Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Dino Dobrinić has a total of 13 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Spatial Distribution Estimation of Urban Population in Zagreb, Croatia, Using LiDAR Data

    by Dino Dobrinić, Ivan Brkić, Damir Medak, Mario Miler

    Accurate information on intra-urban population distribution is essential for urban planning, infrastructure management, exposure assessment, and evidence-based decision-making. However, census data are usually available only for predefined administrative units and often lack the spatial detail required for fine-scale urban analyses. This study evaluates a top-down approach for estimating population distribution within the city of Zagreb, Croatia, using building footprints, three-dimensional building characteristics, OpenStreetMap (OSM) semantic information, and census population counts. The citywide population total was redistributed to LiDAR-derived roof and WSF-derived settlement polygons and aggregated to 17 city districts for validation. Two built-environment datasets were tested: locally derived LiDAR roof polygons and WSF-derived settlement polygons. Area-based scenarios were implemented for both datasets, while height-enhanced scenarios incorporated LiDAR-derived nDSM information. The WSF height-enhanced scenario therefore combined globally available WSF geometry with locally derived LiDAR height information and is referred to as WSF + nDSM. Results show that 3D models consistently outperformed 2D models. Total relative error (TRE) decreased from 15.5% to 11.8% for LiDAR and from 19.6% to 11.4% for WSF. OSM-based refinement further improved all scenarios, with the LiDAR 3D + OSM and WSF + nDSM + OSM scenarios achieving comparable overall performance (TRE = 9.0% for both at the city-district validation level). These findings demonstrate the value of combining vertical and semantic building information for more accurate urban population disaggregation.

  • Open Access

    Mapping the Green Urban: A Comprehensive Review of Materials and Learning Methods for Green Infrastructure Mapping

    by Dino Dobrinić, Mario Miler, Damir Medak

    Green infrastructure (GI) plays a crucial role in sustainable urban development, but effective mapping and analysis of such features requires a detailed understanding of the materials and state-of-the-art methods. This review presents the current landscape of green infrastructure mapping, focusing on the various sensors and image data, as well as the application of machine learning and deep learning techniques for classification or segmentation tasks. After finding articles with relevant keywords, the PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyzes) method was used as a general workflow, but some parts were automated (e.g., screening) by using natural language processing and large language models. In total, this review analyzed 55 papers that included keywords related to GI mapping and provided materials and learning methods (i.e., machine or deep learning) essential for effective green infrastructure mapping. A shift towards deep learning methods can be observed in the mapping of GIs as 33 articles use various deep learning methods, while 22 articles use machine learning methods. In addition, this article presents a novel methodology for automated verification methods, demonstrating their potential effectiveness and highlighting areas for improvement.


  • Open Access

    Monitoring and Prediction of Land Surface Phenology Using Satellite Earth Observations—A Brief Review

    by Mateo Gašparović, Ivan Pilaš, Dorijan Radočaj, Dino Dobrinić

    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.


  • Open Access

    Mapping of Allergenic Tree Species in Highly Urbanized Area Using PlanetScope Imagery—A Case Study of Zagreb, Croatia

    by Mateo Gašparović, Dino Dobrinić, Ivan Pilaš

    Mapping and identifying allergenic tree species in densely urbanized regions is vital for understanding their distribution and prevalence. However, accurately detecting individual allergenic tree species in urban green spaces remains challenging due to their smaller site and patchiness. To overcome these issues, PlanetScope (PS) satellite imagery offers significant benefits compared with moderate or high-resolution RS imagery due to its daily temporal resolution and 3 m spatial resolution. Therefore, the primary objectives of this research were to: assess the feasibility of mapping allergenic tree species in the highly urbanized area using high-resolution PS imagery; evaluate and compare the performance of the most important machine learning and feature selection methods for accurate detection of individual allergenic tree species. The research incorporated three classification scenarios based on ground truth data: The first scenario (CS1) used single-date PS imagery with vegetation indices (VI), while the second and third scenarios (CS2 and CS3) used multitemporal PS imagery with VI, and GLCM and VI, respectively. The study demonstrated the feasibility of using multitemporal eight-band PlanetScope imagery to detect allergenic tree species, with the XGB method outperforming others with an overall accuracy of 73.13% in CS3. However, the classification accuracy varied between the scenarios and species, revealing limitations including the inherent heterogeneity of urban green spaces. Future research should integrate high-resolution satellite imagery with aerial photography or LiDAR data along with deep learning methods. This approach has the potential to classify dominant tree species in highly complex urban environments with increased accuracy, which is essential for urban planning and public health.


  • Open Access

    Sentinel-1 and 2 Time-Series for Vegetation Mapping Using Random Forest Classification: A Case Study of Northern Croatia

    by Dino Dobrinić, Mateo Gašparović, Damir Medak

    Land-cover (LC) mapping in a morphologically heterogeneous landscape area is a challenging task since various LC classes (e.g., crop types in agricultural areas) are spectrally similar. Most research is still mostly relying on optical satellite imagery for these tasks, whereas synthetic aperture radar (SAR) imagery is often neglected. Therefore, this research assessed the classification accuracy using the recent Sentinel-1 (S1) SAR and Sentinel-2 (S2) time-series data for LC mapping, especially vegetation classes. Additionally, ancillary data, such as texture features, spectral indices from S1 and S2, respectively, as well as digital elevation model (DEM), were used in different classification scenarios. Random Forest (RF) was used for classification tasks using a proposed hybrid reference dataset derived from European Land Use and Coverage Area Frame Survey (LUCAS), CORINE, and Land Parcel Identification Systems (LPIS) LC database. Based on the RF variable selection using Mean Decrease Accuracy (MDA), the combination of S1 and S2 data yielded the highest overall accuracy (OA) of 91.78%, with a total disagreement of 8.22%. The most pertinent features for vegetation mapping were GLCM Mean and Variance for S1, NDVI, along with Red and SWIR band for S2, whereas the digital elevation model produced major classification enhancement as an input feature. The results of this study demonstrated that the aforementioned approach (i.e., RF using a hybrid reference dataset) is well-suited for vegetation mapping using Sentinel imagery, which can be applied for large-scale LC classifications.


  • Open Access

    Green Infrastructure Mapping in Urban Areas Using Sentinel-1 Imagery

    by Mateo Gašparović, Dino Dobrinić

    High temporal resolution of synthetic aperture radar (SAR) imagery (e.g., Sentinel-1 (S1) imagery) creates new possibilities for monitoring green vegetation in urban areas and generating land-cover classification (LCC) maps. This research evaluates how different pre-processing steps of SAR imagery affect classification accuracy. Machine learning (ML) methods were applied in three different study areas: random forest (RF), support vector machine (SVM), and extreme gradient boosting (XGB). Since the presence of the speckle noise in radar imagery is inevitable, different adaptive filters were examined. Using the backscattering values of the S1 imagery, the SVM classifier achieved a mean overall accuracy (OA) of 63.14%, and a Kappa coefficient (Kappa) of 0.50. Using the SVM classifier with a Lee filter with a window size of 5×5 (Lee5) for speckle reduction, mean values of 73.86% and 0.64 for OA and Kappa were achieved, respectively. An additional increase in the LCC was obtained with texture features calculated from a grey-level co-occurrence matrix (GLCM). The highest classification accuracy obtained for the extracted GLCM texture features using the SVM classifier, and Lee5 filter was 78.32% and 0.69 for the mean OA and Kappa values, respectively. This study improved LCC with an evaluation of various radiometric and texture features and confirmed the ability to apply an SVM classifier. For the supervised classification, the SVM method outperformed the RF and XGB methods, although the highest computational time was needed for the SVM, whereas XGB performed the fastest. These results suggest pre-processing steps of the SAR imagery for green infrastructure mapping in urban areas. Future research should address the use of multitemporal SAR data along with the pre-processing steps and ML algorithms described in this research.


  • Open Access

    Comparative Assessment of Machine Learning Methods for Urban Vegetation Mapping Using Multitemporal Sentinel-1 Imagery

    by Mateo Gašparović, Dino Dobrinić

    Mapping of green vegetation in urban areas using remote sensing techniques can be used as a tool for integrated spatial planning to deal with urban challenges. In this context, multitemporal (MT) synthetic aperture radar (SAR) data have not been equally investigated, as compared to optical satellite data. This research compared various machine learning methods using single-date and MT Sentinel-1 (S1) imagery. The research was focused on vegetation mapping in urban areas across Europe. Urban vegetation was classified using six classifiers—random forests (RF), support vector machine (SVM), extreme gradient boosting (XGB), multi-layer perceptron (MLP), AdaBoost.M1 (AB), and extreme learning machine (ELM). Whereas, SVM showed the best performance in the single-date image analysis, the MLP classifier yielded the highest overall accuracy in the MT classification scenario. Mean overall accuracy (OA) values for all machine learning methods increased from 57% to 77% with speckle filtering. Using MT SAR data, i.e., three and five S1 imagery, an additional increase in the OA of 8.59% and 13.66% occurred, respectively. Additionally, using three and five S1 imagery for classification, the F1 measure for forest and low vegetation land-cover class exceeded 90%. This research allowed us to confirm the possibility of MT C-band SAR imagery for urban vegetation mapping.


  • Geometric accuracy improvement of WorldView‐2 imagery using freely available DEM data

    by Mateo Gašparović, Dino Dobrinić, Damir Medak

    This paper provides geometric accuracy improvements for very high resolution WorldView‐2 (WV2) Ortho Ready Standard Level‐2A (ORS2A) satellite images in the panchromatic (PAN) band. The entire process can be divided into two steps: (1) sensor orientation, which was conducted on 40 ground control points (GCPs) to determine which sensor model was best depending on various numbers of GCPs; and (2) orthorectification, whose main objective was to compare the accuracy of the process when using different freely available global digital elevation models (DEMs). The research showed that a sensor model based on rational polynomial coefficients (RPCs) with a shift or zero‐order bias correction attained the best geopositioning accuracy during the orientation step with the use of seven GCPs. The highest accuracy was achieved for images orthorectified with the ALOS World 3D‐30 m DEM (AW3D30).


  • Open Access

    HORIZONTAL ACCURACY ASSESSMENT OF PLANETSCOPE, RAPIDEYE AND WORLDVIEW-2 SATELLITE IMAGERY

    by Dino Dobrinic, Mateo Gašparović, M. Gašparović, R. Župan