Developing a Long Short-Term Memory (LSTM)-Based Model for Reconstructing Terrestrial Water Storage Variations from 1982 to 2016 in the Tarim River Basin, Northwest China

Impacts of Climate Change, Glacier Mass Loss and Human Activities on Spatiotemporal Variations in Terrestrial Water Storage of the Qaidam Basin, China

Monitoring the variations in terrestrial water storage (TWS) is crucial for understanding the regional hydrological processes, which helps to allocate and manage basin-scale water resources efficiently. In this study, the impacts of climate change, glacier mass loss, and human activities on the variations in TWS of the Qaidam Basin over the period of 2002−2020 were investigated by using Gravity Recovery and Climate Experiment (GRACE) and GRACE Follow-On (GRACE-FO) data, and other hydrological and meteorological data. The results indicate that TWS anomalies (TWSA) derived from five GRACE solutions experienced significant increasing trends over the study period, with the change rates ranging from 4.85 to 6.90 mm/year (1.37 to 1.95 km3/year). The GRACE TWSA averaged from different GRACE solutions exhibited an increase at a rate of 5.83 ± 0.12 mm/year (1.65 ± 0.03 km3/year). Trends in individual components of TWS indicate that the increase in soil moisture (7.65 mm/year) contributed the most to the variations in TWS. Through comprehensive analysis, it was found that the temporal variations in TWS of the Qaidam Basin were dominated by the variations in precipitation, and the spatial variations in TWS of the Qaidam Basin were mostly driven by the increase in glacier meltwater due to climate warming, particularly in the Narin Gol Basin. In addition, the water consumption associated with human activities had relatively fewer impacts.

A Hybrid Triple Collocation-Deep Learning Approach for Improving Soil Moisture Estimation from Satellite and Model-Based Data

Satellite retrieval and land surface models have become the mainstream methods for monitoring soil moisture (SM) over large regions; however, the uncertainty and coarse spatial resolution of these products limit their applications at the regional and local scales. We proposed a hybrid approach combining the triple collocation (TC) and the long short-term memory (LSTM) network, which was designed to generate a high-quality SM dataset from satellite and modeled data. We applied the proposed approach to merge SM data from Soil Moisture Active Passive (SMAP), Global Land Data Assimilation System-Noah (GLDAS-Noah), and the land component of the fifth generation of European Reanalysis (ERA5-Land), and we then downscaled the merged SM data from 0.36° to 0.01° resolution based on the relationship between the SM data and auxiliary environmental variables (elevation, land surface temperature, vegetation index, surface albedo, and soil texture). The merged and downscaled SM results were validated against in situ observations. The results showed that: (1) the TC-based validation results were consistent with the in situ-based validation, indicating that the TC method was reasonable for the comparison and evaluation of satellite and modeled SM data. (2) TC-based merging was superior to simple arithmetic average merging when the parent products had large differences. (3) Downscaled SM of the TC-based merged product had better performance than that of the parent products in terms of ubRMSE and bias values, implying that the fusion of satellite and model-based SM data would result in better downscaling accuracy. (4) Downscaled SM of TC-based merged data not only improved the representation of the SM spatial variability but also had satisfactory accuracy with a median of R (0.7244), ubRMSE (0.0459 m3/m3), and bias (−0.0126 m3/m3). The proposed approach was effective for generating a SM dataset with fine resolution and reliable accuracy for wide hydrometeorological applications.

Recent Oasis Dynamics and Ecological Security in the Tarim River Basin, Central Asia

As an important agricultural and gathering area in arid inland areas of China, the ecological environments of oasis areas are more sensitive to regional climate change and human activities. This paper investigates the dynamic evolution of the oases in the Tarim River basin (TRB) and quantitatively evaluates the regional ecological security of oases via a remote sensing ecological index (RSEI) and net primary productivity (NPP) through the Carnegie–Ames–Stanford approach (CASA) from 2000 to 2020. The results indicate that the total plain oasis area in the TRB during the study period experienced an increasing trend, with the area expanding by 8.21%. Specifically, the artificial oases (cultivated and industrial land) showed a notable increase, whereas the natural oases (forests and grassland) exhibited an apparent decrease. Among the indictors of oasis change, the Normalised Difference Vegetation Index (NDVI) increased from 0.13 to 0.16, the fraction of vegetation cover (FVC) expanded by 36.79%, and NPP increased by 31.55%. RSEI changes indicated that the eco-environment of the TRB region went from poor grade to general grade; 69% of the region’s eco-environment improved, especially in western mountainous areas, and less than 5% of the regions’ eco-ecological areas were degraded, mainly occurring in the desert-oasis ecotone. Changes in land- use types of oases indicated that human activities had a more significant influence on oases expansion than natural factors. Our results have substantial implications for environment protection and sustainable economic development along the Silk Road Economic Belt.

Prediction of Landslide Displacement Based on the Combined VMD-Stacked LSTM-TAR Model

The volatility of the cumulative displacement of landslides is related to the influence of external factors. To improve the prediction of nonlinear changes in landslide displacement caused by external influences, a new combined forecasting model of landslide displacement has been proposed. Variational modal decomposition (VMD) was used to obtain the trend and fluctuation sequences of the original sequence of landslide displacement. First, we established a stacked long short time memory (LSTM) network model and introduced rainfall and reservoir water levels as influencing factors to predict the fluctuation sequence; next, we used a threshold autoregressive (TAR) model to predict the trend sequence, following which the trend and fluctuation prediction sequence were superimposed to obtain the cumulative predicted displacement of the landslide. Finally, the VMD-stacked LSTM-TAR combination model based on the variational modal decomposition, stacked long short time memory network, and a threshold autoregressive model was built. Taking the landslide of Baishuihe in the Three Gorges Reservoir area as an example, through comparison with the prediction results of the VMD-recurrent neural network-TAR, VMD-back propagation neural network-TAR, and VMD-LSTM-TAR, the proposed combined prediction model was noted to have high accuracy, and it provided a novel approach for the prediction of volatile landslide displacement.