Understanding climate change with statistical downscaling and machine learning
- PDF / 319,475 Bytes
- 21 Pages / 439.37 x 666.142 pts Page_size
- 104 Downloads / 270 Views
Understanding climate change with statistical downscaling and machine learning Julie Jebeile1,2 · Vincent Lam1,2,3 · Tim Räz4 Received: 10 July 2020 / Accepted: 4 September 2020 © Springer Nature B.V. 2020
Abstract Machine learning methods have recently created high expectations in the climate modelling context in view of addressing climate change, but they are often considered as non-physics-based ‘black boxes’ that may not provide any understanding. However, in many ways, understanding seems indispensable to appropriately evaluate climate models and to build confidence in climate projections. Relying on two case studies, we compare how machine learning and standard statistical techniques affect our ability to understand the climate system. For that purpose, we put five evaluative criteria of understanding to work: intelligibility, representational accuracy, empirical accuracy, coherence with background knowledge, and assessment of the domain of validity. We argue that the two families of methods are part of the same continuum where these various criteria of understanding come in degrees, and that therefore machine learning methods do not necessarily constitute a radical departure from standard statistical tools, as far as understanding is concerned.
We thank the participants of the philosophy of science research colloquium in the Spring semester 2020 at the University of Bern for valuable feedback on an earlier draft of the paper. We also wish to thank the participants of the seminar ‘Philosophy of science perspectives on the climate challenge’ and the workshop ‘Big data, machine learning, climate modelling and understanding’ in the Fall semester 2019 at the University of Bern and supported by the Oeschger Centre for Climate Change Research. JJ and VL are grateful to the Swiss National Science Foundation for financial support (Grant PP00P1_170460). TR was funded by the cogito foundation.
B
Tim Räz [email protected]
1
Institute of Philosophy, University of Bern, Länggassstrasse 49a, 3012 Bern, Switzerland
2
Oeschger Centre for Climate Change Research, University of Bern, Hochschulstrasse 4, 3012 Bern, Switzerland
3
School of Historical and Philosophical Inquiry, The University of Queensland, St Lucia, QLD 4072, Australia
4
Institute of Biomedical Ethics and History of Medicine, University of Zürich, Winterthurerstrasse 30, 8006 Zürich, Switzerland
123
Synthese
Keywords Climate models · Understanding · Dynamical and statistical downscaling · Deep neural networks · Machine learning · Climate change
1 Introduction The topic of this paper is understanding with climate models. More specifically, we are interested in the question of how the use of statistical techniques and machine learning in climate models affects our ability to understand the climate system and its response to external forcings. It is tempting to deny that understanding is important to climate modelling in the first place. The central task of climate modelling, it could be argued, is to provide climate projections in order to inform
Data Loading...
