Next Article in Journal
Cross-Validation of Radio-Frequency-Interference Signature in Satellite Microwave Radiometer Observations over the Ocean
Previous Article in Journal
Accuracy Evaluation of Four Greenland Digital Elevation Models (DEMs) and Assessment of River Network Extraction
Previous Article in Special Issue
Bathymetric Inversion and Uncertainty Estimation from Synthetic Surf-Zone Imagery with Machine Learning
Open AccessTechnical Note

Detection of Invasive Species in Wetlands: Practical DL with Heavily Imbalanced Data

1
Brain and Mind Centre, University of Sydney, Sydney 2006, Australia
2
Faculty of Agriculture, Yamagata University, Tsuruoka 997-8555, Japan
3
Institute of Physical Geography and Landscape Ecology, Leibniz University, 30167 Hannover, Germany
4
Faculty of Science, Yamagata University, Yamagata 990-9585, Japan
*
Author to whom correspondence should be addressed.
Remote Sens. 2020, 12(20), 3431; https://doi.org/10.3390/rs12203431
Received: 23 September 2020 / Revised: 12 October 2020 / Accepted: 14 October 2020 / Published: 19 October 2020
(This article belongs to the Special Issue Computer Vision and Deep Learning for Remote Sensing Applications)
Deep Learning (DL) has become popular due to its ease of use and accuracy, with Transfer Learning (TL) effectively reducing the number of images needed to solve environmental problems. However, this approach has some limitations which we set out to explore: Our goal is to detect the presence of an invasive blueberry species in aerial images of wetlands. This is a key problem in ecosystem protection which is also challenging in terms of DL due to the severe imbalance present in the data. Results for the ResNet50 network show a high classification accuracy while largely ignoring the blueberry class, rendering these results of limited practical interest to detect that specific class. Moreover, by using loss function weighting and data augmentation results more akin to our practical application, our goals can be obtained. Our experiments regarding TL show that ImageNet weights do not produce satisfactory results when only the final layer of the network is trained. Furthermore, only minor gains are obtained compared with random weights when the whole network is retrained. Finally, in a study of state-of-the-art DL architectures best results were obtained by the ResNeXt architecture with 93.75 True Positive Rate and 98.11 accuracy for the Blueberry class with ResNet50, Densenet, and wideResNet obtaining close results. View Full-Text
Keywords: unmanned aerial vehicles (UAV)-acquired images; unbalanced data; transfer learning; deep learning; data analysis unmanned aerial vehicles (UAV)-acquired images; unbalanced data; transfer learning; deep learning; data analysis
Show Figures

Graphical abstract

MDPI and ACS Style

Cabezas, M.; Kentsch, S.; Tomhave, L.; Gross, J.; Caceres, M.L.L.; Diez, Y. Detection of Invasive Species in Wetlands: Practical DL with Heavily Imbalanced Data. Remote Sens. 2020, 12, 3431.

Show more citation formats Show less citations formats
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