Adapting machine learning for atmosphere-biosphere coupling in earth system models
12Understanding the interplay of individual processes within the Earth system is fundamental to predicting change and assessing the impacts of anthropogenic activities. Ecosystem responses to these changes are particularly complex due to the vast heterogeneity of organisms, for which we lack fundamental laws. The rapidly growing volume of observations of ecosystem-atmosphere interactions now paves the way for identifying consistent response pattern, however, many challenges remain. While machine learning (ML) methods have made significant advances, particularly in computer vision and natural language processing, they require adaptation to address the unique needs in Earth system sciences. Especially, the mismatch in spatial scales, ranging from individual organisms to entire landscapes, complicates the integration of diverse observations for Earth system modeling.
This presentation explores the challenges and solutions in integrating mechanistic modeling—specifically land models within Earth system modeling—with observations-informed ML approaches. We focus on three critical processes in the land system with feedbacks to the Earth system: First, we apply ML and causality methods to detect and quantify the effects of rising CO2 on ecosystems, a critical factor influencing the land carbon sink in future climate projections. Second, we explore phenology, the seasonal dynamics of ecosystems, employing various ML techniques to model phenological changes and their potential feedbacks on energy, water, and carbon fluxes to the atmosphere. Third, we examine stomatal conductance, the mechanism by which plants regulate gas exchange with the atmosphere through leaf openings. We present a physics-constrained ML approach to infer this stomatal conductance based on observational data, which is then integrated into Earth system models to simulate feedback loops in the land-atmosphere continuum. Finally, we outline a pathway forward for advancing ML-enhanced Earth system models.
We only have 5 years to achieve the United Nations’ sustainable development goals, and AI is impacting people and the planet. We are the AI generation, and it is our responsibility to ensure that no one is left behind.
AI for Good is identifying trustworthy AI applications, building skills and standards, and advancing AI governance for sustainable development.
AI for Good is organized by ITU in partnership with over 40 UN Sister Agencies and co-convened with the Government of Switzerland.
Join the Neural Network!
👉 https://aiforgood.itu.int/neural-network/
The AI for Good networking community platform powered by AI.
Designed to help users build connections with innovators and experts, link innovative ideas with social impact opportunities, and bring the community together to advance the SDGs using AI.
🔴 Watch the latest #AIforGood videos!
📩 Stay updated and join our weekly AI for Good newsletter:
http://eepurl.com/gI2kJ5
🗞 Check out the latest AI for Good news:
https://aiforgood.itu.int/newsroom/
📱 Explore the AI for Good blog:
https://aiforgood.itu.int/ai-for-good-blog/
🌎 Connect on our social media:
Website: https://aiforgood.itu.int/
X: https://twitter.com/AIforGood
LinkedIn Page: https://www.linkedin.com/company/26511907
LinkedIn Group: https://www.linkedin.com/groups/8567748
Instagram: https://www.instagram.com/aiforgood
Facebook: https://www.facebook.com/AIforGood
Disclaimer:
The views and opinions expressed are those of the panelists and do not reflect the official policy of the ITU.