Multi-Depth Soil Moisture Prediction Using Machine Learning Across Türkiye's Diverse Environments

Year 2026, Volume: 32 Issue: 2 , 423 - 438 , 24.03.2026

Muhammed Sungur Demir

https://doi.org/10.15832/ankutbd.1809955

https://izlik.org/JA38LW32KS

Abstract

Efficient agricultural water management is essential to address global water scarcity. Soil moisture serves as a key indicator for irrigation scheduling, crop yield forecasting, and hydrological modeling. However, traditional in-situ measurements are costly, labor-intensive, and spatially limited. This study develops a machine learning framework for predicting soil moisture at multiple depths (20, 40, and 80 cm) using readily available environmental variables. Türkiye was selected as the study area due to its pronounced climatic and pedological heterogeneity, providing an ideal testbed for training robust models. Seven machine learning algorithms were systematically evaluated using data from 201 meteorological stations spanning 2016–2024. Extreme Gradient Boosting (XGBoost) outperformed all alternatives following hyperparameter optimization, achieving strong accuracy across all depths (R² = 0.74, 0.69, and 0.66 at 20, 40, and 80 cm, respectively). Feature importance analysis indicated a depth-dependent shift in the controls on soil moisture. Near the surface (20 cm), short-term meteorological variability and seasonal dynamics were the primary drivers, whereas deeper layers were increasingly regulated by stable soil hydraulic properties, with clay dominating at intermediate depths, and large-scale spatial gradients represented by latitude and elevation. This pattern reflects a transition from weather-driven processes at shallow depths to long-term regulation by soil structure and regional climate patterns in the subsurface. The model maintained robust performance across diverse environmental conditions, with seasonal accuracy varying by nearly 10% between winter and autumn. Spatial analysis revealed regional variations in controlling factors: soil properties (particularly organic carbon) dominated in the northern regions, while their relative importance decreased southward where climatic and temporal variables contributed more substantially, reflecting heightened sensitivity of moisture dynamics to meteorological fluctuations. The framework provides a scalable, cost-effective solution for soil moisture monitoring in data-scarce regions, supporting irrigation optimization, drought early warning, and sustainable water governance. 

Keywords

XGBoost , Root-zone soil moisture , Machine learning model comparison , Temporal cross-validation , Agricultural water management

References

• Ahmad S, Kalra A & Stephen H (2010). Estimating soil moisture using remote sensing data: A machine learning approach. Advances in Water Resources 33(1): 69–80. https://doi.org/10.1016/j.advwatres.2009.10.008
• Ali S, Khorrami B, Jehanzaib M, Tariq A, Ajmal M, Arshad A, Shafeeque M, Dilawar A, Basit I, Zhang L, Sadri S, Niaz M A, Jamil A & Khan S N (2023). Spatial Downscaling of GRACE Data Based on XGBoost Model for Improved Understanding of Hydrological Droughts in the Indus Basin Irrigation System (IBIS). Remote Sensing 15(4): 873. https://doi.org/10.3390/rs15040873
• Allen R, Pereira L, Raes D & Smith M (1998). FAO Irrigation and Drainage Paper No. 56. Bayazıt M (2013). Hidroloji (1st ed.). Istanbul: Birsen Yayınevi.
• Cengı̇ z A I, Güven H, Erşahı̇ n M E, Özgün H, Tuna M & Kinaci C (2022). Investigation of Factors Affecting Per Capita Expenditure of Water and Sewerage Administrations in Turkey. Turkish Journal of Water Science and Management. https://doi.org/10.31807/tjwsm.1182391
• Champagne C, White J, Berg A, Belair S & Carrera M (2019). Impact of Soil Moisture Data Characteristics on the Sensitivity to Crop Yields Under Drought and Excess Moisture Conditions. Remote Sensing 11(4): 372. https://doi.org/10.3390/rs11040372
• Chen L, Hu B, Sun J, Xu Y J, Zhang G, Ma H & Ren J (2025). Using remote sensing and machine learning to generate 100-cm soil moisture at 30-m resolution for the black soil region of China: Implication for agricultural water management. Agricultural Water Management 309: 109353. https://doi.org/10.1016/j.agwat.2025.109353
• Chen T & Guestrin C (2016). XGBoost: A Scalable Tree Boosting System. Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 785–794. https://doi.org/10.1145/2939672.2939785
• Guo J, Zhang F, Li W, Yang A, Fan Y & Li J (2025). Runoff Prediction in the Xiangxi River Basin Under Climate Change: The Application of the HBV-XGBoost Coupled Model. Water 17(16): 2420. https://doi.org/10.3390/w17162420
• Hao R & Bai Z (2023). Comparative Study for Daily Streamflow Simulation with Different Machine Learning Methods. Water 15(6): 1179. https://doi.org/10.3390/w15061179 sensing and
• Harani P, Gautam S, Joshi S K, Asirvatham L G & Rakshith B L (2025). Advancements in soil moisture estimation through integration of remote artificial intelligence https://doi.org/10.1016/j.scitotenv.2025.180503 techniques. Science of The Total Environment 1001: 180503.
• Houben T, Ebeling P, Khurana S, Schmid J S & Boog J (2025). Machine‐learning based spatiotemporal prediction of soil moisture in a grassland hillslope. Vadose Zone Journal 24(2): e70011. https://doi.org/10.1002/vzj2.70011
• Irmak S (2014). Plant Growth and Yield as Affected by Wet Soil Conditions Due to Flooding or Over-Irrigation. University of Nebraska—Lincoln Extension. http://www.ianrpubs.unl.edu
• Karthikeyan L & Mishra A K (2021). Multi-layer high-resolution soil moisture estimation using machine learning over the United States. Remote Sensing of Environment 266: 112706. https://doi.org/10.1016/j.rse.2021.112706
• Li C, Zhou Y, Wu M, Xu J & Fu X (2025). Exploring Nonlinear Threshold Effects and Interactions Between Built Environment and Urban Vitality at the Block Level Using Machine Learning. Land 14(6): 1232. https://doi.org/10.3390/land14061232
• Ma M, Zhao G, He B, Li Q, Dong H, Wang S & Wang Z (2021). XGBoost-based method for flash flood risk assessment. Journal of Hydrology 598: 126382. https://doi.org/10.1016/j.jhydrol.2021.126382
• Mdemu M, Kissoly L, Bjornlund H, Kimaro E, Christen E W, Van Rooyen A, Stirzaker R & Ramshaw P (2020). The role of soil water monitoring tools and agricultural innovation platforms in improving food security and income of farmers in smallholder irrigation schemes in Tanzania. International Journal https://doi.org/10.1080/07900627.2020.1765746 of Water Resources Development 36(sup1): S148–S170.
• Meteoroloji Genel Müdürlüğü. (MGM) (2023). Areal precipitation assessment for the 2023 water year (In Turkish). Republic of Türkiye Ministry of Environment, Urbanization and Climate Change, Research Department, Hydrometeorology Division. Meteoroloji Genel Müdürlüğü. (MGM) (2024). Average temperature in Türkiye: Analysis for the period 1970–2024 (In Turkish). Republic of Türkiye Ministry of Environment, Urbanization and Climate Change.
• Nguyen T T, Ngo H H, Guo W, Chang S W, Nguyen D D, Nguyen C T, Zhang J, Liang S, Bui X T & Hoang N B (2022). A low-cost approach for soil moisture prediction using multi-sensor data and machine learning algorithm. Science of The Total Environment 833: 155066. https://doi.org/10.1016/j.scitotenv.2022.155066
• Nichols S (2011). Review and evaluation of remote sensing methods for soil-moisture estimation. Journal of Photonics for Energy: 028001. https://doi.org/10.1117/1.3534910
• Ölgen M K (2010). Spatial distribution of annual and seasonal precipitation variability in Türkiye (In Turkish). Ege Coğrafya Dergisi 19(1): 85-95.
• Rasheed M W, Tang J, Sarwar A, Shah S, Saddique N, Khan M U, Imran Khan M, Nawaz S, Shamshiri R R, Aziz M & Sultan M (2022). Soil Moisture Measuring Techniques and Factors Affecting the Moisture Dynamics: A Comprehensive Review. Sustainability 14(18): 11538. https://doi.org/10.3390/su141811538
• Romero Martínez M, Carmona Ibáñez P & Martínez Vargas J (2025). Predicting Business Failure with the XGBoost Algorithm: The Role of Environmental Risk. Sustainability 17(11): 4948. https://doi.org/10.3390/su17114948
• Seleiman M F, Al-Suhaibani N, Ali N, Akmal M, Alotaibi M, Refay Y, Dindaroglu T, Abdul-Wajid H H & Battaglia M L (2021). Drought Stress Impacts on Plants and Different Approaches to Alleviate Its Adverse Effects. Plants 10(2): 259. https://doi.org/10.3390/plants10020259
• Özütürk S (2024). Plants under the risk drought and desertification in southeastern Anatolia (Turkey). EPRA International Journal of Multidisciplinary Research (IJMR): 533–544. https://doi.org/10.36713/epra18002
• Susha Lekshmi S U, Singh, D N & Shojaei Baghini, M. (2014). A critical review of soil moisture measurement. Measurement 54: 92–105. https://doi.org/10.1016/j.measurement.2014.04.007
• Sun W, Zhou S, Yu B, Zhang Y, Keenan T & Fu B (2025). Soil moisture-atmosphere interactions drive terrestrial carbon-water trade-offs. Communications Earth & Environment 6(1): 169. https://doi.org/10.1038/s43247-025-02145-z
• Szczepanek R (2022). Daily Streamflow Forecasting in Mountainous Catchment Using XGBoost, LightGBM and CatBoost. Hydrology 9(12): 226. https://doi.org/10.3390/hydrology9120226
• Taktikou E, Bourazanis G, Papaioannou G & Kerkides P (2016). Prediction of Soil Moisture from Remote Sensing Data. Procedia Engineering 162: 309–316. https://doi.org/10.1016/j.proeng.2016.11.066
• Teshome F T, Bayabil H K, Schaffer B, Ampatzidis Y & Hoogenboom G (2024). Improving soil moisture prediction with deep learning and machine learning models. Computers and Electronics in Agriculture 226: 109414. https://doi.org/10.1016/j.compag.2024.109414
• Walker J P, Willgoose G R & Kalma J D (2004). In situ measurement of soil moisture: A comparison of techniques. Journal of Hydrology 293(1–4): 85–99. https://doi.org/10.1016/j.jhydrol.2004.01.008
• Wang R, Zhang J, Shan B, He M & Xu J (2022). XGBoost Machine Learning Algorithm for Prediction of Outcome in Aneurysmal Subarachnoid Hemorrhage. Neuropsychiatric Disease and Treatment Volume 18: 659–667. https://doi.org/10.2147/NDT.S349956
• Wang Y, Shi L, Hu Y, Hu X, Song W & Wang L (2024). A comprehensive study of deep learning for soil moisture prediction. Hydrology and Earth System Sciences 28(4): 917–943. https://doi.org/10.5194/hess-28-917-2024
• Xia Y, Jiang S, Meng L & Ju X (2024). XGBoost-B-GHM: An Ensemble Model with Feature Selection and GHM Loss Function Optimization for Credit Scoring. Systems 12(7): 254. https://doi.org/10.3390/systems12070254
• Yetik A K, Arslan B & Şen B (2024). Trends and variability in precipitation across Turkey: A multimethod statistical analysis. Theoretical and Applied Climatology 155(1): 473–488. https://doi.org/10.1007/s00704-023-04645-4 learning
• Zeraatpisheh M, White A, Darby H, Neher D A, Faulkner J, Hancock L, Kretzler B, El-Naboulsi N, Turner H C, Von Wettberg E J, Wagner C H & Galford G L (2025). Spatial mapping and predictive modeling of soil organic carbon stocks in Vermont agricultural lands using machine and environmental variables. Computers and Electronics in Agriculture 237: 110727. https://doi.org/10.1016/j.compag.2025.110727
• Zha X, Jia S, Han Y, Zhu W & Lv A (2025). Enhancing Soil Moisture Prediction in Drought-Prone Agricultural Regions Using Remote Sensing and Machine Learning Approaches. Remote Sensing 17(2): 181. https://doi.org/10.3390/rs17020181
• Zhang Z, Zhang T & Li J (2023). Unbiased Gradient Boosting Decision Tree with Unbiased Feature Importance. Proceedings of IJCAI-23. https://www.ijcai.org/proceedings/2023/0515.pdf
• Zhang T, Liang Z, Zhou J, Shao Q, Sarukkalige R, Lü H, Zhang J, Bi C, Wang J, Hu Y & Li B (2025). Multi-layer grid-scale soil moisture estimation using spatiotemporal deep learning methods with physical constraints. Journal of Hydrology 657: 133086. https://doi.org/10.1016/j.jhydrol.2025.133086
• Zhu L, Dai W, Huang J & Luo Z (2025). A comparative analysis of deep learning models for accurate spatio-temporal soil moisture prediction. Geocarto International 40(1): 2441382. https://doi.org/10.1080/10106049.2024.2441382