021, 2021
Short summary
Short summary
Contaminant transport in soils is known to be affected by soil heterogeneities such as macropores. The transport properties of heterogeneous porous media can be studied in laboratory columns. However, the results reported in this study (a combination of breakthrough experiments, magnetic resonance imaging and computer simulations of transport) show that these properties can be largely affected by the boundary devices of the columns, thus highlighting the need to take their effect into account.
Thuy Huu Nguyen, Matthias Langensiepen, Jan Vanderborght, Hubert Hüging, Cho Miltin Mboh, and Frank Ewert
Hydrol. Earth Syst. Sci., 24, 4943–4969, https://doi.org/10.5194/hess-24-4943-2020, https://doi.org/10.5194/hess-24-4943-2020, 2020
Short summary
Short summary
The mechanistic Couvreur root water uptake (RWU) model that is based on plant hydraulics and links root system properties to RWU, water stress, and crop development can evaluate the impact of certain crop properties on crop performance in different environments and soils, while the Feddes RWU approach does not possess such flexibility. This study also shows the importance of modeling root development and how it responds to water deficiency to predict the impact of water stress on crop growth.
Lianyu Yu, Yijian Zeng, and Zhongbo Su
Hydrol. Earth Syst. Sci., 24, 4813–4830, https://doi.org/10.5194/hess-24-4813-2020, https://doi.org/10.5194/hess-24-4813-2020, 2020
Short summary
Short summary
Soil mass and heat transfer processes were represented in three levels of model complexities to understand soil freeze–thaw mechanisms. Results indicate that coupled mass and heat transfer models considerably improved simulations of the soil hydrothermal regime. Vapor flow and thermal effects on water flow are the main mechanisms for the improvements. Given the explicit consideration of airflow, vapor flow and its effects on heat transfer were enhanced during the freeze–thaw transition period.
Zhongyi Liu, Zailin Huo, Chaozi Wang, Limin Zhang, Xianghao Wang, Guanhua Huang, Xu Xu, and Tammo Siert Steenhuis
Hydrol. Earth Syst. Sci., 24, 4213–4237, https://doi.org/10.5194/hess-24-4213-2020, https://doi.org/10.5194/hess-24-4213-2020, 2020
Short summary
Short summary
We have developed an integrated surrogate model for arid irrigated areas with shallow groundwater that links crop growth with soil water and salinity in the vadose zone. The model recognizes that field capacity is reached when the matric potential is equal to the height above the groundwater table. The model applies areas with shallow groundwater for which only very few surrogate models are available for most surface irrigation systems in the world without suffering from high groundwater.
M. Shahabul Alam, S. Lee Barbour, and Mingbin Huang
Hydrol. Earth Syst. Sci., 24, 735–759, https://doi.org/10.5194/hess-24-735-2020, https://doi.org/10.5194/hess-24-735-2020, 2020
Short summary
Short summary
This study quantifies uncertainties in the prediction of long-term water balance for mine reclamation soil covers using random sampling of model parameter distributions. Parameter distributions were obtained from model optimization for field monitoring data. Variability in climate is a greater source of uncertainty than the model parameters in evaporation predictions, while climate variability and model parameters exert similar uncertainty on predictions of net percolation.
Alexander Sternagel, Ralf Loritz, Wolfgang Wilcke, and Erwin Zehe
Hydrol. Earth Syst. Sci., 23, 4249–4267, https://doi.org/10.5194/hess-23-4249-2019, https://doi.org/10.5194/hess-23-4249-2019, 2019
Short summary
Short summary
We present our hydrological LAST-Model to simulate preferential soil water flow and tracer transport in macroporous soils. It relies on a Lagrangian perspective of the movement of discrete water particles carrying tracer masses through the subsoil and is hence an alternative approach to common models. Sensitivity analyses reveal the physical validity of the model concept and evaluation tests show that LAST can depict well observed tracer mass profiles with fingerprints of preferential flow.
Lu Zhuo, Qiang Dai, Dawei Han, Ningsheng Chen, and Binru Zhao
Hydrol. Earth Syst. Sci., 23, 4199–4218, https://doi.org/10.5194/hess-23-4199-2019, https://doi.org/10.5194/hess-23-4199-2019, 2019
Short summary
Short summary
This study assesses the usability of WRF model-simulated soil moisture for landslide monitoring in northern Italy. In particular, three advanced land surface model schemes (Noah, Noah-MP, and CLM4) are used to provide multi-layer soil moisture data. The results have shown Noah-MP can provide the best landslide monitoring performance. It is also demonstrated that a single soil moisture sensor located in plain area has a high correlation with a significant proportion of the study area.
Xicai Pan, Stefan Jaumann, Jiabao Zhang, and Kurt Roth
Hydrol. Earth Syst. Sci., 23, 3653–3663, https://doi.org/10.5194/hess-23-3653-2019, https://doi.org/10.5194/hess-23-3653-2019, 2019
Short summary
Short summary
This study suggests an efficient approach to obtain plot-scale soil hydraulic properties for the shallow structural soils via non-invasive ground-penetrating radar measurements. Facilitated by spatial information of lateral water flow, this approach is more efficient than the widely used inversion approaches relying on intensive soil moisture monitoring. The acquisition of such quantitative information is of great interest to fields such as hydrology and precision agriculture.
John C. Hammond, Adrian A. Harpold, Sydney Weiss, and Stephanie K. Kampf
Hydrol. Earth Syst. Sci., 23, 3553–3570, https://doi.org/10.5194/hess-23-3553-2019, https://doi.org/10.5194/hess-23-3553-2019, 2019
Short summary
Short summary
Streamflow in high-elevation and high-latitude areas may be vulnerable to snow loss, making it important to quantify how snowmelt and rainfall are divided between soil storage, drainage below plant roots, evapotranspiration and runoff. We examine this separation in different climates and soils using a physically based model. Results show runoff may be reduced with snowpack decline in all climates. The mechanisms responsible help explain recent observations of streamflow sensitivity to snow loss.
Zhongyi Liu, Xingwang Wang, Zailin Huo, and Tammo Siert Steenhuis
Hydrol. Earth Syst. Sci., 23, 3097–3115, https://doi.org/10.5194/hess-23-3097-2019, https://doi.org/10.5194/hess-23-3097-2019, 2019
Short summary
Short summary
A novel approach is taken in simulating the hydrology of the vadose zone in areas with shallow groundwater. The model recognizes that field capacity is reached when the matric potential is equal to the height above the groundwater table. The model can be used in areas with shallow groundwater to optimize irrigation water use and minimize tailwater losses.
Mohammad Bizhanimanzar, Robert Leconte, and Mathieu Nuth
Hydrol. Earth Syst. Sci., 23, 2245–2260, https://doi.org/10.5194/hess-23-2245-2019, https://doi.org/10.5194/hess-23-2245-2019, 2019
Short summary
Short summary
Modelling of shallow water table fluctuations is usually carried out using physically based numerical models. These models have notable limitations regarding intensive required data and computational burden. This paper presents an alternative modelling approach for modelling of such cases by introducing modifications to the calculation of groundwater recharge and saturated flow of a conceptual hydrologic model.
Jicai Zeng, Jinzhong Yang, Yuanyuan Zha, and Liangsheng Shi
Hydrol. Earth Syst. Sci., 23, 637–655, https://doi.org/10.5194/hess-23-637-2019, https://doi.org/10.5194/hess-23-637-2019, 2019
Short summary
Short summary
Accurately capturing the soil-water–groundwater interaction is vital for all disciplines related to subsurface flow but is difficult when undergoing significant nonlinearity in the modeling system. A new soil-water flow package is developed to solve the switching-form Richards’ equation. A multi-scale water balance analysis joins unsaturated–saturated models at separated scales. The whole system is solved efficiently with an iterative feedback coupling scheme.
Noam Zach Dvory, Yakov Livshitz, Michael Kuznetsov, Eilon Adar, Guy Gasser, Irena Pankratov, Ovadia Lev, and Alexander Yakirevich
Hydrol. Earth Syst. Sci., 22, 6371–6381, https://doi.org/10.5194/hess-22-6371-2018, https://doi.org/10.5194/hess-22-6371-2018, 2018
Short summary
Short summary
This research is paramount given the significance of karst aquifers as essential drinking water sources. While CBZ is considered conservative, CAF is subject to sorption and degradation, and therefore each of these two pollutants can be considered effective tracers for specific assessment of aquifer contamination. The model presented in this paper shows how each of the mentioned contaminants could serve as a better tool for aquifer contamination characterization and its treatment.
Chen-Chao Chang and Dong-Hui Cheng
Hydrol. Earth Syst. Sci., 22, 4621–4632, https://doi.org/10.5194/hess-22-4621-2018, https://doi.org/10.5194/hess-22-4621-2018, 2018
Short summary
Short summary
The soil water retention curve (SWRC) is fundamental to researching water flow and chemical transport in unsaturated media. However, the traditional prediction models underestimate the water content in the dry range of the SWRC. A method was therefore proposed to improve the estimation of the SWRC using a pore model containing slit-shaped spaces. The results show that the predicted SWRCs using the improved method reasonably approximated the measured SWRCs.
Carlos García-Gutiérrez, Yakov Pachepsky, and Miguel Ángel Martín
Hydrol. Earth Syst. Sci., 22, 3923–3932, https://doi.org/10.5194/hess-22-3923-2018, https://doi.org/10.5194/hess-22-3923-2018, 2018
Short summary
Short summary
Saturated hydraulic conductivity (Ksat) is an important soil parameter that highly depends on soil's particle size distribution (PSD). The nature of this dependency is explored in this work in two ways, (1) by using the information entropy as a heterogeneity parameter of the PSD and (2) by using descriptions of PSD in forms of textural triplets, different than the usual description in terms of the triplet of sand, silt, and clay contents.
Matthias Sprenger, Doerthe Tetzlaff, Jim Buttle, Hjalmar Laudon, and Chris Soulsby
Hydrol. Earth Syst. Sci., 22, 3965–3981, https://doi.org/10.5194/hess-22-3965-2018, https://doi.org/10.5194/hess-22-3965-2018, 2018
Short summary
Short summary
We estimated water ages in the upper critical zone with a soil physical model (SWIS) and found that the age of water stored in the soil, as well as of water leaving the soil via evaporation, transpiration, or recharge, was younger the higher soil water storage (inverse storage effect). Travel times of transpiration and evaporation were different. We conceptualized the subsurface into fast and slow flow domains and the water was usually half as young in the fast as in the slow flow domain.
Conrad Jackisch and Erwin Zehe
Hydrol. Earth Syst. Sci., 22, 3639–3662, https://doi.org/10.5194/hess-22-3639-2018, https://doi.org/10.5194/hess-22-3639-2018, 2018
Short summary
Short summary
We present a Lagrangian model for non-uniform soil water dynamics. It handles 2-D diffusion (based on a spatial random walk and implicit pore space redistribution) and 1-D advection in representative macropores (as film flow with dynamic interaction with the soil matrix). The interplay between the domains is calculated based on an energy-balance approach which does not require any additional parameterisation. Model tests give insight into the evolution of the non-uniform infiltration patterns.
Joop Kroes, Iwan Supit, Jos van Dam, Paul van Walsum, and Martin Mulder
Hydrol. Earth Syst. Sci., 22, 2937–2952, https://doi.org/10.5194/hess-22-2937-2018, https://doi.org/10.5194/hess-22-2937-2018, 2018
Short summary
Short summary
Impact of upward flow by capillary rise and recirculation on crop yields is often neglected or underestimated. Case studies and model experiments are used to illustrate the impact of this upward flow in the Dutch delta. Neglecting upward flow results in yield reductions for grassland, maize and potatoes. Half of the withheld water behind these yield effects comes from recirculated percolation water as occurs in free-drainage conditions; the other half from increased upward capillary rise.
Stefan Jaumann and Kurt Roth
Hydrol. Earth Syst. Sci., 22, 2551–2573, https://doi.org/10.5194/hess-22-2551-2018, https://doi.org/10.5194/hess-22-2551-2018, 2018
Short summary
Short summary
Ground-penetrating radar (GPR) is a noninvasive and nondestructive measurement method to monitor the hydraulic processes precisely and efficiently. We analyze synthetic as well as measured data from the ASSESS test site and show that the analysis yields accurate estimates for the soil hydraulic material properties as well as for the subsurface architecture by comparing the results to references derived from time domain reflectometry (TDR) and subsurface architecture ground truth data.
Gaochao Cai, Jan Vanderborght, Matthias Langensiepen, Andrea Schnepf, Hubert Hüging, and Harry Vereecken
Hydrol. Earth Syst. Sci., 22, 2449–2470, https://doi.org/10.5194/hess-22-2449-2018, https://doi.org/10.5194/hess-22-2449-2018, 2018
Short summary
Short summary
Different crop growths had consequences for the parameterization of root water uptake models. The root hydraulic parameters of the Couvreur model but not the water stress parameters of the Feddes–Jarvis model could be constrained by the field data measured from rhizotron facilities. The simulated differences in transpiration from the two soils and the different water treatments could be confirmed by sap flow measurements. The Couvreur model predicted the ratios of transpiration fluxes better.
Coleen D. U. Carranza, Martine J. van der Ploeg, and Paul J. J. F. Torfs
Hydrol. Earth Syst. Sci., 22, 2255–2267, https://doi.org/10.5194/hess-22-2255-2018, https://doi.org/10.5194/hess-22-2255-2018, 2018
Short summary
Short summary
Remote sensing has been popular for mapping surface soil moisture. However, estimating subsurface values using surface soil moisture remains a challenge, as decoupling can occur. Depth-integrated soil moisture values used in hydrological models are affected by vertical variability. Using statistical methods, we investigate vertical variability between the surface (5 cm) and subsurface (40 cm) to quantify decoupling. We also discuss potential controls for decoupling during wet and dry conditions.
Rafael Muñoz-Carpena, Claire Lauvernet, and Nadia Carluer
Hydrol. Earth Syst. Sci., 22, 53–70, https://doi.org/10.5194/hess-22-53-2018, https://doi.org/10.5194/hess-22-53-2018, 2018
Short summary
Short summary
Seasonal shallow water tables (WTs) in lowlands limit vegetation-buffer efficiency to control runoff pollution. Mechanistic models are needed to quantify true field efficiency. A new simplified algorithm for soil infiltration over WTs is tested against reference models and lab data showing WT effects depend on local settings but are negligible after 2 m depth. The algorithm is coupled to a complete vegetation buffer model in a companion paper to analyze pesticide and sediment control in situ.
Claire Lauvernet and Rafael Muñoz-Carpena
Hydrol. Earth Syst. Sci., 22, 71–87, https://doi.org/10.5194/hess-22-71-2018, https://doi.org/10.5194/hess-22-71-2018, 2018
Short summary
Short summary
Vegetation buffers, often placed in lowlands to control runoff pollution, can exhibit limited efficiency due to seasonal shallow water tables (WTs). A new shallow water table infiltration algorithm developed in a companion paper is coupled to a complete vegetation buffer model to quantify pesticide and sediment control in the field. We evaluated the model on two field experiments in France with and without WT conditions and show WTs can control efficiency depending on land and climate settings.
Tobias Karl David Weber, Sascha Christian Iden, and Wolfgang Durner
Hydrol. Earth Syst. Sci., 21, 6185–6200, https://doi.org/10.5194/hess-21-6185-2017, https://doi.org/10.5194/hess-21-6185-2017, 2017
Yonatan Ganot, Ran Holtzman, Noam Weisbrod, Ido Nitzan, Yoram Katz, and Daniel Kurtzman
Hydrol. Earth Syst. Sci., 21, 4479–4493, https://doi.org/10.5194/hess-21-4479-2017, https://doi.org/10.5194/hess-21-4479-2017, 2017
Short summary
Short summary
We monitor infiltration at multiple scales during managed aquifer recharge with desalinated seawater in an infiltration pond, while groundwater recharge is evaluated by simplified and numerical models. We found that pond-surface clogging is negated by the high-quality desalinated seawater or negligible compared to the low-permeability layers of the unsaturated zone. We show that a numerical model with a 1-D representative sediment profile is able to capture infiltration and recharge dynamics.
Stefan Jaumann and Kurt Roth
Hydrol. Earth Syst. Sci., 21, 4301–4322, https://doi.org/10.5194/hess-21-4301-2017, https://doi.org/10.5194/hess-21-4301-2017, 2017
Short summary
Short summary
We investigate the quantitative effect of neglected sensor position, small-scale heterogeneity, and lateral flow on soil hydraulic material properties. Thus, we analyze a fluctuating water table experiment in a 2-D architecture (ASSESS) with increasingly complex studies based on time domain reflectometry and hydraulic potential data. We found that 1-D studies may yield biased parameters and that estimating sensor positions as well as small-scale heterogeneity improves the model significantly.
Cited articles
Abbaszadeh, P., Moradkhani, H., and Zhan, X.: Downscaling SMAP radiometer soil moisture over the CONUS using an ensemble learning method, Water Resour. Res., 55, 324–344, 2019.
Abdel-Hamid, O., Mohamed, A. R., Jiang, H., Deng, L., Penn, G., and Yu, D.: Convolutional neural networks for speech recognition, IEEE T. Audio, Speech, 22, 1533–1545, https://doi.org/10.1109/TASLP.2014.2339736, 2014.
Ahmed, A. A. M., Deo, R. C., Ghahramani, A., Raj, N., Feng, Q., Yin, Z., and Yang, L.: LSTM integrated with Boruta-random forest optimiser for soil moisture estimation under RCP4.5 and RCP8.5 global warming scenarios, Springer Berlin Heidelberg, 1851–1881 pp., https://doi.org/10.1007/s00477-021-01969-3, 2021.
Ajit, A., Acharya, K., and Samanta, A.: A Review of Convolutional Neural Networks, Int. Conf. Emerg. Tr., 1–5, https://doi.org/10.1109/ic-ETITE47903.2020.049, 2020.
Albawi, S., Mohammed, T. A., and Al-Zawi, S.: Understanding of a convolutional neural network, Proc. 2017 Int. Conf. Eng. Technol., ICET 2017, Antalya, Turkey, 21–23 August 2017, IEEE: Piscataway, NJ, USA, 2017, 1–6 https://doi.org/10.1109/ICEngTechnol.2017.8308186, 2018.
Azhar, A. H., Perera, B. J. C., and Nabi, G.: A Simple Soil Moisture Simulation Model to Address Irrigation Water Management Issues, Mehran Univ. Res. J. Eng. Technol., 30, 193–206, 2011.
Breiman, L.: Random forests, Mach. Learn., 45, 5–32, 2001.
Cai, Y., Zheng, W., Zhang, X., Zhangzhong, L., and Xue, X.: Research on soil moisture prediction model based on deep learning, PLoS One, 14, 1–19, https://doi.org/10.1371/journal.pone.0214508, 2019.
Camporese, M., Daly, E., and Paniconi, C.: Catchment-scale Richards equation-based modeling of evapotranspiration via boundary condition switching and root water uptake schemes, Water Resour. Res., 51, 5756–5771, 2015.
Carranza, C., Nolet, C., Pezij, M., and van der Ploeg, M.: Root zone soil moisture estimation with Random Forest, J. Hydrol., 593, 125840, https://doi.org/10.1016/j.jhydrol.2020.125840, 2021.
Chen, Y., Li, L., Whiting, M., Chen, F., Sun, Z., Song, K., and Wang, Q.: Convolutional neural network model for soil moisture prediction and its transferability analysis based on laboratory Vis-NIR spectral data, Int. J. Appl. Earth Obs., 104, 102550, https://doi.org/10.1016/j.jag.2021.102550, 2021.
Connor, J. T., Martin, R. D., and Atlas, L. E.: Recurrent Neural Networks and Robust Time Series Prediction, IEEE T. Neural Networ., 5, 240–254, https://doi.org/10.1109/72.279188, 1994.
Cortes, C. and Vapnik, V.: Support-vector networks, Mach. Learn., 20, 273–297, 1995.
Ding, Y., Zhu, Y., Wu, Y., Jun, F., and Cheng, Z.: Spatio-Temporal attention lstm model for flood forecasting, 2019 International Conference on Internet of Things (iThings) and IEEE Green Computing and Communications (GreenCom) and IEEE Cyber, Physical and Social Computing (CPSCom) and IEEE Smart Data (SmartData), Atlanta, GA, USA, 458–465, https://doi.org/10.1109/iThings/GreenCom/CPSCom/SmartData. 2019.00095, 2019.
Ding, Y., Zhu, Y., Feng, J., Zhang, P., and Cheng, Z.: Interpretable spatio-temporal attention LSTM model for flood forecasting, Neurocomputing, 403, 348–359, https://doi.org/10.1016/j.neucom.2020.04.110, 2020.
Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., Gelly, S., Uszkoreit, J., and Houlsby, N.: An Image is Worth 16 × 16 Words: Transformers for Image Recognition at Scale, arXiv [preprint], https://doi.org/10.48550/arXiv.2010.11929, 2020.
Entin, J. K., Robock, A., Vinnikov, K. Y., Hollinger, S. E., Liu, S., and Namkhai, A.: Meteorologic i Land Surface, J. Geophys. Res., 105, 11865–11877, 2000.
Fang, K., Pan, M., and Shen, C.: The Value of SMAP for Long-Term Soil Moisture Estimation with the Help of Deep Learning, IEEE T. Geosci. Remote, 57, 2221–2233, https://doi.org/10.1109/TGRS.2018.2872131, 2019.
Feng, D., Beck, H., de Bruijn, J., Sahu, R. K., Satoh, Y., Wada, Y., Liu, J., Pan, M., Lawson, K., and Shen, C.: Deep Dive into Global Hydrologic Simulations: Harnessing the Power of Deep Learning and Physics-informed Differentiable Models (δHBV-globe1.0-hydroDL), Geosci. Model Dev. Discuss. [preprint], https://doi.org/10.5194/gmd-2023-190, in review, 2023.
Gill, M. K., Asefa, T., Kemblowski, M. W., and McKee, M.: Soil moisture prediction using support vector machines, J. Am. Water Resour. As., 42, 1033–1046, https://doi.org/10.1111/j.1752-1688.2006.tb04512.x, 2006.
Goodfellow, I., Pouget-Abadie, J., Mirza, M., Xu, B., Warde-Farley, D., Ozair, S., Courville, A., and Bengio, Y.: Generative adversarial nets, Adv. Neur. In., 27, 2672–2680, https://doi.org/10.48550/arXiv.1406.2661, 2014.
Goodfellow, I., Bengio, Y., and Courville, A.: Deep learning, MIT press, ISBN 0262035618, 2016.
Guswa, A. J., Celia, M. A., and Rodriguez-Iturbe, I.: Models of soil moisture dynamics in ecohydrology: A comparative study, Water Resour. Res., 38, 5-1–5-15, https://doi.org/10.1029/2001wr000826, 2002.
He, K., Zhang, X., Ren, S., and Sun, J.: Deep residual learning for image recognition, in: Proceedings of the IEEE conference on computer vision and pattern recognition, Las Vegas, NV, USA, 27–30 June 2016, 770–778, arXiv [preprint], https://doi.org/10.48550/arXiv.1512.03385, 2016.
Heathman, G. C., Cosh, M. H., Merwade, V., and Han, E.: Multi-scale temporal stability analysis of surface and subsurface soil moisture within the Upper Cedar Creek Watershed, Indiana, Catena, 95, 91–103, https://doi.org/10.1016/j.catena.2012.03.008, 2012.
Hochreiter, S. and Schmidhuber, J.: Long short-term memory, Neural Comput., 9, 1735–1780, 1997.
Holzman, M., Rivas, R., Carmona, F., and Niclòs, R.: A method for soil moisture probes calibration and validation of satellite estimates, MethodsX, 4, 243–249, https://doi.org/10.1016/j.mex.2017.07.004, 2017.
Huang, G. Bin, Zhu, Q. Y., and Siew, C. K.: Extreme learning machine: Theory and applications, Neurocomputing, 70, 489–501, https://doi.org/10.1016/j.neucom.2005.12.126, 2006.
Hummel, J. W., Sudduth, K. A., and Hollinger, S. E.: Soil moisture and organic matter prediction of surface and subsurface soils using an NIR soil sensor, Comput. Electron. Agr., 32, 149–165, https://doi.org/10.1016/S0168-1699(01)00163-6, 2001.
Hussain, D., Hussain, T., Khan, A. A., Naqvi, S. A. A., and Jamil, A.: A deep learning approach for hydrological time-series prediction: A case study of Gilgit river basin, Earth Sci. Inform., 13, 915–927, https://doi.org/10.1007/s12145-020-00477-2, 2020.
Jackson, S. H.: Comparison of calculated and measured volumetric water content at four field sites, Agr. Water Manage., 58, 209–222, https://doi.org/10.1016/S0378-3774(02)00078-1, 2003.
Jing, J. R., Li, Q., Ding, X. Y., Sun, N. L., Tang, R., and Cai, Y. L.: Aenn: a generative adversarial neural network for weather radar echo extrapolation, Int. Arch. Photogramm., 42, 89–94, https://doi.org/10.5194/isprs-archives-XLII-3-W9-89-2019, 2019.
Kamilaris, A. and Prenafeta-Boldú, F. X.: Deep learning in agriculture: A survey, Comput. Electron. Agr., 147, 70–90, https://doi.org/10.1016/j.compag.2018.02.016, 2018.
Kilinc, H. C. and Yurtsever, A.: Short-Term Streamflow Forecasting Using Hybrid Deep Learning Model Based on Grey Wolf Algorithm for Hydrological Time Series, Sustainability, 14, 3352, https://doi.org/10.3390/su14063352, 2022.
Lecun, Y., Bengio, Y., and Hinton, G.: Deep learning, Nature, 521, 436–444, https://doi.org/10.1038/nature14539, 2015.
LeCun, Y.: Generalization and network design strategies, Connect. Perspect., 19, 143–155, 1989.
Li, Q., Hao, H., Zhao, Y., Geng, Q., Liu, G., Zhang, Y., and Yu, F.: GANs-LSTM Model for Soil Temperature Estimation from Meteorological: A New Approach, IEEE Access, 8, 59427–59443, https://doi.org/10.1109/ACCESS.2020.2982996, 2020.
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, 1–17, https://doi.org/10.1016/j.geoderma.2021.115651, 2022a.
Li, Q., Li, Z., Shangguan, W., Wang, X., Li, L., and Yu, F.: Improving soil moisture prediction using a novel encoder-decoder model with residual learning, Comput. Electron. Agr., 195, 106816, https://doi.org/10.1016/j.compag.2022.106816, 2022b.
Liu, J., Rahmani, F., Lawson, K., and Shen, C.: A multiscale deep learning model for soil moisture integrating satellite and in situ data, Geophys. Res. Lett., 49, e2021GL096847, https://doi.org/10.1029/2021GL096847, 2022.
Liu, Y., Mei, L., and Ki, S. O.: Prediction of soil moisture based on Extreme Learning Machine for an apple orchard, CCIS 2014 – Proc. 2014 IEEE 3rd Int. Conf. Cloud Comput. Intell. Syst., Proc. Shenzhen, China, 27–29 November 2014, 400–404, https://doi.org/10.1109/CCIS.2014.7175768, 2014.
Lundberg, S. M., Erion, G. G., and Lee, S.-I.: Consistent Individualized Feature Attribution for Tree Ensembles, arXiv [preprint], https://doi.org/10.48550/arXiv.1802.03888, 2018.
Mikolov, T., Kombrink, S., Burget, L., Èernocký, J., and Khudanpur, S.: Extensions of recurrent neural network language model, in: 2011 IEEE international conference on acoustics, speech and signal processing (ICASSP), Prague, Czech Republic, 22–27 May 2011, 5528–5531, https://doi.org/10.1109/ICASSP.2011.5947611, 2021.
Patil, A. and Rane, M.: Convolutional Neural Networks: An Overview and Its Applications in Pattern Recognition, Smart Innov. Syst. Tec., 195, 21–30, https://doi.org/10.1007/978-981-15-7078-0_3, 2021.
Pollack, J. B.: Recursive distributed representations, Artif. Intell., 46, 77–105, 1990.
Prakash, S., Sharma, A., and Sahu, S. S.: Soil moisture prediction using machine learning, in: 2018 Second International Conference on Inventive Communication and Computational Technologies (ICICCT), Coimbatore, India, 20–21 April 2018, 1–6, https://doi.org/10.1109/ICICCT.2018.8473260, 2018.
Prasad, R., Deo, R. C., Li, Y., and Maraseni, T.: Weekly soil moisture forecasting with multivariate sequential, ensemble empirical mode decomposition and Boruta-random forest hybridizer algorithm approach, Catena, 177, 149–166, https://doi.org/10.1016/j.catena.2019.02.012, 2019.
Qiu, Y., Fu, B., Wang, J., and Chen, L.: Spatiotemporal prediction of soil moisture content using multiple-linear regression in a small catchment of the Loess Plateau, China, Catena, 54, 173–195, https://doi.org/10.1016/S0341-8162(03)00064-X, 2003.
Ravuri, S., Lenc, K., Willson, M., Kangin, D., Lam, R., Mirowski, P., Fitzsimons, M., Athanassiadou, M., Kashem, S., Madge, S., Prudden, R., Mandhane, A., Clark, A., Brock, A., Simonyan, K., Hadsell, R., Robinson, N., Clancy, E., Arribas, A., and Mohamed, S.: Skilful precipitation nowcasting using deep generative models of radar, Nature, 597, 672–677, https://doi.org/10.1038/s41586-021-03854-z, 2021.
Sampathkumar, T., Pandian, B. J., Rangaswamy, M. V, Manickasundaram, P., and Jeyakumar, P.: Influence of deficit irrigation on growth, yield and yield parameters of cotton–maize cropping sequence, Agr. Water Manage., 130, 90–102, 2013.
Saxton, K. E., Johnson, H. P., and Shaw, R. H.: Modeling Evapotranspiration and Soil Moisture, Trans. Am. Soc. Agric. Eng., 17, 673–677, https://doi.org/10.13031/2013.36935, 1974.
Schmidhuber, J.: Deep Learning in neural networks: An overview, Neural Networks, 61, 85–117, https://doi.org/10.1016/j.neunet.2014.09.003, 2015.
Semwal, V. B., Gupta, A., and Lalwani, P.: An optimized hybrid deep learning model using ensemble learning approach for human walking activities recognition, J. Supercomput., 77, 12256–12279, https://doi.org/10.1007/s11227-021-03768-7, 2021.
Severyn, A. and Moschitti, A.: UNITN: Training Deep Convolutional Neural Network for Twitter Sentiment Classification, SemEval 2015, 9th Int. Work. Semant. Eval. co-located with 2015 Conf. North Am. Chapter Assoc. Comput. Linguist. Hum. Lang. Technol. NAACL-HLT 2015 – Proc., Amsterdam, The Netherlands, 4–5 June 2015, 464–469, https://doi.org/10.18653/v1/s15-2079, 2015.
Shi, X., Chen, Z., Wang, H., Yeung, D. Y., Wong, W. K., and Woo, W. C.: Convolutional LSTM network: A machine learning approach for precipitation nowcasting, Adv. Neur. In., 28, 802–810, 2015.
Simunek, J., Van Genuchten, M. T., and Sejna, M.: The HYDRUS-1D software package for simulating the one-dimensional movement of water, heat, and multiple solutes in variably-saturated media, Univ. California-Riverside Res. Reports, 3, 1–240, 2005.
Sungmin, O. and Orth, R.: Global soil moisture data derived through machine learning trained with in-situ measurements, Sci. Data, 8, 1–14, 2021.
Sungmin, O., Orth, R., Weber, U., and Park, S. K.: High-resolution European daily soil moisture derived with machine learning (2003–2020), Sci. Data, 9, 1–13, 2022.
Sutskever, I., Vinyals, O., and Le, Q. V: Sequence to sequence learning with neural networks, Adv. Neur. In., 27, 3104–3112, 2014.
Van der Maaten, L. and Hinton, G.: Visualizing data using t-SNE, J. Mach. Learn. Res., 9, 2579–2605, 2008.
Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., Kaiser, Ł., and Polosukhin, I.: Attention is all you need, Adv. Neur. In., 30, 5998–6008, 2017.
Vereecken, H., Huisman, J. A., Bogena, H., Vanderborght, J., Vrugt, J. A., and Hopmans, J. W.: On the value of soil moisture measurements in vadose zone hydrology: A review, Water Resour. Res., 46, 1–21, https://doi.org/10.1029/2008WR006829, 2008.
Vereecken, H., Amelung, W., Bauke, S. L., Bogena, H., Brüggemann, N., Montzka, C., Vanderborght, J., Bechtold, M., Blöschl, G., Carminati, A., Javaux, M., Konings, A. G., Kusche, J., Neuweiler, I., Or, D., Steele-Dunne, S., Verhoef, A., Young, M., and Zhang, Y.: Soil hydrology in the Earth system, Nat. Rev. Earth Environ., 3, 573–587, https://doi.org/10.1038/s43017-022-00324-6, 2022.
Verma, S. and Nema, M. K.: Development of an empirical model for sub-surface soil moisture estimation and variability assessment in a lesser Himalayan watershed, Model. Earth Syst. Environ., 8, 3487–3505, https://doi.org/10.1007/s40808-021-01316-z, 2021.
Xia, K., Huang, J., and Wang, H.: LSTM-CNN Architecture for Human Activity Recognition, IEEE Access, 8, 56855–56866, https://doi.org/10.1109/ACCESS.2020.2982225, 2020.
yanlingw: deep_learning_for_soil_moisture_prediction, Zenodo [data set and code], https://doi.org/10.5281/zenodo.10060492, 2023.
Yu, J., Zhang, X., Xu, L., Dong, J., and Zhangzhong, L.: A hybrid CNN-GRU model for predicting soil moisture in maize root zone, Agr. Water Manage., 245, 106649, https://doi.org/10.1016/j.agwat.2020.106649, 2021.
Short summary
LSTM temporal modeling suits soil moisture prediction; attention mechanisms enhance feature learning efficiently, as their feature selection capabilities are proven through Transformer and attention–LSTM hybrids. Adversarial training strategies help extract additional information from time series’ data. SHAP analysis and t-SNE visualization reveal differences in encoded features across models. This work serves as a reference for time series’ data processing in hydrology problems.
LSTM temporal modeling suits soil moisture prediction; attention mechanisms enhance feature...
