SPATIAL APPLICATION OF INTERNET OF THINGS (IoT) AND MACHINE LEARNING (ML) IN WASTE MANAGEMENT IMPLEMENTATION STRATEGIES FOR AKURE SOUTH LOCAL GOVERNMENT AREA, ONDO STATE, NIGERIA

Abstract

Rapid urbanization, population growth, and changing consumption patterns have significantly increased municipal solid waste generation in many developing cities, creating serious environmental, economic, and public health challenges. Conventional waste management systems are often constrained by inadequate infrastructure, inefficient collection practices, and limited monitoring capabilities, thereby reducing operational effectiveness and environmental sustainability. This study investigates the application of Geographic Information Systems (GIS) for landfill suitability assessment and proposes the integration of Internet of Things (IoT) and Machine Learning (ML) technologies as a smart waste management framework for Akure South Local Government Area, Ondo State, Nigeria. Spatial analyses involving land-use classification, slope evaluation, road network accessibility, drainage proximity assessment, and lineament analysis were conducted within a GIS environment using a Multi-Criteria Decision Analysis (MCDA) approach. Criteria weighting was performed using the Analytic Hierarchy Process (AHP) to enhance decision-making reliability. The analysis identified approximately 45.92 km² of land as highly suitable for landfill development based on environmental and infrastructural considerations. Furthermore, a conceptual IoT and ML enabled framework is proposed to support future real-time waste monitoring, predictive waste generation analysis, and route optimization. The findings demonstrate the effectiveness of GIS-based spatial decision support in landfill site selection and highlight the potential benefits of integrating geospatial technologies, IoT systems, and machine learning techniques for sustainable municipal waste management. The study recommends the adoption of smart waste management strategies, improved waste collection infrastructure, and technology-driven environmental planning to enhance waste management efficiency within the study area.

DOI: https://doi.org/10.5281/zenodo.20393813