Four Cornell faculty members have been awarded grants from the Bezos Earth Fund’s inaugural AI Grand Challenge for Climate and Nature. Among 1,200 global applicants, only 24 were selected – three from the College of Agriculture and Life Sciences (CALS) and one from Cornell Engineering. 

The awards, announced May 21, are the first phase of a multiphase funding opportunity from Amazon founder Jeff Bezos’ philanthropy. The 24 awardees each received roughly $50,000 to explore ideas to address climate change and nature loss through use of artificial intelligence. For this first-ever Grand Challenge award, applicants’ projects centered on sustainable proteins, power grid optimization and biodiversity conservation. Phase I awardees now have the opportunity to apply for a Phase II implementation grant: as many as 15 awardees “will each receive up to $2 million to close the gap between concept and viability,” according to the Earth Fund. 

The awarded projects will address:

AI and artificial cells for sustainable protein production.

To mitigate the climate impact of animal-derived food sources, scientists in academia and private industry have sought to create lab-based substitutes by either replicating actual animal cells or creating plant-based foods that mimic the tastes and textures of animal-based foods. Dan Luo, professor of biological and environmental engineering in CALS, is taking an entirely different approach. 

Luo creates artificial cells that are hydrogel-based, non-living and self-contained, constructed from lysates: the contents of cells once their membranes are broken open. His artificial cells eliminate the need for fermentation and cell culturing – two of the problems that have beset other efforts to create lab-based meats. Luo and collaborator Boxiang Liu, assistant professor at the National University of Singapore, will use AI to rapidly design and test protein combinations to achieve more realistic tastes and textures. 

“In the long term, we plan to miniaturize artificial cell reactors – akin to personal computers – and pre-produce self-contained lysates – akin to preprogrammed software,” Luo said. “This will usher in an era of personalized sustainable proteins, enabling home and community-based production of tailor-made proteins suited to specific dietary needs and cultural preferences. By democratizing protein production, our approach aspires to enhance food security, reduce transportation-related emissions and empower individuals to control their protein intake, thereby revolutionizing sustainable food systems globally.”

Mitigating greenhouse gas emissions from cattle farming.

Strategies to mitigate the impact of livestock farming are hampered by the absence of comprehensive databases, said Miel Hostens, the Robert and Anne Everett Associate Professor of Digital Dairy Management and Data Analytics in CALS. Hostens is leading a project to use large-language models to integrate diverse data sources and provide guidance on reducing greenhouse gas impacts, hoping to particularly benefit producers in emerging economies.

Hostens and his collaborators will connect their AI-based model to data sources such as on-farm readings gathered through the Cornell PRODAIRY network, individual cow methane data generated from Cornell’s first-in-the-nation animal respiration stalls and open-access scientific articles on emissions reduction in cattle. They’ll also create a website and chatbot, available to the public to access data and ask farm-specific questions. 

“The scientifically trained chatbot interface will offer dairy farmers, especially in emerging economies with many smallholder farms, immediate, cost-effective access to optimal practices for methane emission reduction, with actionable recommendations on feed composition, manure management and herd health, allowing farmers to implement effective strategies,” Hostens said. “By integrating structured and unstructured data, our solution provides instant, accessible responses, accelerating carbon-emission mitigation globally.”

Transforming electric vehicles into mobile batteries for the power grid.

Eilyan Bitar, associate professor of electrical and computer engineering, will use his grant to investigate how electric vehicles (EVs) can be transformed into a vast, dispatchable network of mobile energy storage resources. By turning EVs into flexible grid assets, Bitar’s project will help decarbonize both the power grid and transportation sectors.

Working with collaborators, Bitar will develop AI-powered forecasting, aggregation and decision-making tools to coordinate the real-time charging and discharging of millions of spatially distributed EVs – replacing expensive stationary batteries with a nimble, decentralized network of batteries on wheels. “The average personal vehicle is parked more than 95 percent of the time,” Bitar said. “Unlocking even a fraction of that idle time for grid support could reshape energy systems worldwide.”

Without compromising their availability for transportation, Bitar's project will tap into EVs’ unused electricity storage potential to deliver reliable energy services for the power grid. “Using bidirectional charging, millions of EVs can be controlled to act in concert as one massive battery – storing renewable energy when there’s a surplus and injecting it back into the grid during shortfalls,” Bitar said. “This creates a virtuous cycle, where EVs help smooth out the variability of renewables and renewables provide EVs with clean energy.”

Most broadly, the project will support the deep integration of renewable energy, improve grid resilience during extreme weather events, and lower costs for both utilities and EV owners – driving forward a more sustainable, affordable, and zero-emissions energy future.

Revolutionizing bioacoustics monitoring for precision conservation.

Global biodiversity is in decline, posing a significant risk to our planet’s long-term health and human well-being within it. Part of the challenge is that life on earth can be hard to measure. Scientists at the Cornell Lab of Ornithology have a potential solution.

The Lab is developing an approach to bioacoustics monitoring that could eventually yield a real-time picture of life on earth. By combining cutting-edge tools with community engagement, artificial intelligence, and conservation partnerships, the approach unlocks a whole new level of scalability. This, in turn, would enable worldwide applications that could assist in filling data gaps in remote terrestrial and marine habitats, yield more effective conservation approaches, and revolutionize the field of bioacoustics overall. It all starts with the world’s first large-scale deployment of autonomous listening devices to monitor South American wildlife.

“Our goal is to demonstrate this integrated approach in the Pantanal with an eye toward global replication of this framework,” said Holger Klinck, the John W. Fitzpatrick director of the K. Lisa Yang Center for Conservation Bioacoustics at the Cornell Lab. “We believe this project could inspire a new era of global conservation efforts.”

With more than 40 years of experience in bioacoustics and related fields, as well as having developed groundbreaking technological tools like Merlin Bird ID and eBird, the Cornell Lab’s expertise positions it well for the effort. The addition of a robust community and partner network – including collaborators like the Wildlife Conservation Society, Chemnitz University of Technology, Universidade Federal de Mato Grosso do Sul, Mongabay, and industry partners like Google Research and Analog Devices, Inc. – has made global scale a possibility. And the Phase I grant from the Bezos Earth Fund offers important signal and support for the project’s continued development.

“Bioacoustics monitoring can revolutionize conservation decision-making,” said Ian Owens, the Lab’s executive director. “The generous support of the Bezos Earth Fund encourages us to work even harder on developing solutions to balance human needs and conserving the ecosystems on which we depend.”

Krisy Gashler is a writer for the College of Agriculture and Life Sciences.