Deep Learning Model Transfer in Forest Mapping Using Multi-Source Satellite SAR and Optical Images

• Published in: Remote Sensing
• Main Authors: Shaojia Ge, Oleg Antropov, Tuomas Häme, Ronald E. McRoberts, Jukka Miettinen
• Format: Article in Journal/Newspaper
• Language: English
• Published: MDPI AG 2023
• Subjects: vegetation mapping; deep learning; UNet; synthetic aperture radar; forest height; interferometry; Science; Q; taiga; Lapland
• Online Access: https://doi.org/10.3390/rs15215152; https://doaj.org/article/6da10adb37b442adb1024198d3c16255

Deep learning (DL) models are gaining popularity in forest variable prediction using Earth observation (EO) images. However, in practical forest inventories, reference datasets are often represented by plot- or stand-level measurements, while high-quality representative wall-to-wall reference data for end-to-end training of DL models are rarely available. Transfer learning facilitates expansion of the use of deep learning models into areas with sub-optimal training data by allowing pretraining of the model in areas where high-quality teaching data are available. In this study, we perform a “model transfer” (or domain adaptation) of a pretrained DL model into a target area using plot-level measurements and compare performance versus other machine learning models. We use an earlier developed UNet based model (SeUNet) to demonstrate the approach on two distinct taiga sites with varying forest structure and composition. The examined SeUNet model uses multi-source EO data to predict forest height. Here, EO data are represented by a combination of Copernicus Sentinel-1 C-band SAR and Sentinel-2 multispectral images, ALOS-2 PALSAR-2 SAR mosaics and TanDEM-X bistatic interferometric radar data. The training study site is located in Finnish Lapland, while the target site is located in Southern Finland. By leveraging transfer learning, the SeUNet prediction achieved root mean squared error (RMSE) of <semantics> 2.70 </semantics> m and R 2 of 0.882, considerably more accurate than traditional benchmark methods. We expect such forest-specific DL model transfer can be suitable also for other forest variables and other EO data sources that are sensitive to forest structure.