Improvement of multi‐layer soil moisture prediction using support vector machines and ensemble Kalman filter coupled with remote sensing soil moisture datasets over an agriculture dominant basin in China

Abstract

Soil moisture prediction is of great importance in crop yield forecasting and drought monitoring. In this study, the multi-layer root zone soil moisture (0-5, 0-10, 10-40 and 40-100 cm) prediction is conducted over an agriculture dominant basin, namely the Xiang River Basin, in southern China. The support vector machines (SVM) coupled with dual ensemble Kalman filter (EnKF) technique (SVM-EnKF) is compared with SVM for its potential capability to improve the efficiency of soil moisture prediction. Three remote sensing soil moisture products, namely SMAP, ASCAT and AMSR2, are evaluated for their performance in multi-layer soil moisture prediction with SVM and SVM-EnKF, respectively. Multiple cases are designed to investigate the performance of SVM, the effectiveness of coupling dual EnKF technique and the applicability of the remote sensing products in soil moisture prediction. The main results are as follows: (a) The efficiency of soil moisture prediction with SVM using meteorological variables as inputs is satisfactory for the surface layers (0-5 and 0-10 cm), while poor for the root zone layers (10-40 and 40-100 cm). Adding SMAP as input to SVM can improve its performance in soil moisture prediction, with more than 47% increase in the R-value and at least 11% reduction in RMSE for all layers. However, adding ASCAT or AMSR2 has no improvement for its performance. (b) Coupling dual EnKF can significantly improve the performance of SVM in the soil moisture prediction of both surface and the root zone layers. The increase in R-value is above 80%, while the reduction in BIAS and RMSE is respectively more than 90% and 63%. However, adding remote sensing soil moisture products as inputs can no further improve the performance of SVM-EnKF. (c) The SVM-EnKF can eliminate the influence of remote sensing soil moisture extreme values in soil moisture prediction, therefore, improve its accuracy.

Prediction of spring agricultural drought using machine learning algorithms in the southern Songnen Plain, China

“…Therefore, accurate monitoring and forecasting of the spatiotemporal distribution of spring agricultural drought are essential for agricultural production (Cao et al, 2022). SM is the most direct variable for performing drought monitoring and has high spatial heterogeneity, which is influenced by multiple factors, such as meteorological conditions, vegetation cover, topography, and soil properties (Eswar et al, 2018; He et al, 2020; Y. Liu et al, 2020; Zhu et al, 2021). Decreased precipitation and increased evaporation are the main causes of shortage of SM (Dracup et al, 1980; Hao et al, 2018; Y. Liu et al, 2020).…”

“…Consequently, it is important to achieve high-resolution spring SM predictions based on multisource data. Currently, many studies used machine learning and deep learning algorithms to combine multi-source data for downscaling available SM data in order to obtain more refined SM data (Abbaszadeh et al, 2019;de Oliveira et al, 2021;Qu et al, 2019;Xu et al, 2022;Zhu et al, 2021). For example, Park et al (2015) descaled the AMSR2 SM to 1 km using MODIS products, precipitation, and elevation data based on statistical ordinary least squares and RF algorithms.…”

Remote sensing‐based retrieval of soil moisture content using stacking ensemble learning models

“…There are several remote sensing methods, such as reflectance and vegetation index methods based on visible near‐infrared (Przeździecki & Zawadzki, 2020; Tian et al, 2021; Zhou et al, 2022), thermal inertia method based on thermal infrared (Gao et al, 2022; Nguyen et al, 2022), temperature dryness vegetation index method (Wei et al, 2020; Xu et al, 2022), and soil moisture retrieval based on active and passive microwaves (Rigden et al, 2020; Song et al, 2021; Sun et al, 2021). Soil moisture is sensitive to soil characteristics, land cover, and meteorological conditions; therefore, it may exhibit high spatial heterogeneity (Grillakis et al, 2021; Huang et al, 2022; Zhu et al, 2021). The retrieval of SMC based on a single data source is not suitable for practical applications.…”

Spatial Prediction of Total Nitrogen in Soil Surface Layer Based on Machine Learning

“…Models such as BPNN and SVM can solve the nonlinear problem well, which makes the prediction accuracy of the model higher and the nutrient spatial distribution information more accurate. Nonlinear models, mainly BPNN and SVM, have been widely used in soil moisture [18,19], soil organic matter [20], soil heavy metal [21], and soil quality [22].…”