Land Cover Mapping Using Sentinel-1 Time-Series Data and Machine-Learning Classifiers in Agricultural Sub-Saharan Landscape

被引:12
|
作者
Dahhani, Sara [1 ]
Raji, Mohamed [1 ]
Hakdaoui, Mustapha [1 ]
Lhissou, Rachid [2 ]
机构
[1] Hassan II Univ Casablanca, Fac Sci Ben Msik, POB 7955, Casablanca, Morocco
[2] Inst Natl Rech Sci, Ctr ETE, 490 Couronne, Quebec City, PQ GIK 9A9, Canada
关键词
SAR data; PCA; K-D tree KNN; time series; land use; random forest; synthetic aperture radar; CLASSIFICATION; FOREST;
D O I
10.3390/rs15010065
中图分类号
X [环境科学、安全科学];
学科分类号
08 ; 0830 ;
摘要
This paper shows the efficiency of machine learning for improving land use/cover classification from synthetic aperture radar (SAR) satellite imagery as a tool that can be used in some sub-Saharan countries that experience frequent clouds. Indeed, we aimed to map the land use and land cover, especially in agricultural areas, using SAR C-band Sentinel-1 (S-1) time-series data over our study area, located in the Kaffrine region of Senegal. We assessed the performance and the processing time of three machine-learning classifiers applied on two inputs. In fact, we applied the random forest (RF), K-D tree K-nearest neighbor (KDtKNN), and maximum likelihood (MLL) classifiers using two separate inputs, namely a set of monthly S-1 time-series data acquired during 2020 and the principal components (PCs) of the time-series dataset. In addition, the RF and KDtKNN classifiers were processed using different tree numbers for RF (10, 15, 50, and 100) and different neighbor numbers for KDtKNN (5, 10, and 15). The retrieved land cover classes included water, shrubs and scrubs, trees, bare soil, built-up areas, and cropland. The RF classification using the S-1 time-series data gave the best performance in terms of accuracy (overall accuracy = 0.84, kappa = 0.73) with 50 trees. However, the processing time was relatively slower compared to KDtKNN, which also gave a good accuracy (overall accuracy = 0.82, kappa = 0.68). Our results were compared to the FROM-GLC, ESRI, and ESA world cover maps and showed significant improvements in some land use and land cover classes.
引用
收藏
页数:17
相关论文
共 50 条
  • [31] Tracking changes in coastal land cover in the Yellow Sea, East Asia, using Sentinel-1 and Sentinel-2 time-series images and Google Earth Engine
    Liu, Yongchao
    Xiao, Xiangming
    Li, Jialin
    Wang, Xinxin
    Chen, Bangqian
    Sun, Chao
    Wang, Jie
    Tian, Peng
    Zhang, Haitao
    ISPRS JOURNAL OF PHOTOGRAMMETRY AND REMOTE SENSING, 2023, 196 : 429 - 444
  • [32] High resolution land cover mapping and crop classification in the Loukkos watershed (Northern Morocco): An approach using SAR Sentinel-1 time series
    El Mortaji, Nizar
    Wahbi, Miriam
    Kazzi, Mohamed Ait
    Alaoui, Otmane Yazidi
    Boulaassal, Hakim
    Maatouk, Mustapha
    Zaghloul, Mohamed Najib
    El Kharki, Omar
    REVISTA DE TELEDETECCION, 2022, (60): : 47 - 69
  • [33] Woody cover mapping in the savanna ecosystem of the Kruger National Park using Sentinel-1 C-Band time series data
    Urban, Marcel
    Heckel, Kai
    Berger, Christian
    Schratz, Patrick
    Smit, Izak P. J.
    Strydom, Tercia
    Baade, Jussi
    Schmullius, Christiane
    KOEDOE, 2020, 62 (01): : 1 - 6
  • [34] Large-Scale Populus euphratica Distribution Mapping Using Time-Series Sentinel-1/2 Data in Google Earth Engine
    Peng, Yan
    He, Guojin
    Wang, Guizhou
    Zhang, Zhaoming
    REMOTE SENSING, 2023, 15 (06)
  • [35] Land cover and land use classification performance of machine learning algorithms in a boreal landscape using Sentinel-2 data
    Abdi, Abdulhakim Mohamed
    GISCIENCE & REMOTE SENSING, 2020, 57 (01) : 1 - 20
  • [36] IMPROVING RELIABILITY IN GLOBAL FLOOD MAPPING BY GENERATING A SEASONAL REFERENCE WATER MASK USING SENTINEL-1/2 TIME-SERIES DATA
    Martinis, S.
    Groth, S.
    Wieland, M.
    Raettich, M.
    Knopp, L.
    XXIV ISPRS CONGRESS: IMAGING TODAY, FORESEEING TOMORROW, COMMISSION III, 2022, 43-B3 : 1127 - 1132
  • [37] Crop Type and Land Cover Mapping in Northern Malawi Using the Integration of Sentinel-1, Sentinel-2, and PlanetScope Satellite Data
    Kpienbaareh, Daniel
    Sun, Xiaoxuan
    Wang, Jinfei
    Luginaah, Isaac
    Bezner Kerr, Rachel
    Lupafya, Esther
    Dakishoni, Laifolo
    REMOTE SENSING, 2021, 13 (04) : 1 - 21
  • [38] Land cover mapping using time series HJ-1 / CCD data
    ZHONG Bo
    MA Peng
    NIE AiHua
    YANG AiXia
    YAO YanJuan
    Lü WenBo
    ZHANG Hang
    LIU QinHuo
    ScienceChina(EarthSciences), 2014, 57 (08) : 1790 - 1799
  • [39] Land cover mapping using time series HJ-1/CCD data
    Bo Zhong
    Peng Ma
    AiHua Nie
    AiXia Yang
    YanJuan Yao
    WenBo Lü
    Hang Zhang
    QinHuo Liu
    Science China Earth Sciences, 2014, 57 : 1790 - 1799
  • [40] Land cover mapping using time series HJ-1/CCD data
    Zhong Bo
    Ma Peng
    Nie Aihua
    Yang Aixia
    Yao YanJuan
    Lu Wenbo
    Zhang Hang
    Liu QinHuo
    SCIENCE CHINA-EARTH SCIENCES, 2014, 57 (08) : 1790 - 1799