Alen Mangafić

Dr. Alen Mangafić

Geodetic Institute of Slovenia, Ljubljana, Slovenia
orcid

Research Focus & Metrics

Academic Career Length

7Years (2020-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
8 June 2025 in Remote Sensing
Verified
Journal Article
Open access
PDF file
Alen MangafićAlen Mangafić
Alen Mangafić
KOKristof Ostir
Kristof Ostir
Mitja KolarMitja Kolar
Mitja Kolar
MZMarko Zupan
Marko Zupan
This study integrates hyperspectral remote sensing with chemical and pedological data to estimate Zn, Pb, and Cd concentrations in the upper soil layers. Conducted in agricultural fields east and northeast of Celje, Slovenia, an area impacted by past industrial activities such as zinc ore smelting, the research integrates remote sensing and soil sampling to rapidly identify and map soil pollution over large surfaces. A multi-sensor approach was employed, combining two hyperspectral cameras (VNIR and SWIR, aerial), laboratory spectrometry, soil parameters, and content of chemical covariates measured with portable XRF and ICP-OES with a direct comparison of both techniques for this specific purpose. Accurate atmospheric and signal transformations were performed to improve modeling. The importance of covariates was thoroughly evaluated using conditional permutations to assess their contribution to the prediction of metal concentrations. The proposed framework utilizes spectral data and privileged information during training, improving prediction accuracy through a multi-stage model architecture. Here, a base model trained on spectral data is corrected using privileged information. During inference, the model functions without relying on privileged data providing a scalable and cost-effective solution for large-scale environmental monitoring. Our model achieved a reduction of predicted RMSE for Zn and Cd maps in comparison to the baseline models, translating to more precise identification of possibly polluted zones. However, for Pb, no improvements were observed, potentially due to variability in the data, including spectral issues or imbalances in the training and test datasets.

16 September 2022
Verified
Book
Open access
MVMateja Breg Valjavec
Mateja Breg Valjavec
RCRok Ciglič
Rok Ciglič
Špela ČončŠpela Čonč
Špela Čonč
MGMatjaž Geršič
Matjaž Geršič
DPDrago Perko
Drago Perko
GŽGrega Žorž
Grega Žorž
The book Preteklost in prihodnost ('The past and the future') is the sixteenth volume in the GIS v Sloveniji (GIS in Slovenia) book series and commemorates its 30th anniversary. The goal of the volume is to present the wide variety of research findings on geographical information systems in Slovenia in recent years. Powerful geoinformatic tools and precise data facilitate research on processes and phenomena, and their modelling. The volume presents project outputs and research results in areas such as geology, geomorphology, hydrology, pedology, agriculture, natural disasters, environmental protection, geography, surveying, archaeology, transport, telecommunication infrastructure, tourism, cultural heritage, education, cartography, geographical names, remote sensing, and others. Readers discover new features regarding the applicability of geographical information systems and learn about interesting research findings in many areas.

9 September 2020
Verified
Book
Open access
RCRok Ciglič
Rok Ciglič
MGMatjaž Geršič
Matjaž Geršič
DPDrago Perko
Drago Perko
MZMatija Zorn
Matija Zorn
TVTimotej Verbovšek
Timotej Verbovšek
DBDavid Bojc
David Bojc
Modeliranje pokrajine ('Modelling landscape') is the fifteenth volume in the series GIS v Sloveniji (GIS in Slovenia). The goal of the volume is to present the wide variety of research findings on geographical information systems in Slovenia in recent years. Powerful geoinformatic tools and precise data facilitate research on processes and phenomena, and their modelling. The volume presents project outputs and research results in areas such as geology, geomorphology, hydrology, environmental protection, geography, surveying, archaeology, transport, telecommunication infrastructure, tourism, cultural heritage, remote sensing, and others. Readers will discover new features regarding the applicability of geographical information systems and will learn about interesting research findings in many areas.

29 April 2026 in The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences
Verified
Journal Article
Open access
PDF file
TŽTomaž Žagar
Tomaž Žagar
Alen MangafićAlen Mangafić
Alen Mangafić
This paper presents a scalable open-source system for national-level impervious-surface mapping and monitoring that combines GRASS, HDF5 and Python-based machine-learning libraries. Continuous Sentinel-2 multispectral monitoring is paired with targeted very high resolution (VHR) orthophoto segmentation to efficiently detect and delineate land transformation. Sentinel-2 imagery is retrieved from the Microsoft Planetary Computer, organized into a GRASS space-time raster dataset and classified using TorchGeo models fine-tuned on the EuroSAT dataset. Persistent transitions toward impervious-related classes identify disturbance candidates, and these areas trigger semantic segmentation of corresponding orthophoto tiles using GPU-accelerated Random Forests in RAPIDS cuML. The resulting outputs are vectorized, enriched with registry data and disseminated through spatial database services. Applied to Slovenia for the 2020–2025 period, the system detected 99 km² of new impervious surfaces across a 20,271 km² study area, corresponding to 0.5 % land transformation (0.1 % annually). These results demonstrate that integrating continuous multispectral time-series analysis with event-driven VHR segmentation provides an efficient, reproducible and high-detail approach for operational land-change detection and environmental assessment.

30 September 2026
Verified
Book Chapter
Open access
Alen MangafićAlen Mangafić
Alen Mangafić
YCYann Chemin
Yann Chemin
TŽTomaž Žagar
Tomaž Žagar

29 April 2026 in The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences
Verified
Journal Article
Open access
PDF file
Alen MangafićAlen Mangafić
Alen Mangafić
TŽTomaž Žagar
Tomaž Žagar
Hyperspectral satellite missions such as EnMAP, PRISMA and Tanager have made imaging spectroscopy widely accessible, yet their heterogeneous formats, high dimensionality and demanding preprocessing requirements still hinder efficient scientific use. To address these challenges, we developed i.hyper, a multimodule addon for GRASS designed to provide a harmonized, reproducible and scalable workflow for hyperspectral data. The methodology integrates a unified 3D raster data model with per-band metadata, ensuring consistent handling of wavelength, FWHM, validity and radiometric units across sensors. A modular preprocessing engine implements established imaging spectroscopy and machine-learning techniques, including Savitzky–Golay smoothing, baseline correction, continuum removal and several linear and nonlinear dimensionality-reduction methods such as PCA and Nyström approximation—executed spectrally while preserving spatial alignment. The resulting toolset comprises the modules i.hyper.import, i.hyper.preproc, i.hyper.composite, i.hyper.explore and i.hyper.export, which together implement a complete workflow from sensor-specific import through preprocessing, visualization and export. The modules resolve practical gaps such as mixed multi-file product structures and metadata conventions, scalable nonlinear reduction and the need for integrated spectral exploration. The addon is available as an official extension in the GRASS repository, enabling direct integration of imaging spectroscopy into established geospatial workflows. This work demonstrates that GRASS can serve as an efficient environment for hyperspectral processing, reducing the data-engineering overhead that typically precedes scientific modelling, and providing a foundation for further preprocessing steps performed by the powerful, native functionalities that GRASS offers.