Next Article in Journal
Risk Assessment of Potential Food Chain Threats from Edible Wild Mushrooms Collected in Forest Ecosystems with Heavy Metal Pollution in Upper Silesia, Poland
Previous Article in Journal
An Assessment of the Spatial Variability of Tropical Swamp Forest along a 300 km Long Transect in the Usumacinta River Basin, Mexico
Article

A Deep Learning Approach for Calamity Assessment Using Sentinel-2 Data

1
Esri Deutschland, Department Science and Education, Ringstr. 7, 85402 Kranzberg, Germany
2
Department of Forestry, Weihenstephan-Triesdorf University of Applied Science, Hans-Carl-von-Carlowitz-Platz 3, 85354 Freising, Germany
3
HessenForst, Europastraße 10-12, 35394 Gießen, Germany
*
Author to whom correspondence should be addressed.
Forests 2020, 11(12), 1239; https://doi.org/10.3390/f11121239
Received: 23 October 2020 / Revised: 9 November 2020 / Accepted: 20 November 2020 / Published: 24 November 2020
(This article belongs to the Section Forest Inventory, Modeling and Remote Sensing)
The number of severe storm events has increased in recent decades due to climate change. These storms are one of the main causes for timber loss in European forests and damaged areas are prone to further degradation by, for example, bark beetle infestations. Usually, manual mapping of damaged areas based on aerial photographs is conducted by forest departments. This is very time-consuming and therefore automatic detection of windthrows based on active and passive remote sensing data is an ongoing research topic. In this study we evaluated state-of-the-art Convolutional Neural Networks (CNNs) in combination with Geographic Information Systems (GIS) for calamity assessment. The study area is in in the northern part of Hesse (Germany) and was covered by twelve Sentinel-2 scenes from 2018. Labels of damaged areas from the Friedericke storm (18 January 2018) were provided by HessenForst. We conducted several experiments based on a custom U-Net setup to derive the optimal architecture and input data as well as to assess the transferability of the model. Results highlight the possibility to detect damaged forest areas using Sentinel-2 data. Using a binary classification, accuracies of more than 92% were achieved with an Intersection over Union (IoU) score of 46.6%. The proposed workflow was integrated into ArcGIS and is suitable for fast detection of damaged areas directly after a storm and for disaster management but is limited by the deca-meter spatial resolution of the Sentinel-2 data. View Full-Text
Keywords: CNNs; remote sensing; windthrow; forest; Deep Learning; GIS CNNs; remote sensing; windthrow; forest; Deep Learning; GIS
Show Figures

Figure 1

MDPI and ACS Style

Scharvogel, D.; Brandmeier, M.; Weis, M. A Deep Learning Approach for Calamity Assessment Using Sentinel-2 Data. Forests 2020, 11, 1239. https://doi.org/10.3390/f11121239

AMA Style

Scharvogel D, Brandmeier M, Weis M. A Deep Learning Approach for Calamity Assessment Using Sentinel-2 Data. Forests. 2020; 11(12):1239. https://doi.org/10.3390/f11121239

Chicago/Turabian Style

Scharvogel, Daniel, Melanie Brandmeier, and Manuel Weis. 2020. "A Deep Learning Approach for Calamity Assessment Using Sentinel-2 Data" Forests 11, no. 12: 1239. https://doi.org/10.3390/f11121239

Find Other Styles
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Back to TopTop