The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences
Download
Publications Copernicus
Download
Citation
Articles | Volume XLII-3/W12-2020
Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci., XLII-3/W12-2020, 557–562, 2020
https://doi.org/10.5194/isprs-archives-XLII-3-W12-2020-557-2020
Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci., XLII-3/W12-2020, 557–562, 2020
https://doi.org/10.5194/isprs-archives-XLII-3-W12-2020-557-2020

  06 Nov 2020

06 Nov 2020

REMOTE SENSING IMAGE TIME SERIES METRICS FOR DISTINCTION BETWEEN PASTURE AND CROPLANDS USING THE RANDOM FOREST CLASSIFIER

M. A. A. Rodrigues, H. N. Bendini, A. R. Soares, T. S. Körting, and L. M. G. Fonseca M. A. A. Rodrigues et al.
  • Image Processing Division, National Institute for Space Research, INPE, Brazil

Keywords: Time series, Metric images, GEOBIA, Data cube, Random Forest

Abstract. Pasture and croplands play an important role in Brazil’s economic and political scenarios, once its PIB (Raw Internal Product) is mainly based on what is exported from the rural production, such as meat and soybean, and government, with its regulations, is part-responsible for the establishment and maintaining of the conditions so that the trades can go well. In addition, these two types of land use correspond together to aprox. one third of the country extension. Moreover, frequently lands occupation is subject of discussion concerning its potential use for the reason of conflicts including Brazilian traditional communities, landless people and big farmers. Considering it, mapping pasture and croplands accurately is crucial for the country administration, in both economic and political spheres. Certainly, remote sensing is the very manner to tackle this issue, although this may not be an easy task due to the spectral similarity between these patterns. This work, hence, aims to distinct pasture from croplands in an experimental subset area of Brazilian Cerrado biome, using remote sensing metric images derived from one-year time series of the Landsat 8 products. In order to achieve this goal, we utilized six bands of the OLI sensor and calculated seven metrics, attaining a compiled dataset with 42 layers. We performed an object-based supervised classification with the Random Forest algorithm, considering both spectral and geometrical attributes. Results showed global accuracy of 80%, with Kappa index of 0.6, and the potential time series have in separating targets spectrally similar.