The overarching goal of the AI/ML Working Group (WG) within the Environmental System Sciences (ESS) Cyberinfrastructure Working Groups is to empower the ESS research community to leverage artificial intelligence (AI) and machine learning (ML) methods, accelerating scientific discovery in the field. Specific goals include fostering AI/ML literacy, cultivating a foundational understanding of these methods, and enabling their effective application within ESS’s hypothesis-driven Model-Experiment (ModEx) frameworks. Ultimately, this WG equips researchers with the AI/ML skills necessary for developing novel and impactful applications of AI/ML that elucidate the mechanisms governing complex interactions among biological, chemical, and physical environmental processes and systems, and across a wide range of spatial and temporal scales.

To achieve this goal, the AI/ML Working Group plays a key role in organizing seminars, tutorials, training sessions, and hackathons within the ESS community to focus on learning, interdisciplinary collaboration, and innovation. These activities foster knowledge exchange and skill development, targeting both foundational AI/ML concepts and domain-specific applications relevant to ESS.

Key activities of the AI/ML Working Group include:

1. Regular seminars and training sessions: We host monthly or bimonthly AI/ML seminars and training sessions. These events introduce foundational concepts, share best practices, and explore domain-specific applications tailored to ESS. These sessions are open to participants from diverse research backgrounds, fostering a collaborative learning environment while building AI/ML capabilities across ESS.
2. Hackathons: We organize theme-based hackathons annually to address specific challenges and opportunities within ESS. These hands-on events encourage challenges, nurturing creativity and problem-solving skills. Hackathons also serve as a platform to build interdisciplinary teams in a collaborative environment, enhancing peer learning.
3. Resource Sharing: We develop and maintain an active repository of resources, documentation, and tools to support continuous learning. Initial efforts of this AI/ML WG include developing a crowd-sourced handbook that consolidates key AI/ML terms and methods that are relevant to the ESS research community. We use google group as a communication platform for sharing insights, experiences, and developments among participants to build a robust learning community.
4. Collaboration and Networking: By fostering partnerships among national laboratories, academia, and industry, the AI/ML WG aims to bridge expertise across the wide range of scientific disciplines within the ESS community. Seminars, training, and hackathon activities feature contributions from leading experts in AI/ML and domain sciences, providing opportunities for collaboration and establishing connections that drive AI-accelerated ModEx for ESS.

The formation of this working group underscores the commitment of the leads to enhancing cyberinfrastructure capabilities and harnessing the transformative potential of AI/ML technologies. By cultivating expertise and facilitating interdisciplinary collaboration, this WG strives to empower ESS researchers to redefine how grand challenges in ESS can be addressed.

AI Working Group Co-Leads

	Xingyuan Chen Xingyuan.Chen@pnnl.gov Pacific Northwest National Laboratory
	Pamela Weisenhorn pweisenhorn@anl.gov Argonne National Laboratory
	Jesus Gomez gomezvelezjd@ornl.gov Oak Ridge National Laboratory
	Dipankar Dwivedi ddwivedi@lbl.gov Lawrence Berkley National Laboratory