Estimating Forest Canopy Height with Multi-Spectral and Multi-Temporal Imagery Using Deep Learning

Publikation: Bidrag til bog/antologi/rapportKonferencebidrag i proceedingsForskningfagfællebedømt

Canopy height is a vital indicator to asses carbon uptake and productivity of forests. However, precise measurements, such as from airborne or spaceborne 3D laser scanning (LiDAR), are expensive and usually cover only small areas. In this work, we propose a novel deep learning model that can generate detailed maps of tree canopy heights. In contrast to previous approaches that use a single image as input, we process multi-temporal data via a an adaptation of the popular U-Net architecture that is based on the EfficientNet and 3D convolution operators. To that end, our model receives multi-spectral Landsat satellite imagery as input and can predict continuous height maps. As labeled data, we resort to spatially sparse LiDAR data from ICESat-2. Thus, with such a model, one can produce dense canopy height maps given only multi-spectral Landsat data. Our experimental evaluation shows that our our model outperforms existing and improved single-temporal models. To test generalizability, we created a non-overlapping dataset to evaluate our approach and further tested the model performance on out-of-distribution data. The results show that our model can successfully learn drastic changes in distribution.

TitelProceedings - 2021 IEEE International Conference on Big Data, Big Data 2021
RedaktørerYixin Chen, Heiko Ludwig, Yicheng Tu, Usama Fayyad, Xingquan Zhu, Xiaohua Tony Hu, Suren Byna, Xiong Liu, Jianping Zhang, Shirui Pan, Vagelis Papalexakis, Jianwu Wang, Alfredo Cuzzocrea, Carlos Ordonez
Antal sider10
ForlagInstitute of Electrical and Electronics Engineers Inc.
ISBN (Elektronisk)9781665439022
StatusUdgivet - 2021
Begivenhed2021 IEEE International Conference on Big Data, Big Data 2021 - Virtual, Online, USA
Varighed: 15 dec. 202118 dec. 2021


Konference2021 IEEE International Conference on Big Data, Big Data 2021
ByVirtual, Online
SponsorAnkura Collaboration Drives Results, IEEE, IEEE Computer Society, Lyve Cloud, NSF, Seagate

Bibliografisk note

Funding Information:
ACKNOWLEDGEMENT Fabian Gieseke and Stefan Oehmcke would like to acknowledge support from the Independent Research Fund Denmark (DFF) through the grant Monitoring Changes in Big Satellite Data via Massively-Parallel Artificial Intelligence (9131-00110B). Stefan Oehmcke and Fabian Gieseke also acknowledge support by the Villum Foundation through the project Deep Learning and Remote Sensing for Unlocking Global Ecosystem Resource Dynamics (DeReEco).

Publisher Copyright:
© 2021 IEEE.

ID: 306680480