TreeAI is building an open, community-driven global database of annotated tree crowns, training deep learning models for forest monitoring at planetary scale.
Petabytes of sub-meter imagery exist, yet labeled tree-crown datasets remain scarce — this is the gap TreeAI is closing.
Sub-meter imagery archives (bubble ∝ PB); national programmes such as Swisstopo and IGN represent many more. Annotation datasets (bubble ∝ labeled crowns). Click any bubble to view the source.
Team

Dr. Mirela Beloiu Schwenke
Project Lead
ETH Zurich
Mirela Beloiu is a forest ecologist and remote sensing scientist working at the interface of ecology, geospatial data science, and artificial intelligence. She studies forest resilience under climate change by combining field observations, remote sensing, and deep learning, and develops AI-based approaches for tree species identification, forest health assessment, and mortality monitoring. With over 10 years of teaching experience, she actively fosters collaborations across academia and practice, translating large-scale ecological data into actionable insights for sustainable, climate-resilient forest management.

Zhongyu Xia
Deep Learning Lead
ETH Zurich
Specialises in tree detection and species identification using deep learning and high-resolution remote sensing data. Her work spans model development for accurate crown-level species mapping, large-scale dataset curation and processing, and evaluating how well detection models generalise across diverse geographic regions. She is particularly interested in how monitoring species composition can enable more effective and climate-resilient forest management at scale.

Ruoyi Chen
Lead Developer
ETH Zurich
Works at the intersection of software engineering and data science, with expertise in full-stack web development, deep learning pipeline design, and large-scale geospatial dataset infrastructure. She builds research-facing systems that turn complex remote sensing workflows into accessible, reproducible tools for scientists worldwide.

Prof. Dr. Verena Griess
Co-Principal Investigator
ETH Zurich
Head of the Forest Resources Management group at ETH Zurich, where her research focuses on sustainable forest management, forest economics, and ecosystem governance. She provides scientific oversight and strategic direction for the TreeAI initiative.

Dr. Martin Mokros
Co-Principal Investigator
University College London
Lecturer in Earth Observation at UCL, specialising in close-range 3D remote sensing of trees using terrestrial laser scanners, drones, and photogrammetry. He co-conceived the TreeAI initiative with Mirela and continues to guide its scientific direction.
Partners
ETH Zurich
Switzerland
WSL Swiss Federal Institute for Forest, Snow and Landscape Research
Switzerland
Wuhan University
China
University College London
United Kingdom
Norwegian Institute of Bioeconomy Research (NIBIO)
Norway
University of Freiburg
Germany
University of Leipzig
Germany
University of Copenhagen
Denmark
Collaborate
Interested in contributing but not yet ready to submit a dataset? We welcome early conversations about eligibility, data format, or collaboration.
Ready to contribute a dataset?
Go to Submit PageCommunity
Research groups and individuals who have contributed annotated datasets to the initiative.
| Surname | First Name | Institute | Country | Research Area |
|---|