Many global environmental agendas, including halting biodiversity loss, reversing land degradation, and limiting climate change, depend upon retaining forests with high ecological integrity, yet the scale and degree of forest modification remain poorly quantified and mapped. By integrating data on observed and inferred human pressures and an index of lost connectivity, we generate a globally consistent, continuous index of forest condition as determined by the degree of anthropogenic modification. Globally, only 17.4 million km2 of forest (40.5%) has high landscape-level integrity (mostly found in Canada, Russia, the Amazon, Central Africa, and New Guinea) and only 27% of this area is found in nationally designated protected areas. Of the forest inside protected areas, only 56% has high landscape-level integrity. Ambitious policies that prioritize the retention of forest integrity, especially in the most intact areas, are now urgently needed alongside current efforts aimed at halting deforestation and restoring the integrity of forests globally.

No abstract

Land cover mapping via image classification is sometimes realized through object-based 6 image analysis. Objects are typically constructed by partitioning imagery into spatially 7 contiguous groups of pixels through image segmentation and used as the basic spatial unit of 8 analysis. As it is typically desirable to know the accuracy with which the objects have been 9delimited prior to undertaking the classification, numerous methods have been used for accuracy assessment. This paper reviews the state-of-the-art of image segmentation accuracy 11 assessment in land cover mapping applications. First the literature published in three major 12 remote sensing journals during 2014-2015 is reviewed to provide an overview of the field. This revealed that qualitative assessment based on visual interpretation was a widely-used method, but a range of quantitative approaches is available. In particular, the empirical discrepancy or supervised methods that use reference data for assessment are thoroughly 16 reviewed as they were the most frequently used approach in the literature surveyed.Supervised methods are grouped into two main categories, geometric and non-geometric, and are translated here to a common notation which enables them to be coherently and 19 unambiguously described. Some key considerations on method selection for land cover 20 mapping applications are provided, and some research needs are discussed.

This paper presents the multi-modal BigEarthNet (BigEarthNet-MM) benchmark archive made up of 590,326 pairs of Sentinel-1 and Sentinel-2 image patches to support the deep learning (DL) studies in multi-modal multi-label remote sensing (RS) image retrieval and classification. Each pair of patches in BigEarthNet-MM is annotated with multi-labels provided by the CORINE Land Cover (CLC) map of 2018 based on its thematically most detailed Level-3 class nomenclature. Our initial research demonstrates that some CLC classes are challenging to be accurately described by only considering (single-date) BigEarthNet-MM images. In this paper, we also introduce an alternative class-nomenclature as an evolution of the original CLC labels to address this problem. This is achieved by interpreting and arranging the CLC Level-3 nomenclature based on the properties of BigEarthNet-MM images in a new nomenclature of 19 classes. In our experiments, we show the potential of BigEarthNet-MM for multi-modal multi-label image retrieval and classification problems by considering several state-of-theart DL models. We also demonstrate that the DL models trained from scratch on BigEarthNet-MM outperform those pretrained on ImageNet, especially in relation to some complex classes, including agriculture and other vegetated and natural environments. We make all the data and the DL models publicly available at https://bigearth.net, offering an important resource to support studies on multi-modal image scene classification and retrieval problems in RS.