Short-time-series grassland mapping using Sentinel-2 imagery and deep learning-based architecture

被引:18
作者
Abdollahi, Arnick [1 ]
Liu, Yuxia [2 ]
Pradhan, Biswajeet [1 ,3 ,4 ]
Huete, Alfredo [1 ,2 ]
Dikshit, Abhirup [1 ]
Ngoc Nguyen Tran [2 ]
机构
[1] Univ Technol Sydney, Fac Engn & IT, Ctr Adv Modelling & Geospatial Informat Syst CAMG, Sch Civil & Environm Engn, Ultimo, NSW 2007, Australia
[2] Univ Technol Sydney, Fac Sci, Ultimo, NSW 2007, Australia
[3] King Abdulaziz Univ, Ctr Excellence Climate Change Res, POB 80234, Jeddah 21589, Saudi Arabia
[4] Univ Kebangsaan Malaysia, Earth Observat Ctr, Inst Climate Change, Bangi 43600, Selangor, Malaysia
基金
美国国家卫生研究院;
关键词
Grassland mapping; Deep learning; Sentinel-2; image; Remote sensing; NATIONAL-PARK; RANDOM FOREST; CLASSIFICATION;
D O I
10.1016/j.ejrs.2022.06.002
中图分类号
X [环境科学、安全科学];
学科分类号
08 ; 0830 ;
摘要
In the present work, a deep learning-based network called LeNet is applied for accurate grassland map production from Sentinel-2 data for the Greater Sydney region, Australia. First, we apply the technique to the base date Sentinel-2 data (non-seasonal) to make the vegetation maps. Then, we combine short time-series (seasonal) data and enhanced vegetation index (EVI) information to the base date imagery to improve the classification results and generate high-resolution grassland maps. The proposed model obtained an overall accuracy (OA) of 88.36% for the mono-temporal data, and 92.74% for the multi-temporal data. The experimental products proved that, by combining the short time-series images and EVI information to the base date, the classification maps' accuracy is increased by 4.38%. Moreover, the Sentinel-2 produced grassland maps are compared with the pre-existing maps such as Australian Land Use and Management (ALUM) 50 m resolution and Dynamic Land Cover Dataset (DLCD) with 250 m resolution as well as some traditional machine learning methods such as Support Vector Machine (SVM) and Random Forest (RF). The results show the effect of the LeNet network's performance and efficiency for grassland map production from short time-series data. As a result, decision-makers and urban planners can benefit from this work in terms of grassland change identification, monitoring, and planning assessment. (c) 2022 National Authority of Remote Sensing & Space Science. Published by Elsevier B.V. This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/).
引用
收藏
页码:673 / 685
页数:13
相关论文
共 25 条
[1]  
[Anonymous], ESA Copernicus Open Access Hub
[2]   Mapping Productivity and Essential Biophysical Parameters of Cultivated Tropical Grasslands from Sentinel-2 Imagery [J].
Cisneros, Amparo ;
Fiorio, Peterson ;
Menezes, Patricia ;
Pasqualotto, Nieves ;
Van Wittenberghe, Shari ;
Bayma, Gustavo ;
Nogueira, Sandra Furlan .
AGRONOMY-BASEL, 2020, 10 (05)
[3]   Combined use of multi-seasonal high and medium resolution satellite imagery for parcel-related mapping of cropland and grassland [J].
Esch, T. ;
Metz, A. ;
Marconcini, M. ;
Keil, M. .
INTERNATIONAL JOURNAL OF APPLIED EARTH OBSERVATION AND GEOINFORMATION, 2014, 28 :230-237
[4]   UAV Remote Sensing for Urban Vegetation Mapping Using Random Forest and Texture Analysis [J].
Feng, Quanlong ;
Liu, Jiantao ;
Gong, Jianhua .
REMOTE SENSING, 2015, 7 (01) :1074-1094
[5]   Global consequences of land use [J].
Foley, JA ;
DeFries, R ;
Asner, GP ;
Barford, C ;
Bonan, G ;
Carpenter, SR ;
Chapin, FS ;
Coe, MT ;
Daily, GC ;
Gibbs, HK ;
Helkowski, JH ;
Holloway, T ;
Howard, EA ;
Kucharik, CJ ;
Monfreda, C ;
Patz, JA ;
Prentice, IC ;
Ramankutty, N ;
Snyder, PK .
SCIENCE, 2005, 309 (5734) :570-574
[6]   Mangrove forest distributions and dynamics in Madagascar (1975-2005) [J].
Giri, Chandra ;
Muhlhausen, Joseph .
SENSORS, 2008, 8 (04) :2104-2117
[7]   Optical remotely sensed time series data for land cover classification: A review [J].
Gomez, Cristina ;
White, Joanne C. ;
Wulder, Michael A. .
ISPRS JOURNAL OF PHOTOGRAMMETRY AND REMOTE SENSING, 2016, 116 :55-72
[8]   A review of large area monitoring of land cover change using Landsat data [J].
Hansen, Matthew C. ;
Loveland, Thomas R. .
REMOTE SENSING OF ENVIRONMENT, 2012, 122 :66-74
[9]   Country-wide high-resolution vegetation height mapping with Sentinel-2 [J].
Lang, Nico ;
Schindler, Konrad ;
Wegner, Jan Dirk .
REMOTE SENSING OF ENVIRONMENT, 2019, 233
[10]   Monitoring Urban Areas with Sentinel-2A Data: Application to the Update of the Copernicus High Resolution Layer Imperviousness Degree [J].
Lefebvre, Antoine ;
Sannier, Christophe ;
Corpetti, Thomas .
REMOTE SENSING, 2016, 8 (07)