Discovering and forecasting extreme events via active learning in neural operators
Name
s43588-022-00376-0.pdf
Size
2.53 MB
Format
Adobe PDF
Checksum (MD5)
0577776fac0e2a593f069adacc4c943a
Author(s)
Pickering, Ethan
Guth, Stephen
Karniadakis, George Em
Sapsis, Themistoklis P
Date Issued
2022
Journal
Nature Computational Science
Publisher
Springer Science and Business Media LLC
Citation
Pickering, E., Guth, S., Karniadakis, G.E. et al. Discovering and forecasting extreme events via active learning in neural operators. Nat Comput Sci 2, 823–833 (2022).
Version
Final published version
Abstract
Extreme events in society and nature, such as pandemic spikes, rogue waves or structural failures, can have catastrophic consequences. Characterizing extremes is difficult, as they occur rarely, arise from seemingly benign conditions, and belong to complex and often unknown infinite-dimensional systems. Such challenges render attempts at characterizing them moot. We address each of these difficulties by combining output-weighted training schemes in Bayesian experimental design (BED) with an ensemble of deep neural operators. This model-agnostic framework pairs a BED scheme that actively selects data for quantifying extreme events with an ensemble of deep neural operators that approximate infinite-dimensional nonlinear operators. We show that not only does this framework outperform Gaussian processes, but that (1) shallow ensembles of just two members perform best; (2) extremes are uncovered regardless of the state of the initial data (that is, with or without extremes); (3) our method eliminates 'double-descent' phenomena; (4) the use of batches of suboptimal acquisition samples compared to step-by-step global optima does not hinder BED performance; and (5) Monte Carlo acquisition outperforms standard optimizers in high dimensions. Together, these conclusions form a scalable artificial intelligence (AI)-assisted experimental infrastructure that can efficiently infer and pinpoint critical situations across many domains, from physical to societal systems.
MIT Department
Massachusetts Institute of Technology. Department of Mechanical Engineering
Terms of Use
Article is made available in accordance with the publisher's policy and may be subject to US copyright law. Please refer to the publisher's site for terms of use.
Persistent DSpace Link
DOI of Published Version
https://doi.org/10.1038/s43588-022-00376-0
