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.

An understanding of the spatial variation and influence factors of soil nutrients in mining areas can provide a reference for land reclamation and ecological restoration. Daliuta was used as the study area. The spatial variability of soil nutrients was analyzed using traditional statistics and geostatistics. The effects of topography, mining history, and soil erosion were discussed. The results indicate that the soil pH of the Daliuta mining area is slightly acidic to slightly alkaline, and the soil organic matter, available nitrogen, available phosphorus, and available potassium belonged to the five levels (very low), six (extremely low), five (extremely low), and four (moderately low), respectively. The soil water and salt content indicated that the soil environment in the mining area is arid and has normal levels of salinity. The organic matter, available nitrogen, available phosphorus, available potassium, and soil salt varied moderately, and the pH did not change much, while the soil water varied strongly. The organic matter, pH, and soil salinity are moderately spatially autocorrelated, and the available nitrogen, available phosphorus, available potassium, and soil water are weakly spatially autocorrelated. Each nutrient index had a certain spatial trend effect. The slope, aspect, elevation, and topographic wetness index are the primary topographic factors that control the spatial distribution of soil nutrients. The organic matter, pH, and soil salinity are moderately spatially autocorrelated, and the available nitrogen, available phosphorus, available potassium, and soil water are weakly spatially autocorrelated. Each nutrient index had a certain spatial trend effect. The slope, aspect, elevation, and topographic wetness index are the primary topographic factors that control the spatial distribution of soil nutrients. Soil erosion and mining history are also important factors that lead to the spatial variation of soil nutrients.

Studying the movement law and failure mechanism of overburden is important to underground safety production, aquifer protection, surface subsidence and ecological protection. A commonly used model, the arch structure model, for studying overburden movement is systematically reviewed in this paper. First, the arch structure in the mining field is divided into an unconsolidated layer arch, beam arch (hinged arch), and overburden arch according to arching medium. On this basis, the research progress and existing problems of these three arch structure models are discussed according to the research means, including theoretical modeling, numerical simulation, similar simulation, and field measurements. The application of the arch structure model focuses on the prediction and prevention of mining pressure and surface subsidence, and there are relatively few means to actively regulate overburden arch. Thus, three control methods of the arch structure in underground coal mining are proposed: the preset arch structure method before coal mining, process control arch methods during coal mining, and end reinforcement control arch methods after coal mining. Finally, the main research focus on the arch structure model in the future is discussed.