Master of Data Science (Heritage)

Cultural heritage offers a sense of identity, helps maintain social diversity, cohesion, and intercultural dialogue, and forms part of our basic right to participate in cultural life. Data Science techniques are playing an increasing role in this sector, helping practitioners to monitor and protect heritage assets such as archaeological sites, present information to the public and critically assess the role of heritage in contemporary debates.

From personalised medicine, to smart cities and sustainable solutions, data science is building a better world. At the same time, developments in technology have made the field of data science more accessible than ever, creating new opportunities to gain insight into the interactions between people and their natural and cultural environments. This has led to a significant increase in demand for skilled data scientists, and this demand is predicted to further grow.

Drawing on this, we have created the Master of Data Science (Heritage), a conversion course that equips you with the skills to generate, access, clean, analyse and visualise data, opening a future in data science even if your first degree is in a non-quantitative subject. It is likely to appeal to archaeologists, anthropologists, curators, and historians who want to learn how to use the data produced in modern research, industry and government contexts to manage heritage resources and spatio-temporal information flows.

The course provides training in contemporary data science. You will be based in a supportive environment, learning from practicing researchers who are making a difference across a range of industries. Shared core modules across the suite of MDS courses will equip you with wider statistical and machine learning skills, while subject-specific modules develop your quantitative skills in the field.

The course begins with a range of introductory modules before progressing to more advanced contemporary techniques such as neural networks, analysis of spatial and temporal datasets and deep learning. Optional modules allow you to focus on an area of interest.

The MDS culminates in the research project, an in-depth investigation in which you apply the skills learned during the course to a research problem working alongside an expert in the area of application of your choice. There may be an option to carry out the project in conjunction with an industry partner.

Course structure

Core modules:

The Data Science Research Project is a substantial piece of research into an area of data science unfamiliar to you, or in your subject specialisation area with a focus on data science. The project can be practical, theoretical or both, and is designed to develop your research, analysis and report-writing skills.

Critical Perspectives in Data Science develops your understanding of the production, analysis and use of quantified data, and how to analyse these practices anthropologically. You will learn to think ethically and contextually about quantified data, and how to apply this knowledge to practical problems in data science, including your own research project.

Data Analysis in Space and Time provides an understanding of data methods and tools used in the field of earth and environmental sciences, with a particular focus on those used for analysing spatial and temporal datasets. You will also learn about the physical modelling of complex real-world systems and use popular software packages currently used in industry settings.

Data Science Applications in Heritage and Archaeology provides students with experience of handling, amalgamating and analysing diverse datasets from a range of sources and across spatial and temporal scales. The module covers the most commonly used data science techniques in the Heritage and Archaeology sectors, giving the student experience in Geographical Information Systems and Google Earth Engine for prospection and heritage management and protection. The module also touches on the classification and interpretation of geochemical and petrographic digital imagery as well as 3D modelling of artefacts and standing features.

Programming for Data Science uses the popular Python software packages used in a wide range of industry settings. You will learn how to gather, manipulate and process real-world data and learn the key concepts of data analysis and data visualisation.

Introduction to Statistics for Data Science focuses on the fundamentals of statistics you will need for data science. The module covers topics such as exploratory statistics, statistical inference; linear models; classification and clustering methods; and resampling and validation.

The remainder of the course will be made up of core and option modules which will vary depending on prior qualifications and experience.

These have previously included:

• Introduction to Computer Science
• Introduction to Mathematics for Data Science
• Machine Learning
• Text Mining and Language Analytics
• Data Exploration, Visualisation, and Unsupervised Learning
• Strategic Leadership
• Ethics and Bias in Data Science.