Author:
Ezekafor, S. C., Osakwe, O.T., Mmonwuba, N. C.

Doi: 10.26480/jtin.01.2026.41.53

This is an open access article distributed under the Creative Commons Attribution License CC BY 4.0, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited

The rapid urbanization and economic growth in Onitsha have worsened the level of municipal solid waste (MSW) production, exceeding the waste management capacity of the city. The current systems have caused environmental and health risks due to their inefficiency, and therefore, forecasting methods of various systems based on data are required. The nonlinear relationships between socio-economic, demographic and environmental conditions that prevail in traditional linear models as applied by municipal agencies have not been taken into consideration by them, leading to erroneous waste estimates and ineffective infrastructure planning. The study is expected to address (i) the estimation of the daily waste production at the ward level by utilizing field data and machine learning models, (ii) the prediction of the most important elements influencing the volume of waste, and (iii) the creation of the most effective service areas that optimally collect waste and its localization. Primary field data was obtained on 20 wards in Onitsha that was complemented by demographic and economic data of the Anambra State Waste Management Authority. Extreme Gradient Boosting (XGBoost) algorithm, Multiple Linear Regression (MLR), SHAP interpretability, and K-Means clustering were used. XGBoost showed better predictive power (R 2 = 0.9984), where population size, density, and commercial activity were found to be the dominating factors. Machine learning combined with demographic data will increase the accuracy of waste forecasting. Data-driven planning, deployment of more transfer stations, and reinforcement of spatial zoning ought to be a priority for policymakers in creating resilient and sustainable waste management in Onitsha.