Matthew Oyeleye

Matthew Oyeleye

Auto-generated profile, based on publicly available information

Matthew Oyeleye

Department of Computer Science and Engineering, University of Huddersfield, England, United Kingdom

Research Focus & Metrics

Academic Career Length

2Years (2025-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
14 September 2025
Verified
Conference Paper
Open access
OBOluwaseun Bamgboye
Oluwaseun Bamgboye
Xiaodong LiuXiaodong Liu
Xiaodong Liu
MOMatthew Oyeleye
Matthew Oyeleye
Accurate prediction of rainfall is significant for urban planning and critical flood incident management. Traditional meteorological models, such as multivariate analysis, are mostly unsuitable for defining the complex, nonlinear relationships in rainfall data. Furthermore, there are limited comparative studies that evaluate the performance of different Machine Learning regression models on rainfall data specific to these UK regions. This study investigates the performance of regression models to predict rainfall in two major cities in Great Britain (i.e. Edinburgh and Cardiff). Six regression models- Linear Regression, K-Nearest Neighbour, Decision Tree, Random Forest, Gradient Boost, and Multilayer Perceptron regressors were trained on datasets obtained from both cities. Feature selection and hyper-parameter tuning were performed for each model optimisation. Multi-layer Perceptron model emerged as the best-performing model. The results provide an understanding of the comparative analysis of other regression models and suggest their suitability for urban planning and effective decision-making for flood-related events.