Facilitating better and faster simulations of aerosol-cloud interactions in Earth system models
- Pacific Northwest National Lab. (PNNL), Richland, WA (United States)
- Vulcan, Inc., Seattle, WA (United States); Univ. of Washington, Seattle, WA (United States)
- Pacific Northwest National Lab. (PNNL), Richland, WA (United States); Univ. of Wisconsin, Milwaukee, WI (United States)
- Colorado State Univ., Fort Collins, CO (United States)
- Univ. of California, Irvine, CA (United States)
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, and dynamical processes affecting ACI are extremely complex and they range from nanoscale to planetary scale. In each model development cycle, scientists spend significant efforts investigating model deficiencies and uncertainties associated with aerosols (e.g., emissions, chemical processes, aerosol microphysics, and transport) and clouds (e.g., macrophysics, microphysics, turbulence, and large-scale circulation) in order to develop improved treatments. However, despite decades of active research, ACI is still a major source of uncertainty in climate projections, even though great progress has been made. Specific scientific challenges include: (i) Parameterizations are developed based on limited data; (ii) The complexity of a parameterization required for accurate predictions is not understood; (iii) Incomplete and unknown physics leads to errors in the fully coupled Earth system; and (iv) Complex physics is computationally too expensive to employ in ESMs.
- Research Organization:
- Artificial Intelligence for Earth System Predictability (AI4ESP) Collaboration (United States)
- Sponsoring Organization:
- USDOE Office of Science (SC), Biological and Environmental Research (BER)
- DOE Contract Number:
- 35604.1
- OSTI ID:
- 1769709
- Report Number(s):
- AI4ESP-1085
- Country of Publication:
- United States
- Language:
- English
Similar Records
Characterization of Extreme Hydroclimate Events in Earth System Models using ML/AI
Learned implicit representations of aerosol chemistry and physics for enhancing the predictability of water cycle extreme events