Problems of introducing artificial intelligence into hydraulic engineering

The aim of the work is to systematize the philosophical and methodological problems of the introduction of AI in hydraulic engineering and to propose a conceptual framework for its responsible implementation, ensuring not only technological efficiency, but also social legitimacy, engineering safety and environmental sustainability. The implementation of artificial intelligence (AI) technologies in the field of hydraulic engineering opens up new opportunities for improving the efficiency of water resources management, monitoring the condition of hydraulic structures (HS), and forecasting hazardous processes. However, this process is accompanied by a complex of methodological, regulatory, and ethical problems. The aim of the research is to systematize the key philosophical and methodological challenges related to the epistemological limitations of AI models, the ontological status of digital twins, the redistribution of responsibility, issues of cyber resilience, and socio-ecological justice. The methodology is based on an interdisciplinary literature analysis and case studies of typical tasks (flood management, cavitation diagnostics, filtration monitoring). As a result, the necessity of integrating AI not as a replacement for engineering judgment, but as a tool embedded in a system of professional procedures and public control is substantiated. As a conceptual framework, the principles of technological humility are proposed, including transparent model audit, lifecycle management, and clear role distribution. It is concluded that successful implementation requires a paradigm shift from searching for the “most accurate algorithm” to building robust socio-technical systems that ensure not only technological efficiency but also social legitimacy, engineering safety, and environmental sustainability.

1. Shestakov V.M., Korotkov S.I. Hydrogeomechanics of urbanized territories. Moscow, Nauka Publ., 2018. 300 p.1.

2. International Commission on Large Dams (ICOLD). Bulletin 164: Dam Safety Management: Operational Phase of the Dam Life Cycle. Paris: ICOLD, 2017. 120 p.

3. Ahmed A.A., Pradhan B. Applications of machine learning to water resources management: A review // Journal of Cleaner Production. 2024. Vol. 434. P. 139953. DOI: 10.1016/j.jclepro.2023.139953.

4. Huang Y., Li Z., Wang C. Artificial Intelligence in Dam Safety Monitoring: A Review // Water Resources Management. 2023. Vol. 37, № 5. P. 1821-1840. DOI: 10.1007/s11269-023-03465-5.

5. Liu B., Wang Y., Zhang X. Digital Twin Technology in Hydraulic Engineering: Current Status and Future Trends // Journal of Hydraulic Engineering. 2022. Vol. 148, № 9. P. 1-15. DOI: 10.1061/(ASCE)HY.1943-7900.0002000.

6. Doorn N. Artificial intelligence in the water domain: Opportunities for responsible use // Science of the Total Environment. 2021. Vol. 755. P. 142561. DOI: 10.1016/j.scitotenv.2020.142561.

7. Chen L., Wang H., Li M. Review of Artificial Intelligence Applications in Dams and Water Resources // Journal of Hydroinformatics. 2023. Vol. 25, № 2. P. 345-362. DOI: 10.2166/hydro.2023.125.

8. Kuzmin V.A., Goryunov V.N. Stakeholder Engagement in Digital Transformation of Water Infrastructure: A Case of Russian Hydropower // Water Resources Management. 2023. Vol. 37, Is. 8. P. 3147-3163. DOI: 10.1007/s11269-023-03509-w.

9. Parasuraman R., Sheridan T.B., Wickens C.D. A Model for Types and Levels of Human Interaction with Automation // IEEE Transactions on Systems, Man, and Cybernetics – Part A: Systems and Humans. 2000. Vol. 30, № 3. P. 286-297. DOI: 10.1109/3468.844354.

10. Beery J., Kooy M., Funder M. Equity in Water Governance: A Review of Justice-Oriented Water Research // Wiley Interdisciplinary Reviews: Water. 2022. e1604. DOI: 10.1002/wat2.1604.

11. Shin S., Lee S., Judi D.R., Parvania M., McPherson T., Burian S., Marx A. A Systematic Review of Quantitative Resilience Measures for Water Infrastructure Systems // Water. 2018. Vol. 10, № 2. P. 164. DOI: 10.3390/w10020164.

12. Alcaraz C., Lopez J. Digital Twin: A Comprehensive Survey of Security Threats // IEEE Communications Surveys & Tutorials. 2022. Vol. 24, № 3. P. 1475-1503. DOI: 10.1109/COMST.2022.3171465.

13. U.S. Department of Energy. Cybersecurity Considerations for Digital Twins in the Energy Sector. 2023. 62 p. URL: https://www.energy.gov/sites/default/files/2023-10/Cybersecurity%20Considerations%20for%20Digital%20Twins%20in%20the%20Energy%20Sector.pdf (дата обращения: 15.10.2024).

14. Kumar A., Singh R. Enhancing Cybersecurity of Hydroelectric Power Plants through Digital Twin Modeling // IEEE Transactions on Power Systems. 2024. Vol. 39, № 1. P. 456-465. DOI: 10.1109/TPWRS.2023.3321541.