Articles | Volume 25, issue 5
https://doi.org/10.5194/hess-25-2739-2021
© Author(s) 2021. 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-25-2739-2021
© Author(s) 2021. This work is distributed under
the Creative Commons Attribution 4.0 License.
the Creative Commons Attribution 4.0 License.
Research article
| 
25 May 2021
Research article |
| 25 May 2021
| 25 May 2021
Advances in soil moisture retrieval from multispectral remote sensing using unoccupied aircraft systems and machine learning techniques
Earth System Science, Stanford University, Stanford, CA, USA
Anna Fryjoff-Hung
Center for Information Technology in the Interest of Society and the Banatao Institute, University of California, Merced, Merced, CA, USA
Andreas Anderson
Center for Information Technology in the Interest of Society and the Banatao Institute, University of California, Merced, Merced, CA, USA
Joshua H. Viers
Center for Information Technology in the Interest of Society and the Banatao Institute, University of California, Merced, Merced, CA, USA
Department of Civil and Environmental Engineering, University of California, Merced, Merced, CA, USA
Teamrat A. Ghezzehei
Center for Information Technology in the Interest of Society and the Banatao Institute, University of California, Merced, Merced, CA, USA
Life and Environmental Science, University of California, Merced, Merced, CA, USA
Related authors
Samuel N. Araya, Jeffrey P. Mitchell, Jan W. Hopmans, and Teamrat A. Ghezzehei
SOIL, 8, 177–198, https://doi.org/10.5194/soil-8-177-2022, https://doi.org/10.5194/soil-8-177-2022, 2022
Short summary
Short summary
We studied the long-term effects of no-till (NT) and winter cover cropping (CC) practices on soil hydraulic properties. We measured soil water retention and conductivity and also conducted numerical simulations to compare soil water storage abilities under the different systems. Soils under NT and CC practices had improved soil structure. Conservation agriculture practices showed marginal improvement with respect to infiltration rates and water storage.
Samuel N. Araya, Marilyn L. Fogel, and Asmeret Asefaw Berhe
SOIL, 3, 31–44, https://doi.org/10.5194/soil-3-31-2017, https://doi.org/10.5194/soil-3-31-2017, 2017
Short summary
Short summary
This research investigates how fires of different intensities affect soil organic matter properties. This study identifies critical temperature thresholds of significant soil organic matter changes. Findings from this study will contribute towards estimating the amount and rate of changes in soil carbon, nitrogen, and other essential soil properties that can be expected from fires of different intensities under anticipated climate change scenarios.
Samuel N. Araya, Mercer Meding, and Asmeret Asefaw Berhe
SOIL, 2, 351–366, https://doi.org/10.5194/soil-2-351-2016, https://doi.org/10.5194/soil-2-351-2016, 2016
Short summary
Short summary
Using laboratory heating, we studied effects of fire intensity on important topsoil characteristics. This study identifies critical temperature thresholds for significant physical and chemical changes in soils that developed under different climate regimes. Findings from this study will contribute towards estimating the amount and rate of change in essential soil properties that can be expected from topsoil exposure to different intensity fires under anticipated climate change scenarios.
Toshiyuki Bandai and Teamrat A. Ghezzehei
Hydrol. Earth Syst. Sci., 26, 4469–4495, https://doi.org/10.5194/hess-26-4469-2022, https://doi.org/10.5194/hess-26-4469-2022, 2022
Short summary
Short summary
Scientists use a physics-based equation to simulate water dynamics that influence hydrological and ecological phenomena. We present hybrid physics-informed neural networks (PINNs) to leverage the growing availability of soil moisture data and advances in machine learning. We showed that PINNs perform comparably to traditional methods and enable the estimation of rainfall rates from soil moisture. However, PINNs are challenging to train and significantly slower than traditional methods.
Samuel N. Araya, Jeffrey P. Mitchell, Jan W. Hopmans, and Teamrat A. Ghezzehei
SOIL, 8, 177–198, https://doi.org/10.5194/soil-8-177-2022, https://doi.org/10.5194/soil-8-177-2022, 2022
Short summary
Short summary
We studied the long-term effects of no-till (NT) and winter cover cropping (CC) practices on soil hydraulic properties. We measured soil water retention and conductivity and also conducted numerical simulations to compare soil water storage abilities under the different systems. Soils under NT and CC practices had improved soil structure. Conservation agriculture practices showed marginal improvement with respect to infiltration rates and water storage.
Jing Yan and Teamrat Ghezzehei
Biogeosciences Discuss., https://doi.org/10.5194/bg-2022-52, https://doi.org/10.5194/bg-2022-52, 2022
Publication in BG not foreseen
Short summary
Short summary
Although hydraulic redistribution (HR) is a well-documented phenomenon, whether it is a passive happy accident or actively controlled by roots is not well understood. Our modeling study suggests HR is long-range feedback between roots that inhabit heterogeneously resourced soil regions. When nutrients and organic matter are concentrated in shallow layers that experience frequent drying, root-exudation facilitated HR allows plants to mineralize and extract the otherwise inaccessible nutrients.
Daniel Rath, Nathaniel Bogie, Leonardo Deiss, Sanjai J. Parikh, Daoyuan Wang, Samantha Ying, Nicole Tautges, Asmeret Asefaw Berhe, Teamrat A. Ghezzehei, and Kate M. Scow
SOIL, 8, 59–83, https://doi.org/10.5194/soil-8-59-2022, https://doi.org/10.5194/soil-8-59-2022, 2022
Short summary
Short summary
Storing C in subsoils can help mitigate climate change, but this requires a better understanding of subsoil C dynamics. We investigated changes in subsoil C storage under a combination of compost, cover crops (WCC), and mineral fertilizer and found that systems with compost + WCC had ~19 Mg/ha more C after 25 years. This increase was attributed to increased transport of soluble C and nutrients via WCC root pores and demonstrates the potential for subsoil C storage in tilled agricultural systems.
Jing Yan, Nathaniel A. Bogie, and Teamrat A. Ghezzehei
Biogeosciences, 17, 6377–6392, https://doi.org/10.5194/bg-17-6377-2020, https://doi.org/10.5194/bg-17-6377-2020, 2020
Short summary
Short summary
An uneven supply of water and nutrients in soils often drives how plants behave. We observed that plants extract all their required nutrients from dry soil patches in sufficient quantity, provided adequate water is available elsewhere in the root zone. Roots in nutrient-rich dry patches facilitate the nutrient acquisition by extensive growth, water release, and modifying water retention in their immediate environment. The findings are valuable in managing nutrient losses in agricultural systems.
Teamrat A. Ghezzehei, Benjamin Sulman, Chelsea L. Arnold, Nathaniel A. Bogie, and Asmeret Asefaw Berhe
Biogeosciences, 16, 1187–1209, https://doi.org/10.5194/bg-16-1187-2019, https://doi.org/10.5194/bg-16-1187-2019, 2019
Short summary
Short summary
Soil water is a medium from which microbes acquire resources and within which they are able to move. Occupancy and availability of water and oxygen gas in soils are mutually exclusive. In addition, as soil dries the remaining water is held with an increasing degree of adhesive energy, which restricts microbes' ability to extract resources from water. We introduce a mathematical model that describes these interacting effects and organic matter decomposition.
Mehdi Rahmati, Lutz Weihermüller, Jan Vanderborght, Yakov A. Pachepsky, Lili Mao, Seyed Hamidreza Sadeghi, Niloofar Moosavi, Hossein Kheirfam, Carsten Montzka, Kris Van Looy, Brigitta Toth, Zeinab Hazbavi, Wafa Al Yamani, Ammar A. Albalasmeh, Ma'in Z. Alghzawi, Rafael Angulo-Jaramillo, Antônio Celso Dantas Antonino, George Arampatzis, Robson André Armindo, Hossein Asadi, Yazidhi Bamutaze, Jordi Batlle-Aguilar, Béatrice Béchet, Fabian Becker, Günter Blöschl, Klaus Bohne, Isabelle Braud, Clara Castellano, Artemi Cerdà, Maha Chalhoub, Rogerio Cichota, Milena Císlerová, Brent Clothier, Yves Coquet, Wim Cornelis, Corrado Corradini, Artur Paiva Coutinho, Muriel Bastista de Oliveira, José Ronaldo de Macedo, Matheus Fonseca Durães, Hojat Emami, Iraj Eskandari, Asghar Farajnia, Alessia Flammini, Nándor Fodor, Mamoun Gharaibeh, Mohamad Hossein Ghavimipanah, Teamrat A. Ghezzehei, Simone Giertz, Evangelos G. Hatzigiannakis, Rainer Horn, Juan José Jiménez, Diederik Jacques, Saskia Deborah Keesstra, Hamid Kelishadi, Mahboobeh Kiani-Harchegani, Mehdi Kouselou, Madan Kumar Jha, Laurent Lassabatere, Xiaoyan Li, Mark A. Liebig, Lubomír Lichner, María Victoria López, Deepesh Machiwal, Dirk Mallants, Micael Stolben Mallmann, Jean Dalmo de Oliveira Marques, Miles R. Marshall, Jan Mertens, Félicien Meunier, Mohammad Hossein Mohammadi, Binayak P. Mohanty, Mansonia Pulido-Moncada, Suzana Montenegro, Renato Morbidelli, David Moret-Fernández, Ali Akbar Moosavi, Mohammad Reza Mosaddeghi, Seyed Bahman Mousavi, Hasan Mozaffari, Kamal Nabiollahi, Mohammad Reza Neyshabouri, Marta Vasconcelos Ottoni, Theophilo Benedicto Ottoni Filho, Mohammad Reza Pahlavan-Rad, Andreas Panagopoulos, Stephan Peth, Pierre-Emmanuel Peyneau, Tommaso Picciafuoco, Jean Poesen, Manuel Pulido, Dalvan José Reinert, Sabine Reinsch, Meisam Rezaei, Francis Parry Roberts, David Robinson, Jesús Rodrigo-Comino, Otto Corrêa Rotunno Filho, Tadaomi Saito, Hideki Suganuma, Carla Saltalippi, Renáta Sándor, Brigitta Schütt, Manuel Seeger, Nasrollah Sepehrnia, Ehsan Sharifi Moghaddam, Manoj Shukla, Shiraki Shutaro, Ricardo Sorando, Ajayi Asishana Stanley, Peter Strauss, Zhongbo Su, Ruhollah Taghizadeh-Mehrjardi, Encarnación Taguas, Wenceslau Geraldes Teixeira, Ali Reza Vaezi, Mehdi Vafakhah, Tomas Vogel, Iris Vogeler, Jana Votrubova, Steffen Werner, Thierry Winarski, Deniz Yilmaz, Michael H. Young, Steffen Zacharias, Yijian Zeng, Ying Zhao, Hong Zhao, and Harry Vereecken
Earth Syst. Sci. Data, 10, 1237–1263, https://doi.org/10.5194/essd-10-1237-2018, https://doi.org/10.5194/essd-10-1237-2018, 2018
Short summary
Short summary
This paper presents and analyzes a global database of soil infiltration data, the SWIG database, for the first time. In total, 5023 infiltration curves were collected across all continents in the SWIG database. These data were either provided and quality checked by the scientists or they were digitized from published articles. We are convinced that the SWIG database will allow for a better parameterization of the infiltration process in land surface models and for testing infiltration models.
Roland Baatz, Pamela L. Sullivan, Li Li, Samantha R. Weintraub, Henry W. Loescher, Michael Mirtl, Peter M. Groffman, Diana H. Wall, Michael Young, Tim White, Hang Wen, Steffen Zacharias, Ingolf Kühn, Jianwu Tang, Jérôme Gaillardet, Isabelle Braud, Alejandro N. Flores, Praveen Kumar, Henry Lin, Teamrat Ghezzehei, Julia Jones, Henry L. Gholz, Harry Vereecken, and Kris Van Looy
Earth Syst. Dynam., 9, 593–609, https://doi.org/10.5194/esd-9-593-2018, https://doi.org/10.5194/esd-9-593-2018, 2018
Short summary
Short summary
Focusing on the usage of integrated models and in situ Earth observatory networks, three challenges are identified to advance understanding of ESD, in particular to strengthen links between biotic and abiotic, and above- and below-ground processes. We propose developing a model platform for interdisciplinary usage, to formalize current network infrastructure based on complementarities and operational synergies, and to extend the reanalysis concept to the ecosystem and critical zone.
Samuel N. Araya, Marilyn L. Fogel, and Asmeret Asefaw Berhe
SOIL, 3, 31–44, https://doi.org/10.5194/soil-3-31-2017, https://doi.org/10.5194/soil-3-31-2017, 2017
Short summary
Short summary
This research investigates how fires of different intensities affect soil organic matter properties. This study identifies critical temperature thresholds of significant soil organic matter changes. Findings from this study will contribute towards estimating the amount and rate of changes in soil carbon, nitrogen, and other essential soil properties that can be expected from fires of different intensities under anticipated climate change scenarios.
Samuel N. Araya, Mercer Meding, and Asmeret Asefaw Berhe
SOIL, 2, 351–366, https://doi.org/10.5194/soil-2-351-2016, https://doi.org/10.5194/soil-2-351-2016, 2016
Short summary
Short summary
Using laboratory heating, we studied effects of fire intensity on important topsoil characteristics. This study identifies critical temperature thresholds for significant physical and chemical changes in soils that developed under different climate regimes. Findings from this study will contribute towards estimating the amount and rate of change in essential soil properties that can be expected from topsoil exposure to different intensity fires under anticipated climate change scenarios.
T. A. Ghezzehei, D. V. Sarkhot, and A. A. Berhe
Solid Earth, 5, 953–962, https://doi.org/10.5194/se-5-953-2014, https://doi.org/10.5194/se-5-953-2014, 2014
Related subject area
Subject: Vadose Zone Hydrology | Techniques and Approaches: Remote Sensing and GIS
A robust gap-filling approach for European Space Agency Climate Change Initiative (ESA CCI) soil moisture integrating satellite observations, model-driven knowledge, and spatiotemporal machine learning
Exploring the combined use of SMAP and Sentinel-1 data for downscaling soil moisture beyond the 1 km scale
An inverse dielectric mixing model at 50 MHz that considers soil organic carbon
Parameter optimisation for a better representation of drought by LSMs: inverse modelling vs. sequential data assimilation
Multi-decadal analysis of root-zone soil moisture applying the exponential filter across CONUS
Geomorphometric analysis of cave ceiling channels mapped with 3-D terrestrial laser scanning
Analysis of SMOS brightness temperature and vegetation optical depth data with coupled land surface and radiative transfer models in Southern Germany
Developing an improved soil moisture dataset by blending passive and active microwave satellite-based retrievals
Influence of cracking clays on satellite estimated and model simulated soil moisture
Kai Liu, Xueke Li, Shudong Wang, and Hongyan Zhang
Hydrol. Earth Syst. Sci., 27, 577–598, https://doi.org/10.5194/hess-27-577-2023, https://doi.org/10.5194/hess-27-577-2023, 2023
Short summary
Short summary
Remote sensing has opened opportunities for mapping spatiotemporally continuous soil moisture, but it is hampered by data gaps. We propose a robust gap-filling approach to reconstruct daily satellite soil moisture. The merit of our approach is to integrate satellite observations, model-driven knowledge, and spatiotemporal machine learning. We also apply the developed approach to long-term datasets. Our study provides a potential avenue for hydrological applications.
Rena Meyer, Wenmin Zhang, Søren Julsgaard Kragh, Mie Andreasen, Karsten Høgh Jensen, Rasmus Fensholt, Simon Stisen, and Majken C. Looms
Hydrol. Earth Syst. Sci., 26, 3337–3357, https://doi.org/10.5194/hess-26-3337-2022, https://doi.org/10.5194/hess-26-3337-2022, 2022
Short summary
Short summary
The amount and spatio-temporal distribution of soil moisture, the water in the upper soil, is of great relevance for agriculture and water management. Here, we investigate whether the established downscaling algorithm combining different satellite products to estimate medium-scale soil moisture is applicable to higher resolutions and whether results can be improved by accounting for land cover types. Original satellite data and downscaled soil moisture are compared with ground observations.
Chang-Hwan Park, Aaron Berg, Michael H. Cosh, Andreas Colliander, Andreas Behrendt, Hida Manns, Jinkyu Hong, Johan Lee, Runze Zhang, and Volker Wulfmeyer
Hydrol. Earth Syst. Sci., 25, 6407–6420, https://doi.org/10.5194/hess-25-6407-2021, https://doi.org/10.5194/hess-25-6407-2021, 2021
Short summary
Short summary
In this study, we proposed an inversion of the dielectric mixing model for a 50 Hz soil sensor for agricultural organic soil. This model can reflect the variability of soil organic matter (SOM) in wilting point and porosity, which play a critical role in improving the accuracy of SM estimation, using a dielectric-based soil sensor. The results of statistical analyses demonstrated a higher performance of the new model than the factory setting probe algorithm.
Hélène Dewaele, Simon Munier, Clément Albergel, Carole Planque, Nabil Laanaia, Dominique Carrer, and Jean-Christophe Calvet
Hydrol. Earth Syst. Sci., 21, 4861–4878, https://doi.org/10.5194/hess-21-4861-2017, https://doi.org/10.5194/hess-21-4861-2017, 2017
Short summary
Short summary
Soil maximum available water content (MaxAWC) is a key parameter in land surface models. Being difficult to measure, this parameter is usually unavailable. A 15-year time series of satellite-derived observations of leaf area index (LAI) is used to retrieve MaxAWC for rainfed straw cereals over France. Disaggregated LAI is sequentially assimilated into the ISBA LSM. MaxAWC is estimated minimising LAI analyses increments. Annual maximum LAI observations correlate with the MaxAWC estimates.
Kenneth J. Tobin, Roberto Torres, Wade T. Crow, and Marvin E. Bennett
Hydrol. Earth Syst. Sci., 21, 4403–4417, https://doi.org/10.5194/hess-21-4403-2017, https://doi.org/10.5194/hess-21-4403-2017, 2017
Short summary
Short summary
This study applied the exponential filter to produce an estimate of root-zone soil moisture at 20 to 25 cm depths. Four types of microwave, surface satellite soil moisture were used. The study focused on the continental United States, and in situ data were used from the International Soil Moisture Network for comparison. This study spans almost two decades (1997 to 2014). Root mean square error was close to 0.04, which is the baseline value for accuracy designated for many satellite missions.
Michal Gallay, Zdenko Hochmuth, Ján Kaňuk, and Jaroslav Hofierka
Hydrol. Earth Syst. Sci., 20, 1827–1849, https://doi.org/10.5194/hess-20-1827-2016, https://doi.org/10.5194/hess-20-1827-2016, 2016
Short summary
Short summary
This paper presents a novel approach that provides evidence of
environmental conditions during the formation of a cave inferred from
measuring the geometry of the cave surface. We focused on winding
channels with associated cave landforms carved high up in the cave
ceiling inaccessible to direct inspection by speleologists. This was
possible by coupling 3-D laser scanning of the cave and analyzing the
cave morphology by the tools used in 3-D computer graphics and digital
terrain analysis.
F. Schlenz, J. T. dall'Amico, W. Mauser, and A. Loew
Hydrol. Earth Syst. Sci., 16, 3517–3533, https://doi.org/10.5194/hess-16-3517-2012, https://doi.org/10.5194/hess-16-3517-2012, 2012
Y. Y. Liu, R. M. Parinussa, W. A. Dorigo, R. A. M. De Jeu, W. Wagner, A. I. J. M. van Dijk, M. F. McCabe, and J. P. Evans
Hydrol. Earth Syst. Sci., 15, 425–436, https://doi.org/10.5194/hess-15-425-2011, https://doi.org/10.5194/hess-15-425-2011, 2011
Y. Y. Liu, J. P. Evans, M. F. McCabe, R. A. M. de Jeu, A. I. J. M. van Dijk, and H. Su
Hydrol. Earth Syst. Sci., 14, 979–990, https://doi.org/10.5194/hess-14-979-2010, https://doi.org/10.5194/hess-14-979-2010, 2010
Cited articles
Ahmad, S., Kalra, A., and Stephen, H.:
Estimating soil moisture using remote sensing data: A machine learning approach,
Adv. Water Resour.,
33, 69–80, https://doi.org/10.1016/j.advwatres.2009.10.008, 2010.
Ali, I., Greifeneder, F., Stamenkovic, J., Neumann, M., and Notarnicola, C.:
Review of Machine Learning Approaches for Biomass and Soil Moisture Retrievals from Remote Sensing Data,
Remote Sens.-Basel,
7, 16398–16421, https://doi.org/10.3390/rs71215841, 2015.
Ambroise, C. and McLachlan, G. J.:
Selection bias in gene extraction on the basis of microarray gene-expression data,
P. Natl. Acad. Sci. USA,
99, 6562–6566, https://doi.org/10.1073/pnas.102102699, 2002.
Anderson, K. and Gaston, K. J.:
Lightweight unmanned aerial vehicles will revolutionize spatial ecology,
Front. Ecol. Environ.,
11, 138–146, https://doi.org/10.1890/120150, 2013.
Apley, D. W. and Zhu, J.: Visualizing the effects of predictor variables in black box supervised learning models, Roy. Stat. Soc. B, 82, 1059–1086, https://doi.org/10.1111/rssb.12377, 2020.
Araya, S. N.: saraya209/uas-soil-moisture: First release of uas-soil-moisture code and data, Zenodo, https://doi.org/10.5281/zenodo.4743238, 2021.
Barrett, B. W. and Petropoulos, G. P.: Satellite Remote Sensing of Surface Soil Moisture, in: Remote Sensing of Energy Fluxes and Soil Moisture Content,
edited by: Petropoulos, G. P., CRC Press, Boca Raton, FL, 85–120, 2014.
Ben-Dor, E., Chabrillat, S., Demattê, J. A. M., Taylor, G. R., Hill, J., Whiting, M. L., and Sommer, S.:
Using Imaging Spectroscopy to study soil properties,
Remote Sens. Environ.,
113 (Suppl. 1),
S38–S55, https://doi.org/10.1016/j.rse.2008.09.019, 2009.
Ben-Shimon, D. and Shmilovici, A.: Kernels for the Relevance Vector Machine – An Empirical Study, in: Advances in Web Intelligence and Data Mining, edited by: Last, M., Szczepaniak, P. S., Volkovich, Z., and Kandel, A., Springer-Verlag GmbH, Berlin, Heidelberg, 253–263, 2006.
Berni, J. A. J., Zarco-Tejada, P. J., Suárez, L., González-Dugo, V., and Fereres, E.: Remote sensing of vegetation from UAV platforms using lightweight multispectral and thermal imaging sensors, Int. Arch. Photogramm., 38, 6, https://doi.org/10.1007/s11032-006-9022-5, 2009.
Breiman, L.:
Random Forest,
Mach. Learn.,
45, 5–32, https://doi.org/10.1023/A:1010933404324, 2001.
Brownlee, J.: Better Deep Learning Train Faster, Reduce Overfitting, and Make Better Predictions, 1.8., Machine Learning Mastery Pty., available at: https://machinelearningmastery.com/better-deep-learning/ (last access: 7 May 2021), 2020.
California Department of Water Resources:
UC Merced Weather Station,
available at: http://cdec.water.ca.gov/dynamicapp/staMeta?station_id=UCM (last access: 1 February 2019), 2018.
California Irrigation Management Information System:
CIMIS Station Report, available at: https://cimis.water.ca.gov/WSNReportCriteria.aspx (last access: 1 February 2019), 2018.
California Irrigation Management Information System:
Data Overview, available at: https://cimis.water.ca.gov/Resources.aspx, last access: 19 April 2019.
Caruana, R. and Niculescu-Mizil, A.:
An empirical comparison of supervised learning algorithms,
in: Proceedings of the 23rd international conference on Machine learning – ICML '06, ACM Press, New York, USA, 161–168, 2006.
Chen, T. and Guestrin, C.:
XGBoost: A Scalable Tree Boosting System,
in: Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining - KDD '16, ACM Press, New York, USA, 785–794, 2016.
Chen, X. and Jeong, J. C.: Enhanced Recursive Feature Elimination, in: Proc. – 6th Int. Conf. Mach. Learn. Appl. ICMLA 2007, 13–15 December 2007, Cincinnati, OH, USA, 330–335, https://doi.org/10.1109/ICMLA.2007.35, 2007.
Colomina, I. and Molina, P.:
Unmanned aerial systems for photogrammetry and remote sensing: A review,
ISPRS J. Photogramm.,
92, 79–97, https://doi.org/10.1016/j.isprsjprs.2014.02.013, 2014.
Cortes, C. and Vapnik, V. N.:
Support-Vector Networks,
Mach. Learn.,
20, 273–297, https://doi.org/10.1023/A:1022627411411, 1995.
Das, N. N. and Mohanty, B. P.:
Root Zone Soil Moisture Assessment Using Remote Sensing and Vadose Zone Modeling,
Vadose Zone J.,
5, 296, https://doi.org/10.2136/vzj2005.0033, 2006.
Drucker, H., Burges, C. J. C., Kaufman, L., Smola, A., and Vapnik, V. N.: Support vector regression machines, in: Advances in Neural Information Processing Systems 9: Proceedings of the 1996 Conference, edited by: Mozer, M. C., Jordan, M. I., and Petsche, T., MIT Press, Cambridge, Massachusetts, 155–161, 1997.
Elarab, M.: The Application of Unmanned Aerial Vehicle to Precision Agriculture: Chlorophyll, Nitrogen, and Evapotranspiration Estimation, Utah State University, Utah, 2016.
Elith, J., Leathwick, J. R., and Hastie, T.:
A working guide to boosted regression trees,
J. Anim. Ecol.,
77, 802–813, https://doi.org/10.1111/j.1365-2656.2008.01390.x, 2008.
Famiglietti, J. S., Rudnicki, J. W., and Rodell, M.:
Variability in surface moisture content along a hillslope transect: Rattlesnake Hill, Texas,
J. Hydrol.,
210, 259–281, https://doi.org/10.1016/S0022-1694(98)00187-5, 1998.
Friedman, J. H.:
Greedy Function Approximation: A Gradient Boosting Machine,
Ann. Stat.,
29, 1189–1232, https://doi.org/10.1017/CBO9781107415324.004, 2001.
Friedman, J. H.:
Stochastic gradient boosting,
Comput. Stat. Data An.,
38, 367–378, https://doi.org/10.1016/S0167-9473(01)00065-2, 2002.
Fryjoff-Hung, A. F.:
2D Hydrodynamic Modeling for Evaluating Restoration Potential of a Vernal Pool Complex,
University of California, Merced, 2018.
Georganos, S., Grippa, T., Gadiaga, A. N., Linard, C., Lennert, M., Vanhuysse, S., Mboga, N. O., Wolff, E., and Kalogirou, S.: Geographical Random Forests: A Spatial Extension of the Random Forest Algorithm to Address Spatial Heterogeneity in Remote Sensing and Population Modelling, Geocarto Int., 36, 121–136, https://doi.org/10.1080/10106049.2019.1595177, 2019.
Greenwell, B. M.:
pdp: An R Package for Constructing Partial Dependence Plots, R J., 9,
available at: https://github.com/bgreenwell/pdp/issues (last access: 13 June 2019), 2017.
Guyon, I. and Elisseeff, A.:
An Introduction to Variable and Feature Selection,
J. Mach. Learn. Res.,
3, 1157–1182, 2003.
Guyon, I., Weston, J., Barnhill, S., and Vapnik, V.: Gene selection for cancer classification using support vector machines, Mach. Learn., 46, 389–422, https://doi.org/10.1023/A:1012487302797, 2002.
Hassan-Esfahani, L., Torres-Rua, A., Jensen, A., and McKee, M.:
Assessment of surface soil moisture using high-resolution multi-spectral imagery and artificial neural networks,
Remote Sens.-Basel,
7, 2627–2646, https://doi.org/10.3390/rs70302627, 2015.
Hastie, T., Tibshirani, R., and Friedman, J.:
The Elements of Statistical Learning: Data Mining, Inference, and Prediction, 2nd edn.,
Springer New York, New York, NY, 2009.
Haubrock, S.-N., Chabrillat, S., Lemmnitz, C., and Kaufmann, H.:
Surface soil moisture quantification models from reflectance data under field conditions,
Int. J. Remote Sens.,
29, 3–29, https://doi.org/10.1080/01431160701294695, 2008.
Hengl, T., Mendes de Jesus, J., Heuvelink, G. B. M., Ruiperez Gonzalez, M., Kilibarda, M., Blagotić, A., Shangguan, W., Wright, M. N., Geng, X., Bauer-Marschallinger, B., Guevara, M. A., Vargas, R., MacMillan, R. A., Batjes, N. H., Leenaars, J. G. B., Ribeiro, E., Wheeler, I., Mantel, S., and Kempen, B.:
SoilGrids250m: Global gridded soil information based on machine learning,
edited by: Bond-Lamberty, B.,
PLoS One,
12, e0169748, https://doi.org/10.1371/journal.pone.0169748, 2017.
Hengl, T., Nussbaum, M., Wright, M. N., Heuvelink, G. B. M., and Gräler, B.:
Random forest as a generic framework for predictive modeling of spatial and spatio-temporal variables,
PeerJl,
6, e5518, https://doi.org/10.7717/peerj.5518, 2018.
Hillel, D.:
Environmental Soil Physics,
Academic Press, San Diego, CA, 1998.
James, G., Witten, D., Hastie, T., and Tibshirani, R.:
An Introduction to Statistical Learning,
Springer New York, New York, NY, 2013.
Jenness, J., Brost, B., and Beier, P.: Land Facet Corridor Designer, available at: http://www.corridordesign.org (last access: 13 June 2019), 2013.
Karatzoglou, A., Smola, A., Hornik, K., and Zeileis, A.: kernlab – An S4 Package for Kernel Methods in R, J. Stat. Softw., 11, 1–20, https://doi.org/10.18637/jss.v011.i09, 2004.
Keskin, H., Grunwald, S., and Harris, W. G.:
Digital mapping of soil carbon fractions with machine learning,
Geoderma,
339, 40–58, https://doi.org/10.1016/j.geoderma.2018.12.037, 2019.
Korres, W., Reichenau, T. G., Fiener, P., Koyama, C. N., Bogena, H. R., Cornelissen, T., Baatz, R., Herbst, M., Diekkrüger, B., Vereecken, H., and Schneider, K.:
Spatio-temporal soil moisture patterns – A meta-analysis using plot to catchment scale data,
J. Hydrol.,
520, 326–341, https://doi.org/10.1016/j.jhydrol.2014.11.042, 2015.
Kuhn, M.: Building Predictive Models in R Using the caret Package, J. Stat. Softw., 28, 1–26, https://doi.org/10.18637/jss.v028.i05, 2008.
Liaw, A. and Wiener, M.: Classification and Regression by randomForest, R News, 2, 18–22, 2002.
Malley, D. F., Martin, P. D., and Ben-Dor, E.:
Application in Analysis of Soils,
in: Near-Infrared Spectroscopy in Agriculture,
edited by: Craig, R., Windham, R., and Workman, J.,
American Society of Agronomy, Crop Science Society of America, Soil Science Society of America, Madison, WI, USA, 729–784, 2004.
Manfreda, S., McCabe, M., Miller, P., Lucas, R., Pajuelo Madrigal, V., Mallinis, G., Ben Dor, E., Helman, D., Estes, L., Ciraolo, G., Müllerová, J., Tauro, F., de Lima, M., de Lima, J., Maltese, A., Frances, F., Caylor, K., Kohv, M., Perks, M., Ruiz-Pérez, G., Su, Z., Vico, G., and Toth, B.:
On the Use of Unmanned Aerial Systems for Environmental Monitoring,
Remote Sens.-Basel,
10, 641, https://doi.org/10.3390/rs10040641, 2018.
Matei, O., Rusu, T., Petrovan, A., and Mihuţ, G.:
A Data Mining System for Real Time Soil Moisture Prediction,
Procedia Engineer.,
181, 837–844, https://doi.org/10.1016/j.proeng.2017.02.475, 2017.
Molnar, C.: Interpretable Machine Learning: A Guide for Making Black Box Models Explainable, Git Hub, available at: https://christophm.github.io/interpretable-ml-book/, last access: 13 June 2019.
Moore, I. D., Burch, G. J., and Mackenzie, D. H.:
Topographic Effects on the Distribution of Surface Soil Water and the Location of Ephemeral Gullies,
T. ASAE,
31, 1098–1107, https://doi.org/10.13031/2013.30829, 1988.
Muller, E. and Décamps, H.:
Modeling soil moisture–reflectance,
Remote Sens. Environ.,
76, 173–180, https://doi.org/10.1016/S0034-4257(00)00198-X, 2000.
Natekin, A. and Knoll, A.:
Gradient boosting machines, a tutorial,
Front. Neurorobotics,
7, 1–11, https://doi.org/10.3389/fnbot.2013.00021, 2013.
Nichols, S., Zhang, Y., and Ahmad, A.:
Review and evaluation of remote sensing methods for soil-moisture estimation,
J. Photon. Energy,
2, 028001, https://doi.org/10.1117/1.3534910, 2011.
Nussbaum, M., Spiess, K., Baltensweiler, A., Grob, U., Keller, A., Greiner, L., Schaepman, M. E., and Papritz, A.: Evaluation of digital soil mapping approaches with large sets of environmental covariates, SOIL, 4, 1–22, https://doi.org/10.5194/soil-4-1-2018, 2018.
Ochsner, T. E., Cosh, M. H., Cuenca, R. H., Dorigo, W. A., Draper, C. S., Hagimoto, Y., Kerr, Y. H., Njoku, E. G., Small, E. E., and Zreda, M.:
State of the Art in Large-Scale Soil Moisture Monitoring,
Soil Sci. Soc. Am. J.,
77, 1888, https://doi.org/10.2136/sssaj2013.03.0093, 2013.
Pachepsky, Y. A., Timlin, D., and Varallyay, G.:
Artificial Neural Networks to Estimate Soil Water Retention from Easily Measurable Data,
Soil Sci. Soc. Am. J.,
60, 727–733, https://doi.org/10.2136/sssaj1996.03615995006000030007x, 1996.
Paloscia, S., Pampaloni, P., Pettinato, S., and Santi, E.:
A Comparison of Algorithms for Retrieving Soil Moisture from ENVISAT/ASAR Images,
IEEE T. Geosci. Remote,
46, 3274–3284, https://doi.org/10.1109/TGRS.2008.920370, 2008.
Petropoulos, G. P., Ireland, G., and Barrett, B. W.:
Surface soil moisture retrievals from remote sensing: Current status, products & future trends,
Phys. Chem. Earth,
83–84, 36–56, https://doi.org/10.1016/j.pce.2015.02.009, 2015.
Price, J. C.:
Thermal inertia mapping: A new view of the earth,
J. Geophys. Res.,
82, 2582–2590, 1977.
Price, J. C.:
On the analysis of thermal infrared imagery: The limited utility of apparent thermal inertia,
Remote Sens. Environ.,
18, 59–73, https://doi.org/10.1016/0034-4257(85)90038-0, 1985.
Rana, G. and Katerji, N.:
Measurement and estimation of actual evapotranspiration in the field under Mediterranean climate: a review,
Eur. J. Agron.,
13, 125–153, https://doi.org/10.1016/S1161-0301(00)00070-8, 2000.
Reed, R. and Marks II, R. J.:
Neural Smithing: Supervised Learning in Feedforward Artificial Neural Networks,
MIT Press, Cambridge, Massachusetts, 1999.
Ridgeway, G.: Generalized Boosted Models: A guide to the gbm package, available at: https://cran.r-project.org/web/packages/gbm/vignettes/gbm.pdf (last access: 1 January 2018) 2012.
Schaap, M. G., Leij, F. J., and van Genuchten, M. T.:
Rosetta: A computer program for estimating soil hydraulic parameters with hierarchical pedotransfer functions,
J. Hydrol.,
251, 163–176, https://doi.org/10.1016/S0022-1694(01)00466-8, 2001.
Schanda, E.:
Physical Fundamentals of Remote Sensing,
Springer-Verlag, Berlin, Germany, 1986.
Seneviratne, S. I., Corti, T., Davin, E. L., Hirschi, M., Jaeger, E. B., Lehner, I., Orlowsky, B., and Teuling, A. J.:
Investigating soil moisture-climate interactions in a changing climate: A review,
Earth-Sci. Rev.,
99, 125–161, https://doi.org/10.1016/j.earscirev.2010.02.004, 2010.
Singh, K. K. and Frazier, A. E.:
A meta-analysis and review of unmanned aircraft system (UAS) imagery for terrestrial applications,
Int. J. Remote Sens.,
39, 5078–5098, https://doi.org/10.1080/01431161.2017.1420941, 2018.
Sobrino, J., Mattar, C., Jiménez-Muñoz, J. C., Franch, B., and Corbari, C.: On the Synergy between Optical and TIR Observations for the Retrieval of Soil Moisture Content, in: Remote Sensing of Energy Fluxes and Soil Moisture Content, edited by: Petropoulos, G. P., CRC Press, Boca Raton, FL, 363–390, 2014.
Sørensen, R., Zinko, U., and Seibert, J.: On the calculation of the topographic wetness index: evaluation of different methods based on field observations, Hydrol. Earth Syst. Sci., 10, 101–112, https://doi.org/10.5194/hess-10-101-2006, 2006.
Stark, B., McGee, M., and Chen, Y.: Short wave infrared (SWIR) imaging systems using small Unmanned Aerial Systems (sUAS), in: IEEE 2015 International Conference on Unmanned Aircraft Systems (ICUAS), 9–12 June 2015, Denver, CO, 495–501, 2015.
Szabó, B., Szatmári, G., Takács, K., Laborczi, A., Makó, A., Rajkai, K., and Pásztor, L.: Mapping soil hydraulic properties using random-forest-based pedotransfer functions and geostatistics, Hydrol. Earth Syst. Sci., 23, 2615–2635, https://doi.org/10.5194/hess-23-2615-2019, 2019.
Tian, J., Su, H., He, H., and Sun, X.:
An Empirical Method of Estimating Soil Thermal Inertia,
Adv. Meteorol.,
2015, 1–9, https://doi.org/10.1155/2015/428525, 2015.
Tipping, M. E.: The Relevance Vector Machine, in: Advances in Neural Information Processing Systems 12, edited by: Solla, S. A., Leen, T. K., and Muller, K., MIT Press, Cambridge, MA, 652–658, 2000.
Tmušić, G., Manfreda, S., Aasen, H., James, M. R., Gonçalves, G., Ben-Dor, E., Brook, A., Polinova, M., Arranz, J. J., Mészáros, J., Zhuang, R., Johansen, K., Malbeteau, Y., de Lima, I. P., Davids, C., Herban, S., and McCabe, M. F.:
Current Practices in UAS-based Environmental Monitoring,
Remote Sens.-Basel,
12, 1001, https://doi.org/10.3390/rs12061001, 2020.
Torres-Rua, A., Ticlavilca, A., Bachour, R., and McKee, M.:
Estimation of Surface Soil Moisture in Irrigated Lands by Assimilation of Landsat Vegetation Indices, Surface Energy Balance Products, and Relevance Vector Machines,
Water,
8, 167, https://doi.org/10.3390/w8040167, 2016.
Trenberth, K. E., Fasullo, J. T., and Kiehl, J.:
Earth's Global Energy Budget,
B. Am. Meteorol. Soc.,
90, 311–323, https://doi.org/10.1175/2008BAMS2634.1, 2009.
Vereecken, H., Huisman, J. A., Pachepsky, Y. A., Montzka, C., van der Kruk, J., Bogena, H., Weihermüller, L., Herbst, M., Martinez, G., and Vanderborght, J.:
On the spatio-temporal dynamics of soil moisture at the field scale,
J. Hydrol.,
516, 76–96, https://doi.org/10.1016/j.jhydrol.2013.11.061, 2014.
Weidong, L., Baret, F., Xingfa, G., Qingxi, T., Lanfen, Z., and Bing, Z.:
Relating soil surface moisture to reflectance,
Remote Sens. Environ.,
81, 238–246, https://doi.org/10.1016/S0034-4257(01)00347-9, 2002.
Western, A. W., Grayson, R. B., Blöschl, G., Willgoose, G. R., and McMahon, T. A.:
Observed spatial organization of soil moisture and its relation to terrain indices,
Water Resour. Res.,
35, 797–810, https://doi.org/10.1029/1998WR900065, 1999.
Weston, J., Elisseeff, A., Schölkopf, B., and Tipping, M.:
Use of the Zero-Norm with Linear Models and Kernel Methods,
J. Mach. Learn. Res.,
3, 1439–1461, 2003.
Whiting, M. L., Li, L., and Ustin, S. L.:
Predicting water content using Gaussian model on soil spectra,
Remote Sens. Environ.,
89, 535–552, https://doi.org/10.1016/j.rse.2003.11.009, 2004.
Willmott, C. and Matsuura, K.:
Advantages of the mean absolute error (MAE) over the root mean square error (RMSE) in assessing average model performance,
Clim. Res.,
30, 79–82, https://doi.org/10.3354/cr030079, 2005.
Wilson, J. P. and Gallant, J. C.: Digital Terrain Analysis, in: Terrain Analysis: principles and applications, edited by: Wilson, J. P. and Gallant, J. C., John Wiley & Sons, Inc, New York, NY, 1–21, 2000.
Wong, K.: Merced Vernal Pools Joins Natural Reserve System, Univ. Calif. News, 22 January 2014, available at: http://universityofcalifornia.edu/news/merced-vernal-pools-join-natural-reserve-system (last access: 5 August 2020), 2014.
Zaman, B. and Mckee, M.:
Spatio-Temporal Prediction of Root Zone Soil Moisture Using Multivariate Relevance Vector Machines,
Open J. Mod. Hydrol.,
4, 80–90, https://doi.org/10.4236/ojmh.2014.43007, 2014.
Zaman, B., McKee, M., and Neale, C. M. U.:
Fusion of remotely sensed data for soil moisture estimation using relevance vector and support vector machines,
Int. J. Remote Sens.,
33, 6516–6552, https://doi.org/10.1080/01431161.2012.690540, 2012.
Zhang, D. and Zhou, G.:
Estimation of Soil Moisture from Optical and Thermal Remote Sensing: A Review,
Sensors,
16, 1308, https://doi.org/10.3390/s16081308, 2016.
Zhang, Y. and Schaap, M. G.:
Weighted recalibration of the Rosetta pedotransfer model with improved estimates of hydraulic parameter distributions and summary statistics (Rosetta3),
J. Hydrol.,
547, 39–53, https://doi.org/10.1016/j.jhydrol.2017.01.004, 2017.
Zhang, Y., Schaap, M. G., and Zha, Y.:
A High-Resolution Global Map of Soil Hydraulic Properties Produced by a Hierarchical Parameterization of a Physically Based Water Retention Model,
Water Resour. Res.,
54, 9774–9790, https://doi.org/10.1029/2018WR023539, 2018.
Zreda, M., Shuttleworth, W. J., Zeng, X., Zweck, C., Desilets, D., Franz, T., and Rosolem, R.: COSMOS: the COsmic-ray Soil Moisture Observing System, Hydrol. Earth Syst. Sci., 16, 4079–4099, https://doi.org/10.5194/hess-16-4079-2012, 2012.
Short summary
We took aerial photos of a grassland area using an unoccupied aerial vehicle and used the images to estimate soil moisture via machine learning. We were able to estimate soil moisture with high accuracy. Furthermore, by analyzing the machine learning models we developed, we learned how different factors drive the distribution of moisture across the landscape. Among the factors, rainfall, evapotranspiration, and topography were most important in controlling surface soil moisture distribution.
We took aerial photos of a grassland area using an unoccupied aerial vehicle and used the images...
