SatCHM (Satellite Canopy Height Model): Leveraging deep learning for site-specific sub-meter canopy height predictions

Abstract

High-resolution monitoring of forest structure and productivity is essential for effective natural resource management. However, monitoring approaches such as field-based forest inventories or extensive lidar campaigns are costly, time-intensive, and spatially limited. Therefore, inexpensive and accessible methods are needed. SatCHM (Satellite Canopy Height Model) was developed to be an accessible and open-source tool for researchers, allowing for site-specific and temporally flexible predictions of canopy height with limited computational resources. SatCHM requires four inputs: panchromatic satellite imagery, solar and sensor angle metadata of satellite imagery, digital elevation models (DEMs), and lidar-produced CHMs for an area of interest. After SatCHM pre-processes inputs, data is loaded into a collection of convolutional neural networks (CNNs) for image-to-image regression. This ensemble cooperates to yield high-resolution predictions (up to 0.5-meter) of three-dimensional tree structure with discernible tree crowns across a broader defined area of interest. After calculating the mean absolute error for each prediction output, the median of these mean absolute errors was 6.06 meters.

Plant phenotyping relevance

森林キャノピー高と樹冠構造という植物形質を衛星画像等から推定するオープンソース手法を開発し、CNNによる推定と誤差評価まで行っており、植物フェノタイピング手法が研究の中心である。

Code and data availability

The paper describes open-sourcing the SatCHM code ('Publishing this code enables researchers...' and 'This work aims to open source an improved version of the code'), but no authors' public URL or repository identifier for the SatCHM code, data, or trained models appears in the supplied blocks. The only GitHub URL (gea

No evidence-backed public reproduction asset is currently recorded.