Digital methods for predicting foundation settlements

Introduction. In the context of building reconstruction with underground space development, monitoring foundation deformations is of critical importance. Traditional criteria based solely on settlement magnitudes and their relative non-uniformity do not fully capture the spatial distribution of deformations and their correlation with geotechnical and structural factors.

Materials and methods. A digital methodology for predicting deformations of the foundations of reconstructed buildings was applied, based on the approximation of settlement by cubic splines and subsequent analysis of its derivative functions (angle of inclination and curvature). The methodology includes: formalization of the algorithm for constructing continuous settlement profiles and calculating their derivatives from geodetic monitoring data; validation of the methodology using case studies of reconstruction projects in Moscow and St. Petersburg with varying excavation parameters, wall lengths and orientations, as well as geotechnical conditions; application of machine learning methods to identify relationships between excavation geometry, soil parameters, and observed deformations.

Results. The constructed fields of settlement and its derivatives made it possible to localize zones of maximum deformations between benchmarks and to record cases of exceeding normative threshold values. Machine learning methods demonstrated the ability to predict deformation parameters (C′, D′) from external data on geometry and soil properties, providing acceptable accuracy on a limited dataset.

Conclusions. The application of cubic spline approximation of settlements in reconstructed buildings with underground parts, along with the calculation of slope and curvature of the foundation base, expands the traditional analysis toolkit, enabling identification of local deformation zones inaccessible to linear approximation. Integration with machine learning algorithms offers prospects for predicting foundation behavior in new reconstruction projects with underground development under dense urban conditions.

1. Il’ichev V.A., Konovalov P.A., Nikiforova N.S. New methods of measuring building deformations and criteria for their estimation. Soil Mechanics and Foundation Engineering. 2003; 4:8-12. EDN LLWFKS. (rus.).

2. Il’ichev V.A., Nikiforova N.S. Methods for the determination of curvatures and the difference between the slopes of foundations as the criteria of deformation of the basements of buildings and structures. Soil Mechanics and Foundation Engineering. 2018; 3:14-17. EDN YNJLHV. (rus.).

3. Shashkin V.A. Accumulated deformations of the historical development of St. Petersburg. Housing Construction. 2023; 12:32-45. DOI: 10.31659/0044-4472-2023-12-32-45. EDN CITCIO. (rus.).

4. Shashkin V.A. Construction of foundations of range buildings in the XVIII – early XIX century (by example of Saint Petersburg). Geotechnics. 2022; 14(3):6-20. DOI: 10.25296/2221-5514-2022-14-3-6-20. EDN GIYETQ. (rus.).

5. Shashkin V.A. Provision of safety of historical buildings subjected to “excess” deformations caused by new construction. Geotechnics. 2024; 16(4):24-39. DOI: 10.25296/2221-5514-2024-16-4-24-37. EDN VQVXCE. (rus.).

6. Svensson M.. GeoBIM for optimal use of geotechnical data. Proceedings of the Nordic Geotechnical Meeting (NGM). 2016; 66-121.

7. El Sibaii M., Granja J., Bidarra L., Azenha M. Towards efficient BIM use of geotechnical data from geotechnical investigations // Journal of Information Techno-logy in Construction (ITcon). 2022. Vol. 27. Pp. 393–415. DOI: 10.36680/j.itcon.2022.019.

8. Tawelian L.R., Mickovski S.B. The implementation of geotechnical data into the BIM process. Procedia Engineering. 2016; Vol. 143. Pp. 734–741. DOI: 10.1016/j.proeng.2016.06.115.

9. Beck J., Jürgens S., Henke S. Automating stability analysis using BIM-FEA-Integration // Proceedings of the XVIII ECSMGE 2024.

10. Berdigylyjov M., Popa H. The implementation and role of geotechnical data in BIM process // E3S Web of Conferences. 2019. Vol. 85. 08009. DOI: 10.1051/e3sconf/20198508009

11. Razvodovsky D.E., Shulyatiev S.O., Stavnitser L.R. The use of BIM in geotechnics. Housing Construction. 2018; 11:3-8. EDN VOFZRW. (rus.).

12. Fonsati A., Cosentini R.M., Tundo C., Osello A. From Geotechnical Data to GeoBIM Models: Testing Strategies for an Ex-Industrial Site in Turin. Buildings. 2023. Vol. 13(9). Article 2343. DOI: 10.3390/buildings13092343.

13. Liu N. et al. BIM-based digital platform and risk management system for mountain tunnel construction // Scientific Reports. 2023.

14. Utepov Y., Aldungarova A., Mukhamejanova A., Awwad T., Karaulov S., Makasheva I. Voxel Interpolation of Geotechnical Properties and Soil Classification Based on Empirical Bayesian Kriging and Best-Fit Convergence Function. Buildings. 2025; 15(14):2452. DOI: 10.3390/buildings15142452

15. Zaid R. 3D visualization of interpolating geotechnical strata in a BIM environment (Case study of Civil3D). Misan Journal of Engineering Sciences. 2024;5(2):10-18.

16. Krasilnikov V.P., Andrianov A.V., Krasilnikov P.A., Meshcheriakova O.Yu. Prospects and problems of introducing BIM technology in the domestic construction industry. Geotechnics. 2022; 14(2):6-17. DOI: 10.25296/2221-5514-2022-14-2-6-17. EDN SQYXBG. (rus.).

17. Yuan B., Choo C.S., Yeo L.Y., Wang Y., Yang Z., Guan Q. et al. Physics-informed machine learning in geotechnical engineering: a direction paper. Geomechanics and Geoengineering. 2025; 20(5):1128-1159. DOI: 10.1080/17486025.2025.2502029

18. Dahal A., Lombardo L. Towards physics-informed neural networks for landslide prediction. ArXiv. 2024. DOI: 10.48550/arXiv.2407.06785

19. Boldyrev G.G., Idrisov I.Kh., Redin A.V., Diveev A.A. BIM geotechnics and perspectives of its development in the Russian Federation. Geotechnics. 2020; 12(4):6-22. DOI: 10.25296/2221-5514-2020-12-4-6-22. EDN VRURKI. (rus.).

20. Satyanaga A., Aventian G.D., Makenova Y., Zhakiyeva A., Kamaliyeva Z., Moon S.W. et al. Building Information Modelling for Application in Geotechnical Engineering. Infrastructures. 2023; 8(6):103. DOI: 10.3390/infrastructures8060103

21. Samosvat V.V. Three-dimensional digital model of the geological environment as a key element of BIM technology and the highest stage of construction digitalization. Independent electronic journal “GeoInfo”. 2020; (3). (rus.).

22. Kudrevatykh O.A., Seredin V.V., Andrianov A.V., Krasilnikov V.P. On the selection of software for creating BIM in engineering geology. Proceedings of Tula State University. Earth Sciences. 2023; 1:283-296. (rus.).