In complex environments, three-dimensional path planning for agricultural UAVs involves the comprehensive consideration of multiple factors, including obstacle avoidance, path optimization, and computational efficiency, which significantly complicates the achievement of safe and efficient flight. As environmental complexity increases, the search space expands exponentially, thereby making the problem more challenging to solve and categorizing it as an NP-hard problem. To obtain an optimal or near-optimal path within this vast search space, it is essential to balance the path length, safety, and computational cost. This paper proposes a novel UAV path planning method based on the Hybrid Multi-Strategy Dung Beetle Optimization Algorithm (HMSDBO), which effectively reduces path length and improves path smoothness. First, a new Latin hypercube sampling strategy is introduced to significantly enhance the population diversity and improve the global search capabilities. Furthermore, an innovative golden sine strategy is proposed to greatly enhance the algorithm’s robustness. Lastly, a new hybrid adaptive weighting strategy is employed to improve the algorithm’s stability and reliability. To validate the effectiveness of HMSDBO, this study compares its performance with that of the Adaptive Chaotic Gray Wolf Optimization Algorithm (ACGWO), Primitive Dung Beetle Optimization Algorithm (DBO), Whale Optimization Algorithm (WOA), Crayfish Optimization Algorithm (COA), and Hyper-Heuristic Whale Optimization Algorithm (HHWOA) in complex agricultural UAV environments. Experimental results show that the path lengths calculated by HMSDBO are reduced by 21.3%, 7.88%, 19.95%, 8.09%, and 4.2%, respectively, compared to the aforementioned algorithms. This reduction significantly enhances both the optimization effectiveness and the smoothness of three-dimensional path planning for agricultural UAVs.

When the total nitrogen content in water sources exceeds the standard, it can promote the rapid proliferation of algae and other plankton, leading to eutrophication of the water body and also causing damage to the ecological environment of the water source area. Therefore, making timely and accurate predictions of water quality at the source is of vital importance. Since water quality data exhibit non-stationary characteristics, predicting them is quite challenging. This study proposes a novel hybrid deep learning model based on modal decomposition, ERSCB (EMD-RBMO-SVMD-CNN-BiGRU), to enhance the accuracy of water quality forecasting. The model first employs Empirical Mode Decomposition (EMD) technology to decompose the original water quality data. Subsequently, it quantifies the complexity of the subsequences obtained from EMD using Sample Entropy (SE) and further decomposes the most complex subsequences using Sequential Variational Mode Decomposition (SVMD). To address the matter of selecting balanced parameters in SVMD, this study introduces the Red-Billed Blue Magpie Optimization (RBMO) algorithm to optimize the hyperparameters of SVMD. On this basis, a forecasting model is constructed by integrating Convolutional Neural Networks (CNN) and Bidirectional Gated Recurrent Unit (BiGRU) networks. The experimental results show that, compared to existing water quality prediction models, the ERSCB model has an improved prediction accuracy of 4.0% and 3.1% for the KaShi River and GongNaiSi River areas, respectively.

Feature selection (FS) constitutes a critical stage within the realms of machine learning and data mining, with the objective of eliminating irrelevant features while guaranteeing model accuracy. Nevertheless, in datasets featuring a multitude of features, choosing the optimal feature poses a significant challenge. This study presents an enhanced Sand Cat Swarm Optimization algorithm (MSCSO) to improve the feature selection process, augmenting the algorithm’s global search capacity and convergence rate via multiple innovative strategies. Specifically, this study devised logistic chaotic mapping and lens imaging reverse learning approaches for population initialization to enhance population diversity; balanced global exploration and local development capabilities through nonlinear parameter processing; and introduced a Weibull flight strategy and triangular parade strategy to optimize individual position updates. Additionally, the Gaussian–Cauchy mutation strategy was employed to improve the algorithm’s ability to overcome local optima. The experimental results demonstrate that MSCSO performs well on 65.2% of the test functions in the CEC2005 benchmark test; on the 15 datasets of UCI, MSCSO achieved the best average fitness in 93.3% of the datasets and achieved the fewest feature selections in 86.7% of the datasets while attaining the best average accuracy across 100% of the datasets, significantly outperforming other comparative algorithms.

Accurate prediction of PM_2.5 concentration is important for pollution control, public health, and ecological protection. However, due to the nonlinear nature of PM_2.5 data, the accuracy of existing methods suffers and performs poorly in both short-term and long-term predictions. In this study, a deep learning hybrid prediction model based on clustering and quadratic decomposition is proposed. The model utilizes the complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN) to decompose the PM_2.5 sequences into multiple intrinsic modal function components (IMFs), and clusters and re-fuses the subsequences with similar complexity by permutation entropy (PE) and K-means clustering. For the fused high-frequency sequences, a secondary decomposition is performed using the whale optimization algorithm (WOA) optimized variational modal decomposition (VMD). Finally, the nonlinear and temporal features are captured for prediction using the long- and short-term memory neural network (LSTM). Experiments show that this proposed model exhibits good stability and generalization ability. It does not only make accurate predictions in the short term, but also captures the trends in the long-term prediction. There is a significant performance improvement over the baseline models. Further comparisons with existing models outperform the current state-of-the-art models.

PM_2.5 pollution poses an important threat to the atmospheric environment and human health. To precisely forecast PM_2.5 concentration, this study presents an innovative combined model: EMD-SE-GWO-VMD-ZCR-CNN-LSTM. First, empirical mode decomposition (EMD) is used to decompose PM_2.5, and sample entropy (SE) is used to assess the subsequence complexity. Secondly, the hyperparameters of variational mode decomposition (VMD) are optimized by Gray Wolf Optimization (GWO) algorithm, and the complex subsequences are decomposed twice. Next, the sequences are divided into high-frequency and low-frequency parts by using the zero crossing rate (ZCR); the high-frequency sequences are predicted by a convolutional neural network (CNN), and the low-frequency sequences are predicted by a long short-term memory network (LSTM). Finally, the predicted values of the high-frequency and low-frequency sequences are reconstructed to obtain the final results. The experiment was conducted based on the data of 1009A, 1010A, and 1011A from three air quality monitoring stations in the Beijing area. The results indicate that the R² value of the designed model increased by 2.63%, 0.59%, and 1.88% on average in the three air quality monitoring stations, respectively, compared with the other single model and the mixed model, which verified the significant advantages of the proposed model.