Multisensor approach to land use and land cover mapping in Brazilian Amazon

被引:15
作者
Prudente, Victor Hugo Rohden [1 ,2 ]
Skakun, Sergii [2 ,3 ]
Oldoni, Lucas Volochen [1 ]
Xaud, Haron A. M. [4 ]
Xaud, Maristela R. [4 ]
Adami, Marcos [1 ]
Sanches, Ieda Del ' Arco [1 ]
机构
[1] Natl Inst Space Res, Earth Observat & Geoinformat Div, BR-12227010 Sao Jose Dos Campos, SP, Brazil
[2] Univ Maryland, Dept Geog Sci, College Pk, MD 20742 USA
[3] NASA Goddard Space Flight Ctr Code 619, Greenbelt, MD 20771 USA
[4] Brazilian Agr Res Corp, Embrapa Roraima, BR-69301970 Boa Vista, RR, Brazil
关键词
Classification; Sentinel images; Random Forest; Multilayer Perceptron; t-Distributed Stochastic Neighbor Embedding; Roraima state; CLOUD COVER; FOREST; CLASSIFICATION; INTEGRATION; SENTINEL-1; SAR; ACCURACY; FUSION; REGION; IMAGES;
D O I
10.1016/j.isprsjprs.2022.04.025
中图分类号
P9 [自然地理学];
学科分类号
0705 ; 070501 ;
摘要
Remote sensing has an important role in the Land Use and Land Cover (LULC) mapping process worldwide. Combining spaceborne optical and microwave data is essential for accurate classification in areas with frequent cloud cover, such as tropical regions. In this study, we investigate the possible improvements, when SAR data is incorporated into the classification process along with optical data. We used MSI/Sentinel-2 and SAR/Sentinel-1 to provide LULC mapping in the Roraima State, Brazil, in 2019. This State is located in a tropical area, where the cloud cover is frequent over the year. Cloud cover becomes substantial, especially during the May-August period when crops are grown. Twenty-nine scenarios involving a combination of optical-and SAR-based features, as well as times of data acquisition, were considered in this study. Our results showed that optical or SAR data used individually are not enough to provide accurate LULC mapping. The best results in terms of overall accuracy (OA) were achieved using metrics of multi-temporal surface reflectance and vegetation index (VI) for optical imagery, and values of backscatter coefficient in different polarizations and their ratios yielding an OA of 86.41 +/- 1.74%. Analysis of three periods of data (January to April, May to August, and September to December) used for classification allowed us to identify the optimal period for distinguishing specific classes. When comparing our LULC map with a LULC product derived within the MapBiomas project we observed that our method per -formed better to map annual and perennial crops and water classes. Our methodology provides a more accurate LULC for the Roraima State, and the proposed technique can be applied to benefit other regions that are affected by persistent cloud cover.
引用
收藏
页码:95 / 109
页数:15
相关论文
共 80 条
[1]   Seasonality of vegetation types of South America depicted by moderate resolution imaging spectroradiometer (MODIS) time series [J].
Adami, Marcos ;
Bernardes, Sergio ;
Arai, Egidio ;
Freitas, Ramon M. ;
Shimabukuro, Yosio E. ;
Espirito-Santo, Fernando D. B. ;
Rudorff, Bernardo F. T. ;
Anderson, Liana O. .
INTERNATIONAL JOURNAL OF APPLIED EARTH OBSERVATION AND GEOINFORMATION, 2018, 69 :148-163
[2]  
[Anonymous], 2012, MAN TECN VEG BRAS
[3]  
[Anonymous], 2021, IEEE Trans. Broadcast.
[4]   Cloud cover in Landsat observations of the Brazilian Amazon [J].
Asner, GP .
INTERNATIONAL JOURNAL OF REMOTE SENSING, 2001, 22 (18) :3855-3862
[5]  
Barbosa R.I., 2010, Roraima: Homem, Ambiente e Ecologia, P347
[6]  
Barbosa R.I., 2008, Amazonia: Ciencia Desenvolvimento, V4, P131
[7]  
Barni Paulo Eduardo, 2020, Soc. nat., V32, P420, DOI [10.14393/sn-v32-2020-52769, 10.14393/SN-v32-2020-52769]
[8]  
Barni Paulo Eduardo, 2020, Sustentabilidade em Debate, V11, P81, DOI 10.18472/SustDeb.v11n2.2020.27493
[9]   Spatial distribution of forest biomass in Brazil's state of Roraima, northern Amazonia [J].
Barni, Paulo Eduardo ;
Manzi, Antonio Ocimar ;
Conde, Tiago Monteiro ;
Barbosa, Reinaldo Imbrozio ;
Fearnside, Philip Martin .
FOREST ECOLOGY AND MANAGEMENT, 2016, 377 :170-181
[10]  
Burger HC, 2012, PROC CVPR IEEE, P2392, DOI 10.1109/CVPR.2012.6247952