A New Multi-Temporal Forest Cover Classification for the Xingu River Basin, Brazil

Abstract

We describe a new multi-temporal classification for forest/non-forest classes for a 1.3 million square kilometer area encompassing the Xingu River basin, Brazil. This region is well known for its exceptionally high biodiversity, especially in terms of the ichthyofauna, with approximately 600 known species, 10% of which are endemic to the river basin. Global and regional scale datasets do not adequately capture the rapidly changing land cover in this region. Accurate forest cover and forest cover change data are important for understanding the anthropogenic pressures on the aquatic ecosystems. We developed the new classifications with a minimum mapping unit of 0.8 ha from cloud free mosaics of Landsat TM5 and OLI 8 imagery in Google Earth Engine using a classification and regression tree (CART) aided by field photographs for the selection of training and validation points.

A Comparison between Supervised Classification Methods: Study Case on Land Cover Change Detection Caused by a Hydroelectric Complex Installation in the Brazilian Amazon

“…Due to the importance of a comprehensive comparison of different algorithms for LULC classification, aiming to improve knowledge on issues such as accuracy assessment and the selection of suitable algorithms for a historical remote sensing analysis for the VGX, the discussion section intends to sum with other previous initiatives that sought to measure and evaluate manmade transformations in study areas using remote sensing [3,12,15,28,30,31,42,46,66,67].…”

Deciphering the many maps of the Xingu – an assessment of land cover classifications at multiple scales

“…and Landsat 8 OLI imagery (Kalacska et al 2019a). Due to extensive seasonal cloud cover in the region, each mosaic represented the median cloud free reflectance over a reference period of 2-5 years.…”

“…In addition to the multispectral channels described here, many of the optical sensors listed also have panchromatic, thermal or other specialized bands with different spatial and spectral characteristics. (Kalacska et al 2019a) Dashed line illustrates the outline of the Xingu freshwater ecoregion from Abell et al (2008). A) clearing and burning of Arapujá island across from Altamira, B) Belo Monte dam, C) gold mining settlement, D) urban area at the ferry crossing between Belo Monte I and Belo Monte II, E) forest clearing for pasture, F) small homestead, G) confluence of the Xingu and Iriri rivers in the dry season with substrate exposed, H) intact forest in protected area, I) new road construction, J) large scale burning, K) intact forest surrounded by agricultural fields, L) agricultural encroachment on wetlands, M) mega-scale cotton plantation, N) irrigated agriculture, O) Riparian forest and wetland surrounded by agriculture, P) illegal mining, Q) urban area, R) forest burning and influx of water contaminated by mine tailings, S) Riparian forest, T) deciduous forest surrounding Culuene rapids, U) large scale forest burning, V) intact forest surrounding Curuá rapids with the Hydro Energia Buriti dam reservoir in the background.…”

Como os Produtos MODIS têm sido Utilizados para Análise dos Parâmetros Biofísicos em Regiões Semiáridas? Uma Revisão Bibliométrica e de Literatura

“…Destacam-se os estudos de Kalacska et al (2019), os quais realizaram uma classificação multitemporal na Bacia do Rio Xingu, usando imagens do sensor TM/Landsat 5 e OLI/Landsat 8, para identificar as dinâmicas de cobertura da terra e auxiliar a compreensão das pressões antrópicas na região de interesse ambiental. Por sua vez, outros estudos buscaram analisar as dinâmicas de cobertura de pastagens e a degradação dessas áreas usando a coleção de imagens do sensor MODIS (PARENTE & FERREIRA, 2018;PEREIRA et al, 2018).…”