Due to inherent randomness and fluctuation of wind speeds, it is very challenging to develop an effective and practical model to achieve accurate wind speed forecasting, especially over large forecasting horizons. This paper presents a new decomposition-optimization model created by integrating Variational Mode Decomposition (VMD), Backtracking Search Algorithm (BSA), and Regularized Extreme Learning Machine (RELM) to enhance forecasting accuracy. The observed wind speed time series is firstly decomposed by VMD into several relative stable subsequences. Then, an emerging optimization algorithm, BSA, is utilized to search the optimal parameters of the RELM. Subsequently, the well-trained RELM is constructed to do multi-step (1-, 2-, 4-, and 6-step) wind speed forecasting. Experiments have been executed with the proposed method as well as several benchmark models using several datasets from a widely-studied wind farm, Sotavento Galicia in Spain. Additionally, the effects of decomposition and optimization methods on the final forecasting results are analyzed quantitatively, whereby the importance of decomposition technique is emphasized. Results reveal that the proposed VMD-BSA-RELM model achieves significantly better performance than its rivals both on single- and multi-step forecasting with at least 50% average improvement, which indicates it is a powerful tool for short-term wind speed forecasting.

In recent years, the impact of global climate change and human activities on vegetation has become increasingly prominent. Understanding vegetation change and its response to climate variables and human activities are key tasks in predicting future environmental changes, climate changes and ecosystem evolution. This paper aims to explore the impact of Three Gorges Reservoir (TGR) water impoundment on the vegetation–climate response relationship in the Three Gorges Reservoir Region (TGRR) and its surrounding region. Firstly, based on the SPOT/VEGETATION NDVI and ERA5 reanalysis datasets, the correlation between climatic factors (temperature and precipitation) and NDVI was analyzed by using partial correlation coefficient method. Secondly, nonlinear fitting method was used to fit the mapping relationship between NDVI and climatic factors. Then, the residual analysis was conducted to evaluate the impact of TGR impoundment on vegetation–climate response relationship. Finally, sensitivity index (SI), sensitivity variation index (SVI) and difference index (DI) were defined to quantify the variation of vegetation–climate response relationship before and after water impoundment. The results show that water impoundment might have some impacts on the response of vegetation–climate, which gradually reduced with increasing distance from the channel; comparing with the residual analysis method, the SI and DI index methods are more intuitive, and combining these two methods may provide new ideas for the study of the impact of human activities on vegetation.

Runoff forecasting is of great importance for flood mitigation and power generation plan preparation. To explore the better application of time-frequency decomposition technology in runoff forecasting and improve the prediction accuracy, this research has developed a framework of runoff forecasting named Decomposition-Integration-Prediction (DIP) using parallel-input neural network, and proposed a novel runoff forecasting model with Variational Mode Decomposition (VMD), Gated Recurrent Unit (GRU), and Stochastic Fractal Search (SFS) algorithm under this framework. In this model, the observed runoff series is first decomposed into several sub-series via the VMD method to extract different frequency information. Secondly, the parallel layers in the parallel-input neural network based on GRU are trained to receive the input samples of each subcomponent and integrate their output adaptively through the concatenation layers. Finally, the output of concatenation layers is treated as the final runoff forecasting result. In this process, the SFS algorithm was adopted to optimize the structure of the neural network. The prediction performance of the proposed model was evaluated using the historical monthly runoff data at Pingshan and Yichang hydrological stations in the Upper Yangtze River Basin of China, and seven various single and decomposition-based hybrid models were developed for comparison. The results show that the proposed model has obvious advantages in overall prediction performance, model training time, and multi-step-ahead prediction compared to several comparative methods, which is a reasonable and more efficient monthly runoff forecasting method based on time series decomposition and neural networks.

The Three Gorges Reservoir (TGR) intervening basin is one of the most important, ecologically fragile and sensitive areas in the upper reaches of the Yangtze River. Since the completion and operation of the TGR, the change of the ecological environment in this region—with vegetation as an indicator—has been a consistent focus of attention. Based on the six phases of land use data and normalized difference vegetation index (NDVI), temperature and precipitation data from 1998 to 2017, the change and trend of land use and vegetation cover in the TGR intervening basin were analyzed quantitatively by using a transition matrix, linear regression and partial correlation analysis. The area of unchanged land use type is 56,565 km², accounting for 97.27% of the total area of the basin. The vegetation coverage with NDVI as the indicator showed a significant upward trend, with a growth rate of 7.5%/10a. The impact of temperature on vegetation was greater than that of precipitation on vegetation. The non-linear fitting curve of NDVI to temperature and precipitation rose with the time course of TGR impoundment, although the mechanism remains to be studied further. In general, climate change, ecological restoration measures, urbanization and reservoir impoundment did not significantly change the spatial distribution pattern of land use and the climate driving mechanism of vegetation growth in the TGR intervening basin.

The characterization of the mapping relationship (MR) between outflow of the upstream reservoir (OUR) and inflow of the downstream reservoir (IDR) in the short-term generation dispatching of cascade reservoirs (SGDCR) greatly impacts the safe and economic operation of hydropower plants. If this MR is not characterized properly, the operation process of hydropower stations will deviate from the planning dispatching schemes. Especially when the upstream reservoir (UR) undertakes peak load regulation tasks frequently and the downstream reservoir (DR) owns weak re-regulation capacity, the safety of cascade reservoirs will be seriously threatened. In this extreme system, the commonest characterizing models in SGDCR, such as the lag time (LT) model and the Muskingum model, may cause a huge deviation when simulating or forecasting the IDR. Given this dilemma, the Gaussian process regression (GPR) model, which is a representative for Bayesian regression methods, is firstly introduced to handle this MR and compared with the LT and the Muskingum model in this paper. The Three Gorges-Gezhouba cascade reservoirs (TGGCR) in China are selected as a typical case study. The performance indicators of four categories are adopted to evaluate the simulated IDR in a single period and a set of pivotal indicators are proposed to estimate the simulation dispatching in multiple periods. The results show that (1) The GPR model reduces the mean absolute deviation (MAD) about inflow of Gezhouba by 197m3/s and 263m3/s than the LT and the Muskingum model respectively; (2) The distribution characteristics of inflow deviation produced by the GPR model are most competitive. Meanwhile, the GPR model has the strongest ability when conducting the multi-period simulation dispatching and owns best applicability on the whole range of streamflow. (3) The Muskingum model is not recommended to characterize the hour-scale hydraulic connection in the extreme system of SGDCR.