RESUMEN
Soil moisture plays an important role in the water and heat exchanges between the land surface and atmosphere, and it has great importance for agricultural production, ecological planning, and water resources management. Although microwave remote sensing has been widely used in large-scale soil moisture monitoring, the accuracy of the downscaled retrieval results cannot be guaranteed for regions with high vegetation coverage and high soil heterogeneity. To address these challenges, this study built soil moisture indice set based on MODIS and elevation data by calculating the Pearson correlation coefficient (R) and Maximum Information Coefficient (MIC), then constructed decision tree models (Gradient Boosting Decision Tree and Random Forest) about the indice set and low-resolution Soil Moisture Active Passive (SMAP) by using two ensemble learning methods (Bagging and Boosting). The models were applied to the high-resolution soil moisture indices in Jilin Province for the years 2017 to 2020 to generate 1 km-resolution products. In the validation process, Triple Collocation Analysis (TCA), comparison of soil moisture maps with coarse and fine resolution, and in-situ measurements in Lishu County, Tongyu County, and Jilin City were used to evaluate the differences between downscaling soil moisture results and ground observations at network, seasonal and point scales. The results were as follows: (1) The correlation coefficient (R2) calculated by the TCA method was 0.733 (GBDT_36km) > 0.649 (RF_36km), and the error variance was 0.0004 (GBDT_36km) < 0.00058 (RF_36km). (2) R at network scale was 0.798 (GBDT_SM) > 0.662 (RF_SM), RMSE was 0.040 (GBDT_SM) < 0.044 (RF_SM), the point scale R was 0.864 (GBDT_SM) > 0.833 (RF_SM), RMSE was 0.029 (GBDT_SM) < 0.039 (RF_SM). The R in four stages of the growth period was GBDT_SM > RF_SM, RMSE was GBDT_SM < RF_SM. In conclusion, the GBDT and RF models can reliably downscale soil moisture in Jilin Province, and the Boosting ensemble learning method represented by GBDT had a better estimation performance.
RESUMEN
Soil moisture (SM) and groundwater (GW) depletion triggered by anthropogenic and natural climate change are influencing food security via crop production per capita decrease in the Nile River Basin (NRB). However, to the best of our understanding, the causes and impact of SM and GW depletion have not been studied yet comprehensively in the NRB. In this study, GW is derived from the Gravity Recovery and Climate Experiment (GRACE) mission, and SM was estimated using the Triple Collocation Analysis (TCA). SM/GW depletion causes were evaluated via the Land Use Land Cover (LULC) and rainfall/temperature change analysis, whereas impact analysis focused on crop production per capita reduction (food insecurity) during SM depletion. The major findings of this study are 1) TCA analyzed SM show a decreasing trend (-0.06 mm/yr) in agricultural land while increasing (+0.21 mm/yr) in forest land, 2) LULC analysis indicated a vast increment of agricultural land (+9%) and bareland (+9%) although the decreasing pattern of forest (-1.5%) and shrubland (-6.9%) during 1990-2019; 3) the impact of SM depletion on crop production per capita caused food insecurity during a drought year, 4) agriculture drought indices and crop production per capita show high correlations (R2 = 0.86 to 0.60) demonstrated that Vegetation Supply Water Index (VSWI) could provide strategic warning of drought impacts on rainfed agricultural regions. In conclusion, SM and GW depletions are mainly caused by human-induced and climate change factors imposing food insecurity challenges in the NRB coupled with increasing temperature and excessive water extraction for irrigation. Therefore, it is highly recommended to rethink and reverse SM/GW depletion causing factors to sustain food security in NRB and similar basins.