The use of artificial intelligence (AI) and life cycle analysis (LCA) tools for predicting the environmental performance of sustainable transport fuels
This thesis project aims to evaluate the environmental performance of transport fuels using a combined method of artificial intelligence (AI) and life cycle assessment (LCA). The project contributes to developing an integrated framework for sustainable transport fuels using a dynamic lifecycle and novel artificial intelligence (AI) approach.
Background
There is an urgent need to substitute fossil-based fuels in the transport sector. Life cycle analysis (LCA) is a tool to evaluate the potential environmental impacts of alternative transport fuels. It is a comprehensive method for assessing all direct and indirect environmental impacts across the entire life cycle of a product system, from design, to materials acquisition to manufacturing, to use, and to final disposition. Artificial intelligence (AI) and Machine Learning (ML) methods encompass a wide variety of powerful data-driven techniques which have applicability for predicting resource use and environmental impacts.
In this project, students will evaluate the environmental performance of one of the selected alternative transport fuels (e.g., bioethanol, biodiesel, hydrogen), and use of artificial neural networks (ANNs) and adaptive neuro-fuzzy inference system (ANFIS) models for the prediction of environmental impacts considering different scenarios and management options.
Task description
Tentative tasks for this project are:
- To perform inventory analysis on the selected alternative transport fuels
- To evaluate/compare the life cycle environmental impacts of transport fuel
- To determine the significant influencing factors/inputs in the life cycle in terms of environmental impacts and investigate their roles
- To identify potential hotspots and suggest possible measures to improve the environmental impact
- To model the lifecycle of transport fuel using ANNs or other appropriate data-driven methods
- To predict environmental impacts of transport fuels in different scenarios
- To contribute in developing integrated framework for sustainable transport fuels using a dynamic lifecycle and novel artificial intelligence (AI) approach
Criteria for evaluation
Critical criteria in the complete work and method development and metric for the final assessment are:
- Fulfilment of the ILOs for Master Thesis at KTH's ITM School;
- The student's initiative and independence in developing the overall research design;
- A critical and system perspective and critical discussion of the assumptions and results;
- Consideration of the literature.
- The ability to communicate the results of scientific work clearly and coherently.
If the work is of good quality and the student and project partners are interested, the research project will be designed to be suitable for a peer-reviewed publication in a high-quality journal.
Prerequisites
The analysis to be undertaken is interdisciplinary in nature, and requires some knowledge of alternative transport fuels, environmental assessment, data science and machine learning. Students should have an undergraduate degree in chemistry, biology, engineering, economics, or similar fields. Prior knowledge of the LCA and AI; Understanding of energy conversion technologies; Basic knowledge in energy modelling; Experiences in Python/MatLab will be an asset.
Track Specialization
Transformation of Energy System (TES)
Division/Department
Division of Energy Systems – Department of Energy Technology
Research areas:
Start time: anytime soon (January/February 2023)
The student may choose to work individually or in pairs.
How to apply
Send an email expressing your interest on the topic to Dilip Khatiwada (dilip.khatiwada@energy.kth.se).
KTH Supervision and main contact
