earth system

Understanding 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.  

Explore the transformative potential of the Population Dynamics Foundation Model (PDFM), a cutting-edge AI model designed to capture complex, multidimensional interactions among human behaviors, environmental factors, and local contexts. This workshop provides an in-depth introduction to PDFM Embeddings and their applications in geospatial analysis, public health, and socioeconomic modeling. 

Participants will gain hands-on experience with PDFM Embeddings to perform advanced geospatial predictions and analyses while ensuring privacy through the use of aggregated data. Key components of the workshop include: 

• Introduction to PDFM Embeddings: Delve into the model architecture of PDFM and discover how aggregated data (such as search trends, busyness levels, and weather conditions) generates location-specific embeddings.
• Data Preparation: Learn to integrate ground truth data, including health statistics and socioeconomic indicators, with PDFM Embeddings at the postal code or county level.
• Hands-On Exercises: Engage with interactive Colab notebooks to explore real-world applications, such as predicting housing prices using Zillow data and nighttime light predictions with Google Earth Engine data.
• Visualization and Interpretation: Analyze and visualize geospatial predictions and PDFM features in 3D, enhancing your ability to interpret complex datasets. 

By the end of this workshop, participants will have a strong foundation in utilizing PDFM Embeddings to address real-world geospatial challenges.