Науковий вісник НГУ

Investigation of the accuracy of underground control surveying networks through the application of neural network modeling

• 
• 

User Rating:  / 0

PoorBest 

Details

Parent Category: 2026

Category: Content №3 2026

Created on 26 June 2026

Last Updated on 26 June 2026

Published on 30 November -0001

Written by H. S. Ishutina, S. V. Biehichev, L. O. Chumak, A. O. Balashov

Hits: 872

Authors:

H. S. Ishutina*, orcid.org/0000-0002-0665-3040, Ukrainian State University of Science and Technologies, Dnipro, Ukraine, e-mail This email address is being protected from spambots. You need JavaScript enabled to view it.

S. V. Biehichev, orcid.org/0000-0001-9861-8754, Ukrainian State University of Science and Technologies, Dnipro, Ukraine, e-mail This email address is being protected from spambots. You need JavaScript enabled to view it.

L. O. Chumak, orcid.org/0000-0002-3858-8028, Ukrainian State University of Science and Technologies, Dnipro, Ukraine, e-mail This email address is being protected from spambots. You need JavaScript enabled to view it.

A. O. Balashov, orcid.org/0009-0007-5833-0888, Ukrainian State University of Science and Technologies, Dnipro, Ukraine, e-mail This email address is being protected from spambots. You need JavaScript enabled to view it.

* Corresponding author e-mail: This email address is being protected from spambots. You need JavaScript enabled to view it.

повний текст / full article

Naukovyi Visnyk Natsionalnoho Hirnychoho Universytetu. 2026, (3): 175 - 183

https://doi.org/10.33271/nvngu/2026-3/175

Abstract:

Purpose. To evaluate the accuracy of an underground mine surveying control network (UMSCN) by applying neural network modeling and adaptive estimation of the position of the most distant traverse point. To conduct an analysis of methods for estimating the root mean square errors of point positions.

Methodology. Application of deep learning techniques, specifically Conditional Tabular Generative Adversarial Networks (CTGAN), to generate extended synthetic geodetic datasets for evaluating the accuracy of underground mine surveying control networks (UMSCNs). The study also includes an analysis of regulatory frameworks alongside both international and national scientific literature on assessing the accuracy and reliability of mine surveying and geodetic networks using artificial intelligence approaches, such as neural network modeling and adaptive estimation.

Findings. The use of neural network modeling and adaptive estimation enables a quantitative assessment of the accuracy of an underground mine surveying control network (UMSCN) by modeling the angular and linear root mean square errors (RMSE). This has a direct impact on the RMSE of the position of the farthest point within the UMSCN and reflects the convergence of the network’s variance under the adaptive protocol. As the level of uncertainty nears the Safety Constraint Layer, the system indicates that additional gyroscopic measurements are required – data that cannot be derived through analytical approaches or handled using standard spreadsheet tools.

Originality. For the first time, it is proposed to assess the accuracy of a designed underground mine surveying control network (UMSCN) using modern artificial intelligence technologies. The assessment outcomes were examined in line with regulatory standards, applying both analytical techniques and modeling methods. The positional errors of the most distant point, No. 15, were calculated in accordance with the defined tolerance. Furthermore, the root mean square error (RMSE) of the measurements was determined, under which the required condition is met. The RMSE of the position of the most distant traverse point should not exceed 0.3 mm on the plan, which corresponds to 0.6 m for plans at a 1:2,000 scale in coal mines.

Practical value. The accuracy of the underground mine surveying control network (UMSCN) was evaluated using neural network modeling and adaptive estimation. As a result, a displacement of the farthest point in the network was detected, and the probability of failure-free operation of the UMSCN was estimated at 71 %. The proposed approach improves the reliability of accuracy predictions for surveying networks at both the design and operational stages. The use of neural network methods allows for optimization of field measurement volumes, timely identification of critical zones with increased uncertainty, and justification for additional observations (including gyroscopic measurements). The results can be used to automate quality control processes for mine surveying, reduce operational risks in mining conditions, and enhance the safety of operations in coal mines. The proposed methodology is also suitable for integration into modern geographic information and mine surveying decision-support systems.

Keywords: mine surveying network, accuracy assessment, neural network modeling, adaptive estimation, polygon traverse

References.

1. Verkhovna Rada of Ukraine (2021). Rules for the performance of surveying works during the development of deposits of ore and non-ore minerals. Retrieved from https://zakon.rada.gov.ua/laws/show/z0884-21#Text

2. Verkhovna Rada of Ukraine (2025). Safety Rules for Conducting Mining Operations in Coal Mines. Retrieved from https://zakon.rada.gov.ua/laws/show/z1145-25#Text

3. Verkhovna Rada of Ukraine (2023). Mining Law of Ukraine. Retrieved from https://zakon.rada.gov.ua/laws/show/1127-14#Text

4. Verkhovna Rada of Ukraine (2024). Law of Ukraine “On Topographic, Geodetic and Cartographic Activities”. Retrieved from https://zakon.rada.gov.ua/laws/show/353-14#Text

5. Verkhovna Rada of Ukraine (2013). Procedure for the Establishment of the State Geodetic Network. Retrieved from https://zakon.rada.gov.ua/laws/show/646-2013-%D0%BF#n9

6. Ishutina, H. S. (2025). Retrospective Analysis of Studies on the Problem of Reliability of Geodetic Networks. Urban Development and Territorial Planning, (90), 452-462. https://doi.org/10.32347/2076-815x.2025.90.452-462

7. Ishutina, H. S., Behichev, S. V., & Chumak, L. O. (2024). Study of the reliability of a geodetic network to ensure geodetic support of construction. Ukrainian Journal of Construction and Architecture, 5(023), 7-20. https://doi.org/10.30838/UJCEA.2312.301024.07.1087

8. Mrówczyńska, M., & Sztubecki, J. (2021). The network structure evolutionary optimization to geodetic monitoring in the aspect of information entropy, Measurement, 179, 109369. https://doi.org/10.1016/j.measurement.2021.109369

9. Horb, O. I., Nesterenko, S. H., Afanasiev, O. V., & Baistruk, O. V. (2023). Areas of Application of Artificial Intelligence in Geodetic Monitoring of Buildings and Structures. Municipal Economy of Cities, 3(177), 109-114. https://doi.org/10.33042/2522-1809-2023-3-177-109-114

10.      Reiterer, A., Egly, U., Vicovac, T., Mai, E., Moafipoor, S., Grejner-Brzezinska, D. A., & Toth,C. K. (2010). Application of artificial intelligence in Geodesy – A review of theoretical foundations and practical examples. Journal of Applied Geodesy, 4, 201-217. https://doi.org/10.1515/JAG.2010.020

11.      Neuner, H. (2010). Modelling Deformations of a Lock by Means of Artificial Neural Networks. Second Workshop on Application of Artificial Intelligence and Innovations in Engineering Geodesy, 32-41. Retrieved from https://www.researchgate.net/profile/Seyfullah-Demirkaya/publication/259568806_Application_of_Artificial_Intelligence_and_Innovations_in_Engineering_Geodesy/links/5644f0bb08ae451880a8a255/Application-of-Artificial-Intelligence-and-Innovations-in-Engineering-Geodesy.pdf

12.      Neuner, H., & Kutterer, H. (2010). Modellselektion in der ingenieurgeodätischen Deformationsanalyse. Wunderlich, Th. A. (Ed.): “Beiträge zum 16. Internationalen Ingenieurvermessungskurs, München, 2010”, 199-210.

13.      Soja, B. (2024). A geodetic journey from classical statistical methods to machine learning. https://doi.org/10.3929/ethz-b-000661220

14.      Soja, B., Kaselimi, M., Asgarimehr, M., Modiri, S., Sharifi, M. A., Belda, S., …, & Śliwińska-Bronowicz, J. (2025). The Role of AI in Modern Geodesy. Insights from GGOS Focus Area AI4G. https://doi.org/10.3929/ethz-c-000783501

15.      Roumeliotis, A. J., Kaselimi, M., Papafragkakis, A. Z., Panagopoulos, A. D., & Doulamis, N. (2023). Excess attenuation detection in satellite communication channel measurements with deep learning architectures. 17 ^th European Conference on Antennas and Propagation (EuCAP), 1-4. https://doi.org/10.23919/EuCAP57121.2023.10133621

16.      Temenos, A., Temenos, N., Kaselimi, M., Doulamis, A., & Doulamis, N. (2023). Interpretable deep learning framework for land use and land cover classification in remote sensing using SHAP. IEEE geoscience and remote sensing letters, 20, Retrieved from https://ieeexplore.ieee.org/stamp/stamp.jsp?arnumber=10057399

17.      Li, W., Hsu, Ch.-Y., & Hu, M. (2025). Tobler’s First Law in GeoAI: A Spatially Explicit Deep Learning Model for Terrain Feature Detection Under Weak Supervision. https://doi.org/10.48550/arXiv.2508.03745

18.      Stacchio, L., Nepi, L., Paolanti, M., & Pierdicca, R. (2025). RSplitzero: generalized zero-shot learning in remote sensing across attribute splits with single and multi-modal representations. International Journal of Digital Earth, 18(2). https://doi.org/10.1080/17538947.2025.2551869

19.      Pierdicca, R., Paolanti, M., Matrone, F., Martini, M., Morbidoni, C., Malinverni, E. S., Frontoni, E., & Lingua, A. M. (2020). Point cloud semantic segmentation using a deep learning framework for cultural heritage. Remote Sensing, 12(6), 1005. https://doi.org/10.3390/rs12061005

20.      Mai, G., Xie, Y., Jia, X., Lao, N., Rao, J., Zhu, Q., Liu, Y.-Y., Chiang, Jiao, J. (2025). Towards the next generation of Geospatial Artificial Intelligence. International Journal of Applied Earth Observation and Geoinformation, 136, 104368. https://doi.org/10.1016/j.jag.2025.104368

21.      Lou, J., &. Zhang, R. (2021). LF-GNSS: Towards More Robust Satellite Positioning with a Hard Example Mining Enhanced Learning-Filtering Deep Fusion Framework. Journal of latex class files, 14(8). https://doi.org/10.48550/arXiv.2505.19560

22.      Özarpacı, S., Kılıç, B., Can Bayrak, O., Taşkıran, M., Uğur Doğan, U., & Floyd, M. (2024). Machine learning approach for GNSS geodetic velocity estimation. GPS Solutions, 28(65).
https://doi.org/10.1007/s10291-023-01607-1

23.      Özbey, V., Ergintav, S., & Tarı, E. (2024). GNSSTime Series Analysis with Machine Learning Algorithms: A Case Study for Anatolia. Remote Sensing, 16, 3309. https://doi.org/10.3390/rs16173309

24.      Malashchuk, O.S. (2024). Automation of geodetic measurements using artificial intelligence. Nauka і tekhnika siohodni, 11(39), 949-961. https://doi.org/10.52058/2786-6025-2024-11(39)-949-961

25.      Butt, J., Wieser, A., Gojcic, Z., & Zhou, C. (2021). Machine learning and geodesy: A survey. Journal of Applied Geodesy 15(2). https://doi.org/10.1515/jag-2020-0043

26.      McGaughey, J. (2020). Artificial intelligence and big data analytics in mining geomechanics. Journal of the Southern African Institute of Mining and Metallurgy, 120, (1). https://doi.org/10.17159/2411-9717/847/2020

27.      McGaughey, W. J., Laflèche, V., Howlett, C., Sydor, J. L., Campos, D., Purchase, J., & Huynh, S. (2017). Automated, real-time geohazard assessment in deep underground mines. In Wesseloo, J. (Ed.). Proceedings of the Eighth International Conference on Deep and High Stress Mining, Australian Centre for Geomechanics, Perth, (pp. 521-528). https://doi.org/10.36487/ACG_rep/1704_34_McGaughey

28.      Leung, R., Balamurali, M., & Lowe, A. (2021). Surface Warping Incorporating Machine Learning Assisted Domain Likelihood Estimation: A New Paradigm in Mine Geology Modelling and Automation. Mathematical Geosciences. https://doi.org/10.48550/arXiv.2103.03923

• < Prev
• Next >