Evaluation of the Landsat-Based Canadian Wetland Inventory Map Using Multiple Sources: Challenges of Large-Scale Wetland Classification Using Remote Sensing

被引:32
作者
Amani, Meisam [1 ]
Brisco, Brian [2 ]
Mahdavi, Sahel [1 ]
Ghorbanian, Arsalan [3 ]
Moghimi, Armin [3 ]
DeLancey, Evan R. [4 ]
Merchant, Michael [5 ]
Jahncke, Raymond [6 ]
Fedorchuk, Lee [7 ]
Mui, Amy [8 ]
Fisette, Thierry [9 ]
Kakooei, Mohammad [10 ]
Ahmadi, Seyed Ali [3 ]
Leblon, Brigitte [11 ]
LaRocque, Armand [11 ]
机构
[1] Wood Environm & Infrastruct Solut, Ottawa, ON K2E 7L5, Canada
[2] Canada Ctr Mapping & Earth Observat, Ottawa, ON K1A 0G1, Canada
[3] KN Toosi Univ Technol, Fac Geodesy & Geomat Engn, Dept Remote Sensing & Photogrammetry, Tehran 1969764499, Iran
[4] Univ Alberta, Alberta Biodivers Monitoring Inst, Edmonton, AB T6G 2E9, Canada
[5] Ducks Unlimited Canada, Natl Boreal Program, Surrey, BC V3W 0H6, Canada
[6] Nova Scotia Dept Lands & Forestry, Truro, NS B2N IG6, Canada
[7] Manitoba Agr & Resource Dev, Manitoba Forestry Branch, Winnipeg, MB R3J 3W3, Canada
[8] Dalhousie Univ, Dept Earth & Environm Sci, Halifax, NS NS B3H 4R2, Canada
[9] Agr & Agri Food Canada, Ottawa, ON K1A 0C5, Canada
[10] Babol Noshirvani Univ Technol, Dept Elect Engn, Babol 4714871167, Iran
[11] Univ New Brunswick, Fac Forestry & Environm Management, Fredericton, NB E3B 5A3, Canada
关键词
Wetlands; Remote sensing; Earth; Monitoring; Artificial satellites; Biodiversity; Synthetic aperture radar; Big data; Canada; Google Earth Engine; Landsat; remote sensing (RS); wetlands;
D O I
10.1109/JSTARS.2020.3036802
中图分类号
TM [电工技术]; TN [电子技术、通信技术];
学科分类号
0808 ; 0809 ;
摘要
The first Canadian wetland inventory (CWI) map, which was based on Landsat data, was produced in 2019 using the Google Earth Engine (GEE) big data processing platform. The proposed GEE-based method to create the preliminary CWI map proved to be a cost, time, and computationally efficient approach. Although the initial effort to produce the CWI map was valuable with a 71% overall accuracy (OA), there were several inevitable limitations (e.g., low-quality samples for the training and validation of the map). Therefore, it was important to comprehensively investigate those limitations and develop effective solutions to improve the accuracy of the Landsat-based CWI (L-CWI) map. Over the past year, the L-CWI map was shared with several governmental, academic, environmental nonprofit, and industrial organizations. Subsequently, valuable feedback was received on the accuracy of this product by comparing it with various in situ data, photo-interpreted reference samples, land cover/land use maps, and high-resolution aerial images. It was generally observed that the accuracy of the L-CWI map was lower relative to the other available products. For example, the average OA in four Canadian provinces using in situ data was 60%. Moreover, including reliable in situ data, using an object-based classification method, and adding more optical and synthetic aperture radar datasets were identified as the main practical solutions to improve the CWI map in the future. Finally, limitations and solutions discussed in this study are applicable to any large-scale wetland mapping using remote sensing methods, especially to CWI generation using optical satellite data in GEE.
引用
收藏
页码:32 / 52
页数:21
相关论文
共 42 条
[1]  
Amani M., 2018, P REAL TIM WAT QUAL
[2]   Google Earth Engine Cloud Computing Platform for Remote Sensing Big Data Applications: A Comprehensive Review [J].
Amani, Meisam ;
Ghorbanian, Arsalan ;
Ahmadi, Seyed Ali ;
Kakooei, Mohammad ;
Moghimi, Armin ;
Mirmazloumi, S. Mohammad ;
Moghaddam, Sayyed Hamed Alizadeh ;
Mahdavi, Sahel ;
Ghahremanloo, Masoud ;
Parsian, Saeid ;
Wu, Qiusheng ;
Brisco, Brian .
IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING, 2020, 13 :5326-5350
[3]   Supervised wetland classification using high spatial resolution optical, SAR, and LiDAR imagery [J].
Amani, Meisam ;
Mandavi, Sahel ;
Berard, Olivier .
JOURNAL OF APPLIED REMOTE SENSING, 2020, 14 (02)
[4]   A generalized supervised classification scheme to produce provincial wetland inventory maps: an application of Google Earth Engine for big geo data processing [J].
Amani, Meisam ;
Brisco, Brian ;
Afshar, Majid ;
Mirmazloumi, S. Mohammad ;
Mahdavi, Sahel ;
Mirzadeh, Sayyed Mohammad Javad ;
Huang, Weimin ;
Granger, Jean .
BIG EARTH DATA, 2019, 3 (04) :378-394
[5]   Separability analysis of wetlands in Canada using multi-source SAR data [J].
Amani, Meisam ;
Salehi, Bahram ;
Mandavi, Sahel ;
Brisco, Brian .
GISCIENCE & REMOTE SENSING, 2019, 56 (08) :1233-1260
[6]   Canadian Wetland Inventory using Google Earth Engine: The First Map and Preliminary Results [J].
Amani, Meisam ;
Mahdavi, Sahel ;
Afshar, Majid ;
Brisco, Brian ;
Huang, Weimin ;
Mirzadeh, Sayyed Mohammad Javad ;
White, Lori ;
Banks, Sarah ;
Montgomery, Joshua ;
Hopkinson, Christopher .
REMOTE SENSING, 2019, 11 (07)
[7]   A Multiple Classifier System to improve mapping complex land covers: a case study of wetland classification using SAR data in Newfoundland, Canada [J].
Amani, Meisam ;
Salehi, Bahram ;
Mahdavi, Sahel ;
Brisco, Brian ;
Shehata, Mohamed .
INTERNATIONAL JOURNAL OF REMOTE SENSING, 2018, 39 (21) :7370-7383
[8]   Spectral analysis of wetlands using multi-source optical satellite imagery [J].
Amani, Meisam ;
Salehi, Bahram ;
Mandavi, Sahel ;
Brisco, Brian .
ISPRS JOURNAL OF PHOTOGRAMMETRY AND REMOTE SENSING, 2018, 144 :119-136
[9]   Wetland Classification Using Multi-Source and Multi-Temporal Optical Remote Sensing Data in Newfoundland and Labrador, Canada [J].
Amani, Meisam ;
Salehi, Bahram ;
Mahdavi, Sahel ;
Granger, Jean Elizabeth ;
Brisco, Brian ;
Hanson, Alan .
CANADIAN JOURNAL OF REMOTE SENSING, 2017, 43 (04) :360-373
[10]  
[Anonymous], 2004, STAT METHODS ACCURAC