In this study, we developed and trained a deep learning model to classify the drivers of any forest loss—including deforestation—from satellite image time series.

Land cover and land-use data are particularly important due to their ability to provide objective and quantitative information that informs the development, implementation, and assessment of policies.

This collection brings together 21 papers that address the relationship between citizen science and the SDGs and/or other international agreements and frameworks.

The first reference data set and prototype of a globally consistent forest management map with high spatial detail on the most prevalent forest management classes.

Here, we present a biome-wide assessment to show where industrial mine expansion has caused the most deforestation from 2000 to 2019.

In this paper, we develop a system to decide when enough information has been accumulated to confidently declare an image to be classified and remove it from circulation.

Combining global satellite luminosity and built-up areas finds 19% of buildings unlit, majority associated with low levels of well-being.

Citizen science offers a novel solution and an untapped opportunity to complement traditional sources of data for monitoring progress towards the SDGs.

High-resolution crowdsourced drivers of tropical forest loss between 2008 and 2019 to advise EU policy makers and inform the public.