Multi-hazard risk mapping using machine learning
This study maps out Ghana’s multi-hazard risk of flood and drought by using machine learning (ML) models for susceptibility analysis, socioeconomic survey for vulnerability analysis and population density for exposure analysis. The ML models used were Logistic Regression (LR), Random Forest (RF) and...
| Autores principales: | , , |
|---|---|
| Formato: | Informe técnico |
| Lenguaje: | Inglés |
| Publicado: |
CGIAR System Organization
2022
|
| Materias: | |
| Acceso en línea: | https://hdl.handle.net/10568/127621 |
| _version_ | 1855520378815774720 |
|---|---|
| author | Adounkpe, Peniel Ghosh, Surajit Amarnath, Giriraj |
| author_browse | Adounkpe, Peniel Amarnath, Giriraj Ghosh, Surajit |
| author_facet | Adounkpe, Peniel Ghosh, Surajit Amarnath, Giriraj |
| author_sort | Adounkpe, Peniel |
| collection | Repository of Agricultural Research Outputs (CGSpace) |
| description | This study maps out Ghana’s multi-hazard risk of flood and drought by using machine learning (ML) models for susceptibility analysis, socioeconomic survey for vulnerability analysis and population density for exposure analysis. The ML models used were Logistic Regression (LR), Random Forest (RF) and Support Vector Machine (SVM) with inputs of location and features of natural hazards. Topographic, precipitation, temperature, hydrology, land cover and soil cover raster images were also used in these models. The value of the Area Under the Curve (AUC) of Receiver Operating Characteristic Curve (ROC) was above 0.80 for all models except the LR model for drought classification. The best performing model was RF, with an AUC of 0.84 and 0.82 for flood and drought classification. |
| format | Informe técnico |
| id | CGSpace127621 |
| institution | CGIAR Consortium |
| language | Inglés |
| publishDate | 2022 |
| publishDateRange | 2022 |
| publishDateSort | 2022 |
| publisher | CGIAR System Organization |
| publisherStr | CGIAR System Organization |
| record_format | dspace |
| spelling | CGSpace1276212025-03-11T09:50:20Z Multi-hazard risk mapping using machine learning Adounkpe, Peniel Ghosh, Surajit Amarnath, Giriraj drought flood agriculture climate change food systems This study maps out Ghana’s multi-hazard risk of flood and drought by using machine learning (ML) models for susceptibility analysis, socioeconomic survey for vulnerability analysis and population density for exposure analysis. The ML models used were Logistic Regression (LR), Random Forest (RF) and Support Vector Machine (SVM) with inputs of location and features of natural hazards. Topographic, precipitation, temperature, hydrology, land cover and soil cover raster images were also used in these models. The value of the Area Under the Curve (AUC) of Receiver Operating Characteristic Curve (ROC) was above 0.80 for all models except the LR model for drought classification. The best performing model was RF, with an AUC of 0.84 and 0.82 for flood and drought classification. 2022-10-20 2023-01-19T19:12:56Z 2023-01-19T19:12:56Z Report https://hdl.handle.net/10568/127621 en https://hdl.handle.net/10568/121965 Open Access application/pdf CGIAR System Organization Adounkpe P, Ghosh S, Amarnath G. 2022. Multi-hazard Risk Mapping with Machine Learning. CGIAR Climate Resilience Initiative. |
| spellingShingle | drought flood agriculture climate change food systems Adounkpe, Peniel Ghosh, Surajit Amarnath, Giriraj Multi-hazard risk mapping using machine learning |
| title | Multi-hazard risk mapping using machine learning |
| title_full | Multi-hazard risk mapping using machine learning |
| title_fullStr | Multi-hazard risk mapping using machine learning |
| title_full_unstemmed | Multi-hazard risk mapping using machine learning |
| title_short | Multi-hazard risk mapping using machine learning |
| title_sort | multi hazard risk mapping using machine learning |
| topic | drought flood agriculture climate change food systems |
| url | https://hdl.handle.net/10568/127621 |
| work_keys_str_mv | AT adounkpepeniel multihazardriskmappingusingmachinelearning AT ghoshsurajit multihazardriskmappingusingmachinelearning AT amarnathgiriraj multihazardriskmappingusingmachinelearning |