¹û¶³Ó°Ôº

Aims:

To provide an understanding of the different SDGs and the application of machine learning and artificial intelligence to such application domains. To capacitate ML and AI practitioners with problem solving skills and knowledge for the development and deployment of AI systems in this pressing and impactful application area. To capacitate those individuals to be effective team players in interdisciplinary research groups/ organisations and policy making institutions that utilise AI.

Intended learning outcomes:

On successful completion of the module, a student will be able to:

1. Understand the different sustainable development goals and targets terminology and how AI could both be used for leveraging and inhibiting such objectives.
2. Demonstrate knowledge regarding state-of-the-art AI algorithms, as well as the data science work cycle and technical skills necessary within an interdisciplinary team.
3. Skilfully approach data challenges spanning different application domains and core learning tasks.
4. Develop and validate state-of-the art ML and AI approaches.

Indicative content:

The following is indicative of the topics the module will typically cover:

The module introduces students to basic concepts and algorithms in ML and AI and the use of these disciplines within the sustainable development domain. Specifically, the module introduces the 17 Sustainable Development Goals (SDGs) and shows how different AI techniques (supervised, unsupervised and reinforcement learning) could both act as an SDG enabler and an inhibitor, as well as a tool to measure progress towards sustainable development.

Examples include complex AI-enhanced precision agriculture, which could: i) enable an increase in food production (helping towards the SDG on zero hunger), ii) decrease the amount of chemical treatments in crops (which could have environmental and financial advantages), but also iii) create inequalities by producing an increased gap between larger producers and small farmers. We can find another example related to SDG on climate action, where there is great evidence that AI will support the understanding of climate change and the modelling of its impacts. However, efforts to achieve climate action could also be undermined by the high-energy needs for AI applications, especially if non carbon-neutral energy sources are used. Many other examples will be presented in the module through proposed challenges and problem-solving exercises.Ìý

The module will allow the students to develop knowledge of the different branches within AI and hands-on experience applying such methods to real-world datasets related with different SDGs, covering goals related to pressing issues related to society and the environment, as well as interpreting the results and the potential impact of such models in the world.

Requisites:

To be eligible to select this module an optional or elective, a student must be registered on a programme and year of study for which it is formally available.