A review on disaster prediction using machine learning
Climate changes are increasing, with it the natural disasters such as earthquakes, hurricanes forest fire, and floods occurrence rate are also on the rise. These devastating incidents result in human losses, significant impacts on infrastructure and properties and often catastrophic socioeconomic im...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Institute of Information Technology, Kohat University of Science and Technology
2024
|
| Subjects: | |
| Online Access: | http://umpir.ump.edu.my/id/eprint/42622/ http://umpir.ump.edu.my/id/eprint/42622/1/A%20review%20on%20disaster%20prediction%20using%20machine%20learning.pdf |
| _version_ | 1848826661464702976 |
|---|---|
| author | Farghaly, Alaa Taiseer Ngahzaifa, Ab Ghani Abbas Saliimi, Lokman |
| author_facet | Farghaly, Alaa Taiseer Ngahzaifa, Ab Ghani Abbas Saliimi, Lokman |
| author_sort | Farghaly, Alaa Taiseer |
| building | UMP Institutional Repository |
| collection | Online Access |
| description | Climate changes are increasing, with it the natural disasters such as earthquakes, hurricanes forest fire, and floods occurrence rate are also on the rise. These devastating incidents result in human losses, significant impacts on infrastructure and properties and often catastrophic socioeconomic impacts. A lot of approaches have been taken to address issues related to natural disasters i.e. the development of early warning systems, risk assessment and management, disaster response and recovery, and the modelling of the natural disasters for the purposes of prediction and forecasting. The recent development in artificial intelligence (AI), deep learning (DL) and machine learning (ML) can help in better cope with the disaster prediction, detection, mapping, evacuation, and relief activities using sources of big data such as satellite imagery, social media, and geographical information systems (GIS). This paper aims to review research studies that utilize big and complex datasets to develop ML system that can predict and assist before, during and after disasters. Finally, the paper discusses the limitations and future directions of using machine learning for disaster prediction, classification, and highlights the need for further research in this area. Overall, this paper provides a comprehensive overview of the current state of the art in using machine learning for disaster prediction, classification and identifies opportunities for future research. |
| first_indexed | 2025-11-15T03:48:22Z |
| format | Article |
| id | ump-42622 |
| institution | Universiti Malaysia Pahang |
| institution_category | Local University |
| language | English |
| last_indexed | 2025-11-15T03:48:22Z |
| publishDate | 2024 |
| publisher | Institute of Information Technology, Kohat University of Science and Technology |
| recordtype | eprints |
| repository_type | Digital Repository |
| spelling | ump-426222024-09-20T03:38:38Z http://umpir.ump.edu.my/id/eprint/42622/ A review on disaster prediction using machine learning Farghaly, Alaa Taiseer Ngahzaifa, Ab Ghani Abbas Saliimi, Lokman QA75 Electronic computers. Computer science Climate changes are increasing, with it the natural disasters such as earthquakes, hurricanes forest fire, and floods occurrence rate are also on the rise. These devastating incidents result in human losses, significant impacts on infrastructure and properties and often catastrophic socioeconomic impacts. A lot of approaches have been taken to address issues related to natural disasters i.e. the development of early warning systems, risk assessment and management, disaster response and recovery, and the modelling of the natural disasters for the purposes of prediction and forecasting. The recent development in artificial intelligence (AI), deep learning (DL) and machine learning (ML) can help in better cope with the disaster prediction, detection, mapping, evacuation, and relief activities using sources of big data such as satellite imagery, social media, and geographical information systems (GIS). This paper aims to review research studies that utilize big and complex datasets to develop ML system that can predict and assist before, during and after disasters. Finally, the paper discusses the limitations and future directions of using machine learning for disaster prediction, classification, and highlights the need for further research in this area. Overall, this paper provides a comprehensive overview of the current state of the art in using machine learning for disaster prediction, classification and identifies opportunities for future research. Institute of Information Technology, Kohat University of Science and Technology 2024 Article PeerReviewed pdf en cc_by_4 http://umpir.ump.edu.my/id/eprint/42622/1/A%20review%20on%20disaster%20prediction%20using%20machine%20learning.pdf Farghaly, Alaa Taiseer and Ngahzaifa, Ab Ghani and Abbas Saliimi, Lokman (2024) A review on disaster prediction using machine learning. International Journal of Communication Networks and Information Security (IJCNIS), 16 (1 (Special Issue)). pp. 1402-1415. ISSN 2073-607X. (Published) https://www.ijcnis.org/index.php/ijcnis/article/view/7088 |
| spellingShingle | QA75 Electronic computers. Computer science Farghaly, Alaa Taiseer Ngahzaifa, Ab Ghani Abbas Saliimi, Lokman A review on disaster prediction using machine learning |
| title | A review on disaster prediction using machine learning |
| title_full | A review on disaster prediction using machine learning |
| title_fullStr | A review on disaster prediction using machine learning |
| title_full_unstemmed | A review on disaster prediction using machine learning |
| title_short | A review on disaster prediction using machine learning |
| title_sort | review on disaster prediction using machine learning |
| topic | QA75 Electronic computers. Computer science |
| url | http://umpir.ump.edu.my/id/eprint/42622/ http://umpir.ump.edu.my/id/eprint/42622/ http://umpir.ump.edu.my/id/eprint/42622/1/A%20review%20on%20disaster%20prediction%20using%20machine%20learning.pdf |