A science paradigm shift is needed for Earth and Environmental Systems Sciences (EESS) to integrate Knowledge-Guided Artificial Intelligence (KGAI) and lead new EESS-KGAI theories

Voisin, Nathalie; Bennett, Andrew; Fang, Yilin; Nearing, Grey; Nijssen, Bart; Rao, Yuhan

doi:10.2172/1769651

Title: A science paradigm shift is needed for Earth and Environmental Systems Sciences (EESS) to integrate Knowledge-Guided Artificial Intelligence (KGAI) and lead new EESS-KGAI theories

Full Record
Other Related Research

Abstract

The focal area of this white paper is learning from complex data through the use of AI techniques and AI-derived model components. Specifically, we advocate for research programs to develop knowledge-guided AI (KGAI) in the Earth and Environmental Systems sciences (EESS) as a basic research paradigm that is separate from (but supports) any specific Earth system model, modeling components, and modeling workflows, and even separates from specific hypothesis-driven questions about individual Earth system processes.

Authors:

Voisin, Nathalie ^[1]; Bennett, Andrew ^[2]; Fang, Yilin ^[1]; Nearing, Grey ^[3]; Nijssen, Bart ^[2]; Rao, Yuhan ^[4]

Pacific Northwest National Lab. (PNNL), Richland, WA (United States)
Univ. of Washington, Seattle, WA (United States)
Univ. of California, Davis, CA (United States)
North Carolina State Univ., Raleigh, NC (United States)

Publication Date:: 2021-04-15

Research Org.:: Artificial Intelligence for Earth System Predictability (AI4ESP) Collaboration (United States)

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

OSTI Identifier:: 1769651

Report Number(s):: AI4ESP-1138

DOE Contract Number:: 35604.1

Resource Type:: Technical Report

Country of Publication:: United States

Language:: English

Subject:: 54 ENVIRONMENTAL SCIENCES; 58 GEOSCIENCES

Citation Formats


                    Voisin, Nathalie, Bennett, Andrew, Fang, Yilin, Nearing, Grey, Nijssen, Bart, and Rao, Yuhan. A science paradigm shift is needed for Earth and Environmental Systems Sciences (EESS) to integrate Knowledge-Guided Artificial Intelligence (KGAI) and lead new EESS-KGAI theories.  United States: N. p., 2021. 
        Web.  doi:10.2172/1769651.

Copy to clipboard


                    Voisin, Nathalie, Bennett, Andrew, Fang, Yilin, Nearing, Grey, Nijssen, Bart, & Rao, Yuhan. A science paradigm shift is needed for Earth and Environmental Systems Sciences (EESS) to integrate Knowledge-Guided Artificial Intelligence (KGAI) and lead new EESS-KGAI theories.  United States.  https://doi.org/10.2172/1769651

Copy to clipboard


                    Voisin, Nathalie, Bennett, Andrew, Fang, Yilin, Nearing, Grey, Nijssen, Bart, and Rao, Yuhan. 2021.  
        "A science paradigm shift is needed for Earth and Environmental Systems Sciences (EESS) to integrate Knowledge-Guided Artificial Intelligence (KGAI) and lead new EESS-KGAI theories".  United States.  https://doi.org/10.2172/1769651.  https://www.osti.gov/servlets/purl/1769651.

Copy to clipboard


                    
@article{osti_1769651,

  title        = {A science paradigm shift is needed for Earth and Environmental Systems Sciences (EESS) to integrate Knowledge-Guided Artificial Intelligence (KGAI) and lead new EESS-KGAI theories},

  author       = {Voisin, Nathalie and Bennett, Andrew and Fang, Yilin and Nearing, Grey and Nijssen, Bart and Rao, Yuhan},

  abstractNote = {The focal area of this white paper is learning from complex data through the use of AI techniques and AI-derived model components. Specifically, we advocate for research programs to develop knowledge-guided AI (KGAI) in the Earth and Environmental Systems sciences (EESS) as a basic research paradigm that is separate from (but supports) any specific Earth system model, modeling components, and modeling workflows, and even separates from specific hypothesis-driven questions about individual Earth system processes.},

  doi          = {10.2172/1769651},

  url          = {https://www.osti.gov/biblio/1769651},
  journal      = {},
number       = ,

  volume       = ,

  place        = {United States},

  year         = {2021},

  month        = {4}

}

Copy to clipboard

Technical Report:

View Technical Report

https://doi.org/10.2172/1769651

Save / Share:

Export Metadata

Save to My Library

Similar records in OSTI.GOV collections:

Development of Explainable, Knowledge-Guided AI Models to Enhance the E3SM Land Model Development and Uncertainty Quantification

Technical Report Wang, Dali; Kao, Shih-Chieh; Ricciuto, Daniel

Focal Area(s): (2)Predictive modeling using AI techniques and AI-derived model components; use of AI and other tools to design a prediction system comprising of a hierarchy of models. (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: The Energy Exascale Earth System Model (E3SM) is a fully coupled, state-of-the-science Earth system model that uses code optimized for DOE's advanced computers to address the most critical scientific questions facing our nation and society (Golaz et al., 2019). The E3SM Landmore »« less
https://doi.org/10.2172/1769696

Full Text Available
Combining artificial intelligence, Earth observations, and climate models to improve predictability of ice-biogeochemistry interactions

Technical Report Kim, Grace; Mack, Stefanie; Kaufman, Daniel

Focal Area: Predictive Modeling. We describe how artificial intelligence (AI) can be combined with state-of-the-science Earth system models to better predict future regional climate responses. To demonstrate, we describe a case study in biogeochemical interactions with sea ice. Science Challenge: Biogeochemical models are poorly constrained for high latitude systems. Machine learning methods and edge computing can be combined with Earth system models, such as the Energy Exascale Earth System Model (E3SM), to gain insight into ice-biogeochemical interactions and improve sea ice extent prediction.
https://doi.org/10.2172/1769689

Full Text Available
Geophysical Retrievals in an Artificial Intelligence (AI) Framework for Illuminating Processes Controlling Water Cycle

Technical Report Ghate, Virendra; Cadeddu, Maria; Lenzi, Amanda; ...

Focal Area(s): This white paper responds to 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: This white paper addresses the water-cycle and data-model integration grand challenge. It leverages data from the Atmospheric Radiation Measurement (ARM) Climate Research Facility, and Next-Generation Ecosystem Experiment (NGEE), and Science Focus Area (SFA). The white paper focuses on controlling cloud, precipitation, and radiative properties as observed and simulated by the Earth System Models (ESM). The described framework can be readily applied tomore »« less
https://doi.org/10.2172/1769714

Full Text Available
A review of Earth Artificial Intelligence

Journal Article Sun, Ziheng; Sandoval, Laura; Crystal-Ornelas, Robert; ... - Computers and Geosciences

In recent years, Earth system sciences are urgently calling for innovation on improving accuracy, enhancing model intelligence level, scaling up operation, and reducing costs in many subdomains amid the exponentially accumulated datasets and the promising artificial intelligence (AI) revolution in computer science. This paper presents work led by the NASA Earth Science Data Systems Working Groups and ESIP machine learning cluster to give a comprehensive overview of AI in Earth sciences. It holistically introduces the current status, technology, use cases, challenges, and opportunities, and provides all the levels of AI practitioners in geosciences with an overall big picture and tomore »« less
https://doi.org/10.1016/j.cageo.2022.105034
Facilitating better and faster simulations of aerosol-cloud interactions in Earth system models

Technical Report Ma, Po-Lun; Bretherton, Christopher; Stinis, Panos; ...

Focal Area(s): 1. Predictive modeling through the use of AI techniques and AI-derived model components; the use of AI and other tools to design a prediction system comprising a hierarchy of models. 2. 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: One major challenge that Earth system models (ESMs) face in providing credible prediction of the Earth system and its water cycle characteristics (e.g., mean state, variability, and extreme events) is to accurately simulate aerosol-cloud interactions (ACI). The physical, chemical,more »« less
https://doi.org/10.2172/1769709

Full Text Available

Similar Records