RF-XGBoost Modelling (Ilaje, Ondo State, Nigeria)
DATA ANALYSIS
The data analysis process involved the partitioning of the total generated flood points from the field and satellite images into two distinct categories: flood and non-flood occurrences. A total of 1,237 data points were established, with 648 points precisely classified as flood points and the remaining 589 as non-flood points. This data was subsequently partitioned into training, validation and testing sets in a 70:20:10 ratio respectively, ensuring a robust evaluation of the predictive models to avoid overfitting.
PROJECT OVERVIEW
This project aimed to: 1) Mitigate the impacts of coastal floodings through timely and accurate forecasts. 2) Develop a comprehensive adaptive Flood Vulnerability Model (FVM) for Ilaje, Ondo State, Southwest Nigeria by combining Geographic Information Systems (GIS), advanced Machine Learning (ML) and Artificial Intelligence (AI) tools. 3) Validate the model to ensure the accuracy of its predictive solutions.
ACKNOWLEDGEMENT
I wish to express my profound gratitude to the Federal University of Technology, Akure (FUTA), Nigeria, for fostering an academic milieu that facilitated the development and implementation of my B.Tech. project, titled Flood Vulnerability Mapping of Ilaje, Ondo State, Southwest Nigeria Using Machine Learning and Artificial Intelligence. This innovative drone epitomises the practical application of this research, aimed at capturing and monitoring flood conditioning factors contributing to the recurrent coastal floods in Ilaje, Ondo State, Southwest Nigeria. My heartfelt thanks are extended to Dr. Blessing Enakimio and the organising committee of the 7th Nigeria International Energy Summit, 2024 for affording me the opportunity to showcase and demonstrate the real-time application of my findings. This platform proved pivotal in emphasising the practical significance of my project. Furthermore, I am profoundly indebted to my project supervisor, Dr. Joshua Oluwasanmi Owoseni, (Ph.D) for guiding this pro …