AI for Climate Change

Description:

This course is designed for the catalogue of "Lifelong Learning Initiatives" of the PNRR Project of the Innovation Ecosystem "NODES – Digitable and Sustainable North West”, in particular for the subjects of Spoke 4.
This course offers a comprehensive introduction to ML and DL, designed to empower students with the foundational skills needed to address climate change using Al. Assuming no prior knowledge, the lessons combine theoretical instruction with hands-on practice, including coding sessions where students may use advanced tools such as GPT to enhance their learning process. As participants leverage GPT for code generation and to deepen their understanding of complex topics, they will be encouraged to critically evaluate the tool's output, reinforcing the importance of human oversight in Al technology use. The course features interactive content and expert presentations, offering insights into Al's real-world applications for climate science. We will also discuss the modem applications of Al in various sectors related to climate change. This module is an ideal starting point for those aiming to further specialize in ML/DL and data science, as well as for those seeking to comprehend Al's expanding influence in fighting climate change.

The course, designed in collaboration between Politecnico di Torino and the Joint Research Centre, is designed with an inter-disciplinary approach that encourages the exchange of skills and knowledge between professors, employees of partner companies and PhD candidates and students. The course ensures not only a high-level technical training, but also a wide engagement of different actors who will foster collaboration within the Ecosystem. Participants will be able to develop transversal skills that will enhance technological transfer, innovation and research. The course will train climate change specialists able to tackle climate issues with Artificial Intelligence (AI), Machine Learning (ML) and Deep learning (DL).

The complete course agenda is available in the attached file.

lnvolved stakeholders
Joint Research Centre, CIMA Foundation, Internal Displacement Monitoring Centre, lnternational Telecommunications Union, lnternational Organization for Migration, Office for the Coordination of Humanitarian Affairs, World Food Program, universities, private companies and startups.
Assessment and grading
To determine the final grade, students have the choice to either complete five exercises from the lessons, according to the expected quality of work, or undertake a project. The project option requires presenting an application of machine learning/deep learning to a climate-related issue, inspired by resources discussed in class, or devising an original Al application relevant to their own expertise, with guidance from the lecturer. Each project should be concise and include a short report. The presentation will be given on the last day of the lecture. The students are allowed to organise in small groups (max 3) for the activity.