Accurate runoff forecasting is of great significance for the optimization of water resource management and regulation. Given such a challenge, a novel compound approach combining time-varying filtering-based empirical mode decomposition (TVFEMD), sample entropy (SE)-based subseries recombination, and the newly developed deep sequential structure incorporating convolutional neural network (CNN) into a gated recurrent unit network (GRU) is proposed for monthly runoff forecasting. Firstly, the runoff series is disintegrated into a collection of subseries adopting TVFEMD, considering the volatility of runoff series caused by complex environmental and human factors. The subseries recombination strategy based on SE and recombination criterion is employed to reconstruct the subseries possessing the approximate complexity. Subsequently, the newly developed deep sequential structure based on CNN and GRU (CNNGRU) is applied to predict all the preprocessed subseries. Eventually, the predicted values obtained above are aggregated to deduce the ultimate prediction results. To testify to the efficiency and effectiveness of the proposed approach, eight relevant contrastive models were applied to the monthly runoff series collected from Baishan reservoir, where the experimental results demonstrated that the evaluation metrics obtained by the proposed model achieved an average index decrease of 44.35% compared with all the contrast models.

The Tarim Basin in Xinjiang is located in the northwest inland arid region of China, but research shows that the region is rich in groundwater resources. To understand the hydrochemical characteristics and water quality of shallow groundwater in the desert area of the southern margin of the Tarim Basin, the groundwater was systematically sampled and tested. The ion characteristics and evolution mechanism of groundwater were analyzed by mathematical statistics, Schukarev classification, Piper three-line diagram, Gibbs model and ion ratio. Water quality was evaluated by the water quality index method (WQI) and irrigation water suitability-related parameters. The results indicated that the dominant cation in the study area is Na⁺, and the main dominant anions are SO₄²⁻ and Cl⁻. According to total dissolved solids (TDS), the groundwater mainly belongs to brackish water and semi-saline water. The hydrochemical chemistry types are mainly Cl·SO₄-Na·Mg type, followed by Cl-Na type, and the ion source is mainly the weathering and dissolution of evaporation rock, silicate and sulphate. The hydrochemical process is primarily controlled by evaporation concentration and rock weathering, and the cation exchange is weak. Furthermore, the WQI spatial distribution map shows that the groundwater in the middle of the study area is unsuitable for drinking and there are two areas with high WQI values greater than 500. In contrast, the good-excellent groundwater is scattered in the East. The groundwater generally has high to very high salinity, with significant changes in alkalinity. In addition, 54% of the water samples exceed the magnesium hazard (MH) limit. Therefore, certain measures should be taken before irrigation. This study has important implications for the rational development and reasonable utilization of local groundwater.