Multi-hazard susceptibility assessment in the mountainous regions using machine learning techniques: A review
By: Bahuguna, H.N. Bahuguna, S. zaini, S.H.R. and Gupta, S.S
.
Material type: 
BookPublisher: Disaster & Development: NIDM Description: 13(2), Jul-Dec, 2024: p.117-150.Subject(s): Multi-hazard, Machine learning, Susceptibility, Mountainous regions, Disaster nanagement
In:
Disaster & Development: NIDMSummary: Mountainous regions of the world are sites of multiple and overlapping natural hazards that often lead to loss of life, property, and environment. An accurate and timely prediction and assessment of hazardous events can save lives and reduce economic losses in these regions. Multi-hazard susceptibility assessment of mountainous regions may provide holistic valuable insights for effective risk mitigation strategies for future disasters. Currently, Machine learning modeling techniques have enabled novel advances for multi-hazard susceptibility evaluation of natural hazards owing to the availability of the various types of data pertaining to earth observation from multiple sources. Though machine learning modeling techniques have been applied by researchers to provide multi-hazard susceptibility maps for the mountainous regions, building generalized learning techniques of susceptibility and risk evaluation is still a challenge due to the high level of complexity of hazards in these regions. This article contributes a systematic review of machine learning techniques applied by the researchers, especially in the past 10 years for multi-hazard susceptibility assessment in the mountainous regions with adequate contextual information.- Reproduced
https://nidm.gov.in/journal/PDF/Journal/NIDMJOURNAL_JulDec2024/NIDMJOURNAL_JulDec20246.pdf
| Item type | Current location | Call number | Vol info | Status | Date due | Barcode |
|---|---|---|---|---|---|---|
Articles
|
Indian Institute of Public Administration | 13(2), Jul-Dec, 2024: p.117-150 | Available | AR137198 |
Mountainous regions of the world are sites of multiple and overlapping natural hazards that often lead to loss of life, property, and environment. An accurate and timely prediction and assessment of hazardous events can save lives and reduce economic losses in these regions. Multi-hazard susceptibility assessment of mountainous regions may provide holistic valuable insights for effective risk mitigation strategies for future disasters. Currently, Machine learning modeling techniques have enabled novel advances for multi-hazard susceptibility evaluation of natural hazards owing to the availability of the various types of data pertaining to earth observation from multiple sources. Though machine learning modeling techniques have been applied by researchers to provide multi-hazard susceptibility maps for the mountainous regions, building generalized learning techniques of susceptibility and risk evaluation is still a challenge due to the high level of complexity of hazards in these regions. This article contributes a systematic review of machine learning techniques applied by the researchers, especially in the past 10 years for multi-hazard susceptibility assessment in the mountainous regions with adequate contextual information.- Reproduced
https://nidm.gov.in/journal/PDF/Journal/NIDMJOURNAL_JulDec2024/NIDMJOURNAL_JulDec20246.pdf
There are no comments for this item.