Spatio-temporal deep learning approach to map deforestation in Amazon rainforest

R.V. Maretto, Leila M. G. Fonseca, Nathan Jacobs, Thales S. Korting, Hugo N. Bendini, Leandro L. Parente

Research output: Contribution to journalArticleAcademicpeer-review

37 Citations (Scopus)
2 Downloads (Pure)


We address the task of mapping deforested areas in the Brazilian Amazon. Accurate maps are an important tool for informing effective deforestation containment policies. The main existing approaches to this task are largely manual, requiring significant effort by trained experts. To reduce this effort, we propose a fully automatic approach based on spatio-temporal deep convolutional neural networks. We introduce several domain-specific components, including approaches for: image preprocessing; handling image noise, such as clouds and shadow; and constructing the training data set. We show that our preprocessing protocol reduces the impact of noise in the training data set. Furthermore, we propose two spatio-temporal variations of the U-Net architecture, which make it possible to incorporate both spatial and temporal contexts. Using a large, real-world data set, we show that our method outperforms a traditional U-Net architecture, thus achieving approximately 95% accuracy.
Original languageEnglish
Pages (from-to)771-775
Number of pages5
JournalIEEE geoscience and remote sensing letters
Issue number5
Early online date28 Apr 2020
Publication statusPublished - 1 May 2021
Externally publishedYes


  • ITC-CV
  • n/a OA procedure


Dive into the research topics of 'Spatio-temporal deep learning approach to map deforestation in Amazon rainforest'. Together they form a unique fingerprint.

Cite this