Global drivers of forest loss at 1 km resolution

We created a global map of the dominant drivers of forest loss from 2001 to 2022 at 1 km spatial resolution. We used a deep learning model to classify seven driver classes: permanent agriculture, hard commodities, shifting cultivation, logging, wildfires, settlements & infrastructure, and other natural disturbances. As part of the study, we collected a set of 6,955 training samples through interpretation of very high resolution satellite imagery and developed a single world-wide customized residual convolutional neural network model (ResNet) using satellite data (Landsat and Sentinel-2) and ancillary biophysical and population data. The improvement in thematic and spatial resolution allowed us to differentiate losses that may be temporary in nature (due to logging and wood-fiber harvest, wildfire and other natural disturbances) from deforestation (due to agricultural activities, settlements and infrastructure, and hard commodity expansion). In addition, we collected a stratified random sample of 3,574 validation plots through interpretation of very high resolution satellite imagery to estimate the accuracy of the final classification map.

In this repository, we make available both the training and validation data as two separate files. Both datasets were collected by a team of image interpreters and assessed for quality by two additional interpreters. Note that while for the validation data the quality of the primary driver was rigorously assessed, the secondary driver wasn’t subject to the same level of quality control. 

The files follow this specific naming convention (assuming name like training_2001_2022_v1):

Data type: `training` or `validation` 

Start year: `2001`

End year: `2022` or `2023` or `2024`

Version: `v1` or `v1.1` or `v1.2`

We also make availble the global drivers of forest loss raster (drivers_forest_loss_1km.tif)