High Resolution Tree Height Mapping of the Amazon Forest using Planet NICFI Images and LiDAR-Informed U-Net Model

2025-01-17

AI Summary

To address saturation in tall forests (>40–50 m), large systematic biases, and insufficient temporal monitoring in existing remote sensing-based canopy height estimation over the Amazon, this study introduces the first LiDAR-calibrated regression U-Net model applied to high-resolution Planet NICFI optical imagery (~4.78 m). The model enables continuous annual canopy height mapping from 2020 to 2024. Key innovations include architectural modifications for regression tasks, integration of multi-temporal optical features, spatial error correction, and rigorous generalization assessment—collectively overcoming saturation limitations of conventional products. Validation yields a root mean square error (RMSE) of 3.68 m against independent LiDAR validation data; the estimated regional mean canopy height is ~22 m. The method accurately captures fine-scale height dynamics associated with selective logging, deforestation, and forest regeneration—demonstrating substantially improved performance over current global canopy height products.

Technology Category

• Machine Learning: Calibration & Uncertainty Quantification
• Computer Vision: Remote Sensing / Geospatial AI
• Reasoning under Uncertainty: Graphical Models

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Economics, Online Markets and Human Computation: LLM based quality controls for crowd work
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs

Abstract

Tree canopy height is one of the most important indicators of forest biomass, productivity, and ecosystem structure, but it is challenging to measure accurately from the ground and from space. Here, we used a U-Net model adapted for regression to map the mean tree canopy height in the Amazon forest from Planet NICFI images at ~4.78 m spatial resolution for the period 2020-2024. The U-Net model was trained using canopy height models computed from aerial LiDAR data as a reference, along with their corresponding Planet NICFI images. Predictions of tree heights on the validation sample exhibited a mean error of 3.68 m and showed relatively low systematic bias across the entire range of tree heights present in the Amazon forest. Our model successfully estimated canopy heights up to 40-50 m without much saturation, outperforming existing canopy height products from global models in this region. We determined that the Amazon forest has an average canopy height of ~22 m. Events such as logging or deforestation could be detected from changes in tree height, and encouraging results were obtained to monitor the height of regenerating forests. These findings demonstrate the potential for large-scale mapping and monitoring of tree height for old and regenerating Amazon forests using Planet NICFI imagery.

Problem

• Amazon forest
• tree height measurement
• forest health assessment

Innovation

• U-Net model
• Amazon forest tree height measurement
• Environmental monitoring