Robust Inverse Framework using Knowledge-guided Self-Supervised Learning: An application to Hydrology

Rahul Ghosh, Arvind Renganathan, Kshitij Tayal, Xiang Li, Ankush Khandelwal, Xiaowei Jia, Christopher Duffy, John Nieber, Vipin Kumar

Research output: Chapter in Book/Report/Conference proceedingConference contribution

7 Scopus citations

Abstract

Machine Learning is beginning to provide state-of-the-art performance in a range of environmental applications such as streamflow prediction in a hydrologic basin. However, building accurate broad-scale models for streamflow remains challenging in practice due to the variability in the dominant hydrologic processes, which are best captured by sets of process-related basin characteristics. Existing basin characteristics suffer from noise and uncertainty, among many other things, which adversely impact model performance. To tackle the above challenges, in this paper, we propose a novel Knowledge-guided Self-Supervised Learning (KGSSL) inverse framework to extract system characteristics from driver(input) and response(output) data. This first-of-its-kind framework achieves robust performance even when characteristics are corrupted or missing. We evaluate the KGSSL framework in the context of stream flow modeling using CAMELS (Catchment Attributes and MEteorology for Large-sample Studies) which is a widely used hydrology benchmark dataset. Specifically, KGSSL outperforms baseline by 16% in predicting missing characteristics. Furthermore, in the context of forward modelling, KGSSL inferred characteristics provide a 35% improvement in performance over a standard baseline when the static characteristic are unknown.

Original languageEnglish (US)
Title of host publicationKDD 2022 - Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining
PublisherAssociation for Computing Machinery
Pages465-474
Number of pages10
ISBN (Electronic)9781450393850
DOIs
StatePublished - Aug 14 2022
Event28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, KDD 2022 - Washington, United States
Duration: Aug 14 2022Aug 18 2022

Publication series

NameProceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining

Conference

Conference28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, KDD 2022
Country/TerritoryUnited States
CityWashington
Period8/14/228/18/22

Bibliographical note

Funding Information:
6 ACKNOWLEDGEMENT This work was funded by the NSF HDR Grant 1934721 and NSF FAI Grant 2147195. Access to computing facilities was provided by the Minnesota Supercomputing Institute. John Nieber’s effort on this project was partially supported by the USDA National Institute of Food and Agriculture, Hatch/Multistate Project MN 12-109.

Publisher Copyright:
© 2022 ACM.

Keywords

  • forward modeling
  • inverse modeling
  • self-supervised learning

Fingerprint

Dive into the research topics of 'Robust Inverse Framework using Knowledge-guided Self-Supervised Learning: An application to Hydrology'. Together they form a unique fingerprint.

Cite this