Accurate and timely crop yield prediction over large spatial regions is critical to national food security and sustainable agricultural development. However, designing a robust model for crop yield prediction over a large spatial region remains challenging due to inadequate surveyed samples and an under-development of deep-learning frameworks. To tackle this issue, we integrated multi-source (remote sensing, weather, and soil properties) data into a dual-stream deep-learning neural network model for winter wheat in China’s major planting regions. The model consists of two branches for robust feature learning: one for sequential data (remote sensing and weather series data) and the other for statical data (soil properties). The extracted features by both branches were aggregated through an adaptive fusion model to forecast the final wheat yield. We trained and tested the model by using official county-level statistics of historical winter wheat yields. The model achieved an average R² of 0.79 and a root-mean-square error of 650.21 kg/ha, superior to the compared methods and outperforming traditional machine-learning methods. The dual-stream deep-learning neural network model provided decent in-season yield prediction, with an error of about 13% compared to official statistics about two months before harvest. By effectively extracting and aggregating features from multi-source datasets, the new approach provides a practical approach to predicting winter wheat yields at the county scale over large spatial regions.

Typhoon disaster information is characterized by multiple sources, complexity and diversity, and different users of this content have different individual concerns. The expression methods of typhoon disaster information considered in previous research have been relatively simple, which cannot meet the personalized service needs of different users. In this paper, according to the diverse content needs of different users in distinct stages of a typhoon disaster, a typhoon disaster information expression method with a multi-user, multi-stage, multi-channel and multi-element combined mode is investigated. First, the audience and disaster stages are divided via demand analysis, and the demand content is summarized according to the users, stages, and release channels. Similar information is then integrated into the same theme, and it is also determined how information is expressed. Then, the analytic hierarchy process (AHP) is used to filter out the important information in each theme. The theme template is then designed according to the characteristics of particular release channels. Finally, a prototype system is developed, and Typhoon Lekima, which impacted China in 2019, is considered as a real case for analysis. The results show that the proposed method can effectively support different users to obtain disaster characteristics at distinct stages of typhoon disasters, evaluate disaster conditions, assist scientific decision-making, and enhance public awareness of risk prevention.