Title:
AI to Accelerate Scientific Discovery for a Sustainable Future

09:00 - 10:00, Dec. 3, 2023, UTC+8.

Carla P. Gomes

Carla Gomes is the Ronald C. and Antonia V. Nielsen Professor of Computing and Information Science, the director of the Institute for Computational Sustainability at Cornell University, and co-director of the Cornell University AI for Science Institute. Gomes received a Ph.D. in computer science in artificial intelligence from the University of Edinburgh. Her research area is Artificial Intelligence with a focus on large-scale constraint reasoning, optimization, and machine learning. Recently, Gomes has become deeply immersed in research on scientific discovery for a sustainable future and, more generally, in research in the new field of Computational Sustainability. Computational Sustainability aims to develop computational methods to help solve some of the key environmental, economic, and societal challenges to help put us on a path toward a sustainable future. Gomes was the lead PI of two NSF Expeditions in Computing awards. Gomes has (co-)authored over 200 publications, which have appeared in venues spanning Nature, Science, and a variety of conferences and journals in AI and Computer Science, including five best paper awards. Gomes was named the “most influential Cornell professor” by a Merrill Presidential Scholar (2020). Gomes was also the recipient of the Association for the Advancement of Artificial Intelligence (AAAI) Feigenbaum Prize (2021) for “high-impact contributions to the field of artificial intelligence, through innovations in constraint reasoning, optimization, the integration of reasoning and learning, and through founding the field of Computational Sustainability, with impactful applications in ecology, species conservation, environmental sustainability, and materials discovery for energy” and of the 2022 ACM/AAAI Allen Newell Award, for contributions bridging computer science and other disciplines. Gomes is a Fellow of the Association for the Advancement of Artificial Intelligence (AAAI), a Fellow of the Association for Computing Machinery (ACM), and a Fellow of the American Association for the Advancement of Science (AAAS).

Abstract:
Artificial Intelligence (AI) is a rapidly evolving field that has achieved remarkable milestones, spanning computer vision, machine translation, world-champion level Go gameplay, self-driving cars, and Chat-GPT. These groundbreaking achievements have unlocked numerous opportunities for progress across various domains. The tremendous AI progress that we have witnessed in the last decade has been largely driven by deep learning advances and heavily hinges on the availability of large, annotated datasets to supervise model training. However, scientists incorporate sophisticated background knowledge into the data interpretation process: They combine reasoning from first principles with a data-driven interpretation. We therefore need AI systems that combine learning with reasoning about scientific knowledge and find suitable problem representations for scalable solutions. This will enable our AI systems to predict far outside the training distributions as is needed for scientific discovery. I will discuss AI research for advancing scientific discovery for a sustainable future. I will talk about our work in Computational Sustainability, an emerging interdisciplinary field that aims to leverage the ever-growing capabilities of AI to address critical challenges and contribute to human well-being and the betterment of our planet. I will provide examples of computational sustainability challenges such as, biodiversity conservation, multi-criteria strategic planning of hydropower dams in the Amazon basin, and materials discovery for renewable energy materials. I will highlight our work on AI to accelerate materials discovery. In this work, we propose an approach called Deep Reasoning Networks (DRNets), which integrates deep learning with reasoning and requires only modest amounts of (unlabeled) data, in sharp contrast to standard deep learning approaches. DRNets reach super-human performance for crystal-structure phase mapping, a core, long-standing challenge in materials science, enabling the discovery of solar-fuels materials. DRNets provide a general framework for integrating deep learning and reasoning for tackling challenging problems. Finally, I will highlight cross-cutting computational themes and challenges for AI.