Estimating Soil Moisture from Fusion of Soil Physical/Hydraulic Properties and Optical Remote Sensing Observations Using Machine Learning

Document Type : Research Paper


1 Department of Soil Science and Engineering, Faculty of Agriculture, Shahid Chamran University of Ahvaz, Ahvaz, Iran.

2 Associate Professor, Department of soil science, Faculty of Agriculture , Shahid Chamran University of Ahvaz, Iran

3 Department of Environmental Science, University of Arizona,, Arizona, USA


Soil moisture content (SM) is a critical state variable that significantly affects both the hydrological cycle and agricultural production. Therefore, accurate estimation of soil moisture is important for agricultural water resources management. Remote sensing observations in the near- and shortwave infrared have large potential for estimating soil moisture. In addition, soil physical and hydraulic properties affect spatial and temporal variability of soil moisture. The objective of this research was to derive different models for soil moisture estimation in Amir Kabir sugarcane agro-industry fields, Kuzestan province using a combination of soil physical/hydraulic properties and remote sensing observations with machine learning algorithms. Consequently, 166 ground control points and 16 Sentinel-2 satellite images were investigated during the growth period of sugarcane in the year 2021. Six machine learning algorithms including decision tree (DT), support vector machine (SVM), Linear regression, Boosted and Bagged trees, and nural network were used for modeling. Seven models were derived from the combination of soil physical/hydrological properties and remote sensing indices in a hierarchical manner to predict soil moisture content at the field scale. The results indicated that the combination of soil physical/hydraulic properties with remote sensing indices enhances the accuracy of soil moisture estimation. It is observed that almost all developed models performed well for estimating soil moisture, with an RMSE of 0.04-0.06 cm-3cm-3 and an R2 of approximately 0.80. The STR parameter was found to be more sensitive to changes in soil water content than NIR reflectance. Therefore, STR was identified as the most important feature in estimating soil moisture content. Moreover, stepwise linear regression with RMSE value of 0.042 cm3 cm-3 performed the best in soil moisture estimation. According to the results, the models successfully capture the spatiotemporal dynamics of soil moisture and can be used for irrigation scheduling and precision irrigation management at the field scale.


Main Subjects

Acharya, U., Daigh, A. and Oduor, P. (2021). Machine Learning for Predicting Field Soil Moisture Using Soil, Crop, and Nearby Weather Station Data in the Red River Valley of the North. Journal of soilsystems, 5, 57.
Achieng, K.O. (2019). Modelling of soil moisture retention curve using machine learning techniques: Artificial and deep neural networks vs. support vector regression models. Journal of Computers and Geosciences. 2019, 133, 104320.
Adab, M., Morbidelli, R., Saltalippi, C., Moradian, M. and Fallah Ghalhari, G-A. (2020). Machine Learning to Estimate Surface Soil Moisture from Remote Sensing Data. Journal of Water, 12, 3223.
Ahmad, S. and Simonovic, S.P. (2005). An artificial neural network model for generating hydrograph from hydro-meteorological parameters. Journal of Hydrology, 315, 236–251.
Araya1, S. N., Fryjoff-HungA., Anderson, A., Viers, J. H. and Ghezzehei, Teamrat A. (2021). Advances in soil moisture retrieval from multispectral remote sensing using unoccupied aircraft systems and machine learning techniques. Journal of Hydrology and Earth System Sciences. 25, 2739–2758,
Babaeian, E., Sadeghi, M., Franz, T.E., Jones, S., and Tuller, M., (2018). Mapping soil moisture with the OPtical TRApezoid model (OPTRAM) based on long-term MODIS observations. Journal of Remote Sensing of Environment, 211, 425–440.
Babaeian, E., Paheding, S., Siddique, N., Devabhaktuni, V. and Tuller, M. (2021). Estimation of root zone soil moisture from ground and remotely sensed soil information with multisensor data fusion and automated machine learning. Journal of Remote Sensing of Environment, 260, 1-13
Breiman, L. (2001) Random Forest. Mach. Learn., 45, 5–32.
Friedman, J.H. (2001) Greedy Function Approximation: A Gradient Boosting Machine. Ann. Stat., 29, 1189–1232.
Cai, Y., Zheng, W., Zhang, X., Zhangzhong, L. and Xue, X. (2019). Research on soil moisture prediction model based on deep learning. Journal of PLoS ONE,0214508.
Caruana, R., and Niculescu-Mizil, A. (2006). An empirical comparison of supervised learning algorithms, in: Proceedings of the 23rd international conference on Machine learning –. Journal of ICML '06, ACM Press, New York, USA, 161–168. 
Chakrabarti, S., Judge, J., Bongiovanni, T., Rangarajan, A. and Ranka, S. (2018). Spatial Scaling Using Temporal Correlations and Ensemble Learning to Obtain High-Resolution Soil Moisture. IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, VOL. 56, NO. 3.
Elith, J., Leathwick, J.R. and Hastie, T. (2008). A working guide to boosted regression trees. Journal of Animal Ecology, 77, 802–813.
Engman, E.T. (2000). In Remote Sensing in Hydrology and Water Management; Schultz, G.A. Engman, E.T. Eds. Springer: Berlin/Heidelberg, Germany, pp. 197–216.
Fernández-Novales, J., Tardaguila, J., Gutiérrez, S., Marañón, M. and Diago, MP. (2018). In field quantification and discrimination of different vineyard water regimes by on-the-go NIR spectroscopy. Biosystems Engineering 165:47–58.
Friedman, J.H. (2002). Stochastic gradient boosting. Comput. Stat. Data Anal. 38, 367–378.
Flint, A.L. Flint, L.E. Available water. In: Dane, J.H. Topp, G.C. (Eds.), Methods of Soil Analysis, Part 4, Physical Methods. Soil Science Society of America, Madison, pp. 229–233.
Ge, X., Wang, J., Ding, J., Cao, X., Zhang, Z., Liu, J. and Li, X. (2019). Combining UAV-based hyperspectral imagery and machine learning algorithms for soil moisture content monitoring. Journal of peerj, 7e:6926.
Gorthi, S. (2011). Prediction Models for Estimation of Soil Moisture Content. All Graduate Theses and Dissertations. Utah State University. Logan, Utah.
Grimes, D.I.F., Coppola, E., Verdecchia, M. and Visconti, G. (2003). A neural network approach to real-time rainfall estimation for Africa using satellite data. Journal of Hydrometeorol, 4, 1119–1133.
Hamzeh, S., Naseri, A. A., Alavipanah, S. K., Mojaradi, B., Bartholomeus, H. M. and Clevers, J. G. (2013). Estimating salinity stress in sugarcane farms with spaceborne hyperspectral vegetation indices. International Journal of Applied Earth Observation and Geoinformation, 21, 282–290.
Hosseini Chamani, F., Farrokhian Firouzi, A. and Amerikhah, H. (2019). Pedotransfer Function (PTF) for Estimation Soil moisture using NDVI, land surface temperature (LST) and normalized moisture (NDMI) indices. Journal of Water and Soil Conservation, 26 (4), 239-254.
Irons, J.R., Campbell, G.S., Norman, J.M., Graham, D.W. and Kovalick, W.M. (1992). Prediction and measurement of soil bidirectional reflectance. IEEE Transactions On Geoscience and Remote Sensing, 30, 249–260.
James, G., Witten, D. and Hastie, T. (2013). Tibshirani, R. An Introduction to Statistical Learning; Springer: New York, NY, USA.
Joshi, C. and Mohanty, B.P. (2010). Physical controls of near-surface soil moisture across varying spatial scales in an agricultural landscape during SMEX02. Journal of Water Resources Research, 46, 1-21.
Jung, M., Reichstein, M., Ciais, P., Seneviratne, S.I., Sheffield, J. and Goulden, M.L. (2010). Recent decline in the global land evapotranspiration trend due to limited moisture supply. Journal of Nature, 467, 951–954.
Kaleita, A.L. Tian, L.F. Hirschi, M.C. (2005). Relationship between soil moisture content and soil surface reflectance. Trans. ASAE, 48, 1979-1986.
Kalra, A. and Ahmad, S. (2009). Using oceanic–atmospheric oscillations for long lead time streamflow forecasting. Journal of Water Resources Research.,45, W03413.
Liang, L., Di, L., Zhang, L., Deng, M., Qin, Z., Zhao, S. and Lin, H. (2015). Estimation of crop LAI using hyperspectral vegetation indices and a hybrid inversion method. Journal of Remote Sensing of Environment 165:123–134.
Li, T., Hao, X.M. and Kang, S.Z. (2014). Spatiotemporal variability of soil moisture as affected by soil properties during irrigation cycles. Soil Science Society of America, Madison. 78, 598–608.
Manns, H.R., Berg, A.A., Bullock, P.R. and McNairn, H. (2014) Impact of soil surface characteristics on soil water content variability in agricultural fields. Journal of Hydrology. Process. 28, 4340–4351.
McColl, K.A., Alemohammad, S.H., Akbar, R., Konings, A.G., Yueh, S. and Entekhabi, D. (2017). The global distribution and dynamics of surface soil moisture. Journal of Nature Geoscience, 10, 100–104.
Natekin, A. and Knoll, A. (2013). Gradient boosting machines, a tutorial. Front. Neurorobot, 7, 21.
New L. (1971). Influence of alternate furrow irrigation and time of application on grain sorghum production. Texas Agricultural State Program Report No 2953.
Oymak, S. and Soltanolkotabi, M., 2020. Toward moderate Overparameterization: global convergence guarantees for training shallow neural networks. IEEE Journal of Select. Areas Inform. Theor., 1 (1), 84–105.
Prakash., S., Sharma., A., &, Sahu., S. S., (2019). Soil Moisture Prediction Using Machine Learning. Published in: 2018 Second International Conference on Inventive Communication and Computational Technologies (ICICCT).
Rutter, A.J. and Sands, K. (1958). The relation of leaf water deficit to soil moisture tension in Pinus Sylvestris L. Journal of New Phytologist, 57 (1), 50–65.
Sadeghi, M., Jones, B.S. and Philpot, W.D. (2015). A linear physically-based model for remote sensing of soil moisture using shortwave infrared bands. Journal of Remote Sensing. Environmental, 164, 66–76.
Sadeghi, M., Babaeian, E., Tuller, M. and Jones, S. (2017). The optical Trapezoid model: a novel approach to remote sensing of soil moisture applied to Sentinel-2 and Landsat- 8 observations. Journal of Remote Sensing. Environmental, 198, 52–68.
Sadeghi, M., Babaeian, E., Arthur, E., Jones, S.B. and Tuller, M. (2018). Soil physical properties and processes. In: Kutz, M. (Ed.), Handbook of Environmental Engineering. Wiley, Hoboken, NJ, pp. 137–207. ISBN-10: 1118712943.
Schaap, M.G., Leij, F.J. and van Genuchten, M.Th. (2001). ROSETTA: a computer program for estimating soil hydraulic parameters with hierarchical pedotransfer functions. Journal of Hydrology, 251, 163–176.
Scott, C. A., Bastiaanssen, W.G.M. and Ahmad, M.D. (2003). Mapping Root Zone Soil Moisture Using Remotely Sensed Optical Imagery. Journal of Irrigation and Drainage Engineering, 129(5), 326-335.
Sharma, S.K., Mohanty, B.P. and Zhu, J. (2006). Including topography and vegetation attributes for developing pedotransfer functions. Soil Science Society of America Journal, 70, 1430–1440.
Taghizadeh-Mehrjardi, R. Nabiollahi, K. Minasny, B. and Triantafilis, J. (2015). Comparing data mining classifiers to predict spatial distribution of USDAfamily soil groups in Baneh region, Iran. Geoderma, 253, 67-77.
Tuller, M., and Or, D. (2005). Water retention and characteristic curve. Journal of Hydrology Environmental Science, 4 (1), 278–289.
Twarakavi, N.K., Misra, D. and Bandopadhyay, S. (2006). Prediction of arsenic in bedrock derived stream sediments at a gold mine site under conditions of sparse data. Journal of Hydrology Natural Resources Research, 15, 15–26.
Veysi, Sh., Naseri, A.A., Hamzeh, S. and Bartholomeus, H. (2017). A satellite based crop water stress index for irrigation scheduling insugarcane fields. Journal of Hydrology Agricultural Water Management, 189 70–86.
Western, A. W., Grayson, R. B., Blöschl, G., Willgoose, G. R., and McMahon, T. A. (1999). Observed spatial organization of soil moisture and its relation to terrain indices. Journal of Water Resources Research.,35, 797–810.
Whittaker, G., Confesor, R., Di Luzio, M., and Arnold, J.G. (2010). Detection of Overparameterization and Overfitting in an automatic calibration of SWAT. Journal of Trans. ASABE, 53 (5), 1487–1499.
Yang, H., Huang, K., King, I. and Lyu, M.R. (2009). Localized support vector regression for time series prediction. Neurocomputing, 72, 2659–2669.
Yeh, I.C. and Lien, C.H. (2009). The comparisons of data mining techniques for the predictive accuracy of probability ofdefault of credit card clients. Expert Systems with Applications.Volume 36, Issue 2, Part 1, 36, 2473–2480.
Zareie, A., Amin, M.S.R. and Amador-Jiménez, L.E. (2016). Thornthwaite moisture index modeling to estimate the implication of climate change on pavement deterioration. Journal of Transportation Engineering, 142 (4), 04016007.