Project Description
Introduction: the efficient management of waste and the promotion of recycling are fundamental challenges in the quest for a more sustainable and environmentally responsible future. With increasing urbanization and population growth, there is a pressing need to enhance the effectiveness and cost-efficiency of waste management and recycling processes. This PhD research proposal aims to investigate and develop innovative machine learning-based solutions for optimizing waste management and recycling systems, ultimately contributing to environmental conservation and resource preservation. By optimizing these systems, we can work towards a more sustainable, efficient, and environmentally responsible waste management process.
Research Objectives: the primary objectives of this research are as follows:
- Collect data from waste management facilities, recycling centres, and urban areas to establish a database for both the current study and future research endeavours.
- To develop machine learning models for predicting waste generation patterns, recycling rates, and the composition of waste streams.
- To design algorithms that optimize waste collection routes, scheduling, and resource allocation, considering spatial and temporal variations in waste generation.
- To assess the feasibility and effectiveness of machine learning-based solutions in increasing recycling rates, reducing waste disposal costs, and minimizing environmental impacts.
- To explore the use of artificial intelligence and machine learning for automating the sorting and processing of recyclables in recycling facilities.
Research Methodology: the research will encompass a comprehensive methodology that includes the following steps:
- A thorough review of existing literature and case studies on waste management, recycling, and machine learning applications will be conducted to identify gaps in the current knowledge.
- Data will be collected from waste management facilities, recycling centres, and urban areas to create a comprehensive dataset for analysis. This will include waste generation data, recycling rates, geographic information, and relevant temporal information.
- Advanced machine learning models will be developed to predict waste generation, recycling rates, and waste composition. We will investigate ML algorithms for both classification and regression problems in this project. Additionally, algorithms for optimizing waste collection, transportation, and resource allocation will be designed based on existing natural-based optimisation algorithms such as swarm intelligence or evolutionary algorithms.
- Using the developed machine learning models and algorithms, a series of simulations and case studies will be performed to evaluate the effectiveness of waste management and recycling optimization. The analysis will consider technical, economic, and environmental factors.
- Investigate the application of artificial intelligence and machine learning in automating the sorting and processing of recyclables in recycling facilities. Evaluate the potential improvements in recycling rates and operational efficiency.
- Assess the feasibility of implementing machine learning-based solutions in real-world waste management and recycling systems. Identify potential barriers and challenges and provide recommendations for implementation.
Expected Outcomes: this research is expected to yield the following outcomes:
- Advanced machine learning models and a computer program for predicting waste generation and recycling rates.
- Algorithms and computer program for optimizing waste collection, routing, and resource allocation, with a focus on cost-efficiency and environmental impact reduction.
- Insights into the technical, economic, and environmental implications of implementing machine learning-based solutions in waste management and recycling systems.
- Recommendations for policymakers, waste management authorities, and recycling facilities on the adoption of machine learning in enhancing recycling rates and reducing waste management costs.
- Peer reviewed papers, reports, and meta-analyses.
Significance and impacts: the successful implementation of machine learning in waste management and recycling systems has the potential to revolutionize the industry, leading to more sustainable practices, reduced waste disposal costs, and increased recycling rates. It will not only contribute to environmental preservation but also address the growing challenges of urbanization and resource scarcity.
CANDIDATE BACKGROUND
A background in environmental science or engineering and skills in languages like Python or R are essential. GIS skills and familiarity with mathematical modelling and optimization techniques are preferred.
Photo by Chris Ried on Unsplash
Supervisors
Astley HastingsPrimary Supervisor: | Profile: Astley Hastings Email: astley.hastings@abdn.ac.uk Institution: University of Aberdeen Department/School: School of Biological Sciences |
Secondary Supervisor: |
University of Aberdeen, School of Biological Sciences Email: mabdalla@abdn.ac.uk |
Additional Supervisor: | Dr Beatrice Smyth, Queen’s University Belfast, School of Mechanical and Aerospace Engineering Email: beatrice.smyth@qub.ac.uk
Dr Thanh Nguyen, Robert Gordon University Email: t.nguyen11@rgu.ac.uk |
QUADRAT Themes
- environmental-management
