A low-cost approach for soil moisture prediction using multi-sensor data and machine learning algorithm

Thu Thuy Nguyen; Huu Hao Ngo; Wenshan Guo; Soon Woong Chang; Dinh Duc Nguyen; Chi Trung Nguyen; Jian Zhang; Shuang Liang; Xuan Thanh Bui; Ngoc Bich Hoang

doi:10.1016/j.scitotenv.2022.155066

A low-cost approach for soil moisture prediction using multi-sensor data and machine learning algorithm

Sci Total Environ. 2022 Aug 10:833:155066. doi: 10.1016/j.scitotenv.2022.155066. Epub 2022 Apr 7.

Authors

Affiliations

¹ Centre for Technology in Water and Wastewater, School of Civil and Environmental Engineering, University of Technology Sydney, Sydney, NSW 2007, Australia.
² Centre for Technology in Water and Wastewater, School of Civil and Environmental Engineering, University of Technology Sydney, Sydney, NSW 2007, Australia. Electronic address: ngohuuhao121@gmail.com.
³ Department of Environmental Energy Engineering, Kyonggi University, 442-760, Republic of Korea.
⁴ Faculty of Science, Agriculture, Business and Law, UNE Business School, University of New England, Elm Avenue, Armidale, NSW 2351, Australia.
⁵ School of Environmental Science and Engineering, Shandong University, Qingdao 266237, China.
⁶ Key Laboratory of Advanced Waste Treatment Technology & Faculty of Environment and Natural Resources, Ho Chi Minh City University of Technology (HCMUT), Vietnam National University Ho Chi Minh (VNU-HCM), Ho Chi Minh City 700000, Viet Nam.
⁷ NTT Institute of Hi-Technology, Nguyen Tat Thanh University, Ho Chi Minh City, Viet Nam.

PMID: 35398433
DOI: 10.1016/j.scitotenv.2022.155066

Abstract

A high-resolution soil moisture prediction method has recently gained its importance in various fields such as forestry, agricultural and land management. However, accurate, robust and non- cost prohibitive spatially monitoring of soil moisture is challenging. In this research, a new approach involving the use of advance machine learning (ML) models, and multi-sensor data fusion including Sentinel-1(S1) C-band dual polarimetric synthetic aperture radar (SAR), Sentinel-2 (S2) multispectral data, and ALOS Global Digital Surface Model (ALOS DSM) to predict precisely soil moisture at 10 m spatial resolution across research areas in Australia. The total of 52 predictor variables generated from S1, S2 and ALOS DSM data fusion, including vegetation indices, soil indices, water index, SAR transformation indices, ALOS DSM derived indices like digital model elevation (DEM), slope, and topographic wetness index (TWI). The field soil data from Western Australia was employed. The performance capability of extreme gradient boosting regression (XGBR) together with the genetic algorithm (GA) optimizer for features selection and optimization for soil moisture prediction in bare lands was examined and compared with various scenarios and ML models. The proposed model (the XGBR-GA model) with 21 optimal features obtained from GA was yielded the highest performance (R² = 0. 891; RMSE = 0.875%) compared to random forest regression (RFR), support vector machine (SVM), and CatBoost gradient boosting regression (CBR). Conclusively, the new approach using the XGBR-GA with features from combination of reliable free-of-charge remotely sensed data from Sentinel and ALOS imagery can effectively estimate the spatial variability of soil moisture. The described framework can further support precision agriculture and drought resilience programs via water use efficiency and smart irrigation management for crop production.

Keywords: ALOS; Data fusion; Machine learning; Sentinel; Soil moisture.

MeSH terms

Algorithms
Machine Learning*
Radar
Soil*
Water / analysis

Substances

Soil
Water