Spatially explicit information on forest management at a global scale is critical for understanding the status of forests, for planning sustainable forest management and restoration, and conservation activities. Here, we produce the first reference data set and a prototype of a globally consistent forest management map with high spatial detail on the most prevalent forest management classes such as intact forests, managed forests with natural regeneration, planted forests, plantation forest (rotation up to 15 years), oil palm plantations, and agroforestry. We developed the reference dataset of 226 K unique locations through a series of expert and crowdsourcing campaigns using Geo-Wiki (https://www.geo-wiki.org/). We then combined the reference samples with time series from PROBA-V satellite imagery to create a global wall-to-wall map of forest management at a 100 m resolution for the year 2015, with forest management class accuracies ranging from 58% to 80%. The reference data set and the map present the status of forest ecosystems and can be used for investigating the value of forests for species, ecosystems and their services.

During December 2020, a crowdsourcing campaign to understand what has been driving tropical forest loss during the past decade was undertaken. For 2 weeks, 58 participants from several countries reviewed almost 115 K unique locations in the tropics, identifying drivers of forest loss (derived from the Global Forest Watch map) between 2008 and 2019. Previous studies have produced global maps of drivers of forest loss, but the current campaign increased the resolution and the sample size across the tropics to provide a more accurate mapping of crucial factors leading to forest loss. The data were collected using the Geo-Wiki platform (www.geo-wiki.org) where the participants were asked to select the predominant and secondary forest loss drivers amongst a list of potential factors indicating evidence of visible human impact such as roads, trails, or buildings. The data described here are openly available and can be employed to produce updated maps of tropical drivers of forest loss, which in turn can be used to support policy makers in their decision-making and inform the public.

As geomorphological processes operate at various spatial scales, their morphological expressions, i.e., land-surface variables (LSVs) should be scaled accordingly. Most approaches on landslide susceptibility modeling and landslide detection have been performed based on arbitrarily scaled LSVs. We propose a methodology to improve automated landslide detection by fitting each LSV to its optimal scale. We test our approach on two landslide inventories, with different landslide morphology. First, we derive seven LSVs from a DEM in a standard 3 × 3 moving window. Then, we rescale each LSV using focal mean statistics in increasingly larger moving windows until the optimal scale is found, i.e., scale at which logistic regression shows the best fit between the existence of landslide scarps and individual LSVs. The LSVs at the optimal scale are used as input data in a random forest (RF) model. In order to calculate the effect of scaling predictors on the accuracy of the model, we compare the results, using the area under the curve (AUC), against the results from an RF model with unscaled LSVs as input data. The results show (i) that different LSVs have different optimal scales, and (ii) the multi-scale approach improved the models significantly, from AUC = 0.73 to 0.80 for the first study area and from AUC = 0.59 to 0.73 for the second study area. Based on these results, we conclude that a multi-scale approach should be considered when automated models are used in order to detect landslides, in complex terrain settings.

Computer modeling of sporadic and isolated patches of mountain permafrost distribution is difficult to implement without overestimating it. The main challenge is to determine the very areas where the criteria for permafrost maintenance are met. This paper aims to modeling the permafrost distribution in the Southern Carpathians (SC), a typical marginal periglacial mountain range. For this purpose, a collection of 883 bottom temperature of late winter snow cover (BTS) points was used as a proxy for permafrost presence or absence in order to train several machine learning models. The performances of each model were evaluated with AUC with varying between 0.99 for Maxent and 0.74 for K‐nearest neighbors and most models (five) exhibiting values between 0.82 and 0.86. Other tests such as confusion matrices, sensitivity analyses, data shuffling, and data size reduction tests indicated that Maxent, AdaBoost, and support vector machine offered the best results while logistic regression, neural network, and gradient boosting exhibited rather poor permafrost distributions. The final ensemble median model indicated a total permafrost area of 19.2 km ² occupying 1%–9% of the alpine area of the studied massifs. NDVI proved crucial for permafrost prediction because it allows delimiting the debris surfaces where permafrost is probable.