MACHINE LEARNING IN CLIMATE CHANGE MITIGATION SCENARIOS
MACHINE LEARNING IN CLIMATE CHANGE MITIGATION SCENARIOS
20-03-2025
Politecnico di Milano
Machine learning (ML) has emerged as a critical tool in contemporary climate research. This workshop will explore prospects for ML tools to enhance the design and assessment of medium- and long-term scenarios of greenhouse gas emissions. We will cover some of the latest applications, from the use of ML in the development of integrated assessment models (IAMs) of climate change to the opportunities of ML to assist the construction and evaluation of large ensembles of emission scenarios. Due to the specific nature of ML tools, the workshop will also be an occasion to reflect on emerging issues of opacity and the potential challenges in the implementation of ML in influential exercises of climate policy evaluation, such as those of the IPCC.
Specifically, the workshop will address the following questions:
- DATA ENHANCEMENT: Can ML tools be used to streamline the collection and curation of data to feed the models (IAMs) that produce emission scenarios?
- MODEL ENHANCEMENT: Can neural networks and equations discovery tools integrate standard numerical modeling approaches in re-designing IAMs?
- POST-PROCESSING: Are ML emulators fit for detecting bias and infilling missing dimensions of uncertainty in large ensembles of emission scenarios?
- ASSESSMENT: What are the consequences of the use of ML tools on the informativeness and trustworthiness of assessments of large scenario ensembles?
We look forward to the participation of engineers, mathematicians, and other researchers with an expertise in ML. One of the workshop’s aims is to build further capacity to assist climate research, exploring connections across emerging fields.
The workshop will be held in Aula FDS, IV Floor, Department of Mathematics, Politecnico di Milano. Participation is free of charge. Registration is not required.
Speakers:
Alaa Al Khourdajie (Imperial College London)
Jacopo Ghirri (Politecnico di Milano)
Sara Giarola (Università di Brescia / EIEE)
Moderator:
Massimo Tavoni (Politecnico di Milano / EIEE)
Funded by Marie Sklodowska Curie Action. Project: VINCE.
27-28 May 2024
(co-organized with Hernán Bobadilla, Rawad El Skaf, Sara Giarola, Massimo Tavoni, Henrik Thorén, and Giovanni Valente)
Politecnico di Milano
The first day of the conference will be concerned with the theme of illegitimate value influences and the responsibility of scientists and institutions in ensuring relevance and integrity of climate change research. The second day will discuss whether and how considerations of justice should enter the evaluation of mitigation scenarios and how doing so could enhance the credibility and effectiveness of future research. Specific proposals will be discussed for operationalizing justice into quantitative emission scenarios produced by the scientific community.
Invited speakers:
Alaa al Khourdajie (Imperial College London)
Mathias Frisch (Leibniz Universität Hannover)
Franziska Hoffart (University of Gottingen)
Kian Mintz-Woo (University College Cork/ IAASA)
Andrea Saltelli (University of Bergen)
Elena Verdolini (Università degli Studi di Brescia/CMCC)
Discussants:
Chiara Candelise (Bocconi/ Imperial College London)
Francesca Pongiglione (Università San Raffaele)
Marco Grasso (Milano Bicocca)
Amsalu Woldie-Yalew (CMCC)
Caroline Zimm (IAASA)
Funded by Marie Sklodowska Curie Action. Project: VINCE.
NUMBERS AND STORIES: NEW DIRECTIONS FOR CLIMATE STORYLINES AND SCENARIOS
21 June 2023
(co-organized with H. Bobadilla, R. El Skaf, M. Tavoni, and G. Valente)
Politecnico di Milano
The workshop's theme revolves around the use of qualitative and quantitative methods in climate change research, most importantly the development and use of scenarios for emission and decarbonization pathways, the storyline approach to detection and attribution of extreme weather events, and their repercussions for climate policy under deep uncertainty. Scenarios are key tools for depicting future climate and play a key role in assessments such as those of the IPCC; as the community looks forward to developing the next generation of scenarios, it is important to discuss which elements should be included in the narrative and operationalized in the assessments.
Invited Speakers:
Emily Boyd (Sustainability Science, Lund University)
Sara Giarola (Engineering, Politecnico di Milano)
Vincent Lam (Philosophy, University of Bern)
Massimo Marinacci (Economics, Bocconi University)
Julia Mindlin (Climate Science, Buenos Aires)
Steve Yearley (Sociology, University of Edinburgh)
Discussants:
Emanuela Colombo (Engineering, Politecnico di Milano)
Andrea Castelletti (Engineering, Politecnico di Milano)
Mathias Frisch (Philosophy, Hannover University)
Wayne Myrvold (Philosophy, Western University)
Massimo Tavoni (Economics, Politecnico di Milano)
Funded by Marie Sklodowska Curie Action. Project: VINCE.
24-06-2022
(co-organized with D. Chiffi and G. Valente)
Politecnico di Milano
The use of scientific models is often accompanied by significant and deep uncertainties. The problem is especially acute when dealing with complex systems, where the variables are numerous and difficult to control. This workshop brings together philosophical and applied perspectives concerning the quantification of key uncertainties in scientific research.
Speakers:
Paola Berchialla (Statistics, University of Turin)
Giacomo Marangoni (Policy Analysis, TU Delft)
Ahti Pietarinen (Philosophy, Tallinn University of Technology)
Viola Schiaffonati (Philosophy, Politecnico di Milano)
Behnam Taebi (Philosophy, TU Delft)
Funded by PRIN Project: "From Models to Decisions" (G. Valente)