Rina Milošević
Center for Geospatial Technologies, University of Zadar, Department of Ecology, Agronomy and Aquaculture, University of Zadar, Croatia
DOI:
UDC: [502.52:711.4]-043.7:528.85.044.8(497.5)”2017/2025”
Published: August 2026
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
Keywords: Urban land cover, PlanetScope, Machine learning, Temporal domain shift, GIS analysis
Abstract:
This study quantifies land cover change in the City of Zadar between 2017 and 2025 using PlanetScope imagery and Machine Learning classification. Spectral bands were complemented with spectral indices (NDVI, VARI, Brightness, BSI) and a NIR-based texture measure to improve class separability. Random Forest and XGBoost algorithms were evaluated using stratified five-fold cross-validation, while a transfer experiment was conducted to assess temporal robustness. Epoch-specific models achieved high classification accuracy (ACC ≈ 0.94–0.95; ROC AUC ≈ 0.96–0.98), whereas direct model transfer from 2017 to 2025 resulted in reduced performance (ACC = 0.75), confirming the presence of temporal domain shift. At the city scale, impervious surfaces expanded proportionally from 27% to 29%, accompanied by a slight decline and fragmentation of urban green spaces. Hexagon-based spatial analysis identified spatially coherent zones of impervious surface growth, indicating structurally organized urban expansion. The results suggest continued conversion of green areas. Future research should explore multi-annual or sub-annual satellite time series and advanced domain adaptation approaches to improve model generalization across temporal domains.
References:
United Nations, Department of Economic and Social Affairs, Population Division (2018). World Urbanization Prospects: The 2018 Revision. New York: United Nations.
G. Zaro, A. Blaće, J. Baraka Perica, M. Čelhar, F. Jurković Pešić, and K. Gusar, ‘Fleeting fields of Zadar (Croatia): characterizing millennial-scale urban landcover change, green space, and resilience into the twenty first century’, Front. Ecol. Evol., vol. 11, Sep. 2023, doi: 10.3389/fevo.2023.1221730.
N. Kabisch, H. Korn, J. Stadler, and A. Bonn, ‘Nature-Based Solutions to Climate Change Adaptation in Urban Areas—Linkages Between Science, Policy and Practice’, in Nature-Based Solutions to Climate Change Adaptation in Urban Areas: Linkages between Science, Policy and Practice, N. Kabisch, H. Korn, J. Stadler, and A. Bonn, Eds, Cham: Springer International Publishing, 2017, pp. 1–11. doi: 10.1007/978-3-319-56091-5_1.
R. Milošević, S. Šiljeg, and F. Domazetović, GIS Multicriteria Decision Analysis in Selecting the Optimal Location for Urban Green Space: A Case Study of Zadar City. 2023, p. 243. doi: 10.5220/0012031400003473.
C. Kabeja, R. Li, D. E. R. Rwatangabo, and J. Duan, ‘Monitoring Land Use/Cover Changes by Using Multi-Temporal Remote Sensing for Urban Hydrological Assessment: A Case Study in Beijing, China’, Remote Sens., vol. 14, no. 17, Aug. 2022, doi: 10.3390/rs14174273.
B. E. Lefulebe, A. V. der Walt, and S. Xulu, ‘Fine-Scale Classification of Urban Land Use and Land Cover with PlanetScope Imagery and Machine Learning Strategies in the City of Cape Town, South Africa’, Sustainability, vol. 14, no. 15, Jul. 2022, doi: 10.3390/su14159139.
D. Tuia, C. Persello, and L. Bruzzone, ‘Domain Adaptation for the Classification of Remote Sensing Data: An Overview of Recent Advances’, IEEE Geosci. Remote Sens. Mag., vol. 4, no. 2, pp. 41–57, Jun. 2016, doi: 10.1109/MGRS.2016.2548504.
L. Panđa, Imperviousness Density Mapping Based on GIS-MCDA and High-Resolution Worldview-2 Imagery. 2023, p. 229. doi: 10.5220/0011988200003473.
DHMZ – Državni hidrometeorološki zavod’. Accessed: Feb. 16, 2026. [Online]. Available: https://meteo.hr/objave_najave_natjecaji.php?section=onn¶m=objave&el=priopcenja&daj=pr12092017
D. Magaš, ‘Neke promeje u gradskim naseljima zadarske regije u razdoblju 1857. – 1971. godine’, Rad. Zavoda Za Povij. Znan. HAZU U Zadru, no. 33, pp. 239–258, Oct. 1991.
V. Graovac, ‘Populacijski razvoj Zadra’, Geoadria, vol. 9, no. 1, pp. 51–72, Jun. 2004, doi: 10.15291/geoadria.129.
Državni zavod za statitstkiku ‘Popis 2021.’, dzs.gov.hr. Accessed: Feb. 16, 2026. [Online]. Available: https://dzs.gov.hr/u-fokusu/popis-2021/88
S. Hallegatte, C. Green, R. J. Nicholls, and J. Corfee-Morlot, ‘Future flood losses in major coastal cities’, Nat. Clim. Change, vol. 3, no. 9, pp. 802–806, Sep. 2013, doi: 10.1038/nclimate1979.
S. Z. Aldwaik and R. G. Pontius, ‘Intensity analysis to unify measurements of size and stationarity of land changes by interval, category, and transition’, Landsc. Urban Plan., vol. 106, no. 1, pp. 103–114, May 2012, doi: 10.1016/j.landurbplan.2012.02.010.
W. Kuang, Y. Hou, Y. Dou, D. Lu, and S. Yang, ‘Mapping Global Urban Impervious Surface and Green Space Fractions Using Google Earth Engine’, Remote Sens., vol. 13, no. 20, Oct. 2021, doi: 10.3390/rs13204187.
G. Zulian, F. Marando, L. Mentaschi, C. Alzetta, B. Wilk, and J. Maes, ‘Green balance in urban areas as an indicator for policy support: a multi-level application’, One Ecosyst., vol. 7, p. e72685, Mar. 2022, doi: 10.3897/oneeco.7.e72685.