Machine learning in solving spatial problems in the master’s program at the Faculty of Geography and Geoinformation Technologies of the Higher School of Economics

DOI: 10.35595/2414-9179-2025-3-31-414-427

View or download the article (Rus)

About the Authors

Ekaterina S. Podolskaia

Higher School of Economics (HSE University),
20, Myasnitskaya str., Moscow, 101000, Russia,
E-mail: epodolskaya@hse.ru

Maria A. Sakirkina

Higher School of Economics (HSE University),
20, Myasnitskaya str., Moscow, 101000, Russia,
E-mail: masakirkina@gmail.com

Abstract

Paper presents the content and experience of teaching a course on Machine learning (ML) in solving spatial problems, delivered within the master’s program in spatial data and applied geoanalytics of the first year of study at the Faculty of Geography and Geoinformation Technologies, Higher School of Economics in 2025. The authors of the course systematized their educational and production experience of using ML-methods and technologies for students of the Faculty. The course consists of lectures and practical seminar assignments covering the methods and geospatial applications of modern ML using neural networks, and includes 14 pairs of classes. The course examines the place of ML in data science and artificial intelligence, applications and current development of MLs, mathematical bases and types of ML-problems. The classical ML includes a block of classes on cluster analysis, classification and regression with examples in geoinformatics. It is followed by the topic of decision trees and ensembles of algorithms. Special attention is paid to the review of modern neural networks as ML-extension, algorithms and architectures of their work, features and differences with relevant examples in geoinformatics. The course continues with the production use of ML-methods. ML datasets are studied with options for ready-to-use and self-creation both. The concept of ML-model is introduced and Python frameworks for classic ML (Pandas, Scikit-learn, NumPy, Tree ensembles), then Deep learning (DL), such as Keras, TensorFlow and PyTorch, are considered. Creation and optimization of the ML-model in Python, which is part of the ML-project, organization and integration of ML-project into production are discussed for course development. Scientific publications containing tasks with spatial data (examples in agriculture, forecasting risks and natural phenomena, geomarketing) are used in order to demonstrate ML-capabilities to the students. An overview of modern software with ML-functions in geoinformatics is given. Course’s references include researches of 2019–2025. The course materials are planned to be supplemented and updated using news from the various sources, papers, textbooks and specialized conferences on geo-artificial intelligence.

Keywords

geo-artificial intelligence, machine learning, study course, master’s program, spatial data

References

  1. Afroosheh S., Askari M. Fusion of Deep Learning and GIS for Advanced Remote Sensing Image Analysis. Computer Vision and Pattern Recognition, 2024. P. 1–9. DOI: 10.48550/arXiv.2412.19856.
  2. Bakhramkhan Ya.O., Ermakov D.M., Podolskaia E.S. Experience in Developing an Algorithm for Identifying Forest Clearings Under Power Lines in Forest Landscapes Based on Sentinel-2 Data. XII International Conference “Current Problems in Remote Sensing of the Earth from Space”. November 11–15, 2024. Abstracts of the report (in Russian). Moscow: Space Research Institute of the Russian Academy of Sciences.
  3. Belyakov S.L., Rosenberg I.N. Intelligent Geoinformation Systems. Zheleznodorozhny Transport (Railway Transport), 2011. No. 4. P. 32–37 (in Russian).
  4. Benaich N. State of AI Report. Air Street Capital. October 2024. Web resource: https://www.stateof.ai/ (accessed 07.07.2025).
  5. Binetti M.S., Massarelli C., Uricchio V.F. Machine Learning in Geosciences: A Review of Complex Environmental Monitoring Applications. Machine Learning and Knowledge Extraction, 2024. No. 6. P. 1263–1280. DOI: 10.3390/make6020059.
  6. Boutayeb A., Lahsen-cherif I., El Khadimi A. A Comprehensive GeoAI Review: Progress, Challenges and Outlooks. ArXiv.org, 2024. arXiv:2412.11643. P. 1–50. DOI: 10.48550/arXiv.2412.11643. Web resource: https://arxiv.org/abs/2412.11643 (accessed 02.06.2025).
  7. Candrasari R., Makulua J., Noviasmy Y., Makulua K., Siminto S. GPT Chat: Useful or Not in Supporting Learning in Higher Education. International Journal of Language and Ubiquitous Learning, 2024. No. 2 (2). P. 113–125. DOI: 10.70177/ijlul.v2i2.963.
  8. Chatterjee P., Yazdani M., Fernandez-Navarro F., Perez-Rodriguez J. Machine Learning Algorithms and Applications in Engineering (1st ed.). CRC Press, 2023. 328 p. DOI: 10.1201/9781003104858.
  9. Diehr J., Ogunyiola A., Dada O. Artificial Intelligence and Machine Learning-Powered GIS for Proactive Disaster Resilience in a Changing Climate. Annals of GIS, 2025. P. 1–14. DOI: 10.1080/19475683.2025.2473596.
  10. Endovitsky D.A., Gaidar K.M. University Science and Education in the Context of Artificial Intelligence. Vysshee Obrazovanie v Rossii (Higher Education in Russia), 2021. V. 30. No. 6. P. 121–131 (in Russian). DOI: 10.31992/0869-3617-2021-30-6-121-131.
  11. Fakur M., Gruzdev A. Cause-and-Effect Analysis for the Brave and Honest. Moscow: DMK Press, 2025. 594 p. (in Russian).
  12. Gao S., Hu Y., Li W. Handbook of Geospatial Artificial Intelligence (1st ed.). CRC Press, 2023. 468 p. DOI: 10.1201/9781003308423.
  13. Gokhberg L.M., Yatskin D.V., Grebenyuk A.Yu. Top 20 Frontiers of World Science: 2024. Moscow, Institute for Statistical Research and Economics of Knowledge of HSE. Web resource: https://issek.hse.ru/news/1021755371.html (accessed 07.07.2025) (in Russian).
  14. Gong J., Yue P., Woldai T., Tsai F., Vyas A., Wu H., Gruen A., Wang L., Musikhin I. Geoinformatics Education and Outreach: Looking Forward. Geo-Spatial Information Science, 2017. No. 20 (2). P. 209–217. DOI: 10.1080/10095020.2017.1337319.
  15. Gultom A.M., Ashadi A., Fatnalaila F., Azizah S.N., Rosyidah D.M. The Use of Chat GPT for Academic Writing in Higher Education. Formosa Journal of Sustainable Research, 2024. No. 3 (8). P. 1713–1730. DOI: 10.55927/fjsr.v3i8.10162.
  16. Habib M., Okayli M. An Overview of Modern Cartographic Trends Aligned with the ICA’s Perspective. RIG, 2023. P. 1–16. DOI: 10.32604/rig.2023.043399.
  17. Ivanov V.M. Intelligent Systems: A Textbook for Universities. Moscow: Yurait, 2022. 91 p. (in Russian).
  18. Ivanova A. P. The Role of Artificial Intelligence in Solving the Problem of Climate Change (Review Article). Social Sciences and Humanities. Domestic and Foreign Literature. Series 4: State and Law, 2024. No. 1. P. 178–188 (in Russian). DOI: 10.31249 /iajpravo/2024.01.12.
  19. Janowicza K., Gaob S., McKenziec G., Hud Y., Bhadurie B. GeoAI: Spatially Explicit Artificial Intelligence Techniques for Geographic Knowledge Discovery and Beyond. International Journal of Geographical Information Science, 2020. No. 34 (4). P. 625–636.
  20. Juhasz L., Mooney P., Hochmair H.H., Guan B. ChatGPT as a Mapping Assistant: A Novel Method to Enrich Maps with Generative AI and Content Derived from Street-Level Photographs. Spatial Data Science Symposium. Paper Proceedings. UC Santa Barbara Center for Spatial Studies, 2023. P. 1–13. DOI: 10.25436/E2ZW27.
  21. Lansley G., De Smith M., Goodchild M., Longley P. Big Data and Geospatial Analysis. Geospatial Analysis: A Comprehensive Guide to Principles, Techniques and Software Tools. Edinburgh: The Winchelsea Press, 2019. P. 547–570.
  22. Lee H., Li W. Geospatial Artificial Intelligence for Satellite-Based Flood Extent Mapping: Concepts, Advances, and Future Perspectives. ArXiv, 2025. arXiv:2504.02214v1. P. 1–11. DOI: 10.48550/arXiv.2504.02214. Web resource: https://arxiv.org/abs/2504.02214 (accessed 02.06.2025).
  23. Lunga D., Hu Y., Newsam S., Gao S., Martins B., Yang L., Deng X. GeoAI at ACM SIGSPATIAL: The New Frontier of Geospatial Artificial Intelligence Research. SIGSPATIAL Special, 2022. No. 13 (3). P. 21–32.
  24. Mai G., Xie Y., Jia X., Lao N., Rao J., Zhu Q., Liu Z., Chiang Y.-Y., Jiao J. Towards the Next Generation of GeoAI. International Journal of Applied Earth Observation and Geoinformation, 2025. V. 136. P. 1–21. DOI: 10.1016/j.jag.2025.104368.
  25. Mooney P., Cui W., Guan B., Juhasz L. Towards Understanding the Geospatial Skills of ChatGPT: Taking a Geographic Information Systems (GIS) Exam. GeoAI’23: Proceedings of the 6th ACM SIGSPATIAL International Workshop on AI for Geographic Knowledge Discovery, 2023. P. 85–94.
  26. Openshaw S., Openshaw C. Artificial Intelligence in Geography. Chichester: Wiley, 1997. 352 p.
  27. Platonov A.V. Machine Learning: A Textbook for Universities. Moscow: Yurait, 2023. 85 p. (in Russian).
  28. Podolskaia E.S. Open Sources Machine Learning Methods and GIS Tools in Forest Transport Modeling. Forest Science Issues, 2023. V. 6. No. 3. P. 1–10 (in Russian). DOI: 10.31509/2658-607x-202363-130.
  29. Podolskaia E.S. Geoinformation Technologies in Intelligent Systems as a Discipline in the Training Program for Students Majoring in Cartography and Geoinformatics. Geodesy and Cartography, 2024a. No. 8. P. 51–60 (in Russian). DOI: 10.22389/0016-7126-2024-1010-8-51-60.
  30. Podolskaia E.S. Experience in Preparing and Conducting Courses on Intelligent Geographic Information Systems for University Students. Proceedings of First International Scientific and Practical Conference “Digital Reality: New Challenges in Cartography, GIS and Remote Sensing”. November 7–8. Almaty, 2024b. P. 146–149 (in Russian). DOI: 10.13140/RG.2.2.35745.62563.
  31. Podolskaia E.S., Kokurkin A.D. Results of Testing Neural Network Architectures for Road Recognition. Regional Problems of Earth Remote Sensing. Proceedings of the XI International Scientific Conference. Krasnoyarsk: Siberian Federal University, 2024. P. 323–326 (in Russian).
  32. Podolskaia E.S., Shayakhmetov A.R. Modern Neural Networks for Recognition of Forestry Infrastructure Objects. Abstracts of the IX All-Russian (With International Participation) Conference “Aerospace Methods and Geoinformation Technologies in Forestry and Ecology” (in Russian). Moscow, 2025.
  33. Varlamova J.A., Korneychenko E.N. Artificial Intelligence in the Russian Regions. Russian Journal of Economics and Law, 2024. No. 18 (3). P. 641–662 (in Russian). DOI: 10.21202/2782-2923.2024.3.641-662.
  34. Wang A., Liu L., Chen H., Lin Z., Han J., Ding G. YOLOE: Real-Time Seeing Anything. ArXiv, 2025. arXiv:2503.07465v1. P. 1–15. DOI: 10.48550/arXiv.2503.07465. Web resource: https://arxiv.org/abs/2503.07465 (accessed 02.06.2025).
  35. Zhang Y., He Z., Li J., Lin J., Guan Q., Yu W. MapGPT: An Autonomous Framework for Mapping by Integrating Large Language Model and Cartographic Tools. Cartography and Geographic Information Science, 2024. P. 1–25. DOI: 10.1080/15230406.2024.2404868.
  36. Zhang Y., Wei C., He Z., Yu W. GeoGPT: An Assistant for Understanding and Processing Geospatial Tasks. International Journal of Applied Earth Observation and Geoinformation, 2024. No. 131. P. 1–21.

For citation: Podolskaia E.S., Sakirkina M.A. Machine learning in solving spatial problems in the master’s program at the Faculty of Geography and Geoinformation Technologies of the Higher School of Economics. InterCarto. InterGIS. Moscow: MSU, Faculty of Geography, 2025. V. 31. Part 3. P. 414–427. DOI: 10.35595/2414-9179-2025-3-31-414-427 (in Russian)