Towards implementing artificial intelligence post-processing in weather and climate: proposed actions from the Oxford 2019 workshop

Abstract

The most mature aspect of applying artificial intelligence (AI)/machine learning (ML) to problems in the atmospheric sciences is likely post-processing of model output. This article provides some history and current state of the science of post-processing with AI for weather and climate models. Deriving from the discussion at the 2019 Oxford workshop on Machine Learning for Weather and Climate, this paper also presents thoughts on medium-term goals to advance such use of AI, which include assuring that algorithms are trustworthy and interpretable, adherence to FAIR data practices to promote usability, and development of techniques that leverage our physical knowledge of the atmosphere. The coauthors propose several actionable items and have initiated one of those: a repository for datasets from various real weather and climate problems that can be addressed using AI. Five such datasets are presented and permanently archived, together with Jupyter notebooks to process them and assess the results in comparison with a baseline technique. The coauthors invite the readers to test their own algorithms in comparison with the baseline and to archive their results. This article is part of the theme issue ‘Machine learning for weather and climate modelling’.

A framework for probabilistic weather forecast post-processing across models and lead times using machine learning

“…The authors recognize that comprehensive comparisons of our approach to other probabilistic post-processing approaches (in addition to raw NWP output) will be important to consider when choosing the best approach for any operational set-up. While we do not offer such comparisons in this study, we have made our dataset openly accessible as one of several benchmark datasets compiled by Haupt et al [39] at in the hope that it will facilitate comparison of different post-processing approaches on common benchmarks in the future.…”

“…Our dataset has been made available with permission from the Met Office and Highways England, for which we are grateful. It is available for download along with several other open weather forecast post-processing datasets collated by Haupt et al [39] at . In addition, the code for this study can be accessed at…”

Opportunities and challenges for machine learning in weather and climate modelling: hard, medium and soft AI

“…There are several papers concerning the problem of data assimilation, an important and expensive part of weather prediction. Contributions also take on the subject of probabilistic forecasting, a key approach to forecasting on all timescales, as well as the exciting topic of machine learning for post-processing (please see Haupt [39] in this issue for an overview on post-processing approaches).…”

AI ethics: A framework for measuring embodied carbon in AI systems

“…One aspect of AI ethics that has not been as strongly assessed, however, is its overall climate impact [2,3], i.e., its impact on the planet and the role that it has in contributing to climate change. The significant majority of the discussions focus rather on its positive effects on measuring or improving humanities response to climate change [4,5]. As a result, the impact that AI has from a climate justice perspective are also not widely discussed the fact that the beneficiaries of AI are mainly based in the so-called developed nations while the lower GDP countries will increasingly face the burdens of dealing with the environmental impact of AI; initial work in this space has been done related to e.g., impacts of the semiconductor industry [6][7][8][9], but there is no assessment of the justice aspects of destroying the environment in Malaysia for the benefit of users in the USA, Europe, Oceania and elsewhere in Asia.…”