The impact of global climate change has intensified, and the frequent occurrence of meteorological disasters has posed a serious challenge to crop production. This article conducts an integrated risk assessment of agricultural drought disasters in the main grain-producing areas of Jilin Province using the temperature and precipitation data of the study area from 1955 to 2020, the sown area of crops, historical disaster data, regional remote sensing images, and statistical yearbook data. The agricultural drought integrated risk assessment model was built around four factors: drought hazards, vulnerability of hazard-bearing bodies, sensitivity of disaster-pregnant environments, and stability of disaster mitigation capacity. The results show that the study area has shown a trend of changing from wet to dry and then wet over the past 66 years, with the occasional occurrence of severe drought, and a decreasing trend at a rate of −0.089. (10a)−1 overall. The integrated risk of drought in the study area exhibits regional clustering, and the overall risk level has some relationship spatially with the regional geological tectonic units, with the high-risk level concentrated in the central area of Song Liao Basin and close to the geological structure of Yishu Graben and the low risk level concentrated in the marginal area of Song Liao Basin. Based on the results of the risk factor analysis, integrated risk prevention suggestions for drought in the main grain-producing areas of Jilin Province were put forward from four aspects. Fine identification and evaluation of high-risk areas of agricultural drought can provide a quantitative basis for effective drought resistance activities in relevant areas.
The rapid and accurate discovery of damage information of the affected buildings is of great significance for postdisaster emergency rescue. In some related studies, the models involved can detect damaged buildings relatively accurately, but their time cost is high. Models that can guarantee both detection accuracy and high efficiency are urgently needed. In this paper, we propose a new transfer-learning deep attention network (TDA-Net). It can achieve a balance of accuracy and efficiency. The benchmarking network for TDA-Net uses a pair of deep residual networks and is pretrained on a large-scale dataset of disaster-damaged buildings. The pretrained deep residual networks have strong sensing properties on the damage information, which ensures the effectiveness of the network in prefeature grasping. In order to make the network have a more robust perception of changing features, a set of deep attention bidirectional encoding and decoding modules is connected after the TDA-Net benchmark network. When performing a new task, only a small number of samples are needed to train the network, and the damage information of buildings in the whole area can be extracted. The bidirectional encoding and decoding structure of the network allows two images to be input into the model independently, which can effectively capture the features of a single image, thereby improving the detection accuracy. Our experiments on the xView2 dataset and three datasets of disaster regions achieve high detection accuracy, which demonstrates the feasibility of our method.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.