Improved semi-supervised UNet deep learning model for forest height mapping with satellite SAR and optical data
Loading...
Access rights
openAccess
publishedVersion
URL
Journal Title
Journal ISSN
Volume Title
A1 Alkuperäisartikkeli tieteellisessä aikakauslehdessä
This publication is imported from Aalto University research portal.
View publication in the Research portal (opens in new window)
View/Open full text file from the Research portal (opens in new window)
Other link related to publication (opens in new window)
View publication in the Research portal (opens in new window)
View/Open full text file from the Research portal (opens in new window)
Other link related to publication (opens in new window)
Date
2022
Major/Subject
Mcode
Degree programme
Language
en
Pages
12
Series
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, Volume 15, pp. 5776-5787
Abstract
In this study, we introduce an improved semisupervised deep learning approach, and demonstrate its suitability for modeling the relationship between forest structural parameters and satellite remote sensing imagery and producing forest maps. The improved approach is based on a popular UNet model, modified and fine-tuned to improve the forest parameter prediction performance. Within the improved model, squeeze-and-excitation blocks are embedded to recalibrate the multisource features via retrieved channel-wise self-attention and a novel cross-pseudo regression strategy is implemented to train the model in a semisupervised way. The improvement imposes consistency learning on two perturbed network branches: 1) generating regression pseudo-reference; 2) expanding the dataset size. For demonstration, we used satellite synthetic aperture radar (SAR) Sentinel-1 and multispectral optical Sentinel-2 images as remote sensing data, complemented with reference data represented by forest tree height as one of the key forest structural variables. The study area is located in a boreal forestland in Central Finland. Proposed approach showed larger accuracy compared to traditional machine learning methods such as random forests and boosting trees, and baseline UNet model. Best accuracy figures for forest tree height were achieved with combined SAR and optical imagery and were as small as 24.1% root-mean-square error (RMSE) on pixel-level and 15.4% RMSE on forest stand level.Description
Lataa julkaisu, kun saatavilla.
Keywords
Biomedical optical imaging, Data models, deep learning, Forestry, Optical imaging, Optical sensors, regression, Satellites, semi-supervised, Sentinel-1, Sentinel-2, synthetic aperture radar, Synthetic aperture radar, UNet
Other note
Citation
Ge, S, Gu, H, Su, W, Praks, J & Antropov, O 2022, ' Improved semi-supervised UNet deep learning model for forest height mapping with satellite SAR and optical data ', IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, vol. 15, pp. 5776-5787 . https://doi.org/10.1109/JSTARS.2022.3188201