An Interventional Approach to Real-Time Disaster Assessment via Causal Attribution

2025-09-15

AI Summary

Traditional disaster assessment tools rely heavily on historical data, limiting their capacity for counterfactual scenario simulation and causal attribution. To address this, we propose the first intervenable real-time disaster assessment framework that integrates multi-source streaming data—including satellite remote sensing, news reports, and social media—to establish a dynamic analysis pipeline grounded in causal modeling and counterfactual reasoning. Our framework enables users to intervene on key variables (e.g., rainfall intensity, evacuation response timing) and quantifies their causal effect pathways on regional disaster severity, generating actionable mitigation strategies. Experimental evaluation demonstrates its effectiveness in regional-scale dynamic causal attribution, interactive policy simulation, and intervention outcome forecasting. The implementation is open-sourced and designed for integration into operational emergency response systems.

Technology Category

• Reasoning under Uncertainty: Causality
• Machine Learning: Causal Learning
• Knowledge Representation and Reasoning: Diagnosis and Abductive Reasoning

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• User Modeling, Personalization and Recommendation: Attacks and countermeasures in recommendation systems
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs

Abstract

Traditional disaster analysis and modelling tools for assessing the severity of a disaster are predictive in nature. Based on the past observational data, these tools prescribe how the current input state (e.g., environmental conditions, situation reports) results in a severity assessment. However, these systems are not meant to be interventional in the causal sense, where the user can modify the current input state to simulate counterfactual "what-if" scenarios. In this work, we provide an alternative interventional tool that complements traditional disaster modelling tools by leveraging real-time data sources like satellite imagery, news, and social media. Our tool also helps understand the causal attribution of different factors on the estimated severity, over any given region of interest. In addition, we provide actionable recourses that would enable easier mitigation planning. Our source code is publicly available.

Problem

• Develops interventional tool for real-time disaster assessment
• Enables causal what-if simulations using diverse data sources
• Identifies causal factors and provides mitigation recourses

Innovation

• Interventional tool for real-time disaster assessment
• Leverages satellite imagery, news, and social media
• Provides causal attribution of disaster severity factors