Machine Learning for Disaster Management: Insights from past research and future implications

Abstract

Natural disasters can cause destructive harm and tremendous loss to lives on earth. It destroys residential and industrial areas and negatively affects the water quality in rivers and streams. Disasters cause substantial financial losses and impact the mental state and emotions of the survivors who lose everything. There is a significant need for proper disaster management systems and strategies to cope with the situations and reduce the impact. The advancement in information technology and communications has made the availability of large datasets that are highly useful for researchers. Machine learning technologies have proven invaluable in disaster and crisis management, specifically pre-disaster and post-disaster stages. Recent works discuss machine learning applications in disaster management, growing exponentially. This paper addresses a detailed discussion on machine learning models for disaster management and its various stages, such as recovering and consolidating information, searching and rescuing, and post-disaster assessment. This paper gives an insight into the multimodal machine learning framework for planning efficient strategies for disaster management.

Cite this work

No public copy is stored for this record, so only the metadata is cited.

Stored only when both papers are in the corpus — 31 citations exist upstream.

Papers that cite the same references — the relational fallback while embeddings are still backfilling.