Mapping deforested areas in the Cerrado Biome through recurrent neural networks

B. M. Matosak, R. V. Maretto, T. S. Korting, M. Adami, L. M.G. Fonseca

Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

1 Citation (Scopus)

Abstract

The Brazilian Savannah, also known as Cerrado Biome, is a hotspot for the Brazilian biodiversity and is also important for this country water supply. One of the most active Brazilian agricultural frontiers, the region has a history of primary vegetation suppression. Accurately map this phenomenon is an important step to inform and enable government conservation programs. In this work, we used a Long Short-Term Memory network to generate a deforestation map for the Cerrado. The PRODES deforestation inventory was used as ground truth during training and evaluation. We used as inputs a dense Landsat 8 time series composed by 6 spectral bands and 3 vegetation indices, as well as the SRTM terrain slope. The methodology was tested on an area comprising about 31,450 km2, achieving approximately 98.5% global accuracy.

Original languageEnglish
Title of host publication2020 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2020 - Proceedings
PublisherIEEE
Pages1389-1392
Number of pages4
ISBN (Electronic)9781728163741
DOIs
Publication statusPublished - 26 Sep 2020
Externally publishedYes
Event2020 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2020 - Virtual, Waikoloa, United States
Duration: 26 Sep 20202 Oct 2020

Conference

Conference2020 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2020
Country/TerritoryUnited States
CityVirtual, Waikoloa
Period26/09/202/10/20

Keywords

  • Brazilian Savannah
  • Cerrado Biome
  • Deep Learning
  • Deforestation
  • LSTM
  • ITC-CV

Fingerprint

Dive into the research topics of 'Mapping deforested areas in the Cerrado Biome through recurrent neural networks'. Together they form a unique fingerprint.

Cite this