Machine learning and climate change: learning from present-day observations to predict the future
0Global climate change projections are still subject to substantial modelling uncertainties. A variety of Emergent Constraints (ECs) have been suggested to address these uncertainties, but they remain heavily debated in the scientific community. Still, the central idea behind ECs to relate future projections to already observable quantities has no real substitute. \n\nHere we discuss machine learning (ML) approaches for new types of controlling factor analysis (CFA) as a promising alternative. The principal idea is to use ML to find climate-invariant relationships in historical data, which also hold approximately under strong climate change scenarios. On the basis of existing big data archives, these climate-invariant relationships can be validated in perfect-climate-model frameworks. \n\nFrom a ML perspective, we argue that CFA is more promising for three reasons: (a) it can be objectively validated both for past data and future data and (b) it provides more direct – by design physically-plausible – links between historical observations and potential future climates compared to ECs and (c) it can take higher-dimensional relationships into account that better characterize the complex nature of the multi-scale climate system. We highlight these advantages for two recently published examples in the form of constraints on climate feedback mechanisms (clouds, stratospheric water vapour). \n\nSpeakers:\n\nPaulo Ceppi\nSenior Lecturer\nImperial College London\n\nPeer Nowack\nChair for AI in Climate and Environmental Sciences\nKarlsruhe Institute of Technology (KIT)\n\nModerators:\n\nDuncan Watson-Parris\nAssistant Professor\nUniversity of California San Diego\n\nPhilip Stier\nProfessor of Atmospheric Physics\nUniversity of Oxford\n\nThe AI for Good Global Summit is the leading action-oriented United Nations platform promoting AI to advance health, climate, gender, inclusive prosperity, sustainable infrastructure, and other global development priorities. AI for Good is organized by the International Telecommunication Union (ITU) – the UN specialized agency for information and communication technology – in partnership with 40 UN sister agencies and co-convened with the government of Switzerland.\n\nJoin the Neural Network!\nhttps://aiforgood.itu.int/neural-network/\nThe AI for Good networking community platform powered by AI. \nDesigned to help users build connections with innovators and experts, link innovative ideas with social impact opportunities, and bring the community together to advance the SDGs using AI.\n\n Watch the latest #AIforGood videos!\n\n\n Stay updated and join our weekly AI for Good newsletter:\nhttp://eepurl.com/gI2kJ5\n\nCheck out the latest AI for Good news:\nhttps://aiforgood.itu.int/newsroom/\n\nExplore the AI for Good blog:\nhttps://aiforgood.itu.int/ai-for-good-blog/\n\n Connect on our social media:\nWebsite: https://aiforgood.itu.int/\nTwitter: https://twitter.com/AIforGood\nLinkedIn Page: https://www.linkedin.com/company/26511907 \nLinkedIn Group: https://www.linkedin.com/groups/8567748 \nInstagram: https://www.instagram.com/aiforgood \nFacebook: https://www.facebook.com/AIforGood\n\nDisclaimer:\nThe views and opinions expressed are those of the panelists and do not reflect the official policy of the ITU.