Tomislav Hengl

• PhD
• Managing Director at OpenGeoHub foundation

Production and validation of an open global ensemble digital terrain model (GEDTM30) and derived land surface parameters at ∼30 m spatial resolution is described. Copernicus DEM, ALOS World3D, and object height models were combined in a data fusion approach to generate a globally consistent DTM. This DTM was then used to compute 15 standard land su...

The paper describes the production and evaluation of annual livestock densities of cattle, horses, sheep and goats (including per-pixel 95% probability prediction intervals) at 1 km spatial resolution for the 2000—2022 period using spatiotemporal Machine Learning. A compilation of subnational livestock census data has been imported, harmonized and...

The production and evaluation of the analysis-ready and cloud-optimized (ARCO) data cube for continental Europe (including Ukraine, the UK, and Türkiye), derived from the Landsat analysis-ready dataset version 2 (ARD V2) produced by Global Land Analysis and Discovery (GLAD) team and covering the period from 2000 to 2022, is described. The data cube...

This study presents a methodological framework for predicting soil organic carbon (SOC) using laboratory spectral recordings from a handheld near-infrared (NIR, 1350–2550 nm) device combined with open geospatial data derived from remote sensing sensors related to landform, climate, and vegetation. Initial experiments proved the superiority of convo...

Background Ticks are the primary vectors of numerous zoonotic pathogens, transmitting more pathogens than any other blood-feeding arthropod. In the northern hemisphere, tick-borne disease cases in humans, such as Lyme borreliosis and tick-borne encephalitis, have risen in recent years, and are a significant burden on public healthcare systems. The...

Soil spectroscopy is a widely used method for estimating soil properties that are important to environmental and agricultural monitoring. However, a bottleneck to its more widespread adoption is the need for establishing large reference datasets for training machine learning (ML) models, which are called soil spectral libraries (SSLs). Similarly, t...

The Anthropocene presents challenges for preserving and restoring ecosystems in human-altered landscapes. Policy development and landscape planning must consider long-term developments to maintain and restore functional ecosystems, ideally by using wildlife umbrella species as proxies. Forest and Landscape Restoration (FLR) aims to support both env...

The paper describes the production and evaluation of global grassland extent mapped annually for 2000–2022 at 30 m spatial resolution. The dataset showing the spatiotemporal distribution of cultivated and natural/semi-natural grassland classes was produced by using GLAD Landsat ARD-2 image archive, accompanied by climatic, landform and proximity co...

The paper describes production of a high spatial resolution (30 m) bimonthly Light Use Efficiency (LUE) based Gross Primary Productivity (GPP) data set representing grasslands for the period 2000 to 2022. The data set is based on using reconstructed global complete consistent bimonthly Landsat archive (400TB of data), combined with 1 km MOD11A1 tem...

Processing large collections of earth observation (EO) time-series, often petabyte-sized, such as NASA’s Landsat and ESA’s Sentinel missions, can be computationally prohibitive and costly. Despite their name, even the Analysis Ready Data (ARD) versions of such collections can rarely be used as direct input for modeling because of cloud presence and...

The paper describes the production of a high spatial resolution (30 m) soil type map for the pan-EU based on the IUSS's World Reference Base classification system and Ensemble Machine Learning with a large set of covariates. 19,680 legacy soil survey points collated from multiple national and European projects were harmonized and combined to produc...

The paper describes a comprehensive framework for soil organic carbon density (SOCD) (kg/m3) modeling and mapping, based on spatiotemporal Random Forest (RF) and Quantile Regression Forests (QRF). 22,428 SOCD measurements and a wide range of covariate layers—particularly the 30m Landsat-based spectral indices were used to fit models and produce 30~...

The production and evaluation of the Analysis Ready and Cloud Optimized (ARCO) data cube for continental Europe (including Ukraine, the UK, and Turkey), derived from the Landsat Analysis Ready Data version 2 (ARD V2) produced by Global Land Analysis and Discovery team (GLAD) and covering the period from 2000 to 2022 is described. The data cube cons...

The paper describes the production and evaluation of global grassland dynamics mapped annually for 2000-2022 at 30~m spatial resolution. The dataset showing the spatiotemporal distribution of cultivated and natural/semi-natural grassland classes was produced by using GLAD Landsat ARD-2 image archive, accompanied by climatic, landform and proximity...

The paper describes the production and evaluation of global grassland dynamics mapped annually for 2000-2022 at 30~m spatial resolution. The dataset showing the spatiotemporal distribution of cultivated and natural/semi-natural grassland classes was produced by using GLAD Landsat ARD-2 image archive, accompanied by climatic, landform and proximity...

The paper describes the production and evaluation of global grassland dynamics mapped annually for 2000-2022 at 30~m spatial resolution. The dataset showing the spatiotemporal distribution of cultivated and natural/semi-natural grassland classes was produced by using GLAD Landsat ARD-2 image archive, accompanied by climatic, landform and proximity...

Processing extremely large collections of Earth Observation (EO) time-series, often petabyte-sized, such as NASA's Landsat and ESA's Sentinel missions, can be computationally prohibitive and costly. Despite their name, even the Analysis Ready Data (ARD) versions of such collections can rarely be used as direct input for modeling and require additio...

Processing extremely large collections of Earth Observation (EO) time-series, often petabyte-sized, such as NASA's Landsat and ESA's Sentinel missions, can be computationally prohibitive and costly. Despite their name, even the Analysis Ready Data (ARD) versions of such collections can rarely be used as direct input for modeling and require additio...

The article presents results of using remote sensing images and machine learning to map and assess land potential based on time-series of potential Fraction of Absorbed Photosynthetically Active Radiation (FAPAR) composites. Land potential here refers to the potential vegetation productivity in the hypothetical absence of short–term anthropogenic i...

The impacts of the Anthropocene on climate and biodiversity pose societal and ecological problems that may only be solved by ecosystem restoration. Local to regional actions are required, which need to consider the prevailing present and future conditions of a certain landscape extent. Modeling approaches can be of help to support management effort...

Background Ticks are an important driver of veterinary health care, causing irritation and sometimes infection to their hosts. We explored epidemiological and geo-referenced data from > 7 million electronic health records (EHRs) from cats and dogs collected by the Small Animal Veterinary Surveillance Network (SAVSNET) in Great Britain (GB) between...

Soil spectroscopy is a widely used method for estimating soil properties that are important to environmental and agricultural monitoring. However, a bottleneck to its more widespread adoption is the need for establishing large reference datasets for training machine learning (ML) models, which are called soil spectral libraries (SSLs). Similarly, t...

Diffuse reflectance spectroscopy has been extensively employed to deliver timely and cost-effective predictions of a number of soil properties. However, although several soil spectral laboratories have been established worldwide, the distinct characteristics of instruments and operations still hamper further integration and interoperability across...

The paper presents results of using remote sensing time series and machine learning to map and assess land potential based on time-series of potential Fraction of Absorbed Photosynthetically Active Radiation (FAPAR) composites. Monthly aggregated FAPAR time series of three percentiles (0.05, 0.50 and 0.95 probability) at 250 m spatial resolution we...

The paper presents results of using remote sensing images and machine learning to map and assess land potential based on time-series of potential Fraction of Absorbed Photosynthetically Active Radiation (FAPAR) composites. Land potential here refers to the potential vegetation productivity in the hypothetical absence of short–term anthropogenic inf...

A three-dimensional predictive soil mapping approach for predicting soil organic carbon (SOC) stocks (t/ha) at high spatial resolution (30 m) for Alberta for 2020–2021 is described. A remote sensing data stack was first prepared covering Alberta’s agricultural lands. A total of 404 sampling locations were distributed across Alberta using 2-scale sa...

Using machine learning and earth observation data to capture real-world variability in spatial predictive mapping depends on sample size, design, and spatial extent. Nonetheless, there is still ambiguity in answering some basic questions: a) How many samples are necessary for fitting the model? b) Which sampling techniques are suitable for modeling...

This dataset presents global soil organic carbon stocks in mangrove forests at 30 m resolution, predicted for 2020. We used spatiotemporal ensemble machine learning to produce predictions of soil organic carbon content and bulk density (BD) to 1 m soil depth, which were then aggregated to calculate soil organic carbon stocks. This was done by using...

Here, we present and release the Global Rainfall Erosivity Database (GloREDa), a multi-source platform containing rainfall erosivity values for almost 4000 stations globally. The database was compiled through a global collaboration between a network of researchers, meteorological services and environmental organisations from 65 countries. GloREDa i...

The global potential distribution of biomes (natural vegetation) was modelled using 8,959 training points from the BIOME 6000 dataset and a stack of 72 environmental covariates representing terrain and the current climatic conditions based on historical long term averages (1979-2013). An ensemble machine learning model based on stacked regularizati...

The article describes the production steps and accuracy assessment of an analysis-ready, open-access European data cube consisting of 2000–2020+ Landsat data, 2017–2021+ Sentinel-2 data and a 30 m resolution digital terrain model (DTM). The main purpose of the data cube is to make annual continental-scale spatiotemporal machine learning tasks acces...

The global potential distribution of biomes (natural vegetation) was modelled using 8959 training points from the BIOME 6000 dataset and a stack of 72 environmental covariates representing terrain and the current climatic conditions based on historical long term averages (1979–2013). An ensemble machine learning model based on stacked regularizatio...

Background: Ticks are an important driver of veterinary health care, causing infection and irritation to their hosts. Monitoring and mapping tick occurrences on companion animals can help understand and map risks for tick attachment in pets. Methods: Over seven million electronic health records (EHRs), among which 11741 EHRs reported tick attachme...

The paper describes production steps and accuracy assessment of an analysis-ready open environmental data cube (2000--2021+) for continental Europe; at working resolutions from 10~m to 30~m and with quarterly to annual estimates. The data cube is based on processing and harmonizing earth observation (EO) images: Landsat GLAD ARD (2000- -2020+), Sen...

The paper describes production steps and accuracy assessment of an analysis-ready open environmental data cube (2000--2021+) for continental Europe; at working resolutions from 10~m to 30~m and with quarterly to annual estimates. The data cube is based on processing and harmonizing earth observation (EO) images: Landsat GLAD ARD (2000- -2020+), Sen...

The paper describes production steps and accuracy assessment of an analysis-ready (complete, consistent, correct and current) open environmental data cube (2000–2021+) for continental Europe; at working resolutions from 10 m to 30 m and with quarterly to annual estimates. The data cube is based on processing and harmonizing earth observation (EO) i...

The paper describes the production steps and accuracy assessment of an analysis-ready, open-access European data cube consisting of 2000–2020+ Landsat data, 2017–2021+ Sentinel-2 data and a 30m resolution Digital Terrain Model (DTM). The main purpose of the data cube is to make annual continental-scale spatiotemporal machine learning tasks accessib...

Most agricultural soils have experienced substantial soil organic carbon losses in time. These losses motivate recent calls to restore organic carbon in agricultural lands to improve biogeochemical cycling and for climate change mitigation. Declines in organic carbon also reduce soil infiltration and water holding capacity, which may have important...

The document provides information for transparency and reproducibility of the study according to the standard for species distribution modeling (ODMAP protocol) from Zurrell et al. (2020). Additional information reported include: (1) implementation strategy and results of spatial filtering operation, (2) hyperparameter space for model optimization...

This paper describes a data-driven framework based on spatiotemporal machine learning to produce distribution maps for 16 tree species (Abies alba Mill., Castanea sativa Mill., Corylus avellana L., Fagus sylvatica L., Olea europaea L., Picea abies L. H. Karst., Pinus halepensis Mill., Pinus nigra J. F. Arnold, Pinus pinea L., Pinus sylvestris L., P...

The representation of land surface processes in hydrological and climatic models critically depends on the soil water characteristics curve (SWCC) that defines the plant availability and water storage in the vadose zone. Despite the availability of SWCC datasets in the literature, significant efforts are required to harmonize reported data before S...

A spatiotemporal machine learning framework for automated prediction and analysis of long-term Land Use/Land Cover dynamics is presented. The framework includes: (1) harmonization and preprocessing of spatial and spatiotemporal input datasets (GLAD Landsat, NPP/VIIRS) including five million harmonized LUCAS and CORINE Land Cover-derived training sa...

This paper describes a data-driven framework based on spatiotemporal machine learning to produce distribution maps for 16 tree species (Abies alba Mill., Castanea sativa Mill., Corylus avellana L., Fagus sylvatica L., Olea europaea L., Picea abies L. H. Karst., Pinus halepensis Mill., Pinus nigra J. F. Arnold, Pinus pinea L., Pinus sylvestris L., P...

The poster describes a data-driven framework based on spatio-temporal ensemble machine learning to produce distribution maps for 16 tree species at high spatial resolution (30m). Tree occurrence data for a total of 3 million of points was used to train different Machine Learning (ML) algorithms: random forest, gradient-boosted trees, generalized li...

Hydrological and climatic modeling of near-surface water and energy fluxes is critically dependent on the availability of soil hydraulic parameters. Key among these parameters is the soil water characteristic curve (SWCC), a function relating soil water content (θ) to matric potential (ψ). The direct measurement of SWCC is laborious, hence, reporte...

This paper describes a data-driven framework based on spatiotemporal machine learning to produce distribution maps for 16 tree species (Abies alba Mill., Castanea sativa Mill., Corylus avellana L., Fagus sylvatica L., Olea europaea L., Picea abies L. H. Karst., Pinus halepensis Mill., Pinus nigra J. F. Arnold, Pinus pinea L., Pinus sylvestris L., P...

As part of the environmental regulatory framework to minimize risk to receptors, concentrations of chemicals in soil or water exceeding regulatory guidelines that can be attributed to industrial activities at a site require remediation and/or monitoring. This process is complicated by the fact that various chemical parameters are naturally elevated...

A seamless spatiotemporal machine learning framework for automated prediction, uncertainty assessment, and analysis of land use / land cover (LULC) dynamics is presented. The framework includes: (1) harmonization and preprocessing of high-resolution spatial and spatiotemporal covariate datasets (GLAD Landsat, NPP/VIIRS) including 5 million harmoniz...

A seamless spatiotemporal machine learning framework for automated prediction, uncertainty assessment, and analysis of long-term LULC dynamics is presented. The framework includes: (1) harmonization and preprocessing of high-resolution spatial and spatiotemporal input datasets (GLAD Landsat, NPP/VIIRS) including 5~million harmonized LUCAS and CORIN...

A seamless spatiotemporal machine learning framework for automated prediction and analysis of long-term Land Use / Land Cover dynamics is presented. The framework includes: (1) harmonization and preprocessing of high-resolution spatial and spatiotemporal input datasets (GLAD Landsat, NPP/VIIRS) including 5 million harmonized LUCAS and CORINE Land C...

A spatiotemporal machine learning framework for automated prediction and analysis of long-term Land Use / Land Cover dynamics is presented. The framework includes: (1) harmonization and preprocessing of spatial and spatiotemporal input datasets (GLAD Landsat, NPP/VIIRS) including 5 million harmonized LUCAS and CORINE Land Cover-derived training sam...

The saturated soil hydraulic conductivity (Ksat) is a key parameter in many hydrological and climate models. Ksat values are primarily determined from basic soil properties and may vary over several orders of magnitude. Despite the availability of Ksat datasets in the literature, significant efforts are required to combine the data before they can...

Soil property and class maps for the continent of Africa were so far only available at very generalised scales, with many countries not mapped at all. Thanks to an increasing quantity and availability of soil samples collected at field point locations by various government and/or NGO funded projects, it is now possible to produce detailed pan-Afric...

Soil property and class maps for the continent of Africa were so far only available at very generalised scales, with many countries not mappedat all. Thanks to an increasing quantity and availability of soil samples collected at field point locations by various government and/or NGOfunded projects, it is now possible to produce detailed pan-African...

Saturated soil hydraulic conductivity (Ksat) is a key parameter in many hydrological and climatic modeling applications, as it controls the partitioning between precipitation, infiltration and runoff. Ksat values are primarily determined from soil textural properties and soil forming processes, and may vary over several orders of magnitude. Despite...

Soil organic carbon (SOC) information is fundamental for improving global carbon cycle modeling efforts, but discrepancies exist from country‐to‐global scales. We predicted the spatial distribution of SOC stocks (topsoil; 0–30 cm) and quantified modeling uncertainty across Mexico and the conterminous United States (CONUS). We used a multisource SOC...

Most soil hydraulic information used in Earth System Models (ESMs) is derived from pedo-transfer functions that use easy-to-measure soil attributes to estimate hydraulic parameters. This parameterization relies heavily on soil texture, but overlooks the critical role of soil structure originated by soil biophysical activity. Soil structure omission...

Rapid losses of mangroves over the past 50 years have had negative consequences on the environment, climate, and humanity, through diminished benefits such as carbon storage, coastal protection and fish production. Restoration of mangrove forests is possible, and has already been undertaken in many settings, but such efforts have been piecemeal, an...

Using the term "Open data" has become a bit of a fashion, but using it without clear specifications is misleading i.e. it can be considered just an empty phrase. Probably even worse is the term "Open Science" — can science be NOT open at all? Are we reinventing something that should be obvious from start? This guide tries to clarify some key aspect...

Random forest and similar Machine Learning techniques are already used to generate spatial predictions, but spatial location of points (geography) is often ignored in the modeling process. Spatial auto-correlation, especially if still existent in the cross-validation residuals, indicates that the predictions are maybe biased, and this is suboptimal...

RFsp—Random Forest for spatial data (R tutorial)

Potential natural vegetation (PNV) is the vegetation cover in equilibrium with climate, that would exist at a given location if not impacted by human activities. PNV is useful for raising public awareness about land degradation and for estimating land potential. This paper presents results of assessing machine learning algorithms—neural networks (n...

Using the term "Open data" has become a bit of a fashion, but using it without clear specifications is misleading i.e. it can be considered just an empty phrase. Probably even worse is the term "Open Science" — can science be NOT open at all? Are we reinventing something that should be obvious from start? This guide tries to clarify some key aspect...

Using the term "Open data" has become a bit of a fashion, but using it without clear specifications is misleading i.e. it can be considered just an empty phrase. Probably even worse is the term "Open Science" — can science be NOT open at all? Are we reinventing something that should be obvious from start? This guide tries to clarify some key aspect...

In rainfed crop production, root zone plant-available water holding capacity (RZ-PAWHC) of the soil has a large influence on crop growth and the yield response to management inputs such as improved seeds and fertilisers. However, data are lacking for this parameter in sub-Saharan Africa (SSA). This study produced the first spatially explicit, coher...

Random forest and similar Machine Learning techniques are already used to generate spatial predictions, but spatial location of points (geography) is often ignored in the modeling process. Spatial auto-correlation, especially if still existent in the cross-validation residuals, indicates that the predictions are maybe biased, and this is suboptimal...

Random forest and similar Machine Learning techniques are already used to generate spatial predictions, but spatial location of points (geography) is often ignored in the modeling process. Spatial auto-correlation, especially if still existent in the cross-validation residuals, indicates that the predictions are maybe biased, and this is suboptimal...

Potential Natural Vegetation (PNV) is the vegetation cover in equilibrium with climate, that would exist at a given location non-impacted by human activities. PNV is useful for raising public awareness about land degradation and for estimating land potential. This paper presents results of assessing Machine Learning Algorithms (MLA) for operational...

Potential Natural Vegetation (PNV) is the vegetation cover in equilibrium with climate, that would exist at a given location non-impacted by human activities. PNV is useful for raising public awareness about land degradation and for estimating land potential. This paper presents results of assessing Machine Learning Algorithms (MLA) for operational...

Random forest and similar Machine Learning techniques are already used to generate spatial predictions, but spatial location of points (geography) is often ignored in the modeling process. Spatial auto-correlation, especially if still existent in the cross-validation residuals, indicates that the predictions are maybe biased, and this is suboptimal...

With the growing recognition that effective action on climate change will require a combination of emissions reductions and carbon sequestration, protecting, enhancing and restoring natural carbon sinks have become political priorities. Mangrove forests are considered some of the most carbon-dense ecosystems in the world with most of the carbon sto...

An approach for using lasso (Least Absolute Shrinkage and Selection Operator) regression in creating sparse 3D models of soil properties for spatial prediction at multiple depths is presented. Modeling soil properties in 3D benefits from interactions of spatial predictors with soil depth and its polynomial expansion, which yields a large number of...

Potential Natural Vegetation (PNV) is the vegetation cover in equilibrium with climate, that would exist at a given location non-impacted by human activities. PNV is useful for raising public awareness about land degradation and for estimating land potential. This paper presents results of assessing Machine Learning Algorithms (MLA) for operational...

Random forest and similar Machine Learning techniques are already used to generate spatial predictions, but spatial location of points (geography) is often ignored in the modeling process. Spatial auto-correlation, especially if still existent in the cross-validation residuals, indicates that the predictions are maybe biased, and this is suboptimal...

This study evaluates the SoilGrids as predictors, using points data from Cameroon national soil profiles data compilation, together with a set of covariates representing soil forming factors. Much effort was placed on the preparation of the Cameroon soil database (Camsadat 0.1). We predicted Soil Organic Carbon and Clay content at 250m resolution i...

Motivation Past sea level fluctuations have shaped island area and archipelago configuration. The availability of global high‐resolution data on bathymetry and past sea levels allows reconstruction of island palaeo‐geography. Studies on the role of palaeo‐area often consider only the Last Glacial Maximum, which neglects the dynamics of island fusio...

Core Ideas Ensemble machine learning methods were used to obtain gridded soil property and class maps. Final predictions were generated for six soil properties and two soil classes at 100‐m resolution. Soil data are easier to integrate with spatially explicit models compared with multicomponent map units. Soil property maps are available at seven s...

Legacy soil data have been produced over 70 years in nearly all countries of the world. Unfortunately, data, information and knowledge are still currently fragmented and at risk of getting lost if they remain in a paper format. To process this legacy data into consistent, spatially explicit and continuous global soil information, data are being res...

Core Ideas A soil bulk density pedotransfer function for the conterminous United States. Across a climate gradient, PTF provided bulk densities to estimate SOC stocks. PTF model and the resulting bulk density estimates are available for use under an Open Data license. This paper describes a method to develop a soil bulk density pedotransfer functi...