Sentinel-1 Backscatter and Interferometric Coherence for Soil Moisture Retrieval in Winter Wheat Fields Within a Semiarid South-Mediterranean Climate: Machine Learning Versus Semiempirical Models
Jamal Ezzahar, Abdelghani Chehbouni, Nadia Ouaadi, Mohammed Madiafi, Saïd Khabba, Salah Er‐Raki, Ahmed Laamrani, Adnane Chakir, Zohra Lili‐Chabaane, Mehrez Zribi
Abstract
This work aims to assess the effectiveness of machine learning (ML) algorithms and semi-empirical models for surface soil moisture (SSM) retrieval by exploring the Sentinel-1 backscatter and interferometric coherence data. Firstly, three commonly used categories of ML algorithms are evaluated using data gathered from diverse rainfed and irrigated wheat fields located in Morocco and Tunisia. Specifically, these algorithms include: artificial neural network (ANN), deep neural network (DNN), three support vector regression (SVR) models (radial basis function (SVR_rbf), linear (SVR_linear) and polynomial (SVR_quad) kernels) and two tree-based methods (Random Forest (RF) and XGBoost). The comparison between predicted and measured SSM showed that the best retrieval results were obtained using Sentinel-1 data at VV polarization with R ranging between <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$ 0.68$</tex-math></inline-formula> and <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$ 0.76$</tex-math></inline-formula> and RMSE of <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$ 0.05 m^{3}/m^{3}$</tex-math></inline-formula> and <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$ 0.06 m^{3}/m^{3}$</tex-math></inline-formula> . Secondly, to further assess their transferability, the ANN, SVR_rbf and XGBoost that demonstrated the most favorable results from each category were evaluated and compared against the coupled Water Cloud and Oh models (WCM), using a second dataset collected over a drip-irrigated wheat field in Morocco. Overall, the best retrieval results were achieved by ANN and SVR_rbf with R and RMSE of <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$ 0.81$</tex-math></inline-formula> and <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$ 0.034 m^{3}/m^{3}$</tex-math></inline-formula> , respectively. In addition, their performances were consistent with that of WCM which yielded R and RMSE values of <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$ 0.81$</tex-math></inline-formula> and <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$ 0.04 m^{3}/m^{3}$</tex-math></inline-formula> , respectively. Finally, due to its good compromise between retrieval accuracy of SSM, processing time and simplicity, SVR_rbf was chosen to generate high-resolution SSM maps from Sentinel-1 data over irrigated wheat fields.