Collections »

About this collection

Extent

1 digital object.

Description

This collection contains data used and generated in the study entitled "Harnessing AI data-driven global weather models for climate attribution: An analysis of the 2017 Oroville Dam extreme atmospheric river". This study explores storyline-based climate attribution due to their short inference times, which can accelerate the number of events studied, and provide real time attributions when public attention is heightened. The analysis is framed on the extreme atmospheric river episode of February 2017 that contributed to the Oroville dam spillway incident in Northern California. “Past” and “future” simulations are generated by perturbing the initial conditions with the pre-industrial and the late-21st century temperature climate change signals, respectively. The simulations are compared to results from a dynamical model which represents plausible “pseudo-realities” under both climate environments. In particular, this collection contains 1) the CMIP5 climate change signals for the temperature variables for the pre-industrial and late-21st century emission scenarios, 2) the initial condition fields to run the simulations, 3) the simulations for the "past", "present", and "future" simulations for the AI models, and 4) the mean and standard deviation of the variables computed over the period 1979-2022. The code used to generate the AI-based simulations is available at the following Github repository: https://github.com/CW3E/AI-attribution.

Creation Date

• 2017-02-05 to 2017-02-11

Date Issued

• 2025

Authors

• Baño-Medina, Jorge
• Delle Monache, Luca
• Kalansky, Julie
• Michaelis, Allison
• Sengupta, Agniv
• Watson-Parris, Duncan

Funding

This work was supported by the California Department of Water Resources Atmospheric River Program Phase III and Phase IV (Grants 4600014294 and 4600014942, respectively) and U.S. Army Corps of Engineers (USACE) Forecast Informed Reservoir Operations Phase 2 Award (USACE W912HZ192). A.S. was partly supported by the National Aeronautics and Space Administration (Grant 80NSSC22K0926).

Geographics

• California
• Feather River Basin (California)
• Oroville Dam (California)
• Western United States

Topics

• Algorithm: Supervised learning
• Artificial intelligence
• Atmospheric rivers
• Climate attribution
• Climate science
• Domain: Earth sciences
• Earth sciences
• Extreme events
• Task: Forecasting

Format

View formats within this collection

• data

Language

• English

Identifier

Identifier: Agniv Sengupta: https://orcid.org/0000-0003-3687-5549

Identifier: Allison Michaelis: https://orcid.org/0000-0002-0793-5779

Identifier: Duncan Watson-Parris: https://orcid.org/0000-0002-5312-4950

Identifier: Jorge Baño-Medina: https://orcid.org/0000-0003-3380-1579

Identifier: Julie Kalansky: https://orcid.org/0000-0003-2562-7398

Identifier: Luca Delle Monache: https://orcid.org/0000-0003-4953-0881

Related Resources

Primary associated publication

• Baño-Medina, J., Sengupta, A., Michaelis, A., Delle Monache, L., Kalansky, J., & Watson-Parris, D. (2025). Harnessing AI data-driven global weather models for climate attribution: An analysis of the 2017 Oroville Dam extreme atmospheric river. Artificial Intelligence for the Earth Systems. https://doi.org/10.1175/AIES-D-24-0090.1
• Baño-Medina, Jorge; Sengupta, Agniv; Michaelis, Allison; Delle Monache, Luca; Kalansky, Julie; Watson-Parris, Duncan (2024). "Harnessing AI data-driven global weather models for climate attribution: An analysis of the 2017 Oroville Dam extreme atmospheric river." arXiv:2409.11605. https://doi.org/10.48550/arXiv.2409.11605

Software

• Github repository with material and code: https://github.com/CW3E/AI-attribution

Collection image

• Image credit: Jorge Baño-Medina, Agniv Sengupta, Allison Michaelis, Luca Delle Monache, Julie Kalansky, Duncan Watson-Parris. "Schematic of the proposed strategy to conduct climate attribution studies with AI global weather models."