LAND COVER MAPPING IN THE BRAZILIAN PAMPA WITH LANDSAT OLI AND TIRS BANDS

When different time periods are considered, detection of past and present changes in land cover are enabled, also for quantifying and qualifying those changes. Land cover/use maps are the primary tools for the management and conservation of natural and man-made areas. For this, remote sensing bands of the reflected spectrum are usually used, leaving aside the thermal data. The objective of this work was to evaluate the inclusion of the thermal band (b10) of the TIRS (Thermal Infrared Sensor) sensor of landsat 8 satellite to increase the land cover maps accuracy in the Pampa biome from object-oriented classification. For the development of the research, 11 scenes of the Landsat 8, OLI sensor and TIRS were used. Thus, 14 cells were selected in the Brazilian Pampa, totaling 5% of its area. The following steps were performed: obtaining land surface temperature (LST) data and vegetation indices; data preparation; object-oriented classification; validation with 1354 reference points and analysis of the results. The results showed that the insertion of thermal bands, especially from different dates, increased the discrimination among classes. The classification presented 86% of global accuracy. Therefore, it is recommended to insert thermal data for mapping and environmental monitoring of the Pampa biome

[1]  Limin Zhao,et al.  Global comparison of diverse scaling factors and regression models for downscaling Landsat-8 thermal data , 2020 .

[2]  Huazhong Ren,et al.  Evaluation of Land Surface Temperature Retrieval from Landsat 8/TIRS Images before and after Stray Light Correction Using the SURFRAD Dataset , 2020, Remote. Sens..

[3]  V. Ribeiro,et al.  Deforestation Monitoring in Different Brazilian Biomes: Challenges and Lessons , 2020, 2020 IEEE Latin American GRSS & ISPRS Remote Sensing Conference (LAGIRS).

[4]  Nájila Souza da Rocha,et al.  Seasonal Assessment Of Surface Temperature With Normalized Vegetation Index And Surface Albedo Over Pampa Biome , 2020, 2020 IEEE Latin American GRSS & ISPRS Remote Sensing Conference (LAGIRS).

[5]  André C. P. L. F. de Carvalho,et al.  TerraBrasilis: A Spatial Data Analytics Infrastructure for Large-Scale Thematic Mapping , 2019, ISPRS Int. J. Geo Inf..

[6]  T. M. Kuplich,et al.  Seasonal dynamics of vegetation indices as a criterion for grouping grassland typologies , 2019, Scientia Agricola.

[7]  Le Yu,et al.  Exploring the addition of Landsat 8 thermal band in land-cover mapping , 2019, International Journal of Remote Sensing.

[8]  Andrei Dornik,et al.  Classification of Soil Types Using Geographic Object-Based Image Analysis and Random Forests , 2017, Pedosphere.

[9]  Matthew Montanaro,et al.  Derivation and Validation of the Stray Light Correction Algorithm for the Thermal Infrared Sensor Onboard Landsat 8 , 2017 .

[10]  Hui Li,et al.  A multiple-point spatially weighted k-NN method for object-based classification , 2016, Int. J. Appl. Earth Obs. Geoinformation.

[11]  Joanne C. White,et al.  Optical remotely sensed time series data for land cover classification: A review , 2016 .

[12]  Ugur Avdan,et al.  Application of Open Source Coding Technologies in the Production of Land Surface Temperature (LST) Maps from Landsat: A PyQGIS Plugin , 2016, Remote. Sens..

[13]  Karsten Schulz,et al.  The Improvement of Land Cover Classification by Thermal Remote Sensing , 2015, Remote. Sens..

[14]  Abbas Alimohammadi,et al.  Land cover mapping based on random forest classification of multitemporal spectral and thermal images , 2015, Environmental Monitoring and Assessment.

[15]  Mario Chica-Olmo,et al.  Incorporating the downscaled landsat TM thermal band in land-cover classification using random forest , 2012 .

[16]  A. Ehsani,et al.  Efficiency of Landsat ETM+ Thermal Band for Land Cover Classification of the Biosphere Reserve “Eastern Carpathians†(Central Europe) Using SMAP and ML Algorithms , 2010 .

[17]  Antonio J. Plaza,et al.  Land Surface Emissivity Retrieval From Different VNIR and TIR Sensors , 2008, IEEE Transactions on Geoscience and Remote Sensing.

[18]  Kai An,et al.  Object-oriented urban dynamic monitoring — A case study of Haidian District of Beijing , 2007 .

[19]  José A. Sobrino,et al.  Land surface temperature retrieval from LANDSAT TM 5 , 2004 .

[20]  J. Paruelo,et al.  Land cover classification in the Argentine Pampas using multi-temporal Landsat TM data , 2003 .

[21]  V. Caselles,et al.  Mapping land surface emissivity from NDVI: Application to European, African, and South American areas , 1996 .

[22]  Manfred Owe,et al.  On the relationship between thermal emissivity and the normalized difference vegetation index for natural surfaces , 1993 .

[23]  M. Čekada,et al.  Grassland Recognition with the Usage of Thermal Weights , 2018 .

[24]  A. Trémeau,et al.  International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences - ISPRS Archives , 2013 .

[25]  Thomas Blaschke,et al.  Object based image analysis for remote sensing , 2010 .

[26]  J. Strobl,et al.  Object-Oriented Image Processing in an Integrated GIS/Remote Sensing Environment and Perspectives for Environmental Applications , 2000 .