Prediction of waterlogged zones under heavy rainfall conditions using machine learning and GIS tools: a case study of Mumbai
Published in GeoJournal, 2022
Flooding is a recurrent issue in coastal Indian cities like Mumbai and Chennai. This study employs machine learning techniques, including Logistic Regression, Support Vector Machines, K-Nearest Neighbour (KNN), Random Forest, and Gradient Boosting, to predict flood occurrences in Mumbai. Using historical flood events and contributing factors processed through GIS tools, the models classify flood risk with KNN achieving the highest accuracy (84%), followed by Random Forest (81%). Our model successfully identified flood-prone locations in August 2020, offering valuable insights for flood mitigation and relief planning.
Recommended citation: Khatri, S., Kokane, P., Kumar, V. and Pawar, S., 2023. Prediction of waterlogged zones under heavy rainfall conditions using machine learning and GIS tools: a case study of Mumbai. GeoJournal, 88(Suppl 1), pp.277-291.
Download Paper