Special Issue on Artificial Intelligence and Natural Hazard Monitoring, Prediction, and Early Warning

Artificial Intelligence (AI) is reshaping systems for monitoring, predicting, and issuing early warnings for natural hazards. With advancements in remote sensing, the Internet of Things (IoT), and sensor technologies, the capability to acquire multi-source, multi-scale disaster data has markedly improved. However, this progress also presents higher demands for processing and modeling vast amounts of heterogeneous information. Traditional methods exhibit limitations in efficiency, adaptability, and the depth of integration with disaster mechanism theories. Therefore, there is a clear need to establish a new generation of research paradigms capable of deeply integrating advanced computing, domain knowledge, physical laws, and multi-source data.

This special issue aims to showcase the latest developments in AI, geotechnical engineering, data science, and related fields concerning the monitoring, prediction, and early warning of natural hazards. We place a particular emphasis on innovative research that establishes connections between data, models, and decision-making. We encourage submissions that achieve synergy between mechanistic models and data intelligence in methodology, and demonstrably enhance the effectiveness of hazard risk identification, process simulation, and early warning response in application.

Topics of interest include, but are not limited to:

• Intelligent data cleaning and fusion methods for multi-source heterogeneous monitoring data.
• Precise identification models for geological hazards integrating domain knowledge and AI algorithms.
• Technologies for simulating hazard processes and predicting their evolution by coupling physical mechanisms with data-driven approaches.
• Construction of intelligent early-warning decision-making systems based on real-time monitoring and dynamic risk assessment

Submitted manuscripts should clearly elucidate: (1) the specific domain expertise applied in the research; (2) how the research enhances capabilities in natural hazard monitoring, prediction, and/or early warning; and (3) the improvements offered by the proposed model in terms of generalization capability, interpretability, and result reliability, supported by corresponding validation and evidence.

Note: This special issue will form part of "the special issue of academic papers of the 28th Annual Meeting of The China Association for Science and Technology".

Guest Editors:

• Lu Zheng, Fuzhou University; Email: zhenglu@fzu.edu.cn
• Yingbin Zhang, Southwest Jiaotong University; Email: yingbinz516@126.com
• Yange Li, Central South University; Email: liyange@csu.edu.cn
• Jing Liu, Southwest Jiaotong University; Email: jingliu@swjtu.edu.cn
• Zhiyuan Li, China University of Mining and Technology, Beijing; Email: lizhiyuan_brave@163.com
• Zishuang Han, China University of Mining and Technology, Beijing; Email: hanzishuang96@163.com

Submission deadline:

May 15, 2026