Forest fires have a significant impact on terrestrial ecosystems, leading to harm to biodiversity and environment. To mitigate the ecological damage caused by forest fires, it was necessary to develop prediction models of fire risk. In this study, by evolving the optimal architecture and parameters using the particle swarm optimization (PSO) algorithm, a convolutional neural network (CNN) deep learning model was proposed to predict forest fire risk on a national scale. Utilizing fire data and fire risk factors from 2001 to 2020 in China, the PSO-CNN-based deep learning model (PSO-CNN) was utilized and tested. Compared to logistic regression, random forest, support vector machine, k-nearest neighbors, and CNN models, the PSO-CNN model exhibited superior performance with an accuracy of 82.2% and an AUC value of 0.92. These results clearly highlighted the effectiveness of the PSO-CNN model in enhancing the accuracy of forest fire prediction. Furthermore, the forest fire risk prediction level estimated by the proposed model on a national scale for the entire country was mostly consistent with actual fire data distribution, indicating its potential to be used as an important direction for deep learning in forest fire prediction research.

The deployment volume of urban surveillance cameras has reached hundreds of thousands or even millions with the advancement of intelligent transportation systems (ITSs), indicating an enormous scale. However, the number of small-field-of-view surveillance cameras in large-scale traffic areas is insufficient to achieve full coverage of urban traffic zones. In the fields of ITSs, this study proposes a traffic information-based driving route inference method to clarify target vehicles’ paths in zones with monitoring blind spots and enhance the collaborative capability between surveillance cameras and traffic networks. First, this study maps traffic roads containing monitoring blind spots and their topologies into Bayesian network (BN) structures. The influencing factors of the target vehicle path can be analyzed, extracted, and quantified by the known data in a traffic network. A weight analysis method is utilized to estimate the weight coefficients of the influencing factors on the basis of the traditional BN model, thereby realizing the driving routes based on traffic networks. This study conducted experiments in Xinbei District, Changzhou City, and Jiangsu Province, China. Experimental results verify that the proposed method can accurately infer and reconstruct driving routes with monitoring blind zones. This method can provide theoretical support for analyzing driving directions at complex traffic intersections and enabling driving route inference in traffic network areas with monitoring blind spots.

In mountainous regions with uneven gauge coverage, satellite precipitation errors are amplified by nonlinear rainfall–runoff processes, while conventional hourly merging often relies on a single continuous regression that inadequately handles zero inflation and intensity heterogeneity. We propose a hierarchical intensity-aware framework comprising a wet/dry gate, a frequency-matched four-class intensity router, and a shared long short-term memory (LSTM) network with class-conditional outputs. In the upper Fujiang River basin, GPM, CMORPH, ERA5-Land and topographic variables were used as predictors; models were trained on 2010–2013, with 2014 retained for temporally held-out validation across point and areal scales, spatial cross-validation and streamflow simulation. Progressive ablation shows that intensity stratification drives the main point-scale gain (Kling–Gupta efficiency (KGE), 0.22 → 0.43), while temporal modeling improves held-out catchment-event performance (KGE 0.75). Oracle diagnosis identifies intensity routing as the main remaining bottleneck, and attribution and source-ablation analyses show that data-source value varies with prediction stage and evaluation scale. Hydrologically, merged precipitation raises the overall Nash–Sutcliffe efficiency (NSE) from −0.13 (GPM) and −0.21 (CMORPH) to 0.40 and reduces absolute peak bias from 52–55% to 32%. Routing discrimination remains the principal residual limitation under the present architecture.