Methodology for classification of land use and vegetation cover using MODIS-EVI data

Abstract

This study aimed to verify the applicability of using MODIS-EVI sensor time series for land use and vegetation cover mapping in the Pampa biome, Rio Grande do Sul state, Brazil. The study period comprised the months from June 2013 to June 2014. The procedures included the use of MODIS Sensor images, altimetric data and nighttime images, associated with a hierarchical decision tree classifier, constructed using the C4.5 algorithm. The proposed approach stems from the consideration that the study area has varying characteristics and, therefore, should be treated simultaneously by different and intuitive classifiers, which justifies the choice of decision tree. To evaluate the results, reference data acquired from Landsat 8-OLI satellite images and IBGE data were used. The classification using the MODIS time series showed a global accuracy of 90.09% and Kappa index of 0.8885. When compared to the IBGE reference data, the Soybean class obtained a correlation coefficient of 0.94, the rice class obtained 0.97 and the silviculture class obtained the lowest value, 0.78. The highest spectral similarities were found in the vegetation cover classes, such as grassland, forest and silviculture. Therefore, with the use of multitemporal data from the MODIS sensor, combined with the use of altimetric data and nighttime images, it is possible to generate a land use and vegetation cover map for the Pampa biome with an acceptable accuracy, considering the MODIS sensor resolution limitations.

Assessment of Forest Cover Changes in Vavuniya District, Sri Lanka: Implications for the Establishment of Subnational Forest Reference Emission Level

“…The following previous studies found similar results to ours. For example, the variability in EVI thresholds underestimated the soybean cultivation area by 11.4%, while areas of rice field and silviculture were overestimated by 12.8% and 14.3%, respectively [110]. Similarly, three EVI values (0.400, 0.450, and 0.500) used for classifying forests in Guyana, produced biases of 10.0% to 30.0% from lower to higher EVI thresholds [111].…”

Sensor system for acquisition of vegetation indexes

“…Vegetation indexes can be calculated using images acquired from orbital (Zhang & Roy, 2016;Mengue et al, 2019) and suborbital (Ghazal et al, 2015;Zheng et al, 2016) platforms such as remotely piloted aircrafts. However, both data collection platforms present limitations.…”

Seasonal and Long-Term Changes of Vegetation Index of Arable Lands of Bryansk Region (Central Russia): Regularities and Dynamics Factors

“…A comparison of the dynamics of the VI of the surface of the plots with different types of plants, natural conditions of vegetation, and land use features allows highlighting the changes determined by local causes and processes of regional and (or) global rank. The influence of the latter is manifested in similar changes in the productivity of sites with unequal vegetation conditions and species composition of plants (Piedallu et al, 2018;Chen et al, 2015;Mengue et al, 2019). The causes of differences in dynamics are rarely detected by statistical methods due to the wide variety of vegetation conditions and the weak connection between the productivity dynamics and the factors determining it.…”