Flooding remains one of the most destructive and recurrent natural disasters worldwide, causing significant loss of life, damage to infrastructure, and disruption to socioeconomic activities. In Ghana, the frequency and severity of floods have increased in recent years due to rapid urbanization, inadequate drainage systems, deforestation, and the growing impacts of climate change. Urban centers such as Accra, Kumasi, and Tamale have become particularly vulnerable, where seasonal rains often lead to widespread inundation, property loss, and displacement of communities. These challenges highlight the urgent need for reliable, data-driven tools to detect, predict, and mitigate flood risks effectively.
This project presents the design and implementation of an intelligent Flood Detection System that employs Artificial Intelligence (AI) and Machine Learning (ML) algorithms to provide automated flood risk detection and assessment. The system integrates the Normalized Difference Water Index (NDWI), derived from satellite imagery, to identify and delineate flooded areas accurately. To enhance precision and minimize false detections caused by shadows and built-up environments, the system leverages Google Gemini AI, a multimodal generative model capable of performing contextual image interpretation. This hybrid approach combines traditional remote sensing techniques with AI-driven reasoning to produce more reliable flood assessments.
A web-based platform was developed to make the system accessible and user-friendly. Users can upload satellite or aerial images, or alternatively input geographical coordinates of areas of interest, to receive comprehensive flood risk analyses. The backend of the system, implemented with Python and FastAPI, handles image preprocessing, NDWI computation, and AI-assisted refinement, while the Next.js frontend provides an interactive interface for visualizing results, including flooded regions, risk classifications, and confidence scores.
Extensive testing was conducted using publicly available satellite datasets from historically flood-prone areas in Ghana, such as the Odaw Basin (Accra), Anloga Junction (Kumasi), and Sagnarigu (Tamale). The system achieved promising results, with accurate identification of flood zones and confidence scores exceeding 70%, validating its effectiveness for real-world applications.
Overall, this project demonstrates the potential of integrating AI and remote sensing in disaster management. It contributes a scalable, cost-effective, and automated solution that supports national flood monitoring efforts and strengthens Ghana’s disaster preparedness framework. The Flood Detection System can serve as a foundation for future enhancements, including real-time alert integration and regional scalability across West Africa, promoting resilience and proactive flood risk management.
Research Area
Machine Learning: Machine Learning (ML) research in Computer Science and Information Technology focuses on the development of algorithms and models that enable computers to learn from data and improve their performance over time without being explicitly programmed. It is a subset of Artificial Intelligence that uses statistical techniques to give machines the ability to learn patterns, make decisions, and predict outcomes based on data.
Supervised learning, a key area of ML research, involves training models on labeled data, where the input-output relationships are predefined. This method is widely used for tasks such as classification (e.g., spam detection) and regression (e.g., predicting house prices). Unsupervised learning, on the other hand, involves finding hidden patterns in data without predefined labels, with clustering and association being typical applications in areas such as customer segmentation and anomaly detection.
Reinforcement learning is another area of ML that focuses on teaching agents to make decisions by interacting with their environment and receiving feedback in the form of rewards or penalties. It is often applied in robotics, game playing, and autonomous systems, where continuous learning and adaptation are required.
Project Main Objective
To develop an intelligent satellite-based flood risk detection and assessment platform that uses advanced image processing and artificial intelligence to deliver accurate, user-friendly, and timely flood risk information tailored to Ghana’s local needs
Academic Year
2024/2025
Date Uploaded
Feb 3, 2026
Group Members
KOOMSON ROBERT, ABBEY JEMILA, ASEIDU ENOCH, ABUBAKAR ABDUL FATAHI PAMBO