Next Article in Journal
Using Heterogeneous Satellites for Passive Detection of Moving Aerial Target
Next Article in Special Issue
Landsat-Based Indices Reveal Consistent Recovery of Forested Stream Catchments from Acid Deposition
Previous Article in Journal
Generative Adversarial Networks Based on Collaborative Learning and Attention Mechanism for Hyperspectral Image Classification
Previous Article in Special Issue
Landscape Representation by a Permanent Forest Plot and Alternative Plot Designs in a Typhoon Hotspot, Fushan, Taiwan
Open AccessArticle

Automatic Windthrow Detection Using Very-High-Resolution Satellite Imagery and Deep Learning

Botanical Garden-Institute of the Far Eastern Branch of the Russian Academy of Science, Makovskogo St. 142, 690024 Vladivostok, Russia
*
Author to whom correspondence should be addressed.
Remote Sens. 2020, 12(7), 1145; https://doi.org/10.3390/rs12071145
Received: 29 February 2020 / Revised: 26 March 2020 / Accepted: 1 April 2020 / Published: 3 April 2020
(This article belongs to the Special Issue Remote Sensing of Natural Forest Disturbances)
Wind disturbances are significant phenomena in forest spatial structure and succession dynamics. They cause changes in biodiversity, impact on forest ecosystems at different spatial scales, and have a strong influence on economics and human beings. The reliable recognition and mapping of windthrow areas are of high importance from the perspective of forest management and nature conservation. Recent research in artificial intelligence and computer vision has demonstrated the incredible potential of neural networks in addressing image classification problems. The most efficient algorithms are based on artificial neural networks of nested and complex architecture (e.g., convolutional neural networks (CNNs)), which are usually referred to by a common term—deep learning. Deep learning provides powerful algorithms for the precise segmentation of remote sensing data. We developed an algorithm based on a U-Net-like CNN, which was trained to recognize windthrow areas in Kunashir Island, Russia. We used satellite imagery of very-high spatial resolution (0.5 m/pixel) as source data. We performed a grid search among 216 parameter combinations defining different U-Net-like architectures. The best parameter combination allowed us to achieve an overall accuracy for recognition of windthrow sites of up to 94% for forested landscapes by coniferous and mixed coniferous forests. We found that the false-positive decisions of our algorithm correspond to either seashore logs, which may look similar to fallen tree trunks, or leafless forest stands. While the former can be rectified by applying a forest mask, the latter requires the usage of additional information, which is not always provided by satellite imagery. View Full-Text
Keywords: convolutional neural network; deep learning; image segmentation; machine learning; forest disturbance; windthrow convolutional neural network; deep learning; image segmentation; machine learning; forest disturbance; windthrow
Show Figures

Graphical abstract

MDPI and ACS Style

Kislov, D.E.; Korznikov, K.A. Automatic Windthrow Detection Using Very-High-Resolution Satellite Imagery and Deep Learning. Remote Sens. 2020, 12, 1145. https://doi.org/10.3390/rs12071145

AMA Style

Kislov DE, Korznikov KA. Automatic Windthrow Detection Using Very-High-Resolution Satellite Imagery and Deep Learning. Remote Sensing. 2020; 12(7):1145. https://doi.org/10.3390/rs12071145

Chicago/Turabian Style

Kislov, Dmitry E.; Korznikov, Kirill A. 2020. "Automatic Windthrow Detection Using Very-High-Resolution Satellite Imagery and Deep Learning" Remote Sens. 12, no. 7: 1145. https://doi.org/10.3390/rs12071145

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
Search more from Scilit
 
Search
Back to TopTop