Machine learning to extend and understand the sources and limits of water cycle predictability on subseasonal-to-decadal timescales in the Earth system

Dagon, Katherine; Molina, Maria J.; Meehl, Gerald A.; Richter, Jadwiga H.; Barnes, Elizabeth; Berner, Judith; Caron, Julie M.; Chapman, Will; Danabasoglu, Gokhan; Gage, David John; Glanville, Sasha; Haupt, Sue Ellen; Hu, Aixue; Martin, Zane; Mayer, Kirsten; Pegion, Kathy; Raeder, Kevin; Simpson, Isla; Subramanian, Aneesh; Yeager, Steve

doi:10.2172/1769744

Title: Machine learning to extend and understand the sources and limits of water cycle predictability on subseasonal-to-decadal timescales in the Earth system

Full Record
Other Related Research

Abstract

This white paper provides initial insight on how artificial intelligence (AI) and machine learning (ML), including interpretability and explainable AI (XAI) methods, can be leveraged to glean insight from complex data for a paradigm-changing improvement in Earth system predictability on subseasonal-to-seasonal (S2S) and seasonal-to-decadal (S2D) timescales. The application of AI to extend and improve predictability, in combination with causal inference and uncertainty quantification, could lead to a transformative understanding of the integrative water cycle and associated extremes.

Authors:

Dagon, Katherine ^[1]; Molina, Maria J. ^[1]; Meehl, Gerald A. ^[1]; Richter, Jadwiga H. ^[1]; Barnes, Elizabeth ^[2]; Berner, Judith ^[1]; Caron, Julie M. ^[1]; Chapman, Will ^[3]; Danabasoglu, Gokhan ^[1]; Gage, David John ^[1]; Glanville, Sasha ^[1]; Haupt, Sue Ellen ^[1]; Hu, Aixue ^[1]; Martin, Zane ^[2]; Mayer, Kirsten ^[2]; Pegion, Kathy ^[4]; Raeder, Kevin ^[1]; Simpson, Isla ^[1]; Subramanian, Aneesh ^[5]; Yeager, Steve ^[1]

National Center for Atmospheric Research (NCAR), Boulder, CO (United States)
Colorado State Univ., Fort Collins, CO (United States)
Univ. of California, San Diego, CA (United States). Scripps Inst. of Oceanography
George Mason Univ., Fairfax, VA (United States)
Univ. of Colorado, Boulder, CO (United States)

Publication Date:: 2021-02-12

Research Org.:: National Center for Atmospheric Research (NCAR), Boulder, CO (United States); Colorado State Univ., Fort Collins, CO (United States); Univ. of California, San Diego, CA (United States). Scripps Inst. of Oceanography; George Mason Univ., Fairfax, VA (United States); Univ. of Colorado, Boulder, CO (United States)

Sponsoring Org.:: USDOE Office of Science (SC), Biological and Environmental Research (BER)

OSTI Identifier:: 1769744

Report Number(s):: AI4ESP1032

Resource Type:: Technical Report

Country of Publication:: United States

Language:: English

Subject:: 58 GEOSCIENCES; 54 ENVIRONMENTAL SCIENCES; 97 MATHEMATICS AND COMPUTING

Citation Formats


                    Dagon, Katherine, Molina, Maria J., Meehl, Gerald A., Richter, Jadwiga H., Barnes, Elizabeth, Berner, Judith, Caron, Julie M., Chapman, Will, Danabasoglu, Gokhan, Gage, David John, Glanville, Sasha, Haupt, Sue Ellen, Hu, Aixue, Martin, Zane, Mayer, Kirsten, Pegion, Kathy, Raeder, Kevin, Simpson, Isla, Subramanian, Aneesh, and Yeager, Steve. Machine learning to extend and understand the sources and limits of water cycle predictability on subseasonal-to-decadal timescales in the Earth system.  United States: N. p., 2021. 
        Web.  doi:10.2172/1769744.

Copy to clipboard


                    Dagon, Katherine, Molina, Maria J., Meehl, Gerald A., Richter, Jadwiga H., Barnes, Elizabeth, Berner, Judith, Caron, Julie M., Chapman, Will, Danabasoglu, Gokhan, Gage, David John, Glanville, Sasha, Haupt, Sue Ellen, Hu, Aixue, Martin, Zane, Mayer, Kirsten, Pegion, Kathy, Raeder, Kevin, Simpson, Isla, Subramanian, Aneesh, & Yeager, Steve. Machine learning to extend and understand the sources and limits of water cycle predictability on subseasonal-to-decadal timescales in the Earth system.  United States.  https://doi.org/10.2172/1769744

Copy to clipboard


                    Dagon, Katherine, Molina, Maria J., Meehl, Gerald A., Richter, Jadwiga H., Barnes, Elizabeth, Berner, Judith, Caron, Julie M., Chapman, Will, Danabasoglu, Gokhan, Gage, David John, Glanville, Sasha, Haupt, Sue Ellen, Hu, Aixue, Martin, Zane, Mayer, Kirsten, Pegion, Kathy, Raeder, Kevin, Simpson, Isla, Subramanian, Aneesh, and Yeager, Steve. 2021.  
        "Machine learning to extend and understand the sources and limits of water cycle predictability on subseasonal-to-decadal timescales in the Earth system".  United States.  https://doi.org/10.2172/1769744.  https://www.osti.gov/servlets/purl/1769744.

Copy to clipboard


                    
@article{osti_1769744,

  title        = {Machine learning to extend and understand the sources and limits of water cycle predictability on subseasonal-to-decadal timescales in the Earth system},

  author       = {Dagon, Katherine and Molina, Maria J. and Meehl, Gerald A. and Richter, Jadwiga H. and Barnes, Elizabeth and Berner, Judith and Caron, Julie M. and Chapman, Will and Danabasoglu, Gokhan and Gage, David John and Glanville, Sasha and Haupt, Sue Ellen and Hu, Aixue and Martin, Zane and Mayer, Kirsten and Pegion, Kathy and Raeder, Kevin and Simpson, Isla and Subramanian, Aneesh and Yeager, Steve},

  abstractNote = {This white paper provides initial insight on how artificial intelligence (AI) and machine learning (ML), including interpretability and explainable AI (XAI) methods, can be leveraged to glean insight from complex data for a paradigm-changing improvement in Earth system predictability on subseasonal-to-seasonal (S2S) and seasonal-to-decadal (S2D) timescales. The application of AI to extend and improve predictability, in combination with causal inference and uncertainty quantification, could lead to a transformative understanding of the integrative water cycle and associated extremes.},

  doi          = {10.2172/1769744},

  url          = {https://www.osti.gov/biblio/1769744},
  journal      = {},
number       = ,

  volume       = ,

  place        = {United States},

  year         = {2021},

  month        = {2}

}

Copy to clipboard

Technical Report:

View Technical Report

https://doi.org/10.2172/1769744

Save / Share:

Export Metadata

Save to My Library

Similar records in OSTI.GOV collections:

Initialized Earth system prediction from subseasonal to decadal timescales

Journal Article Meehl, Gerald; Richter, Jadwiga; Teng, Haiyan; ... - Nature Reviews Earth and Environment

Initialized Earth system predictions are made by starting a numerical prediction model in a state as consistent as possible to observations, and running it forward in time for up to ten years. Skillful predictions at time slices from subseasonal to seasonal (S2S), seasonal to interannual (S2I) and seasonal to decadal (S2D) offer information useful for various stakeholders, from agriculture to water resource management, and human and infrastructure safety. In this Review, we examine the processes influencing predictability, and discuss estimates of skill across S2S, S2I and S2D timescales. There are encouraging signs that skillful predictions can be made: at S2Smore »« less
https://doi.org/10.1038/s43017-021-00155-x
Initialized Earth System prediction from subseasonal to decadal timescales

Journal Article Meehl, Gerald; Richter, Jadwiga; Teng, Haiyan; ... - Nature Reviews Earth & Environment

Initialized Earth System predictions are made by starting a numerical prediction model in a state as consistent as possible to observations and running it forward in time for up to 10 years. Skilful predictions at time slices from subseasonal to seasonal (S2S), seasonal to interannual (S2I) and seasonal to decadal (S2D) offer information useful for various stakeholders, ranging from agriculture to water resource management to human and infrastructure safety. In this Review, we examine the processes influencing predictability, and discuss estimates of skill across S2S, S2I and S2D timescales. There are encouraging signs that skilful predictions can be made: onmore »« less
https://doi.org/10.1038/s43017-021-00155-x

Full Text Available
Hybridizing Machine Learning and Physically-based Earth System Models to Improve Prediction of Multivariate Extreme Events (AI Exploration of Wildland Fire Prediction)

Technical Report Zou, Yufei; Rasch, Philip; Wang, Hailong

Focal Areas: This project responds to two focal areas identified in the DOE Call for AI4ESP White Papers: 1) Predictive modeling through the use of artificial intelligence (AI) techniques, and 2) insights gleaned from complex data using explainable AI and big data analytics. Science Challenge: Large wildland fires (hereafter wildfires) appearing as high-impact compound climate extreme events are closely related to hydroclimate and water cycle extremes that modulate surface fuel supply and combustibility. These compound events have multivariate climatic features (e.g., temperature, precipitation, relative humidity, wind, lightning) and societal drivers (e.g., forest management, land use change, human caused ignitions). Meanwhile,more »« less
https://doi.org/10.2172/1769718

Full Text Available
Assessing Teleconnections-Induced Predictability of Regional Water Cycle on Seasonal to Decadal Timescales Using Machine Learning Approaches

Technical Report Mahajan, Salil; Passarella, Linsey; Hoffman, Forrest; ...

Focal Area: (3) Insight gleaned from complex data (both observed and simulated) using AI, big data analytics, and other advanced methods, including explainable AI and physics- or knowledge-guided AI. Science Challenge: Predictive understanding of the regional water cycle based on teleconnections of climate modes of variability using AI methods.
https://doi.org/10.2172/1769676

Full Text Available
Using machine learning and artificial intelligence to improve model-data integrated earth system model predictions of water and carbon cycle extremes

Technical Report Tang, Jinyun; Riley, William; Zhu, Qing; ...

The research proposed here focuses on improving the predictive power of the land component of earth system models (ESMs) using (1) model-data fusion enabled by machine learning (ML) and artificial intelligence (AI), (2) predictive modeling through the combination of ML, AI, and big-data (comprising both model output and observations), and (3) insight of ESM structure and process mechanisms gleaned from complex data using ML and AI.
https://doi.org/10.2172/1769794

Full Text Available

Similar Records