PrediTree: A Multi-Temporal Sub-meter Dataset of Multi-Spectral Imagery Aligned With Canopy Height Maps
This addresses a critical gap in forest monitoring for researchers and practitioners by enabling deep learning methods to predict tree growth, though it is incremental as it focuses on dataset creation and model adaptation.
The paper tackles the problem of predicting tree height from multi-temporal and multi-spectral imagery by introducing PrediTree, a comprehensive open-source dataset with 3,141,568 images aligned with LiDAR-derived canopy height maps, and shows that a U-Net model trained on it achieves a masked mean squared error of 11.78%, outperforming ResNet-50 by 12%.
We present PrediTree, the first comprehensive open-source dataset designed for training and evaluating tree height prediction models at sub-meter resolution. This dataset combines very high-resolution (0.5m) LiDAR-derived canopy height maps, spatially aligned with multi-temporal and multi-spectral imagery, across diverse forest ecosystems in France, totaling 3,141,568 images. PrediTree addresses a critical gap in forest monitoring capabilities by enabling the training of deep learning methods that can predict tree growth based on multiple past observations. To make use of this PrediTree dataset, we propose an encoder-decoder framework that requires the multi-temporal multi-spectral imagery and the relative time differences in years between the canopy height map timestamp (target) and each image acquisition date for which this framework predicts the canopy height. The conducted experiments demonstrate that a U-Net architecture trained on the PrediTree dataset provides the highest masked mean squared error of $11.78\%$, outperforming the next-best architecture, ResNet-50, by around $12\%$, and cutting the error of the same experiments but on fewer bands (red, green, blue only), by around $30\%$. This dataset is publicly available on https://huggingface.co/datasets/hiyam-d/PrediTree, and both processing and training codebases are available on {GitHub}.