Utilizing a fusion of remote sensing data and machine learning models to forecast flood risks to agriculture in Hanoi City, Vietnam

• Published in: Letters in spatial and resource sciences Vol. 17; no. 1; p. 21
• Main Author: Do, Anh Ngoc Thi
• Format: Journal Article
• Language: English
• Published: Berlin/Heidelberg Springer Berlin Heidelberg 01.12.2024; Springer Nature B.V
• Subjects: Agricultural Economics; Agriculture; Amalgamation; Cities; Demography; Economics; Economics and Finance; Environmental Economics; Floods; Food security; Geographical Information Systems/Cartography; Imagery; Landscape/Regional and Urban Planning; Natural disasters; Original Paper; Preservation; Principal components analysis; Regional/Spatial Science; Remote sensing; Strategic planning; Support vector machines; Zoning; Agriculture; SPOT satellite; CRNN model; Flood susceptibility
• ISSN: 1864-4031; 1864-404X
• DOI: 10.1007/s12076-024-00382-y

Floods represent a substantial and consequential from of natural disasters within Hanoi City. To minimize the detrimental effects on agriculture, an all-encompassing decision support instrument is necessary for flood management and alert systems. The primary aim of the current study is to delineate flood susceptible regions by employing SPOT satellite imagery and a hybrid Principal Component Analysis-Support Vector Machine (PCA-SVM) model, thereby gauging the influence of floods on land utilization for agricultural purposes in Hanoi City. The prediction results demonstrate a high model performance with R 2 test  = 0.904, and AUC = 0.921. Areas classified as exhibiting high to very high flood susceptible encompass 55.882% of the overall expanse, while those classified as having low and very low flood risk account for 10.357% and 6.278% respectively. The amalgamation of satellite imagery and the PCA-SVM model in the formulation of flood susceptible zoning maps confers valuable insights to bolster flood prevention endeavors. The current research findings will make a substantial contribution to the strategic planning and preservation of food security for the nation.