Publications

High-resolution sensors and deep learning models for tree resource monitoring

​

Nature Reviews Electrical Engineering, 2025

​

We summarized our experiences gained over the past years.

A strong but uneven increase in urban tree cover in China over the recent decade

​

Nature Cities, 2025

​

We used RapidEye and PlanetScope to study tree cover changes over hundreds of cities in China over 2010-2019.

Severe decline in large farmland trees in India over recent decade

​

Nature Sustainability, 2024

​

We tracked 0.6 billion large trees from 2010 to 2022 and found that many disappeared.

Forest classification

________________________________

Tree detection confidence is classified into contiguous forests, trees outside forests, and forest gaps. Can also be used as binary tree/no-tree mask.

Forest classification

________________________________

Tree detection confidence is classified into contiguous forests, trees outside forests, and forest gaps. Can also be used as binary tree/no-tree mask.

Forest classification

________________________________

Tree detection confidence is classified into contiguous forests, trees outside forests, and forest gaps. Can also be used as binary tree/no-tree mask.

Forest classification

________________________________

Tree detection confidence is classified into contiguous forests, trees outside forests, and forest gaps. Can also be used as binary tree/no-tree mask.

Forest classification

________________________________

Tree detection confidence is classified into contiguous forests, trees outside forests, and forest gaps. Can also be used as binary tree/no-tree mask.