Imagen de Portada

Implementing multi-criteria decision-making approaches to evaluate and map drought vulnerability with Geospatial Artificial Intelligence (Geo-AI) based investigations

Guardado en:
Publicado en:SN Applied Sciences vol. 7, no. 10 (Oct 2025), p. 1185
Autor principal: Shalwee
Otros Autores: Dhupper, Renu, Kumari, Maya, Gupta, Anil Kumar, Kumar, Deepak
Publicado:
Springer Nature B.V.
Materias:
India
Climate change
Spatial analysis
Socioeconomic factors
Humidity
Artificial intelligence
Water resources management
Assessments
Surface water
Trends
Multiple criterion
Drought
Remote sensing
Population density
Hydrology
Machine learning
Decision making
Economic factors
Deep learning
Radiation
Resource management
Economics
Agriculture
Vegetation
Parameter identification
Global climate
Precipitation
Spatial data
Groundwater
Land use
Literature reviews
Stream flow
Rain
Environmental
Acceso en línea:Citation/Abstract
Full Text
Full Text - PDF
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
Resumen:Assessing and mitigating drought vulnerability is crucial in the context of global climate change. This research aims to improve the precision of drought vulnerability assessments in future. The study identifies key parameters that influence drought vulnerability and integrates environmental, social, and economic factors to develop a comprehensive framework for accurate drought vulnerability mapping. This enhanced accuracy is vital for resource management and mitigation planning in drought-prone regions. The study focuses on the Ranchi district in Jharkhand, India, to analyse various types of droughts with suitable drought vulnerability parameters. An expert survey was conducted to consider the significance of these parameters that implement multi-criteria decision-making (MCDM) entropy approaches. The study weighted parameters according to different drought types, including meteorological, hydrological, and agricultural, for detailed analysis. The findings highlight the potential of MCDM methods in generating high-resolution and accurate drought vulnerability assessments, significantly contributing to sustainable water resource management and resilience-building efforts. The synthesis of spatial data from remote sensing and GIS with socio-economic, environmental, and hydrological criteria creates a comprehensive drought vulnerability model. The final drought vulnerability map for the district revealed that 15% of the area is under severe drought conditions, while 71% is moderately affected. Hydrological drought was identified as the primary cause of vulnerability, indicating a critical need to improve the district's hydrological reservoirs. Geo-AI techniques, such as machine learning and deep learning algorithms, will analyse complex spatial and temporal patterns in drought-affected regions. This research highlights the transformative role of AI-driven decision-making frameworks in addressing complex environmental challenges to provide valuable insights for policymakers and resource managers in implementing targeted drought mitigation strategies.
ISSN:2523-3963
2523-3971
DOI:10.1007/s42452-025-07189-6
Fuente:Science Database