Non-Invasive Inversion and Characteristic Analysis of Soil Moisture in 0–300 cm Agricultural Soil Layers

Shujie Jia, Yaoyu Li, Boxin Cao, Yuwei Cheng, Abdul Sattar Mashori, Zheyu Bai, Mingyi Cui, Zhimin Zhang, Linqiang Deng () and Wuping Zhang ()
Additional contact information
Shujie Jia: College of Software, Shanxi Agricultural University, Jinzhong 030801, China
Yaoyu Li: College of Software, Shanxi Agricultural University, Jinzhong 030801, China
Boxin Cao: College of Software, Shanxi Agricultural University, Jinzhong 030801, China
Yuwei Cheng: College of Software, Shanxi Agricultural University, Jinzhong 030801, China
Abdul Sattar Mashori: College of Software, Shanxi Agricultural University, Jinzhong 030801, China
Zheyu Bai: School of Public Administration, Shanxi University of Finance and Economics, Taiyuan 030801, China
Mingyi Cui: College of Software, Shanxi Agricultural University, Jinzhong 030801, China
Zhimin Zhang: College of Software, Shanxi Agricultural University, Jinzhong 030801, China
Linqiang Deng: College of Software, Shanxi Agricultural University, Jinzhong 030801, China
Wuping Zhang: College of Software, Shanxi Agricultural University, Jinzhong 030801, China

Agriculture, 2025, vol. 15, issue 20, 1-21

Abstract: Accurate profiling of deep (20–300 cm) soil moisture is crucial for precision irrigation but remains technically challenging and costly at operational scales. We systematically benchmark eight regression algorithms—including linear regression, Lasso, Ridge, elastic net, support vector regression, multi-layer perceptron (MLP), random forest (RF), and gradient boosting trees (GBDT)—that use easily accessible inputs of 0–20 cm surface soil moisture (SSM) and ten meteorological variables to non-invasively infer soil moisture at fourteen 20 cm layers. Data from a typical agricultural site in Wenxi, Shanxi (2020–2022), were divided into training and testing datasets based on temporal order (2020–2021 for training, 2022 for testing) and standardized prior to modeling. Across depths, non-linear ensemble models significantly outperform linear baselines. Ridge Regression achieves the highest accuracy at 0–20 cm, SVR performs best at 20–40 cm, and MLP yields consistently optimal performance across deep layers from 60 cm to 300 cm (R 2 = 0.895–0.978, KGE = 0.826–0.985). Although ensemble models like RF and GBDT exhibit strong fitting ability, their generalization performance under temporal validation is relatively limited. Model interpretability combining SHAP, PDP, and ALE shows that surface soil moisture is the dominant predictor across all depths, with a clear attenuation trend and a critical transition zone between 160 and 200 cm. Precipitation and humidity primarily drive shallow to mid-layers (20–140 cm), whereas temperature variables gain relative importance in deeper profiles (200–300 cm). ALE analysis eliminates feature correlation biases while maintaining high predictive accuracy, confirming surface-to-deep information transmission mechanisms. We propose a depth-adaptive modeling strategy by assigning the best-performing model at each soil layer, enabling practical non-invasive deep soil moisture prediction for precision irrigation and water resource management.

Keywords: deep soil moisture; machine learning; non-invasive monitoring; model interpretability; SHAP analysis; precision agriculture (search for similar items in EconPapers)
JEL-codes: Q1 Q10 Q11 Q12 Q13 Q14 Q15 Q16 Q17 Q18 (search for similar items in EconPapers)
Date: 2025
References: Add references at CitEc
Citations:

Downloads: (external link)
https://www.mdpi.com/2077-0472/15/20/2143/pdf (application/pdf)
https://www.mdpi.com/2077-0472/15/20/2143/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:gam:jagris:v:15:y:2025:i:20:p:2143-:d:1771876

Access Statistics for this article

Agriculture is currently edited by Ms. Leda Xuan

More articles in Agriculture from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().