Utilizing Machine Learning to Understand and Quantify Extreme Environmental Temperature Change

Successful students will typically be able to

1. be able to critically evaluate advanced literature on data science and analytics topics relevant to their chosen project;
2. be able to refer to the findings of other academic writers to justify their chosen approach to the development of a solution, and to evaluate the outcomes of their project work;
3. be able to combine their knowledge of the subject, their reading of research papers and the outcome of their own investigations to conceive original ideas of their own;

4. be able to plan and manage a substantial body of work, identify any risks inherent in their chosen approach, and work independently with minimum supervision;
5. be able to select and use appropriate techniques and tools employed in data science and analytics in order to conduct a practical investigation into a particular data science and analytics problem;
6. be able to both critically evaluate and discuss the outcome of their project work in written and oral form;
7. be able to articulate the broader contexts of their work in relation to legal, social, ethical, and professional issues, and assess the economic impact of their project.

Late submission of coursework will typically attract a lateness penalty. For each day or part thereof for up to five days after the published deadline, coursework submitted late (including deferred coursework, but with the exception of referred coursework), will have the numeric grade reduced by 10 grade points until or unless the numeric grade reaches or is a bare pass (i.e. 40 for undergraduate modules, 50 for postgraduate modules). Where the numeric grade awarded for the assessment is less than the bare pass, no lateness penalty will be applied.

• Late submission of online timed assessments typically will not be accepted.
• Coursework (including deferred coursework) submitted later than five days (five working days in the case of hard copy submission) after the published deadline will be awarded a grade of zero (0).
• Late submission of referred coursework will automatically be awarded a mark of zero.
• You are strongly advised to submit your work one hour before the submission deadline, to give time to resolve difficulties. The application of lateness penalty is automated and therefore any submission after the deadline will attract a lateness penalty.

Aim of the Project

In this MSc project, it propose the utilization of state-of-art machine learning and algorithm techniques in providing stepwise change in improving human ability to pin down environmental temperature change impact on human, plant and animal survival. Hence it aims at apply environmental data science in developing an algorithm to aid in understanding and quantification of extreme temperature changes.

Research Question

Environmental temperature change has dramatic impact on the climate change with challenging societal functioning, thus it requires a sustainable and considerable adaptation of technological innovation to improve understanding of the climatic weather patterns in the future. With the enhanced environmental data technology, the project proposes the utilization of machine learning innovations to help understand and quantify alteration in extreme environmental temperature change and the implication of flood and heat waves.  The research topic tends to apply machine learning algorithms to trigger breakthrough in solving the puzzle of extreme changes in environmental temperature change. Machine learning coupled with environmental data analysis will be form the basis of research investigation on how best to incorporate other technological innovation such as neural network systems to aid climate analysis.

Research Objective

The proposed research study aim to accomplish the following aims and objectives

i.To apply environmental data science in developing an algorithm to aid in understanding and quantification of extreme temperature changes.

ii.To develop and evaluate a sustainable environmental (Earth) system module for climate prediction through machine learning technique.

iii.To identify crucial physical drivers through model system to aid in reducing the rampant uncertainties in forecasting and prediction of climate patterns.  To curve the identified physical drivers of climate change to devise aa novel climate risk assessment model