Welcome to ECAI Lab!
Enabling trustworthy AI for agro- and natural ecosystem sciences!
Introduction to ECAI Lab
The ECosystem Analytics and Intelligence (ECAI) Lab at the University of Wisconsin–Madison was formed on Jan 1st, 2026. We are interested in advancing agriculture and ecosystem sciences with knowledge-guided machine learning. Our lab spans the spectrum of ecosystem AI and process-based modeling, data–model fusion, and cross-scale sensing. We are dedicated to produce reliable science and technology to support global food security and environmental sustainability.
More things
News
-
New publication on IEEE Geoscience and Remote Sensing Magazine
From 2D Flat Maps to 4D Living Models: A review of UAV remote sensing in agriculture
-
New publication on In Proceedings of the 32nd ACM SIGKDD Conference on Knowledge Discovery and Data Mining
LLM-based Evaluation Policy Extraction for Ecological Modeling
-
New dataset for 3D crop modeling
UAV3DCrop is a large-scale benchmark for 3D reconstruction across crop types, growth stages and repeated UAV acquisitions.
-
New publication on Journal of Geophysical Research: Biogeosciences
Revising the magnitude and trends of the global methane soil sink with process‐based, machine‐learning, and atmospheric inversion modeling approaches
-
New publication on Geoscientific Model Development
mLDNDCv1.0: a machine learning-based surrogate of LandscapeDNDC for optimising cropping systems in Denmark
-
New publication on Nature Communications
Isotopic constraints in methane inversions reveal larger trends in wetland emissions with improved linkage to terrestrial water storage
-
New publication on Global Change Biology
Multi-Decadal Dynamics of Wetland Methane Emissions Revealed by Knowledge-Guided Machine Learning
-
New publication on In Proceedings of the 32nd ACM SIGKDD Conference on Knowledge Discovery and Data Mining
X-MethaneWet: A Cross-scale Global Wetland Methane Emission Benchmark Dataset for Advancing Science Discovery with AI
-
New publication on Global Change Biology
Knowledge-guided machine learning for global change ecology research
-
New publication on Remote Sensing of Environment
Knowledge-guided graph machine learning improves corn yield mapping in the US Midwest