DOI
10.34229/KCA2522-9664.25.6.12
UDC 004, 528, 338
S.Yu. Drozd
National Technical University “Igor Sikorsky Kyiv Polytechnic Institute,” Kyiv, Ukraine;
Anhalt University of Applied Sciences, Kothen, Germany; Institute for Space Research
of the National Academy of Sciences of Ukraine and the State Space Agency of Ukraine,
Kyiv, Ukraine, 
sofi.drozd.13@gmail.com
N.M. Kussul
National Technical University “Igor Sikorsky Kyiv Polytechnic Institute,” Kyiv, Ukraine;
University of Maryland, College Park, USA; Institute for Space Research
of the National Academy of Sciences of Ukraine and the State Space Agency of Ukraine,
Kyiv, Ukraine, kussul@umd.edu
MULTI-CRITERION ANALYSIS OF INVESTMENT
APPEAL OF RURAL AREAS OF UKRAINE
USING GIS AND ARTIFICIAL INTELLIGENCE
Abstract. A comprehensive assessment of the investment attractiveness of Ukraine’s rural areas was carried out using a multi-criteria geospatial analysis based on three key criteria: natural potential, infrastructure accessibility, and the level of military security. Additionally, within the natural potential criterion, four main investment directions were considered as sub-criteria: agriculture, renewable energy (solar and wind), and tourism. To determine the weights of the criteria using the Saaty pairwise comparison method, five large language models (LLMs) — GPT-4, Claude, Gemini, Deepseek, and Grok 3 — were engaged as virtual experts. The results of the LLM survey were compared with the responses of nine human experts. It was found that virtual models exhibit less inconsistency in their answers compared to humans. The LLM assessments aligned with expert opinions on the three key investment attractiveness criteria but showed lower consensus regarding specific investment directions. Most models identified security as the most important criterion and agriculture as the most attractive investment direction. Six thematic maps and an overall map of the investment attractiveness of Ukrainian villages were created. It was determined that the villages in Western Ukraine are more attractive for investment, while those in the East and South are the least attractive.
Keywords: investment appeal of territories, multi-criterion analysis, GIS, satellite data, artificial intelligence, large language models.
full text
REFERENCES
- 1. Greene R., Devillers R., Luther J., Eddy B. GIS-Based multiple-criteria decision analysis. Geography Compass. 2011. Vol. 5. P. 412–432. https://doi.org/10.1111/j.1749-8198.2011.00431.x.
- 2. Silvero N.E.Q., Dematt J.A.M., Vieira J. de S. et al. Soil property maps with satellite images at multiple scales and its impact on management and classification. Geoderma. 2021. Vol. 397, 115089. https://doi.org/10.1016/j.geoderma.2021.115089.
- 3. Kussul N., Shelestov A., Drozd S. et al. Innovative models and applications of satellite intelligence. In: Space Research in Ukraine. Kyiv: Akademperiodyka. 2024. P. 115–123. URL: https://www.researchgate.net/publication/381879688_ Innovative_models_and_applications_of_satellite_intelligence. https://doi.org/10.15407/akademperiodyka.507.172.
- 4. Kussul N., Shelestov A., Yailymova H., Shumilo L., Drozd S. Agriculture land appraisal with use of remote sensing and infrastructure data. IGARSS 2022–2022 IEEE International Geoscience and Remote Sensing Symposium (Kuala Lumpur, Malaysia, 17–22 July 2022). IEEE, 2022. P. 2785–2788. https://doi.org/10.1109/igarss46834.2022.9884045.
- 5. Oshri B., Hu A., Adelson P. et al. Infrastructure quality assessment in Africa using satellite imagery and deep learning. KDD’18: The 24th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (19–23 August, 2018, London, United Kingdom). New York: Association for Computing Machinery, 2018. P. 616–625. https://doi.org/10.1145/3219819.3219924.
- 6. Sahin G., Koc A., van Sark W. Multi-criteria decision making for solar power — Wind power plant site selection using a GIS-intuitionistic fuzzy-based approach with an application in the Netherlands. Energy Strategy Reviews. 2024. Vol. 51, 101307. https://doi.org/10.1016/j.esr.2024.101307.
- 7. Kussul N.M., Drozd S.Yu. Geospatial analysis of the potential of Ukrainian territories for the placement of solar power plants based on satellite data. Space Science and Technology. 2024. Vol. 30, No. 1 (146). P.31–43. https://doi.org/10.15407/knit2024.01.031.
- 8. Drozd S., Kussul N. Solar energy potential mapping in Ukraine through integration of GIS, remote sensing, and fuzzy logic. European Journal of Remote Sensing. 2024. Vol. 57, N 1. https://doi.org/10.1080/22797254.2024.2362390.
- 9. Hussain, S., Nasim, W., Mubeen, M., Fahad, S. et al. Agricultural land suitability analysis of Southern Punjab, Pakistan using analytical hierarchy process (AHP) and multi-criteria decision analysis (MCDA) techniques. Cogent Food & Agriculture. 2024. Vol. 10, N 1. https://doi.org/10.1080/23311932.2023.2294540.
- 10. Mahmoudzadeh H., Abedini A., Aram F., Mosavi A. Evaluating urban environmental quality using multi criteria decision making. Heliyon. 2024. Vol. 10, N 3, e24921. https://doi.org/10.1016/j.heliyon.2024.e24921.
- 11. Svoboda I., Lande D. Enhancing multi-criteria decision analysis with AI: Integrating analytic hierarchy process and GPT-4 for automated decision support. arXiv:2402.07404 [cs.AI]. 2024. https://doi.org/10.48550/arXiv.2402.07404.
- 12. Wang H., Zhang F., Mu C. One for all: A general framework of LLMs-based multi-criteria decision making on human expert level. arXiv:2502.15778 [cs.AI]. 2025. https://doi.org/10.48550/arXiv.2502.15778.
- 13. Wang X., Wu X. Can ChatGPT serve as a multi-criteria decision maker? A novel approach to supplier evaluation. ICASSP 2024 — 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (, 14–19 April, 2024, Seoul, Republic of Korea). IEEE, 2024. P. 10281–10285. https://doi.org/10.1109/ICASSP48485.2024.10447204.
- 14. Hengl T. Soil pH in H2O at 6 standard depths (0, 10, 30, 60, 100 and 200 cm) at 250 m resolution. Zenodo. 2018. https://doi.org/10.5281/zenodo.2525664.
- 15. Hengl T. Soil texture classes (USDA system) for 6 soil depths (0, 10, 30, 60, 100 and 200 cm) at 250 m. Zenodo. 2018. https://doi.org/10.5281/zenodo.2525817.
- 16. Hengl T., Wheeler I. Soil organic carbon content in 5 g/kg at 6 standard depths (0, 10, 30, 60, 100 and 200 cm) at 250 m resolution (v0.2). Zenodo. 2018. https://doi.org/10.5281/zenodo.2525553.
- 17. Global black soil distribution map (v1.0). FAO Catalog. 2022. URL: https://www.fao.org/global-soil-partnership/gbsmap/en/.
- 18. SRTM. NASA Earthdata. 2024. URL: https://www.earthdata.nasa.gov/data/instruments/srtm.
- 19. ERA5-Land hourly data from 1950 to present. Copernicus Climate Data Store. 2025. URL: https://cds.climate.copernicus.eu/datasets/reanalysis-era5-land?tab=overview.
- 20. Kussul N., Lavreniuk M., Skakun S., Shelestov A. Deep learning classification of land cover and crop types using remote sensing data. IEEE Geoscience and Remote Sensing Letters. 2017. P. 1–5. https://doi.org/10.1109/LGRS.2017.2681128.
- 21. Global Wind Atlas. URL: https://globalwindatlas.info/en/.
- 22. OpenStreetMap. URL: https://www.openstreetmap.org/about.
- 23. About ACLED. 2025. URL: https://acleddata.com/about-acled.
- 24. Ukraine — Subnational Administrative Boundaries. State Scientific Production Enterprise «Kartographia». 2024. URL: https://data.humdata.org/dataset/cod-ab-uk.
- 25. Saaty T.L. Decision making — the analytic hierarchy and network processes (AHP/ANP). Journal of Systems Science and Systems Engineering. 2004. Vol. 13. P. 1–35. https://doi.org/10.1007/s11518-006-0151-5.
- 26. Czerny T. CO-STAR framework for prompt structuring. Jan 26, 2024. URL: https://medium.com/@thomasczerny/co-star-framework-for-prompt-structuring-7f9a8c221224.
- 27. Goepel K. Implementing the analytic hierarchy process as a standard method for multi-criteria decision making in corporate enterprises — a new AHP Excel template with multiple inputs. International Symposium on the Analytic Hierarchy Process. 2023. https://doi.org/10.13033/isahp.y2013.047.
