[FROM: http://iridl.ldeo.columbia.edu/maproom/Fire/Regional/Amazonia/SST_Fire_Forecast.html] These graphs include July-September fire season anomaly hindcasts and forecasts in the Western Amazon. The incidence is on a standardized scale and is based on the north tropical Atlantic (NTA) sea surface temperature (SST) seasonal forecast issued in April, May and June. Positive values indicate an expected active fire season and negative values stand for a mild fire season. Lead 1 stands for the first trimester SST forecast and Lead-2 for the the second trimester SST forecast. For example, March Lead-1 forecast uses April-June SST forecast to calculate the NTA index and predict the following JAS fire season. March Lead-2 uses May-July SST forecast to calculate the NTA and predict JAS fire season and so on. As we advance in the seasons, the more accurate the forecast is expected to be. Use the drop-down menus at the top of the page to select the map field (Forecast or Observed) and the forecast issue month to display.

This dataset was produced using Landsat 8 Operational Land Imager and Landsat 7 Enhanced Thematic Mapper Plus surface reflectance data spanning 2013–2018 and Spectral Mixture Analysis for the identification of patterns of forest loss for each year. High-resolution Planet Dove (3m) and RapidEye (5m) imagery were used to validate the forest loss map. Overall Accuracy obtained for the forest loss map was 96%. Publication: https://doi.org/10.1088/1748-9326/ab57c3 Google Earth Engine code: https://code.earthengine.google.com/024b42f8eb3ab0c5fa8e0ad8fba86f36 For more information on SERVIR, visit http://www.servirglobal.net

Project Foresight was launched, in early 2019, as a continuous effort to develop machine-learning based deforestation and forest fire risk assessment for tropical forests, using increasing higher resolution satellite data and official country data on anthropogenic activity. Version 1.0 included maps of the Peruvian and Colombian Amazon using 18 years of official deforestation data and the open source release of Maxent, as the machine-learning algorithm. Newer versions have been developed using mutli-model ensembles in R and Google Earth Engine.

Amazonia holds the largest continuous area of tropical forests with intense land use change dynamics inducing water, carbon, and energy feedbacks with regional and global impacts. Much of our knowledge of land use change in Amazonia comes from studies of the Brazilian Amazon, which accounts for two thirds of the region. Amazonia outside of Brazil has received less attention because of the difficulty of acquiring consistent data across countries. We present here an agricultural statistics database of the entire Amazonia region, with a harmonized description of crops and pastures in geospatial format, based on administrative boundary data at the municipality level. The spatial coverage includes countries within Amazonia and spans censuses and surveys from 1950 to 2012. Harmonized crop and pasture types are explored by grouping annual and perennial cropping systems, C3 and C4 photosynthetic pathways, planted and natural pastures, and main crops. Our analysis examined the spatial pattern of ratios between classes of the groups and their correlation with the agricultural extent of crops and pastures within administrative units of the Amazon, by country, and census/survey dates. Significant correlations were found between all ratios and the fraction of agricultural lands of each administrative unit, with the exception of planted to natural pastures ratio and pasture lands extent. Brazil and Peru in most cases have significant correlations for all ratios analyzed even for specific census and survey dates. Results suggested improvements, and potential applications of the database for carbon, water, climate, and land use change studies are discussed. The database presented here provides an Amazon-wide improved data set on agricultural dynamics with expanded temporal and spatial coverage.