Reconstructing three decades of land use and land cover changes in brazilian biomes with landsat archive and earth engine

Brazil has a monitoring system to track annual forest conversion in the Amazon and most recently to monitor the Cerrado biome. However, there is still a gap of annual land use and land cover (LULC) information in all Brazilian biomes in the country. Existing countrywide efforts to map land use and land cover lack regularly updates and high spatial resolution time-series data to better understand historical land use and land cover dynamics, and the subsequent impacts in the country biomes. In this study, we described a novel approach and the results achieved by a multi-disciplinary network called MapBiomas to reconstruct annual land use and land cover information between 1985 and 2017 for Brazil, based on random forest applied to Landsat archive using Google Earth Engine. We mapped five major classes: forest, non-forest natural formation, farming, non-vegetated areas, and water. These classes were ...

DOI: 10.3390/rs12172735

Date: 2020-08-25

Automatic Mapping of Center Pivot Irrigation Systems from Satellite Images Using Deep Learning

The availability of freshwater is becoming a global concern. Because agricultural consumption has been increasing steadily, the mapping of irrigated areas is key for supporting the monitoring of land use and better management of available water resources. In this paper, we propose a method to automatically detect and map center pivot irrigation systems using U-Net, an image segmentation convolutional neural network architecture, applied to a constellation of PlanetScope images from the Cerrado biome of Brazil. Our objective is to provide a fast and accurate alternative to map center pivot irrigation systems with very high spatial and temporal resolution imagery. We implemented a modified U-Net architecture using the TensorFlow library and trained it on the Google cloud platform with a dataset built from more than 42,000 very high spatial resolution PlanetScope images acquired between August 2017 and November 2018. The U-Net implementation achieved a precision of 99% and a recall of 88% to detect and map center pivot irrigation systems in our study area. This method, proposed to detect and map center pivot irrigation systems, has the potential to be scaled to larger areas and improve the monitoring of freshwater use by agricultural activities.

DOI: 10.3390/rs12030558

Date: 2020-02-07

Construção de mosaicos temporais normalizados de imagens planet

The compact multispectral satellite constellation, Planet, collects daily images with a spatial resolution of 3 to 4 m. These images have the potential to contribute significantly to the improvement of land use and land cover mapping accuracy and to enhance the detection and monitoring capabilities of anthropogenic interferences over natural landscapes. A fundamental step for the ef ective use of Planet´s images is the detection and removal of clouds, shades and other types of atmospheric noise, plus the radiometric normalisation of such dataset. In this article, we briefly present the Nextgen Map Project, as well as, share its advances towards the generation of normalised cloud-free mosaics. In here, the Google Earth Engine algorithm is detailed presented, and the mosaic final repository is shared. Finally, we discuss the next steps to overcome some of the limitations that have not yet been addressed in this phase of the project.

DOI: 10.29327/xix-sbsr.a1

Date: 2019-04-17