Yale Planetary Solutions (YPS) is pushing the frontiers of research with two groundbreaking projects that tackle pressing environmental challenges. These initiatives, supported by the Bezos Earth Fund, aim to enhance our understanding and action against climate change through marine carbon removal and livestock methane emissions. Julie Zimmerman, Yale’s provost for planetary solutions, emphasized the transformative impact of these projects, noting their role in fostering “bold, interdisciplinary” research.
Zimmerman explained, “This support from the Bezos Earth Fund is critical to advancing our understanding of both marine carbon removal and livestock methane emissions and their potential for climate mitigation.”
The mCDR Forecasting Stack
Leading the charge in marine carbon dioxide removal (mCDR) is the innovative forecasting “Stack,” spearheaded by Elizabeth Yankovsky and Luke Gloege. This project integrates machine learning with simulations to enhance monitoring, reporting, and verification (MRV) processes, crucial for climate mitigation efforts.
The Stack’s primary focus is on supporting technologies that extract carbon dioxide from the atmosphere and convert it into dissolved bicarbonate within the ocean. This process, while pivotal, presents challenges in terms of quantifying efficiency and durability. Noah Planavsky, a key contributor to the Stack’s development, will oversee its implementation.
Yankovsky describes the Stack as “fast, intuitive, and scientifically robust,” providing advanced forecasting capabilities to a diverse range of users. The project bridges existing AI and physics models across various disciplines to address the complexities of MRV for carbon removal.
Despite the ocean’s vast capacity to store bicarbonate, the process faces obstacles due to inefficiencies and turbulence. Small-scale turbulence, for instance, can disperse added alkalinity before it effectively captures atmospheric carbon dioxide. Current models struggle with precision and speed in tracking these carbon fluxes.
The Stack aims to overcome these challenges by integrating a new, GPU-optimized ocean model with a biogeochemistry model, specifically designed for simulating carbon dioxide removal strategies. Additionally, it will leverage AI-driven atmospheric forecasts developed by NVIDIA, known for its cutting-edge GPU technology.
Users of the Stack will gain access to detailed forecasts of net carbon removal and its long-term stability. It promises unprecedented forecasting capabilities, offering decadal-scale predictions in hours and millennia-scale forecasts in days.
“We’ll be able to do granular forecasting of atmospheric carbon dioxide uptake and storage to enable high-fidelity MRV, better planning of specific interventions, site selection, and a basis for durable carbon crediting,” Gloege highlighted.
The Rumen Digital Twin
The Rumen Digital Twin project is a collaborative effort involving the Alliance of Biodiversity International, the International Center for Tropical Agriculture (CIAT), BiomEdit, and Dixit from Yale Engineering. This initiative aims to provide innovative solutions for reducing livestock methane emissions, another critical aspect of climate change mitigation.
Original Story at news.yale.edu