aalto1 untyped-item.component.html

Improved LSTM Model for Boreal Forest Height Mapping Using Sentinel-1 Time Series

Loading...
Thumbnail Image

Access rights

openAccess
publishedVersion

URL

Journal Title

Journal ISSN

Volume Title

A1 Alkuperäisartikkeli tieteellisessä aikakauslehdessä

Major/Subject

Mcode

Degree programme

Language

en

Pages

20

Series

Remote Sensing, Volume 14, issue 21

Abstract

Time series of SAR imagery combined with reference ground data can be suitable for producing forest inventories. Copernicus Sentinel-1 imagery is particularly interesting for forest mapping because of its free availability to data users; however, temporal dependencies within SAR time series that can potentially improve mapping accuracy are rarely explored. In this study, we introduce a novel semi-supervised Long Short-Term Memory (LSTM) model, CrsHelix-LSTM, and demonstrate its utility for predicting forest tree height using time series of Sentinel-1 images. The model brings three important modifications to the conventional LSTM model. Firstly, it uses a Helix-Elapse (HE) projection to capture the relationship between forest temporal patterns and Sentinel-1 time series, when time intervals between datatakes are irregular. A skip-link based LSTM block is introduced and a novel backbone network, Helix-LSTM, is proposed to retrieve temporal features at different receptive scales. Finally, a novel semisupervised strategy, Cross-Pseudo Regression, is employed to achieve better model performance when reference training data are limited. CrsHelix-LSTM model is demonstrated over a representative boreal forest site located in Central Finland. A time series of 96 Sentinel-1 images are used in the study. The developed model is compared with basic LSTM model, attention-based bidirectional LSTM and several other established regression approaches used in forest variable mapping, demonstrating consistent improvement of forest height prediction accuracy. At best, the achieved accuracy of forest height mapping was 28.3% relative root mean squared error (rRMSE) for pixel-level predictions and 18.0% rRMSE on stand level. We expect that the developed model can also be used for modeling relationships between other forest variables and satellite image time series.

Description

Funding Information: This study was supported by the National Natural Science Foundation of China (Grant No. 62001229, 62101264, 62101260) and by China Postdoctoral Science Foundation (Grant No. 2020M681604). O.A. was supported by Multico project funded by Business Finland and Forest Carbon Monitoring project funded by European Space Agency. Publisher Copyright: © 2022 by the authors.

Other note

Citation

Ge, S, Su, W, Gu, H, Rauste, Y, Praks, J & Antropov, O 2022, 'Improved LSTM Model for Boreal Forest Height Mapping Using Sentinel-1 Time Series', Remote Sensing, vol. 14, no. 21, 5560. https://doi.org/10.3390/rs14215560

Endorsement

Review

Supplemented By

Referenced By