Capturing Temporal Dynamics in Large-Scale Canopy Tree Height Estimation

2025-01-31

AI Summary

To address the need for large-scale, dynamic monitoring of forest canopy height (CH), this study proposes a novel paradigm integrating multi-temporal optical remote sensing with airborne LiDAR–guided supervised learning. Leveraging Sentinel-2 time-series imagery (10 m resolution) and GEDI full-waveform LiDAR-derived ground-truth CH data, we develop a CNN-LSTM hybrid deep learning model deployed on Google Earth Engine to generate annual continental-scale CH maps across Europe for 2019–2022. This work delivers the first pan-European, four-year continuous, 10 m resolution CH time-series atlas. Validation shows the 2020 product achieves significantly higher accuracy than state-of-the-art methods, reducing RMSE by 18.3%. All datasets and source code are publicly released, providing a high spatiotemporal resolution foundational product and a fully reproducible technical framework for global forest carbon stock estimation, ecological change analysis, and long-term dynamic monitoring.

Technology Category

• Computer Vision: Remote Sensing / Geospatial AI
• Machine Learning: Life-Long and Continual Learning
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

With the rise in global greenhouse gas emissions, accurate large-scale tree canopy height maps are essential for understanding forest structure, estimating above-ground biomass, and monitoring ecological disruptions. To this end, we present a novel approach to generate large-scale, high-resolution canopy height maps over time. Our model accurately predicts canopy height over multiple years given Sentinel-2 time series satellite data. Using GEDI LiDAR data as the ground truth for training the model, we present the first 10m resolution temporal canopy height map of the European continent for the period 2019-2022. As part of this product, we also offer a detailed canopy height map for 2020, providing more precise estimates than previous studies. Our pipeline and the resulting temporal height map are publicly available, enabling comprehensive large-scale monitoring of forests and, hence, facilitating future research and ecological analyses. For an interactive viewer, see https://europetreemap.projects.earthengine.app/view/temporalcanopyheight.

Problem

• Forest Inventory
• Tree Height Estimation
• Carbon Cycling

Innovation

• Sentinel-2 data
• GEDI LiDAR technology
• Temporal canopy height maps