Next Article in Journal
Supervised and Semi-Supervised Self-Organizing Maps for Regression and Classification Focusing on Hyperspectral Data
Next Article in Special Issue
Mapping Forested Wetland Inundation in the Delmarva Peninsula, USA Using Deep Convolutional Neural Networks
Previous Article in Journal
Combination of AIRS Dual CO2 Absorption Bands to Develop an Ice Clouds Detection Algorithm in Different Atmospheric Layers
Open AccessArticle

Comparing Deep Learning and Shallow Learning for Large-Scale Wetland Classification in Alberta, Canada

1
Alberta Biodiversity Monitoring Institute, University of Alberta, Edmonton, AB T6G 2E9, Canada
2
Independent Researcher, Revelstoke, BC 2773, Canada
3
C-CORE and Department of Electrical Engineering, Memorial University of Newfoundland, St. John’s, NL A1B 3X5, Canada
4
Canada Centre for Mapping and Earth Observation, Natural Resources Canada, 560 Rochester Street, Ottawa, ON K1A 0Y7, Canada
5
Alberta Environment and Parks, Government of Alberta, 200 5 Ave S, Lethbridge, AB T1J 4L1, Canada
*
Author to whom correspondence should be addressed.
Remote Sens. 2020, 12(1), 2; https://doi.org/10.3390/rs12010002
Received: 31 October 2019 / Revised: 9 December 2019 / Accepted: 11 December 2019 / Published: 18 December 2019
(This article belongs to the Special Issue Wetland Landscape Change Mapping Using Remote Sensing)
Advances in machine learning have changed many fields of study and it has also drawn attention in a variety of remote sensing applications. In particular, deep convolutional neural networks (CNNs) have proven very useful in fields such as image recognition; however, the use of CNNs in large-scale remote sensing landcover classifications still needs further investigation. We set out to test CNN-based landcover classification against a more conventional XGBoost shallow learning algorithm for mapping a notoriously difficult group of landcover classes, wetland class as defined by the Canadian Wetland Classification System. We developed two wetland inventory style products for a large (397,958 km2) area in the Boreal Forest region of Alberta, Canada, using Sentinel-1, Sentinel-2, and ALOS DEM data acquired in Google Earth Engine. We then tested the accuracy of these two products against three validation data sets (two photo-interpreted and one field). The CNN-generated wetland product proved to be more accurate than the shallow learning XGBoost wetland product by 5%. The overall accuracy of the CNN product was 80.2% with a mean F1-score of 0.58. We believe that CNNs are better able to capture natural complexities within wetland classes, and thus may be very useful for complex landcover classifications. Overall, this CNN framework shows great promise for generating large-scale wetland inventory data and may prove useful for other landcover mapping applications. View Full-Text
Keywords: wetlands; Sentinel-1; Sentinel-2; Google Earth Engine; remote sensing; Alberta; segmentation convolutional neural nets; XGBoost; land cover; SAR; machine learning wetlands; Sentinel-1; Sentinel-2; Google Earth Engine; remote sensing; Alberta; segmentation convolutional neural nets; XGBoost; land cover; SAR; machine learning
Show Figures

Graphical abstract

MDPI and ACS Style

DeLancey, E.R.; Simms, J.F.; Mahdianpari, M.; Brisco, B.; Mahoney, C.; Kariyeva, J. Comparing Deep Learning and Shallow Learning for Large-Scale Wetland Classification in Alberta, Canada. Remote Sens. 2020, 12, 2. https://doi.org/10.3390/rs12010002

AMA Style

DeLancey ER, Simms JF, Mahdianpari M, Brisco B, Mahoney C, Kariyeva J. Comparing Deep Learning and Shallow Learning for Large-Scale Wetland Classification in Alberta, Canada. Remote Sensing. 2020; 12(1):2. https://doi.org/10.3390/rs12010002

Chicago/Turabian Style

DeLancey, Evan R.; Simms, John F.; Mahdianpari, Masoud; Brisco, Brian; Mahoney, Craig; Kariyeva, Jahan. 2020. "Comparing Deep Learning and Shallow Learning for Large-Scale Wetland Classification in Alberta, Canada" Remote Sens. 12, no. 1: 2. https://doi.org/10.3390/rs12010002

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