Overview: 242: Mosaic of small cultivated land parcels with different cultivation types(annual and permanent crops, as well as pastures), potentially with scattered houses or gardens. Traceability (lineage): This dataset was produced with a machine learning framework with several input datasets, specified in detail in Witjes et al., 2022 (in review, preprint available at https://doi.org/10.21203/rs.3.rs-561383/v3 ) Scientific methodology: The single-class probability layers were generated with a spatiotemporal ensemble machine learning framework detailed in Witjes et al., 2022 (in review, preprint available at https://doi.org/10.21203/rs.3.rs-561383/v3 ). The single-class uncertainty layers were calculated by taking the standard deviation of the three single-class probabilities predicted by the three components of the ensemble. The HCL (hard class) layers represents the class with the highest probability as predicted by the ensemble. Usability: The HCL layers have a decreasing average accuracy (weighted F1-score) at each subsequent level in the CLC hierarchy. These metrics are 0.83 at level 1 (5 classes):, 0.63 at level 2 (14 classes), and 0.49 at level 3 (43 classes). This means that the hard-class maps are more reliable when aggregating classes to a higher level in the hierarchy (e.g. 'Discontinuous Urban Fabric' and 'Continuous Urban Fabric' to 'Urban Fabric'). Some single-class probabilities may more closely represent actual patterns for some classes that were overshadowed by unequal sample point distributions. Users are encouraged to set their own thresholds when postprocessing these datasets to optimize the accuracy for their specific use case. Uncertainty quantification: Uncertainty is quantified by taking the standard deviation of the probabilities predicted by the three components of the spatiotemporal ensemble model. Data validation approaches: The LULC classification was validated through spatial 5-fold cross-validation as detailed in the accompanying publication. Completeness: The dataset has chunks of empty predictions in regions with complex coast lines (e.g. the Zeeland province in the Netherlands and the Mar da Palha bay area in Portugal). These are artifacts that will be avoided in subsequent versions of the LULC product. Consistency: The accuracy of the predictions was compared per year and per 30km*30km tile across europe to derive temporal and spatial consistency by calculating the standard deviation. The standard deviation of annual weighted F1-score was 0.135, while the standard deviation of weighted F1-score per tile was 0.150. This means the dataset is more consistent through time than through space: Predictions are notably less accurate along the Mediterrranean coast. The accompanying publication contains additional information and visualisations. Positional accuracy: The raster layers have a resolution of 30m, identical to that of the Landsat data cube used as input features for the machine learning framework that predicted it. Temporal accuracy: The dataset contains predictions and uncertainty layers for each year between 2000 and 2019. Thematic accuracy: The maps reproduce the Corine Land Cover classification system, a hierarchical legend that consists of 5 classes at the highest level, 14 classes at the second level, and 44 classes at the third level. Class 523: Oceans was omitted due to computational constraints.

Overview: 313: Vegetation formation composed principally of trees, including shrub and bush understory,where neither broad-leaved nor coniferous species predominate. Traceability (lineage): This dataset was produced with a machine learning framework with several input datasets, specified in detail in Witjes et al., 2022 (in review, preprint available at https://doi.org/10.21203/rs.3.rs-561383/v3 ) Scientific methodology: The single-class probability layers were generated with a spatiotemporal ensemble machine learning framework detailed in Witjes et al., 2022 (in review, preprint available at https://doi.org/10.21203/rs.3.rs-561383/v3 ). The single-class uncertainty layers were calculated by taking the standard deviation of the three single-class probabilities predicted by the three components of the ensemble. The HCL (hard class) layers represents the class with the highest probability as predicted by the ensemble. Usability: The HCL layers have a decreasing average accuracy (weighted F1-score) at each subsequent level in the CLC hierarchy. These metrics are 0.83 at level 1 (5 classes):, 0.63 at level 2 (14 classes), and 0.49 at level 3 (43 classes). This means that the hard-class maps are more reliable when aggregating classes to a higher level in the hierarchy (e.g. 'Discontinuous Urban Fabric' and 'Continuous Urban Fabric' to 'Urban Fabric'). Some single-class probabilities may more closely represent actual patterns for some classes that were overshadowed by unequal sample point distributions. Users are encouraged to set their own thresholds when postprocessing these datasets to optimize the accuracy for their specific use case. Uncertainty quantification: Uncertainty is quantified by taking the standard deviation of the probabilities predicted by the three components of the spatiotemporal ensemble model. Data validation approaches: The LULC classification was validated through spatial 5-fold cross-validation as detailed in the accompanying publication. Completeness: The dataset has chunks of empty predictions in regions with complex coast lines (e.g. the Zeeland province in the Netherlands and the Mar da Palha bay area in Portugal). These are artifacts that will be avoided in subsequent versions of the LULC product. Consistency: The accuracy of the predictions was compared per year and per 30km*30km tile across europe to derive temporal and spatial consistency by calculating the standard deviation. The standard deviation of annual weighted F1-score was 0.135, while the standard deviation of weighted F1-score per tile was 0.150. This means the dataset is more consistent through time than through space: Predictions are notably less accurate along the Mediterrranean coast. The accompanying publication contains additional information and visualisations. Positional accuracy: The raster layers have a resolution of 30m, identical to that of the Landsat data cube used as input features for the machine learning framework that predicted it. Temporal accuracy: The dataset contains predictions and uncertainty layers for each year between 2000 and 2019. Thematic accuracy: The maps reproduce the Corine Land Cover classification system, a hierarchical legend that consists of 5 classes at the highest level, 14 classes at the second level, and 44 classes at the third level. Class 523: Oceans was omitted due to computational constraints.

222: Cultivated parcels planted with fruit trees and shrubs, intended for fruit production, including nuts. The planting pattern can be by single or mixed fruit species, both in association with permanently grassy surfaces.

Overview: Potential Natural Vegetation (PNV): potential probability of occurrence for the Silver fir from 2018 to 2020 Traceability (lineage): This is an original dataset produced with a machine learning framework which used a combination of point datasets and raster datasets as inputs. Point dataset is a harmonized collection of tree occurrence data, comprising observations from National Forest Inventories (EU-Forest), GBIF and LUCAS. The complete dataset is available on Zenodo. Raster datasets used as input are: monthly time series air and surface temperature and precipitation from a reprocessed version of the Copernicus ERA5 dataset; long term averages of bioclimatic variables from CHELSA; elevation, slope and other elevation-derived metrics and long term monthly averages snow probability. For a more comprehensive list refer to Bonannella et al. (2022) (in review, preprint available at: https://doi.org/10.21203/rs.3.rs-1252972/v1). Scientific methodology: Probability and uncertainty maps were the output of a spatiotemporal ensemble machine learning framework based on stacked regularization. Three base models (random forest, gradient boosted trees and generalized linear models) were first trained on the input dataset and their predictions were used to train an additional model (logistic regression) which provided the final predictions. More details on the whole workflow are available in the listed publication. Usability: Probability maps are particularly useful when compared with existing products of potential distribution of species or when combined with maps of realized distribution: gaps in potential and realized distribution can be identified and used as information for future programs of tree planting or forest restoration. Uncertainty quantification: Uncertainty is quantified by taking the standard deviation of the probabilities predicted by the three components of the spatiotemporal ensemble model. Data validation approaches: Distribution maps were validated using a spatial 5-fold cross validation following the workflow detailed in the listed publication. Completeness: The raster files perfectly cover the entire Geo-harmonizer region as defined by the landmask raster dataset available here. Consistency: Areas which are outside of the calibration area of the point dataset (Iceland, Norway) usually have high uncertainty values. This is not only a problem of extrapolation but also of poor representation in the feature space available to the model of the conditions that are present in this countries. Positional accuracy: The rasters have a spatial resolution of 30m. Temporal accuracy: The maps cover the period 2018 - 2020 Thematic accuracy: Both probability and uncertainty maps contain values from 0 to 100: in the case of probability maps, they indicate the probability of occurrence of a single individual of the target species, while uncertainty maps indicate the standard deviation of the ensemble model.

osm: Greenhouses rasterized from OSM landuse polygons, first to 10m spatial resolution and after downsampled to 30m by spatial average.

324: Transitional bushy and herbaceous vegetation with occasional scattered trees. Can represent woodland degradation, forest regeneration / recolonization or natural succession. Areas representing natural development of forest formations, consisting of young plants of broad–leaved and coniferous species, with herbaceous vegetation and dispersed solitary adult trees. Transitional process can be for instance natural succession on abandoned agricultural land, regeneration of forest after damages of various origin (e.g. storm, avalanche), stages of forest degeneration caused by natural or anthropogenic stress factors (e.g. drought, pollution), reforestation after clearcutting, afforestation on formerly non-forested natural or semi-natural areas etc.

Overview: Actual Natural Vegetation (ANV): probability of occurrence for the Pedunculate oak in its realized environment for the period 2000 - 2033 Traceability (lineage): This is an original dataset produced with a machine learning framework which used a combination of point datasets and raster datasets as inputs. Point dataset is a harmonized collection of tree occurrence data, comprising observations from National Forest Inventories (EU-Forest), GBIF and LUCAS. The complete dataset is available on Zenodo. Raster datasets used as input are: harmonized and gapfilled time series of seasonal aggregates of the Landsat GLAD ARD dataset (bands and spectral indices); monthly time series air and surface temperature and precipitation from a reprocessed version of the Copernicus ERA5 dataset; long term averages of bioclimatic variables from CHELSA, tree species distribution maps from the European Atlas of Forest Tree Species; elevation, slope and other elevation-derived metrics; long term monthly averages snow probability and long term monthly averages of cloud fraction from MODIS. For a more comprehensive list refer to Bonannella et al. (2022) (in review, preprint available at: https://doi.org/10.21203/rs.3.rs-1252972/v1). Scientific methodology: Probability and uncertainty maps were the output of a spatiotemporal ensemble machine learning framework based on stacked regularization. Three base models (random forest, gradient boosted trees and generalized linear models) were first trained on the input dataset and their predictions were used to train an additional model (logistic regression) which provided the final predictions. More details on the whole workflow are available in the listed publication. Usability: Probability maps can be used to detect potential forest degradation and compositional change across the time period analyzed. Some possible applications for these topics are explained in the listed publication. Uncertainty quantification: Uncertainty is quantified by taking the standard deviation of the probabilities predicted by the three components of the spatiotemporal ensemble model. Data validation approaches: Distribution maps were validated using a spatial 5-fold cross validation following the workflow detailed in the listed publication. Completeness: The raster files perfectly cover the entire Geo-harmonizer region as defined by the landmask raster dataset available here. Consistency: Areas which are outside of the calibration area of the point dataset (Iceland, Norway) usually have high uncertainty values. This is not only a problem of extrapolation but also of poor representation in the feature space available to the model of the conditions that are present in this countries. Positional accuracy: The rasters have a spatial resolution of 30m. Temporal accuracy: The maps cover the period 2000 - 2020, each map covers a certain number of years according to the following scheme: (1) 2000--2002, (2) 2002--2006, (3) 2006--2010, (4) 2010--2014, (5) 2014--2018 and (6) 2018--2020 Thematic accuracy: Both probability and uncertainty maps contain values from 0 to 100: in the case of probability maps, they indicate the probability of occurrence of a single individual of the target species, while uncertainty maps indicate the standard deviation of the ensemble model.

corine: Landcover sample points

Overview: 243: Areas principally occupied with agriculture, interspersed with significantsemi-natural areas in a mosaic pattern. Traceability (lineage): This dataset was produced with a machine learning framework with several input datasets, specified in detail in Witjes et al., 2022 (in review, preprint available at https://doi.org/10.21203/rs.3.rs-561383/v3 ) Scientific methodology: The single-class probability layers were generated with a spatiotemporal ensemble machine learning framework detailed in Witjes et al., 2022 (in review, preprint available at https://doi.org/10.21203/rs.3.rs-561383/v3 ). The single-class uncertainty layers were calculated by taking the standard deviation of the three single-class probabilities predicted by the three components of the ensemble. The HCL (hard class) layers represents the class with the highest probability as predicted by the ensemble. Usability: The HCL layers have a decreasing average accuracy (weighted F1-score) at each subsequent level in the CLC hierarchy. These metrics are 0.83 at level 1 (5 classes):, 0.63 at level 2 (14 classes), and 0.49 at level 3 (43 classes). This means that the hard-class maps are more reliable when aggregating classes to a higher level in the hierarchy (e.g. 'Discontinuous Urban Fabric' and 'Continuous Urban Fabric' to 'Urban Fabric'). Some single-class probabilities may more closely represent actual patterns for some classes that were overshadowed by unequal sample point distributions. Users are encouraged to set their own thresholds when postprocessing these datasets to optimize the accuracy for their specific use case. Uncertainty quantification: Uncertainty is quantified by taking the standard deviation of the probabilities predicted by the three components of the spatiotemporal ensemble model. Data validation approaches: The LULC classification was validated through spatial 5-fold cross-validation as detailed in the accompanying publication. Completeness: The dataset has chunks of empty predictions in regions with complex coast lines (e.g. the Zeeland province in the Netherlands and the Mar da Palha bay area in Portugal). These are artifacts that will be avoided in subsequent versions of the LULC product. Consistency: The accuracy of the predictions was compared per year and per 30km*30km tile across europe to derive temporal and spatial consistency by calculating the standard deviation. The standard deviation of annual weighted F1-score was 0.135, while the standard deviation of weighted F1-score per tile was 0.150. This means the dataset is more consistent through time than through space: Predictions are notably less accurate along the Mediterrranean coast. The accompanying publication contains additional information and visualisations. Positional accuracy: The raster layers have a resolution of 30m, identical to that of the Landsat data cube used as input features for the machine learning framework that predicted it. Temporal accuracy: The dataset contains predictions and uncertainty layers for each year between 2000 and 2019. Thematic accuracy: The maps reproduce the Corine Land Cover classification system, a hierarchical legend that consists of 5 classes at the highest level, 14 classes at the second level, and 44 classes at the third level. Class 523: Oceans was omitted due to computational constraints.

ERA5-Land total precipitation monthly time series for Mauritania at 30 arc seconds (ca. 1000 meter) resolution (2019 - 2023) Source data: ERA5-Land is a reanalysis dataset providing a consistent view of the evolution of land variables over several decades at an enhanced resolution compared to ERA5. ERA5-Land has been produced by replaying the land component of the ECMWF ERA5 climate reanalysis. Reanalysis combines model data with observations from across the world into a globally complete and consistent dataset using the laws of physics. Reanalysis produces data that goes several decades back in time, providing an accurate description of the climate of the past. Total precipitation: Accumulated liquid and frozen water, including rain and snow, that falls to the Earth's surface. It is the sum of large-scale precipitation (that precipitation which is generated by large-scale weather patterns, such as troughs and cold fronts) and convective precipitation (generated by convection which occurs when air at lower levels in the atmosphere is warmer and less dense than the air above, so it rises). Precipitation variables do not include fog, dew or the precipitation that evaporates in the atmosphere before it lands at the surface of the Earth. This variable is accumulated from the beginning of the forecast time to the end of the forecast step. The units of precipitation are depth in metres. It is the depth the water would have if it were spread evenly over the grid box. Care should be taken when comparing model variables with observations, because observations are often local to a particular point in space and time, rather than representing averages over a model grid box and model time step. Processing steps: The original hourly ERA5-Land data has been spatially enhanced from 0.1 degree to 30 arc seconds (approx. 1000 m) spatial resolution by image fusion with CHELSA data (V1.2) (https://chelsa-climate.org/). For each day we used the corresponding monthly long-term average of CHELSA. The aim was to use the fine spatial detail of CHELSA and at the same time preserve the general regional pattern and fine temporal detail of ERA5-Land. The steps included aggregation and enhancement, specifically: 1. spatially aggregate CHELSA to the resolution of ERA5-Land 2. calculate proportion of ERA5-Land / aggregated CHELSA 3. interpolate proportion with a Gaussian filter to 30 arc seconds 4. multiply the interpolated proportions with CHELSA Using proportions ensures that areas without precipitation remain areas without precipitation. Only if there was actual precipitation in a given area, precipitation was redistributed according to the spatial detail of CHELSA. The spatially enhanced daily ERA5-Land data has been aggregated to monthly resolution, by calculating the sum of the precipitation per pixel over each month. File naming: ERA5_land_monthly_prectot_sum_30sec_YYYY_MM_01T00_00_00_int.tif e.g.:ERA5_land_monthly_prectot_sum_30sec_2023_12_01T00_00_00_int.tif The date within the filename is year and month of aggregated timestamp. Pixel values: mm * 10 Scaled to Integer, example: value 218 = 21.8 mm Projection + EPSG code: Latitude-Longitude/WGS84 (EPSG: 4326) Spatial extent: north: 28:18N south: 14:42N west: 17:05W east: 4:49W Temporal extent: January 2019 - December 2023 Spatial resolution: 30 arc seconds (approx. 1000 m) Temporal resolution: monthly Lineage: Dataset has been processed from original Copernicus Climate Data Store (ERA5-Land) data sources. As auxiliary data CHELSA climate data has been used. Software used: GRASS GIS 8.3.2 Format: GeoTIFF Original ERA5-Land dataset license: https://cds.climate.copernicus.eu/api/v2/terms/static/licence-to-use-copernicus-products.pdf CHELSA climatologies (V1.2): Data used: Karger D.N., Conrad, O., Böhner, J., Kawohl, T., Kreft, H., Soria-Auza, R.W., Zimmermann, N.E, Linder, H.P., Kessler, M. (2018): Data from: Climatologies at high resolution for the earth's land surface areas. Dryad digital repository. http://dx.doi.org/doi:10.5061/dryad.kd1d4 Original peer-reviewed publication: Karger, D.N., Conrad, O., Böhner, J., Kawohl, T., Kreft, H., Soria-Auza, R.W., Zimmermann, N.E., Linder, P., Kessler, M. (2017): Climatologies at high resolution for the Earth land surface areas. Scientific Data. 4 170122. https://doi.org/10.1038/sdata.2017.122 Representation type: Grid Processed by: mundialis GmbH & Co. KG, Germany (https://www.mundialis.de/) Contact: mundialis GmbH & Co. KG, info@mundialis.de Acknowledgements: This study was partially funded by EU grant 874850 MOOD. The contents of this publication are the sole responsibility of the authors and don't necessarily reflect the views of the European Commission.