Bowen Zuo

Forest and grassland fires have become increasingly severe under climate change, posing significant threats to ecosystems and human safety. Accurate wildfire prediction using remote sensing data remains challenging due to complex spatiotemporal dynamics and heterogeneous data sources. To address this issue, this study proposes a hybrid deep learning framework integrating U-Net and an attention-enhanced bidirectional long short-term memory network (AUBLSTM) for spatiotemporal wildfire prediction using multi-source remote sensing and meteorological data. The U-Net is employed for spatial feature extraction, while AUBLSTM captures temporal dependencies and improves fire spread modeling with attention mechanisms. An encoder–decoder architecture is adopted to enhance multi-scale feature representation, and meteorological constraints are incorporated to improve physical consistency. Experimental results demonstrate that the proposed model outperforms baseline methods, including convolutional long short-term memory (ConvLSTM) and fully connected networks, achieving superior performance in terms of MSE, RRMSE, PSNR, SSIM, IoU, and F1-Score. The framework is efficient, scalable, and suitable for deployment in electronic monitoring and early warning systems, providing a practical solution for integrating multi-source data into wildfire surveillance applications.

Urban transportation is a crucial aspect of modern societal development, with bus route optimization playing a central role in urban transit planning. Well-designed bus routes can enhance the efficiency and attractiveness of public transportation, alleviate traffic congestion and pollution, and ultimately contribute to the overall growth of a city. This study investigates the selection of bus stop locations and route optimization from three perspectives: population density, facility distribution, and route length. The main methodological contribution lies not in the Pareto filtering itself, but in the development of a unified pipeline. This pipeline first generates and prunes candidate stops by applying road-network and intersection-safety constraints. It then constructs feasible routes using a constraint-driven heuristic that enforces stop spacing, ensures monotonic progress away from the origin and toward the destination, and maintains route smoothness. Finally, it integrates population-grid and POI indicators into a tri-objective evaluation framework prior to non-dominated sorting. The proposed method for bus stop location and route optimization is universally applicable to urban bus routes and can be validated through case studies in different cities. An empirical analysis is conducted using Route 119 in Kunming City, Yunnan Province, as a case study. Compared with the original bus route, the optimized route demonstrates improvements of 18.26% in route distance, 15.79% in Points of Interest (POI) accessibility, and 10.53% in population coverage.

Urban transportation is a crucial aspect of modern societal development, with bus route optimization playing a central role in urban transit planning. Well-designed bus routes can enhance the efficiency and attractiveness of public transportation, alleviate traffic congestion and pollution, and ultimately contribute to the overall growth of a city. This study investigates the selection of bus stop locations and route optimization from three perspectives: population density, facility distribution, and route length. Firstly, a scheme for optimizing bus stop locations is proposed based on population grid data, Points of Interest (POI), and road network data. Next, candidate points are generated using the road network, and a new heuristic algorithm is introduced to initially establish optimized routes. A nondominated sorting algorithm is then employed to identify the optimal solution set, balancing population coverage, facility accessibility, and route distance. The proposed method for bus stop location and route optimization is universally applicable to urban bus routes and can be validated through case studies in different cities. Finally, an empirical analysis is conducted using Route 119 in Kunming City, Yunnan Province, as a case study. Compared with the original bus route, the optimized route demonstrates improvements of 18.26% in route distance, 15.79% in Points of Interest (POI) accessibility, and 10.53% in population coverage.