Mateo Gašparović
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Mateo Gašparović has a total of 128 co-authors. Here are the top co-authors by number of shared publications:
- Dorijan Radočaj
Faculty of Agrobiotechnical Sciences Osijek, Josip Juraj Strossmayer University of Osijek, Vladimira Preloga 1, 31000 Osijek, Croatia
12 shared publications - Mladen Jurišić
Faculty of Agrobiotechnical Sciences Osijek, Josip Juraj Strossmayer University of Osijek, Vladimira Preloga 1, 31000 Osijek, Croatia
11 shared publications - Dino Dobrinić
Chair of Geoinformatics, Faculty of Geodesy, University of Zagreb, 10000 Zagreb, Croatia
7 shared publications - Ivan Balenović
Division for Forest Management and Forestry Economics, Croatian Forest Research Institute, Cvjetno naselje 41, 10450 Jastrebarsko, Croatia
5 shared publications - Ivan Pilaš
Croatian Forest Research Institute, Division of Ecology, Cvjetno naselje 41, 10450 Jastrebarsko, Croatia
5 shared publications D. Medak
Faculty of Geodesy, Chair of Geoinformatics, University of Zagreb, 10000 Zagreb, Croatia
4 shared publications
Latest Publications
- Open Access
- 2 October 2026
- Published by MDPI AG in Smart Cities
- Vol. 9 (10) , 166
Developing a Machine Learning Approach for Estimating Urban NO2 Concentrations Using Multi-Source Remote Sensing Data
Accurate estimation of air pollutants, particularly nitrogen dioxide (NO2), is essential for assessing air quality and supporting informed policy decisions. This study investigates the application of machine learning techniques to estimate ground-level NO2 concentrations in the city of Zagreb, employing two ensemble machine learning methods: Random Forest (RF) and Extreme Gradient Boosting (XGB). The resulting models were developed using a multivariable modelling approach that integrated diverse data sources, including ground-based measurements from national air quality monitoring stations, publicly available satellite data collected through remote sensing (i.e., TROPOMI on Sentinel-5P and MSI on Sentinel-2), and meteorological and climate variables from the ERA5 reanalysis dataset and Copernicus Climate Change Service (C3S). These variables capture spatial, temporal, and atmospheric dynamics relevant to NO2 distribution across the urban area. Performance metrics indicate strong predictive capabilities, with the RF model achieving R2 = 0.74, RMSE = 9.86 µg/m3, and MAE = 6.89 µg/m3, while the XGB model yielded slightly better results (R2 = 0.78; RMSE = 8.76 µg/m3; MAE = 6.09 µg/m3). Analysis using SHAP values revealed that the tropospheric vertical column of NO2, elevation, and boundary layer height are the variables with greatest importance in both models. High-resolution maps of estimated ground-level NO2 concentrations were generated for the area of interest to gain insight into the spatial visualization of pollutant distribution across the city. Furthermore, a detailed seasonality analysis was performed, which indicated elevated NO2 levels during autumn and winter, with lower concentrations observed in spring and summer. These seasonal variations are likely driven by changes in meteorological conditions, emission sources, and atmospheric dispersion characteristics. This study has shown that high-quality models for local mapping the pollutant NO2 can be developed using data from air quality monitoring stations and publicly available data from the Copernicus programme.
- 2 October 2026
- Published by MDPI AG in Smart Cities
- Vol. 9 (10) , 166
Open AccessDeveloping a Machine Learning Approach for Estimating Urban NO2 Concentrations Using Multi-Source Remote Sensing Data
Accurate estimation of air pollutants, particularly nitrogen dioxide (NO2), is essential for assessing air quality and supporting informed policy decisions. This study investigates the application of machine learning techniques to estimate ground-level NO2 concentrations in the city of Zagreb, employing two ensemble machine learning methods: Random Forest (RF) and Extreme Gradient Boosting (XGB). The resulting models were developed using a multivariable modelling approach that integrated diverse data sources, including ground-based measurements from national air quality monitoring stations, publicly available satellite data collected through remote sensing (i.e., TROPOMI on Sentinel-5P and MSI on Sentinel-2), and meteorological and climate variables from the ERA5 reanalysis dataset and Copernicus Climate Change Service (C3S). These variables capture spatial, temporal, and atmospheric dynamics relevant to NO2 distribution across the urban area. Performance metrics indicate strong predictive capabilities, with the RF model achieving R2 = 0.74, RMSE = 9.86 µg/m3, and MAE = 6.89 µg/m3, while the XGB model yielded slightly better results (R2 = 0.78; RMSE = 8.76 µg/m3; MAE = 6.09 µg/m3). Analysis using SHAP values revealed that the tropospheric vertical column of NO2, elevation, and boundary layer height are the variables with greatest importance in both models. High-resolution maps of estimated ground-level NO2 concentrations were generated for the area of interest to gain insight into the spatial visualization of pollutant distribution across the city. Furthermore, a detailed seasonality analysis was performed, which indicated elevated NO2 levels during autumn and winter, with lower concentrations observed in spring and summer. These seasonal variations are likely driven by changes in meteorological conditions, emission sources, and atmospheric dispersion characteristics. This study has shown that high-quality models for local mapping the pollutant NO2 can be developed using data from air quality monitoring stations and publicly available data from the Copernicus programme.
- Open Access
- 30 July 2026
- Published by Copernicus GmbH in The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences
- Vol. XLIX-B3-20, 589-594
Automatic Estimation of Building Construction Year and Height from Earth Observation Data for Urban Risk Assessment
Reliable urban risk assessment requires accurate and up-to-date information on building characteristics, particularly construction year and height, which are often incomplete or unavailable in existing databases. This study presents a cloud-based methodology for the automatic estimation of these parameters using multispectral and very high-resolution Earth Observation (EO) data. The proposed approach integrates temporal analysis of multispectral satellite imagery (Sentinel-2 and Landsat) with photogrammetric processing of very high-resolution stereo imagery (Pléiades). Building construction year is estimated by detecting temporal changes in spectral indices using spline-based modeling and discrete-difference analysis, achieving an accuracy of better than ±3 years. Building height is derived from digital surface models generated from satellite stereo imagery, with a mean accuracy of less than 2 m relative to LiDAR reference data (~1.40 m). The methodology was implemented in a cloud computing environment (Google Earth Engine and Google Colab) and tested in the City of Zagreb, Croatia. Validation results show robust performance, with an F1-score of 0.819 for construction year estimation and strong agreement between EO-derived and LiDAR-based height values. The results demonstrate the potential of EO-based methods for scalable, reliable extraction of building information, thereby supporting improved urban risk assessment and decision-making.
- 30 July 2026
- Published by Copernicus GmbH in The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences
- Vol. XLIX-B3-20, 589-594
Open AccessAutomatic Estimation of Building Construction Year and Height from Earth Observation Data for Urban Risk Assessment
Reliable urban risk assessment requires accurate and up-to-date information on building characteristics, particularly construction year and height, which are often incomplete or unavailable in existing databases. This study presents a cloud-based methodology for the automatic estimation of these parameters using multispectral and very high-resolution Earth Observation (EO) data. The proposed approach integrates temporal analysis of multispectral satellite imagery (Sentinel-2 and Landsat) with photogrammetric processing of very high-resolution stereo imagery (Pléiades). Building construction year is estimated by detecting temporal changes in spectral indices using spline-based modeling and discrete-difference analysis, achieving an accuracy of better than ±3 years. Building height is derived from digital surface models generated from satellite stereo imagery, with a mean accuracy of less than 2 m relative to LiDAR reference data (~1.40 m). The methodology was implemented in a cloud computing environment (Google Earth Engine and Google Colab) and tested in the City of Zagreb, Croatia. Validation results show robust performance, with an F1-score of 0.819 for construction year estimation and strong agreement between EO-derived and LiDAR-based height values. The results demonstrate the potential of EO-based methods for scalable, reliable extraction of building information, thereby supporting improved urban risk assessment and decision-making.
- Open Access
- 30 April 2026
- Published by MDPI AG in Atmosphere
- Vol. 17 (5) , 466
Spatial Decoupling of Surface and Atmospheric Urban Heat: Differential Land Cover Associations in Zagreb
Urban heat islands present a significant obstacle to climate adaptation strategies, yet the interplay between surface and atmospheric thermal elements is not fully understood. This research investigates the spatial relationship between land surface temperature (LST) and near-surface air temperature (TAIR) across Zagreb’s 218 local councils during the summer of 2024, assessing the premise that these constitute separate thermal dimensions with varying land cover correlations. Landsat 8/9-derived LST and CERRA-derived TAIR, temporally aligned to the Landsat overpass slot (09:00 UTC), were examined through spatial autocorrelation (Moran’s I, Getis–Ord Gi*), correlation analysis, and Fisher’s z-tests to compare the effects of the Normalized Difference Vegetation Index (NDVI) and Normalized Difference Built-up Index (NDBI). The findings indicated partial coupling (r = 0.537, R2 = 0.288), with 71.2% of the variance remaining unexplained, suggesting considerable surface-atmospheric decoupling. Furthermore, hot spot overlap analysis revealed limited convergence (11.9% of neighborhoods), while 44.5% displayed divergent thermal extremes. Land cover showed much stronger connections with LST (NDVI: r = −0.970, R2 = 0.941; NDBI: r = +0.973, R2 = 0.947) than with TAIR (NDVI: r = −0.478; NDBI: r = +0.496), representing reductions in explained variance of 63–64% (p < 0.001). These findings suggest that surface and atmospheric urban heat are related but distinct thermal aspects.
- 30 April 2026
- Published by MDPI AG in Atmosphere
- Vol. 17 (5) , 466
Open AccessSpatial Decoupling of Surface and Atmospheric Urban Heat: Differential Land Cover Associations in Zagreb
Urban heat islands present a significant obstacle to climate adaptation strategies, yet the interplay between surface and atmospheric thermal elements is not fully understood. This research investigates the spatial relationship between land surface temperature (LST) and near-surface air temperature (TAIR) across Zagreb’s 218 local councils during the summer of 2024, assessing the premise that these constitute separate thermal dimensions with varying land cover correlations. Landsat 8/9-derived LST and CERRA-derived TAIR, temporally aligned to the Landsat overpass slot (09:00 UTC), were examined through spatial autocorrelation (Moran’s I, Getis–Ord Gi*), correlation analysis, and Fisher’s z-tests to compare the effects of the Normalized Difference Vegetation Index (NDVI) and Normalized Difference Built-up Index (NDBI). The findings indicated partial coupling (r = 0.537, R2 = 0.288), with 71.2% of the variance remaining unexplained, suggesting considerable surface-atmospheric decoupling. Furthermore, hot spot overlap analysis revealed limited convergence (11.9% of neighborhoods), while 44.5% displayed divergent thermal extremes. Land cover showed much stronger connections with LST (NDVI: r = −0.970, R2 = 0.941; NDBI: r = +0.973, R2 = 0.947) than with TAIR (NDVI: r = −0.478; NDBI: r = +0.496), representing reductions in explained variance of 63–64% (p < 0.001). These findings suggest that surface and atmospheric urban heat are related but distinct thermal aspects.
- Open Access
Disentangling Climate and Demographic Drivers of Urban Heat Risk: A Geographically Weighted Regression Analysis of Zagreb (2001–2024)
Urban heat risk is intensifying globally, yet the relative contributions of climate warming and demographic restructuring to spatiotemporal risk change remain poorly understood, particularly in post-socialist cities experiencing simultaneous thermal intensification and population aging. This study develops a Heat Risk Population Index (HRPI) integrating satellite-derived land surface temperature, CERRA reanalysis air temperature, and census-based demographic sensitivity for 218 Zagreb neighborhood councils (2001–2024). A multi-scale analytical framework combining additive decomposition, enhanced partial correlations, and geographically weighted regression (GWR) was applied to disentangle the drivers of heat risk change. HRPI increased significantly across all neighborhood councils (mean ΔHRPI = 0.197, p < 0.001), with strong positive spatial autocorrelation (Moran’s I = 0.416). While air temperature change dominated the city-wide mean increase (72.1%), demographic sensitivity change explained the largest share of spatial variance across neighborhood councils (partial r = 0.677 vs. 0.524 for air temperature), driven by spatially heterogeneous demographic transitions—youth out-migration, aging-in-place in southeastern post-socialist estates, and gentrification in central districts. GWR substantially outperformed global OLS (ΔAICc = 60.1; Adj. R2: 0.649 → 0.816), with local demographic effect sizes varying fivefold across the city. These results demonstrate that heat risk drivers operate at distinct spatial scales: climate dominates city-wide magnitude while demographics determine spatial differentiation. Effective adaptation requires universal thermal interventions combined with spatially targeted demographic strategies in identified hotspot neighborhoods. The multi-scale framework is applicable to other post-socialist cities undergoing concurrent climate and demographic change.
Open AccessDisentangling Climate and Demographic Drivers of Urban Heat Risk: A Geographically Weighted Regression Analysis of Zagreb (2001–2024)
Urban heat risk is intensifying globally, yet the relative contributions of climate warming and demographic restructuring to spatiotemporal risk change remain poorly understood, particularly in post-socialist cities experiencing simultaneous thermal intensification and population aging. This study develops a Heat Risk Population Index (HRPI) integrating satellite-derived land surface temperature, CERRA reanalysis air temperature, and census-based demographic sensitivity for 218 Zagreb neighborhood councils (2001–2024). A multi-scale analytical framework combining additive decomposition, enhanced partial correlations, and geographically weighted regression (GWR) was applied to disentangle the drivers of heat risk change. HRPI increased significantly across all neighborhood councils (mean ΔHRPI = 0.197, p < 0.001), with strong positive spatial autocorrelation (Moran’s I = 0.416). While air temperature change dominated the city-wide mean increase (72.1%), demographic sensitivity change explained the largest share of spatial variance across neighborhood councils (partial r = 0.677 vs. 0.524 for air temperature), driven by spatially heterogeneous demographic transitions—youth out-migration, aging-in-place in southeastern post-socialist estates, and gentrification in central districts. GWR substantially outperformed global OLS (ΔAICc = 60.1; Adj. R2: 0.649 → 0.816), with local demographic effect sizes varying fivefold across the city. These results demonstrate that heat risk drivers operate at distinct spatial scales: climate dominates city-wide magnitude while demographics determine spatial differentiation. Effective adaptation requires universal thermal interventions combined with spatially targeted demographic strategies in identified hotspot neighborhoods. The multi-scale framework is applicable to other post-socialist cities undergoing concurrent climate and demographic change.
- Open Access
- 4 April 2026
- Published by Wiley in River Research and Applications
- Vol. 42 (6) , 1223-1238
Meander‐Bend Erosion Dynamics Along a Gravel‐Bed River: Insights From Short‐Term UAV Monitoring
Riverbank erosion is a natural process in meandering rivers that contributes to sediment supply and geomorphic diversity, yet it can threaten infrastructure and human activities within the floodplain. Recently, many studies have used high‐resolution remote sensing technologies to measure bank erosion, but they often focus on technical aspects or platform comparisons rather than analyzing the geomorphic and hydrological drivers of its spatial variability. This research aimed to investigate short‐term patterns and controlling factors of bank erosion at 10 meander bends along an actively eroding gravel‐bed river. Repeated field surveys involving UAV (unmanned aerial vehicle) data acquisition and GNSS (Global Navigation Satellite System) measurements were conducted between March 2022 and May 2024, covering periods of both significant floods and low‐flow conditions. Three key bank erosion metrics were calculated: bank retreat rate, area of eroded floodplain, and volume of eroded material. Riverbank lines were automatically vectorized using Laplacian edge detection filtering of digital surface models (DSMs) in GIS, and erosion volumes were quantified through temporal DSM differencing. The results indicated that erosion rates were positively correlated with meander sinuosity only during the high discharge period. Greater erosion was generally measured in meanders with grass‐covered banks compared to those stabilized by woody vegetation. This study contributes to understanding the short‐term dynamics of riverbank erosion at high spatial resolution, particularly under varying flow conditions. It also presents a practical workflow based on UAV data for rapid bankline delineation and erosion quantification, offering a valuable tool for river management.
- 4 April 2026
- Published by Wiley in River Research and Applications
- Vol. 42 (6) , 1223-1238
Open AccessMeander‐Bend Erosion Dynamics Along a Gravel‐Bed River: Insights From Short‐Term UAV Monitoring
Riverbank erosion is a natural process in meandering rivers that contributes to sediment supply and geomorphic diversity, yet it can threaten infrastructure and human activities within the floodplain. Recently, many studies have used high‐resolution remote sensing technologies to measure bank erosion, but they often focus on technical aspects or platform comparisons rather than analyzing the geomorphic and hydrological drivers of its spatial variability. This research aimed to investigate short‐term patterns and controlling factors of bank erosion at 10 meander bends along an actively eroding gravel‐bed river. Repeated field surveys involving UAV (unmanned aerial vehicle) data acquisition and GNSS (Global Navigation Satellite System) measurements were conducted between March 2022 and May 2024, covering periods of both significant floods and low‐flow conditions. Three key bank erosion metrics were calculated: bank retreat rate, area of eroded floodplain, and volume of eroded material. Riverbank lines were automatically vectorized using Laplacian edge detection filtering of digital surface models (DSMs) in GIS, and erosion volumes were quantified through temporal DSM differencing. The results indicated that erosion rates were positively correlated with meander sinuosity only during the high discharge period. Greater erosion was generally measured in meanders with grass‐covered banks compared to those stabilized by woody vegetation. This study contributes to understanding the short‐term dynamics of riverbank erosion at high spatial resolution, particularly under varying flow conditions. It also presents a practical workflow based on UAV data for rapid bankline delineation and erosion quantification, offering a valuable tool for river management.
- Open Access
- 31 March 2026
- Published by Croatian Geodetic Society in Geodetski list: Journal of the Croatian Geodetic Society
- Vol. 80 (103) (1) , 17-38
Analiza prostornih podataka za praćenje kvalitete zraka
Ovaj rad daje pregled praćenja kvalitete zraka, naglašavajući koliko je precizno i kontinuirano praćenje ključno za zaštitu ljudskog zdravlja u suvremenom svijetu, gdje su posljedice zagađenja zraka ozbiljan javnozdravstveni izazov. Posebna pažnja posvećena je dušikovom dioksidu (NO2), jednom od najvažnijih pokazatelja urbanog onečišćenja zraka. Analiza se temelji na podacima prizemnih koncentracija NO2, kao i atmosferskih koncentracija NO2 dobivenih satelitskim mjerenjima, uz dodatnu analizu meteoroloških, atmosferskih i geomorfoloških podataka kako bi se istražila prostorna i vremenska varijabilnost NO2 na području Zagreba. Rezultati pokazuju da satelitske metode značajno nadopunjuju ograničenja točkastih mjerenja i omogućuju detaljnije razumijevanje i praćenje zagađenja, dok istovremeno ukazuju na složenost odnosa između NO2, meteoroloških uvjeta i urbanih čimbenika. Rad također naglašava potrebu za naprednim modelima u svrhu preciznije procjene i praćenja kvalitete zraka.
- 31 March 2026
- Published by Croatian Geodetic Society in Geodetski list: Journal of the Croatian Geodetic Society
- Vol. 80 (103) (1) , 17-38
Open AccessAnaliza prostornih podataka za praćenje kvalitete zraka
Ovaj rad daje pregled praćenja kvalitete zraka, naglašavajući koliko je precizno i kontinuirano praćenje ključno za zaštitu ljudskog zdravlja u suvremenom svijetu, gdje su posljedice zagađenja zraka ozbiljan javnozdravstveni izazov. Posebna pažnja posvećena je dušikovom dioksidu (NO2), jednom od najvažnijih pokazatelja urbanog onečišćenja zraka. Analiza se temelji na podacima prizemnih koncentracija NO2, kao i atmosferskih koncentracija NO2 dobivenih satelitskim mjerenjima, uz dodatnu analizu meteoroloških, atmosferskih i geomorfoloških podataka kako bi se istražila prostorna i vremenska varijabilnost NO2 na području Zagreba. Rezultati pokazuju da satelitske metode značajno nadopunjuju ograničenja točkastih mjerenja i omogućuju detaljnije razumijevanje i praćenje zagađenja, dok istovremeno ukazuju na složenost odnosa između NO2, meteoroloških uvjeta i urbanih čimbenika. Rad također naglašava potrebu za naprednim modelima u svrhu preciznije procjene i praćenja kvalitete zraka.
- Open Access
Urban Heat Islands and Land-Use Patterns in Zagreb: A Composite Analysis Using Remote Sensing and Spatial Statistics
Urban heat islands (UHIs) present a growing environmental issue in swiftly urbanizing regions, where impermeable surfaces and a lack of vegetation increase local temperatures. This research analyzes the spatial distribution of urban heat islands in Zagreb, Croatia, utilizing remote sensing data, urban planning metrics, and spatial-statistical analysis. Composite rasters of land surface temperature (LST) and the Normalized Difference Vegetation Index (NDVI) were generated from four cloud-free Landsat 9 images obtained in the summer of 2024. The data were consolidated into regulatory planning units through zonal statistics, facilitating the evaluation of the impact of built-up density and designated green space on surface temperatures. A composite UHI index was developed by combining normalized land surface temperature (LST) and normalized difference vegetation index (NDVI) measurements, while spatial clustering was examined with Local Moran’s I and Getis-Ord Gi*. The results validate spatial patterns of heat intensity, with high temperatures centered in densely built residential areas. This research addresses the gap in past UHI studies by providing a reproducible approach for detecting thermal stress zones, linking satellite data with spatial planning variables. The results support the development of localized climate adaptation methods and highlight the importance of integrating green infrastructure into urban planning methodologies.
Open AccessUrban Heat Islands and Land-Use Patterns in Zagreb: A Composite Analysis Using Remote Sensing and Spatial Statistics
Urban heat islands (UHIs) present a growing environmental issue in swiftly urbanizing regions, where impermeable surfaces and a lack of vegetation increase local temperatures. This research analyzes the spatial distribution of urban heat islands in Zagreb, Croatia, utilizing remote sensing data, urban planning metrics, and spatial-statistical analysis. Composite rasters of land surface temperature (LST) and the Normalized Difference Vegetation Index (NDVI) were generated from four cloud-free Landsat 9 images obtained in the summer of 2024. The data were consolidated into regulatory planning units through zonal statistics, facilitating the evaluation of the impact of built-up density and designated green space on surface temperatures. A composite UHI index was developed by combining normalized land surface temperature (LST) and normalized difference vegetation index (NDVI) measurements, while spatial clustering was examined with Local Moran’s I and Getis-Ord Gi*. The results validate spatial patterns of heat intensity, with high temperatures centered in densely built residential areas. This research addresses the gap in past UHI studies by providing a reproducible approach for detecting thermal stress zones, linking satellite data with spatial planning variables. The results support the development of localized climate adaptation methods and highlight the importance of integrating green infrastructure into urban planning methodologies.
- Open Access
- 7 May 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
- Vol. 18 (19391404) , 12675-12683
Enhancing Authalic Latitude Calculation for the rHEALPix DGGS
Discrete global grid systems (DGGSs) enable georeferencing spatial data directly on the surface of the ellipsoid by linking data to areal cells with unique identifiers. The rHEALPix DGGS is one such example which also has a characteristic that all cells have the same area (equal-area DGGS). For the rHEALPix DGGS, cells are firstly constructed on the sphere and then mapped to the ellipsoid. This mapping must be area-preserving, so it is based on the so-called authalic latitude. Although equations for converting geodetic to the authalic latitude are well known, various authors have suggested their modifications that are optimized for the floating-point calculations. We applied these optimized equations to the current rHEALPix DGGS library and showed that optimization resulted in, on average, approximately 21 times higher computation accuracy when converting geodetic to authalic latitude. For the inverse conversion, accuracy is even higher, it is increased for multiple orders of magnitude. Regarding the execution time, the optimized Python code is approximately 2.7 times faster when converting geodetic to the authalic latitude and approximately 1.7 times faster when converting geodetic to the authalic latitude. Although the increase in calculation accuracy brings rHEALPix DGGS closer to being numerically truly equal-area, results show that for most use-cases it does not have a significant effect on cell areas. This, however, does not diminish the fact that introduced enhancement can be beneficial in some other use-cases and that drop in the execution time that is brought by optimization is highly beneficial from the practical application standpoint.
- 7 May 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
- Vol. 18 (19391404) , 12675-12683
Open AccessEnhancing Authalic Latitude Calculation for the rHEALPix DGGS
Discrete global grid systems (DGGSs) enable georeferencing spatial data directly on the surface of the ellipsoid by linking data to areal cells with unique identifiers. The rHEALPix DGGS is one such example which also has a characteristic that all cells have the same area (equal-area DGGS). For the rHEALPix DGGS, cells are firstly constructed on the sphere and then mapped to the ellipsoid. This mapping must be area-preserving, so it is based on the so-called authalic latitude. Although equations for converting geodetic to the authalic latitude are well known, various authors have suggested their modifications that are optimized for the floating-point calculations. We applied these optimized equations to the current rHEALPix DGGS library and showed that optimization resulted in, on average, approximately 21 times higher computation accuracy when converting geodetic to authalic latitude. For the inverse conversion, accuracy is even higher, it is increased for multiple orders of magnitude. Regarding the execution time, the optimized Python code is approximately 2.7 times faster when converting geodetic to the authalic latitude and approximately 1.7 times faster when converting geodetic to the authalic latitude. Although the increase in calculation accuracy brings rHEALPix DGGS closer to being numerically truly equal-area, results show that for most use-cases it does not have a significant effect on cell areas. This, however, does not diminish the fact that introduced enhancement can be beneficial in some other use-cases and that drop in the execution time that is brought by optimization is highly beneficial from the practical application standpoint.
- Open Access
- 2 January 2025
- Published by MDPI AG in Applied Sciences
- Vol. 15 (1) , 372
Cropland Suitability Prediction Method Based on Biophysical Variables from Copernicus Data and Machine Learning
The goal of this study was to propose and validate a method for predicting cropland suitability based on biophysical variables and machine learning according to an FAO land suitability standard using soybean (Glycine max L.) as a representative crop, aiming to provide an alternative to geographic information system (GIS)-based multicriteria analysis. The peak leaf area index (LAI) and the fraction of absorbed photosynthetically active radiation (FAPAR) from PROBA-V/Sentinel-3 data were calculated according to ground-truth soybean agricultural parcels in continental Croatia during 2015–2021. Four machine learning regression algorithms, including random forest (RF), support vector machine (SVM), and extreme gradient boosting (XGB), as well as their combination, were evaluated for predicting the peak LAI and FAPAR on the entire agricultural land in the study area, with RF producing the highest prediction accuracy with an R2 in the range of 0.250–0.590. The translation from K-means classes to the FAO land suitability standard was performed using a relative-based approach, ranking five resulting classes based on their relative mean sums of LAI and FAPAR values. The results of the proposed approach indicate that it is viable for major crops, while cropland suitability prediction for minor crops would require higher spatial resolution, such as vegetation indices from Sentinel-2 imagery.
- 2 January 2025
- Published by MDPI AG in Applied Sciences
- Vol. 15 (1) , 372
Open AccessCropland Suitability Prediction Method Based on Biophysical Variables from Copernicus Data and Machine Learning
The goal of this study was to propose and validate a method for predicting cropland suitability based on biophysical variables and machine learning according to an FAO land suitability standard using soybean (Glycine max L.) as a representative crop, aiming to provide an alternative to geographic information system (GIS)-based multicriteria analysis. The peak leaf area index (LAI) and the fraction of absorbed photosynthetically active radiation (FAPAR) from PROBA-V/Sentinel-3 data were calculated according to ground-truth soybean agricultural parcels in continental Croatia during 2015–2021. Four machine learning regression algorithms, including random forest (RF), support vector machine (SVM), and extreme gradient boosting (XGB), as well as their combination, were evaluated for predicting the peak LAI and FAPAR on the entire agricultural land in the study area, with RF producing the highest prediction accuracy with an R2 in the range of 0.250–0.590. The translation from K-means classes to the FAO land suitability standard was performed using a relative-based approach, ranking five resulting classes based on their relative mean sums of LAI and FAPAR values. The results of the proposed approach indicate that it is viable for major crops, while cropland suitability prediction for minor crops would require higher spatial resolution, such as vegetation indices from Sentinel-2 imagery.
- Open Access
- 22 December 2024
- Published by MDPI AG in Applied Sciences
- Vol. 14 (24) , 12020
Monitoring and Prediction of Land Surface Phenology Using Satellite Earth Observations—A Brief Review
Monitoring and predicting land surface phenology (LSP) are essential for understanding ecosystem dynamics, climate change impacts, and forest and agricultural productivity. Satellite Earth observation (EO) missions have played a crucial role in the advancement of LSP research, enabling global and continuous monitoring of vegetation cycles. This review provides a brief overview of key EO satellite missions, including the advanced very-high resolution radiometer (AVHRR), moderate resolution imaging spectroradiometer (MODIS), and the Landsat program, which have played an important role in capturing LSP dynamics at various spatial and temporal scales. Recent advancements in machine learning techniques have further enhanced LSP prediction capabilities, offering promising approaches for short-term prediction of vegetation phenology and cropland suitability assessment. Data cubes, which organize multidimensional EO data, provide an innovative framework for enhancing LSP analyses by integrating diverse data sources and simplifying data access and processing. This brief review highlights the potential of satellite-based monitoring, machine learning models, and data cube infrastructure for advancing LSP research and provides insights into current trends, challenges, and future directions.
- 22 December 2024
- Published by MDPI AG in Applied Sciences
- Vol. 14 (24) , 12020
Open AccessMonitoring and Prediction of Land Surface Phenology Using Satellite Earth Observations—A Brief Review
Monitoring and predicting land surface phenology (LSP) are essential for understanding ecosystem dynamics, climate change impacts, and forest and agricultural productivity. Satellite Earth observation (EO) missions have played a crucial role in the advancement of LSP research, enabling global and continuous monitoring of vegetation cycles. This review provides a brief overview of key EO satellite missions, including the advanced very-high resolution radiometer (AVHRR), moderate resolution imaging spectroradiometer (MODIS), and the Landsat program, which have played an important role in capturing LSP dynamics at various spatial and temporal scales. Recent advancements in machine learning techniques have further enhanced LSP prediction capabilities, offering promising approaches for short-term prediction of vegetation phenology and cropland suitability assessment. Data cubes, which organize multidimensional EO data, provide an innovative framework for enhancing LSP analyses by integrating diverse data sources and simplifying data access and processing. This brief review highlights the potential of satellite-based monitoring, machine learning models, and data cube infrastructure for advancing LSP research and provides insights into current trends, challenges, and future directions.