Soil Moisture Prediction from Remote Sensing Images Coupled with Climate, Soil Texture and Topography via Deep Learning

Abstract

Soil moisture (SM) is an important biophysical parameter by which to evaluate water resource potential, especially for agricultural activities under the pressure of global warming. The recent advancements in different types of satellite imagery coupled with deep learning-based frameworks have opened the door for large-scale SM estimation. In this research, high spatial resolution Sentinel-1 (S1) backscatter data and high temporal resolution soil moisture active passive (SMAP) SM data were combined to create short-term SM predictions that can accommodate agricultural activities in the field scale. We created a deep learning model to forecast the daily SM values by using time series of climate and radar satellite data along with the soil type and topographic data. The model was trained with static and dynamic features that influence SM retrieval. Although the topography and soil texture data were taken as stationary, SMAP SM data and Sentinel-1 (S1) backscatter coefficients, including their ratios, and climate data were fed to the model as dynamic features. As a target data to train the model, we used in situ measurements acquired from the International Soil Moisture Network (ISMN). We employed a deep learning framework based on long short-term memory (LSTM) architecture with two hidden layers that have 32 unit sizes and a fully connected layer. The accuracy of the optimized LSTM model was found to be effective for SM prediction with the coefficient of determination (R2) of 0.87, root mean square error (RMSE) of 0.046, unbiased root mean square error (ubRMSE) of 0.045, and mean absolute error (MAE) of 0.033. The model’s performance was also evaluated concerning above-ground biomass, land cover classes, soil texture variations, and climate classes. The model prediction ability was lower in areas with high normalized difference vegetation index (NDVI) values. Moreover, the model can better predict in dry climate areas, such as arid and semi-arid climates, where precipitation is relatively low. The daily prediction of SM values based on microwave remote sensing data and geophysical features was successfully achieved by using an LSTM framework to assist various studies, such as hydrology and agriculture.

Next-level vegetation health index forecasting: A ConvLSTM study using MODIS Time Series

“…Wang et al ( 2022 ) showed that the accuracy of the yield estimation results of LSTM was generally better than those of conventional ML methods. Celik et al ( 2022 ) investigated soil moisture forecasting based on satellite-derived data with LSTM and they obtained accurate soil moisture values for the next day. Previous research on weather-induced vegetation stress forecasting using LSTM involves utilizing precipitation-based drought indices, such as Standardized Precipitation Index (SPI), Standardized Precipitation Evapotranspiration Index (SPEI), or combining them with other hydro-meteorological factors such as temperature, humidity, and wind speed (Vo et al 2023 ; Wu et al 2022 ).…”

Sensitivity of the land surface temperature and NDWI index to soil moisture on wheat and barley

“…Under controlled irrigation, Liu et al (2018) found that SIF and indices calculated at wavelengths between 680 nm and 750 nm are related to soil moisture at different depths and exhibit different response times on wheat. Therefore, it should be noted that the responses of spectral indices to soil water profile and response times depend on the climatic regimes of the study area, the type of vegetation and its phenological stage, the depth and distribution of the roots, the soil physical characteristics and the spatial scale of the observation (Celik et al 2022;Li et al 2022;Liu et al 2018;Pablos et al 2014).…”

Medium-Scale Soil Moisture Retrievals Using an ELBARA L-Band Radiometer Using Time-Dependent Parameters for Wetland-Meadow-Cropland Site

“…Soil moisture (SM) monitoring plays a crucial role in the context of many branches, with the main impact on agriculture around the world [1][2][3], as a deficit of water available for plants is the main factor governing the agricultural drought assessment [4]. On the other hand, soil moisture monitoring is a still widely explored issue in the research world [5][6][7][8]. For the tens of years of space exploration, soil monitoring techniques have been expanded to include an additional research area focusing on the harmonisation and fusion of soil moisture data obtained at different spatial and temporal scales [9][10][11].…”