TY - GEN

T1 - Estimating Forest Canopy Height with Multi-Spectral and Multi-Temporal Imagery Using Deep Learning

AU - Oehmcke, Stefan

AU - Nyegaard-Signori, Thomas

AU - Grogan, Kenneth

AU - Gieseke, Fabian

N1 - Publisher Copyright: © 2021 IEEE.

PY - 2021

Y1 - 2021

N2 - 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.

AB - 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.

KW - Canopy Height Prediction

KW - ICESat-2

KW - Landsat

KW - Neural Networks

KW - Spatio-Temporal Data

U2 - 10.1109/BigData52589.2021.9672018

DO - 10.1109/BigData52589.2021.9672018

M3 - Article in proceedings

AN - SCOPUS:85125292283

SP - 4915

EP - 4924

BT - Proceedings - 2021 IEEE International Conference on Big Data, Big Data 2021

A2 - Chen, Yixin

A2 - Ludwig, Heiko

A2 - Tu, Yicheng

A2 - Fayyad, Usama

A2 - Zhu, Xingquan

A2 - Hu, Xiaohua Tony

A2 - Byna, Suren

A2 - Liu, Xiong

A2 - Zhang, Jianping

A2 - Pan, Shirui

A2 - Papalexakis, Vagelis

A2 - Wang, Jianwu

A2 - Cuzzocrea, Alfredo

A2 - Ordonez, Carlos

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2021 IEEE International Conference on Big Data, Big Data 2021

Y2 - 15 December 2021 through 18 December 2021

ER -