Bioresources Data Fusion and Mapping for a Rural Energy Development Plan

As the global energy landscape shifts towards sustainable, bioenergy, especially from agricultural by-products, emerges as a promising alternative to reduce reliance on fossil fuels. This thesis investigates the optimisation of bioenergy systems in rural Chinese regions through the integration of Artificial Intelligence (AI) technologies and Geographic Information Systems with Multi-Criteria Decision Analysis (GIS-MCDA). The research follows a logical progression through the “3-P” concepts: Potential, Prediction, and Position. In Chapter 2, AI models, including Artificial Neural Networks (ANN) and Support Vector Machine (SVM), are systematically reviewed for their role in enhancing biomass detection and optimising production processes. Chapter 3 applies these AI tools, specifically Backpropagation Artificial Neural Networks (BP-ANN), to estimate bioenergy potential from crop residues, such as rice, maize, and wheat, under various climate scenarios by 2030. Key findings indicate that bioenergy output could decrease by 11% without effective climate mitigation, while moderate climate control could significantly increase output, particularly for rice residues. Building on these findings, Chapter 4 presents a case study in the Jianghan Plain, a rural region in China, which integrates these AI-based bioenergy potential forecasts into a GIS-MCDA framework. This approach identifies 45-66 optimal bioenergy plant sites, strategically located to maximise energy output while minimising environmental impacts. Chapter 5 broadens the scope beyond bioenergy, exploring how renewable energy communities (RECs) can leverage innovative techniques like AI and GIS-based approaches for comprehensive resource management, providing a forward-looking perspective on rural energy resilience and development. Overall, this thesis highlights the transformative role of AI and GIS-MCDA in addressing bioenergy resource variability and optimising rural energy infrastructure in response to climate change. Future research should focus on applying these tools to broader renewable energy systems, refining their integration with socio-economic and environmental factors to facilitate holistic energy planning and sustainable development in rural areas.