ExpAI2ES proposes to add San Diego State University (SDSU) and the University of California - Irvine (UCI) to the NSF AI institute AI2ES (“AI Institute for Research on Trustworthy AI in Weather, Climate and Coastal Oceanography”) as the new Partners. SDSU is a Hispanic-Serving Institution (HSI) with 33.1% of its 2022 enrolled students Hispanic. UCI is an HSI and an Asian American and Native American Pacific Islander-serving institution with 25.7% of its 2022 enrolled students Hispanic and half of its undergraduates being first-generation students. Both SDSU and UCI have a solid foundation in AI research and education and a joint graduate program in Computational Science. ExpAI2ES will scale up our research and education capacities in AI and atmospheric sciences and create new initiatives to meet the unprecedented demand by our URM students for opportunities in AI across all disciplines, and especially in the geosciences and climate. ExpAI2ES will (a) advance research on explainable AI for precipitation extremes and their uncertainty, (b) develop engaging visualization tools for research, student and teacher training, and (c) bring to the workforce a diverse and untapped talent pool through sustainable collaborations with AI2ES.

The ExpAI2ES partnership will provide intellectual contributions to data science, atmospheric science, software development, and URM training of the AI workforce. The research focus of ExpAI2ES is on AI/ML modeling of the space-time organization and multiscale structure of precipitation and other atmospheric variables, with special emphasis on extremes and uncertainty quantification. The partnership developed by ExpAI2ES will make it possible for the development of 4D data visualization tools for student and teacher training, a wider application of progressive education pedagogy for atmospheric sciences and AI, and the creation of new courses. Specifically, the ExpAI2ES collaboration will (i) advance the accuracy and explainability of AI/ML algorithms in reproducing the multiscale structure of precipitation and high-impact weather; (ii) introduce a wealth of auxiliary remote sensing datasets, e.g., cloud structure and dynamics, for improved understanding and modeling of extreme storms; (iii) advance engaging and easy-to-use data visualization and delivery technology for climate data and AI2ES products; (iv) develop materials for an interactive book on AI applications in atmospheric sciences that allows students to use the online algorithms, computer codes, and data to learn by engaging examples; and (vi) establish a new BS degree program on data science at San Diego State University, which will sustainably scale up the AI training capacity for URM students.

ExpAI2ES will expand the AI2ES AI institute to two additional HSI/MSI universities, which will significantly diversify the pool of talent in both basic AI research and AI applications in Environmental Science. Its innovative research, education, and infrastructure development will help improve workforce diversity in AI, data analytics, and science, which is necessary to effectively address imminent challenges in climate change, environmental sustainability, and the costly weather extremes and hazards. The Progressive Education for Atmospheric Science (PEAS) framework proposed here will improve the educational offerings of AI for atmospheric sciences for SDSU, UCI, and across the AI2ES institutions. Our PEAS+AS framework will be further extended to the training of schoolteachers who, together with students, can use the proposed 4-dimensional visual delivery (4DVD) technology for climate data. The real data engagement combined with modern video-based 4DVD tools will engage and inspire students towards STEM careers. A new BS data science degree program to be initiated at SDSU will certainly aid the building of a pipeline to guide more URM students into careers in AI and environmental sciences.