DLR-Logo -> http://www.dlr.de
DLR Portal Home | Imprint | Privacy Policy | Contact | Deutsch
Fontsize: [-] Text [+]

Transfer learning of U-Net convolutional networks for TanDEM-X forest/non-forest mapping at large scales

Kukunda, Collins and Erasmi, Stefan and Wessel, Birgit and Schlund, Michael (2019) Transfer learning of U-Net convolutional networks for TanDEM-X forest/non-forest mapping at large scales. TerraSAR-X / TanDEM-X Science Team Meeting 2019, 21.-24. Okt. 2019, DLR Oberpfaffenhofen, Germany.

Full text not available from this repository.


Accurate mapping of forest/non-forest areas supports monitoring, verification and reporting on forest resources. The potential of TanDEM-X coherence (due to volume decorrelation) to distinguish between forest and non-forest classes has been recognized. Growing literature shows that deep learning classifiers are able to automatically learn relevant features in image data and mostly outperform traditional classifiers at image classification tasks. This study assesses the potential of U-Net convolutional networks for TanDEM-X forest/non-forest classification and their transferability in time and space. Trained U-Net convolutional networks are used to discriminate forest/non-forest classes with TanDEM-X data and their potential to transfer on TanDEM-X data collected at different time steps and from different geographical areas is evaluated. First, we trained the networks on 50% of reference TanDEM-X images and evaluated their learning rate and prediction power using the remaining 50% of reference images. Second, transfer of the networks across time as well as geographical area was done after evaluating environmental similarity between the reference and transfer TanDEM-X images using Mahalanobis distances. Finally, model performance was assessed using, overall accuracy (OA) and Area Under Curve (AUC), considering complete transfer scenarios as well as transfer with augmentation training; in which additional training of the networks with parts of transfer images was done. Preliminary results show that the networks classify forest/non-forest areas in reference images with high accuracy in German temperate forests (OA>0.95, AUC > 0.92). We expect that transfer of the networks across time will have marginal influence on model performance compared to transfer of the networks across geographic areas. In general, lower environmental similarity may result in bigger losses in model performance. However, marginal augmentation training (e.g. up to 20% of transfer images) may boost model performance back to the model performance achieved with reference images. This work demonstrates how deep learning algorithms can support applications in forest resource and disturbance mapping at regional to global scales using TanDEM-X data.

Item URL in elib:https://elib.dlr.de/129955/
Document Type:Conference or Workshop Item (Poster)
Title:Transfer learning of U-Net convolutional networks for TanDEM-X forest/non-forest mapping at large scales
AuthorsInstitution or Email of AuthorsAuthor's ORCID iDORCID Put Code
Kukunda, CollinsUniversität GöttingenUNSPECIFIEDUNSPECIFIED
Erasmi, StefanUniversität GöttingenUNSPECIFIEDUNSPECIFIED
Wessel, BirgitUNSPECIFIEDhttps://orcid.org/0000-0002-8673-2485UNSPECIFIED
Schlund, MichaelUniversität GöttingenUNSPECIFIEDUNSPECIFIED
Refereed publication:No
Open Access:No
Gold Open Access:No
In ISI Web of Science:No
Keywords:TanDEM-X, InSAR, cnn, forest
Event Title:TerraSAR-X / TanDEM-X Science Team Meeting 2019
Event Location:DLR Oberpfaffenhofen, Germany
Event Type:international Conference
Event Dates:21.-24. Okt. 2019
Organizer:DLR Oberpfaffenhofen
HGF - Research field:Aeronautics, Space and Transport
HGF - Program:Space
HGF - Program Themes:Earth Observation
DLR - Research area:Raumfahrt
DLR - Program:R EO - Earth Observation
DLR - Research theme (Project):R - TSX/TDX Payload Ground Segment
Location: Oberpfaffenhofen
Institutes and Institutions:German Remote Sensing Data Center > Land Surface Dynamics
Deposited By: Wessel, Dr.-Ing. Birgit
Deposited On:05 Nov 2019 12:04
Last Modified:05 Nov 2019 12:04

Repository Staff Only: item control page

Help & Contact
electronic library is running on EPrints 3.3.12
Website and database design: Copyright © German Aerospace Center (DLR). All rights reserved.