Search

• A deep-learning-based data-driven approach is developed for human activity affected wildfire risk prediction; • A combination of state-of-the-art deep-learning techniques, including CNN, LSTM, channel-spatial attention, Vision transformer and ANN; • The approach adopts internal structural features of samples for capturing details like mountain trails in hilly terrains. • Our predicted wildfire risk shows significant accuracy enhancement compared to traditional FWI and ConvLSTM predictions. Wildfire risk prediction is a critical component of disaster prevention and mitigation, often closely associated with local human activities in most regions. Recent studies demonstrate that employing joint modeling techniques using diverse datasets alongside Convolutional Neural Networks-Long Short-Term Memory Networks (ConvLSTM) produces favorable predictive results. However, previous research inadequately explored the different impact of factors across different categories and spatial orientations, and neglected the impact of fuels and human activities inside the samples. This study focuses on the six eastern provinces of China, utilizing a multi-source dataset comprising satellite-monitored wildfire products from 2012 to 2022, along with various factors indicating terrestrial and human activities, simulated meteorological elements and high-resolution vegetation imagery. By introducing channel and spatial attention mechanisms and visual transformer mode, this research optimizes the ConvLSTM wildfire prediction model. Results indicate a noteworthy enhancement, elevating accuracy, Kappa coefficient, and AUC of ROC curves from 91.15%, 80.87%, and 97.01% to 92.79%, 84.48%, and 97.90%, respectively. Consequently, it reinforces the accuracy by increase of the structural features within samples and quantifying the differences in the importance of different factors, which is also validated by prediction application of the samples in the entire year of 2023. Sensitivity analysis reveals that the current model is still highly dependent on the meteorological factors. Notably, the impact of structural features significantly surpasses the influence of terrain and terrestrial ecology elements, which should be considered in further models. Thus, this study has developed a methodology integrating multiple attention mechanisms and sample structural features, which could furnish high-precision daily kilometer-level wildfire risk prediction products. This method could improve the efficiency of prevention and control by improving the accuracy and narrowing the high-risk areas. [ABSTRACT FROM AUTHOR]

A typhoon is one of the most dangerous natural disasters in the Yangtze River Delta of China. Based on an integrated assessment of the disaster risk elements, including hazard factor, exposure, and vulnerability, the risk level of a typhoon disaster for the Yangtze River Delta as a county-level unit was ultimately determined. The result shows that the risk levels of typhoon hazard factor are gradually weakened from the southeastern coastal areas to the northwest, and the highest-risk areas are located in the southeastern coastal regions. Due to many towns, dense population, a developed economy, and a huge disaster-bearing body in the north of the Yangtze River Delta, which is also located on the plain for a high susceptibility to a disaster-breeding environment, the exposure risk level in the northern areas is higher than in the south. The most vulnerable counties are Chun'an, Xianju, Tiantai, and Sanmen in Zhejiang Province, and Baoying and Xinghua in Jiangsu Province. The highest-risk areas for a typhoon disaster are primarily located in the southeastern coastal areas of Zhejiang Province, Hangzhou Bay, and Shanghai near the Yangtze River Estuary, while the lowest-risk areas are distributed in the western portion of Hangzhou and the northern area of the Yangtze River Delta. [ABSTRACT FROM AUTHOR]

The risk of drought in the Yangtze River Delta Region (YRDR) was assessed using the method of natural disaster risk assessment. Based on the index of disaster risk, the assessment results of risk elements such as drought hazard and vulnerability were calculated in the YRDR. The division of relative drought risk levels in the YRDR was produced at the scale of county (city, district) and township. The results indicated that the areas of highest hazard of drought are located in the northern area of the YRDR. Areas with the greatest vulnerability of drought included Shanghai, Jiaxing, Wuxi, and Hangzhou. The highest risks of drought were mainly distributed in the north of the YRDR; the proportion of slightly high and extremely high risk areas in Shanghai, Nantong, Zhenjiang, Yangzhou, and Taizhou (Jiangsu province) is over 95%. The lowest-risk areas included the southeast coastal area of the YRDR, especially in Hangzhou, and Taizhou (Zhejiang province), where the proportion of slightly high and extremely high risk areas is below 5%. Based on this drought risk assessment, it is critical to establish a drought assessment system including both guarding against and addressing drought. [ABSTRACT FROM AUTHOR]