Machine Learning for Geospatial Applications

Cod y Modiwl: EAM5520
Teitl y Modiwl: Machine Learning for Geospatial Applications
Blwyddyn Academaidd: 2027/2028
Semester: Semester 2
Cyd-gysylltydd y Modiwl: Dr Pete Bunting
Rhestr Ddarllen: Gweld ar Aspire
Rhagofynion: EAM4020
Staff Eraill sy'n Cyfrannu: Dr Andy Hardy

Dulliau Asesu

Math o Asesiad	Manylion Asesiad	Cyfran
Asesiad Semester	Journal Article: Students will apply a habitat suitability analysis with appropriate input datasets, with one provided through the application of a machine learning based classification, for a given topic. 4000 Words	70%
Asesiad Semester	Laboratory Notebook: Students will submit a laboratory notebook from the practical sessions for the regression analysis annotating the analysis they having undertaken to demonstrate their interpretation of the results and understanding of the methods applied. 1000 Words	30%
Asesiad Ailsefyll	Journal Article: Students will apply a habitat suitability analysis with appropriate input datasets, with one provided through the application of a machine learning based classification, for a given topic. 4000 Words	70%
Asesiad Ailsefyll	Laboratory Notebook: Students will submit a laboratory notebook from the practical sessions for the regression analysis annotating the analysis they having undertaken to demonstrate their interpretation of the results and understanding of the methods applied. 1000 Words	30%

Canlyniadau Dysgu

Wedi cwblhau'r modiwl dylai'r myfyrwyr fedru:

Demonstrate familiarity with the use of machine learning techniques used to undertake a land cover classification
Show awareness of how to appropriately assess the accuracy of a classification product.
Be able to appropriately apply a habitat suitability analysis and select input datasets
Demonstrate familiarity with the use of machine learning techniques to solve regression problems using geospatial data.
Critically evaluate machine learning methodologies to assess whether they are suitable for the task in hand.
Design and implement a research plan to solve a given problem
Present findings in a concise, informative and professional manner

Disgrifiad cryno

This module aims to provide students with the experience and knowledge to apply machine learning and artificial intelligence techniques to solve problems using geospatial data such as those from Earth Observation (EO) and Geographical Information Systems (GIS). This module will also provide students with further opportunities to apply scripting and automation to the analysis of geospatial data. For Geospatial data analysis, these techniques are becoming more essential, and a good understanding of these methods and techniques is vital for opportunities within the job market.

Nod

Cynnwys

The module will be taught through a combination of lectures and practical sessions, where the lecture sessions will be used to convey key information and understanding of the methods and techniques required to undertake the practical components of the module.

The module will consider key techniques such as:

• The application of machine learning for classification problems
• How we appropriately assess the accuracy of our classification results
• How we can map change and assess the accuracy of change.
• Modelling habitats using habitat suitability modelling
• Applying machine learning to predict continuous variables through regression

Sgiliau Modiwl

Math o Sgiliau	Manylion Sgiliau
Cyfathrebu proffesiynol	Writing to a scientific audience
Datrys Problemau Creadigol	Independently using the methods taught to solve the problems set for the assessments
Gallu digidol	Using machine learning techniques to solve problems and scripting solution to automate analysis
Meddwl beirniadol a dadansoddol	Appropriate interpretation and further analysis of the results of a data processing task
Sgiliau Pwnc-benodol	Appropriately using and understanding geospatial data to solve problems

Nodau

Mae'r modiwl hwn yn cydymffurfio a FfCChC Lefel 7