Machine Learning Application of Flood Detecting and Mapping in Urban Area with Geographic Information Data

DOI

10.2991/978-94-6463-678-9_36How to use a DOI?

Keywords

Flood Detecting; Geographic Information System (GIS); Machine Learning (ML)

Abstract

Flooding is a prevalent natural calamity in urban areas, particularly in tropical regions like Indonesia. Some places in Palembang are more likely to flood than others because of how people act and how nature acts. Human activities that contribute to flooding in Palembang include the construction of illicit structures on water channels, littering, and disregarding the priority of the surrounding water flow. In this study, the application of Machine Learning (ML) to flood mapping and detection is examined through the use of Geographic Information System (GIS) data. Sentinel-1 satellite images were preprocessed by the Sentinel Application Platform (SNAP) to remove thermal noise, calibrate the radiometric data, rectify the geometry, and filter out speckles. This enhanced the quality of spatial data. We employed machine learning algorithms, such as linear regression for precipitation forecasting and Convolutional Neural Networks (CNN) for spatial feature extraction, to enhance flood risk evaluation. The results suggested that regions like Ilir Timur II and Kemuning, which are particularly vulnerable to inundation due to their low elevation and proximity to river courses, are particularly susceptible. The integration of GIS and ML demonstrated considerable accuracy in predicting flood-prone regions and precipitation trends, producing precise and actionable flood risk maps. These findings provide critical information for policymaking, urban planning, and disaster management, improving preparedness and resilience in areas vulnerable to urban flooding.

Copyright

© 2025 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Leni Novianti
AU  - Ermatita
AU  - Abdiansah
AU  - Ade Silvia Handyani
AU  - Novie Rahmadani
AU  - Nyayu Latifah Husni
PY  - 2025
DA  - 2025/05/01
TI  - Machine Learning Application of Flood Detecting and Mapping in Urban Area with Geographic Information Data
BT  - Proceedings of the 8th FIRST 2024 International Conference on Global Innovations (FIRST-ESCSI 2024 )
PB  - Atlantis Press
SP  - 374
EP  - 384
SN  - 2352-5401
UR  - https://doi.org/10.2991/978-94-6463-678-9_36
DO  - 10.2991/978-94-6463-678-9_36
ID  - Novianti2025
ER  -