Vol. 337 No. 8 (2026)
DOI https://doi.org/10.18799/24131830/2026/8/5054
Approximation and noise reduction in oil well thermometry by distributed fiber optic sensors
Relevance. The use of distributed fiber-optic temperature sensors in oil production wells can improve the quality of data obtained during operation. Aim. To show that the captured temperature distribution contains random fluctuations, the magnitude of which is comparable to the magnitude of thermoanomalies caused by the filtration flow of oil in the reservoir. Methods. To reduce the noise of the original signal taken from a real oil well, various approximation methods: median smoothing, moving average, exponential smoothing, Fourier filtering, decision tree, random forest, adaptive boosting and Nadaraya–Watson kernel regression method, were analyzed. Results and conclusions. The authors analyzed the results of application of these types of signal post-processing in terms of the following parameters: accuracy of approximation of equilibrium geothermal distribution in the well sump, where analytical determination of temperature distribution is possible, smoothness of the approximating function, uniqueness of the solution and demandingness of computational resources. It is shown that the application of adaptive boosting and Fourier filtering for this problem gives the largest approximation errors. Median smoothing, exponential smoothing and random forest give similar results in accuracy and low computational costs. The first does not have smoothness of solution. The second one depends to a large extent on the tuning parameters and the obtained solution may be either noisy as well, or the smooth solution may exhibit systematic error caused by random deviations of the initial points. Such error can be compensated by additional averaging at the initial stages of exponential smoothing. The random forest approximation is also tuning dependent, and regions of overfitting where the approximation replicates the original signal may be adjacent to a very coarse approximation of the original signal; this always produces a new approximation at each generation. The best results were obtained by the Nadaraya–Watson kernel regression method, since the solution found has the lowest error, high smoothness and uniqueness, in contrast to machine learning methods. On the basis of analyzing the features of the algorithm of this method, as well as the machine representation of real numbers, we propose methods to improve the computational efficiency of the Nadaraya–Watson kernel regression.
For citation: Nikulin I.L., Mishurinskikh S.V., Chudinov P.Yu., Semenov A.S., Melekhin A.A., Nikulina D.I. Approximation and noise reduction in oil well thermometry by distributed fiber optic sensors. Bulletin of the Tomsk Polytechnic University. Geo Assets Engineering, 2026, vol. 337, no. 8, pp. 77–89. http://doi.org/10.18799/24131830/2026/8/5054
Keywords:
thermogram, temperature anomalies, geothermal gradient, signal filtering, signal post-processing, exponential smoothing, machine learning, Nadaraya–Watson kernel regression
References:
1. Privalova O.R., Taigina M.E., Asylgareev I.N. Complex application of well and core research methods in substantiation of reservoir properties of productive strata on the example of poorly studied carbonate sediments of Cenomanian. Oil economy, 2024, no. 9, pp. 45–49. (In Russ.) DOI: 10.24887/0028-2448-2024-9-45-49
2. Grinchenko V.A., Valeev R.R., Abdullin M.M., Shchekotov I.V., Kopylov A.V., Svyashenko A.V., Yashchenko S.A., Kobyashev A.V., Komyagin A.I., Mandrugin A.V., Istisheva V.F. Features of complex field geophysical studies to control field development in complicated conditions of Eastern Siberia. Oil industry, 2020, no. 11, pp. 56–61. (In Russ.) DOI: 10.24887/0028-2448-2020-11-56-61
3. Ipatov A.I., Malyavko E. What happens to the inflow profiles of horizontal wells after development. Neftegazovaya vertical, 2022, no. 6, pp. 110–119. (In Russ.)
4. Cherepanov V.V., Akhmedsafin S.K., Cherepanov S.K., Akhmedsafin S.K., Kirsanov S.A. Application of neutron well logging technologies in the development of oil and gas condensate fields. State and prospects of development. Gas Industry, 2019, no. S1 (782), pp. 44–49. (In Russ.)
5. Herlinger R. Jr, Bonzanini L.A.F., Vidal A.C. Residual oil saturation in Pre-salt Brazilian carbonates: A multi-approach core-to-log case study. Journal of South American Earth Sciences, 2024, vol. 140, no. 104905. DOI: 10.1016/j.jsames.2024.104905.
6. Herlinger R., De Ros L.F., Surmas R. Residual oil saturation investigation in Barra Velha Formation reservoirs from the Santos Basin, Offshore Brazil: a sedimentological approach. Sedimentary Geology, 2023, vol. 448, no. 106372. DOI: 10.1016/j.sedgeo.2023.106372.
7. Valiullin R.A., Sharafutdinov R.F., Ramazanov A.Sh., Kanafin I.V., Imaev A.I., Bazhenov V.V. Method of determination of working intervals by active thermometry method. Patent RF, no 2808650, 2023. (In Russ.)
8. Davletshin F.F., Islamov D.F., Khabirov T.R., Gayazov M.S., Nizayeva I.G. Study of heat-exchange processes at induction heating of a casing string in relation to determination of casing overflows. Physical and Mathematical Modelling. Oil, Gas, Power Engineering, 2023, vol. 9, no. 1 (33), pp. 60–77. (In Russ.) DOI: 0.21684/2411-7978-2023-9-1-60-77.
9. Potashev K.A., Salimyanova D.R., Mazo A.B., Davletshin A.A., Kosterin A.V.. Sensitivity of interpretation of thermometry results of an isolated section of an injection well to the error of the initial data. Scientific Notes of Kazan University. Series of physical and mathematical sciences, 2024, vol. 16, book 2, pp. 238–249. (In Russ.) DOI: 10.26907/2541-7746.2024.2.238-249.
10. Ipatov A.I., Kremenetsky M.I., Khudiev E.R., Gubarev A.Yu., Skopinov S.A., Solovyeva V.V., Gulyaev D.N. Effectiveness of depth distributed fibre optic monitoring of horizontal wells equipped with electric centrifugal pump units in ‘Gazpromneft’. Oil industry, 2023, no. 12, pp. 58–63. (In Russ.)
11. Cai J., Duan Y. Study on temperature distribution along wellbore of fracturing horizontal wells in oil reservoir. Petroleum, 2015, vol. 1, no. 4, pp. 358–365. DOI: 10.1016/j.petlm.2015.10.003.
12. Naidanova E.S., Rybka V.F., Chudinov P.Yu. Experience of using fibre optic technologies in geophysical borehole surveys. Logger, 2019, no. 5 (299), pp. 62–72. (In Russ.)
13. Grosswig S. Detection and determination of the fluid level in the annulus in the Kiel underground gas storage facility (Germany) using fibre optic temperature measurements. SMRI Fall 2002 Meeting. DOI: 10.13140/RG.2.1.1936.0800.
14. Grosswig S., Crotogino F., Hurtig E., Vogel B., Crotogino F., Schoenebeck J., Riekenberg R., Groenefeld P. Integrity testing using the fibre optic temperature sensing mechanical integrity testing using the fibre optictemperature sensing technique. SMRI Fall 2003 Meeting. DOI: 10.13140/RG.2.1.3246.8004.
15. Bücker, C., Großwig, S., Lundershausen, S. Surveying of the cementation process in wells using fiber optic temperature measurements. SMRI Fall 2005 Conference. DOI: 10.13140/RG.2.1.4557.5209.
16. Grosswig S., Dijk H., Den Hartogh M., Pfeiffer T., Rembe M., Perk M., Domurath L. Leakage detection in a casing string of a brine production well by means of simultaneous fibre optic DTS/DAS measurements. Oil Gas European Magazine, 2019, vol. 45, no. 4, pp. 161–169.
17. Lee D.S., Park K.G., Lee C., Choi S.J. Distributed temperature sensing monitoring of well completion processes in a CO2 geological storage demonstration site. Sensors, 2018, vol. 18, no. 12. DOI:10.3390/s18124239.
18. Garcia-Ceballos A., Jin G., Collett T.S., Merey S., Haines S. Long-term distributed temperature sensing monitoring for near-wellbore gas migration and gas hydrate formation. SPE Journal, 2024, vol. 29, no. 11, pp. 5804–5819 DOI: 10.2118/223111-PA.
19. Luo H., Li H., Lu Y., Li Y., Guo Z. Inversion of distributed temperature measurements to interpret the flow profile for a multistage fractured horizontal well in low-permeability gas reservoir. Applied Mathematical Modelling, 2020, vol. 77. pp. 360–377. DOI: 10.1016/j.apm.2019.07.047.
20. Yan C., Ren J., Shi Q., Li X., Bai Y., Yu W. Flow profiling analysis of a refractured tight oil well using distributed temperature sensing. Processes, 2024, vol. 12, no. 10. DOI: 10.3390/pr12102106.
21. Williams G., Brown G., Hawthorne W., Hartog A., Waite P. Distributed temperature sensing (DTS) to characterize the performance of producing oil wells. Proceedings of SPIE, 2000, vol. 4202. DOI: 10.1117/12.411726.
22. Ghorbani H., Wood D., Moghadasi J., Choubineh A., Abdizadeh P., Mohamadian N. Predicting liquid flow-rate performance through wellhead chokes with genetic and solver optimizers: an oil field case study. Journal of Petroleum Exploration and Production Technology, 2019, vol. 9, no. 2, pp. 1355–1373. DOI: 10.1007/s13202-018-0532-6.
23. Sharafutdinov R.F., Kanafin I.V., Khabirov T.R., Nizayeva I.G. Numerical study of the temperature field in the system ‘well - formation’ during oil degassing. Bulletin of Tyumen State University. Physics and Mathematical Modelling. Oil, gas, energy, 2017, vol. 3, no. 2, pp. 8–20. (In Russ.) DOI: 10.21684/2411-7978-2017-3-2-8-20.
24. Sharafutdinov R.F., Valiullin R.A., Babanazarov D.I., Kanafin I.V. Simulation of the thermal field in reservoir during the filtration of live oil and water with considering the heat of oil degassing and thermodynamic effects. Tyumen State University Herald. Physical and Mathematical Modeling. Oil, Gas, Energy, 2024, vol. 10 (1), pp. 6–18.
DOI: 10.21684/241179782024101618.
25. Wei N., Sun W., Meng Y., Zhao J., Zhang L., Li H., Li Q., Liu A. Wellbore temperature field prediction in marine drilling. Proceedings of the International Field Exploration and Development Conference, 2018, pp. 573–587 DOI: 10.1007/978-981-13-7127-1_52.
26. Asylgareev A.A., Sharafutdinov R.F., Valiullin R.A., Kosmylin D.V. Experimental study of thermohydrodynamic processes during filtration of oil-water emulsion. Bulletin of Tyumen State University. Physics and Mathematical Modelling. Oil, gas, power engineering, 2022, vol. 8, no. 1 (29), pp. 8–22. (In Russ.) DOI: 10.21684/2411-7978-2022-8-1-8-22.
27. Sudakova M.S., Belov M.V., Ponimaskin A.O., Pirogova A.S., Tokarev M.Yu., Kolyubakin A.A. Features of data processing of vertical seismic profiling of offshore shallow wells with fibre-optic distributed systems. Geophysics, 2021, no. 6, pp. 110–118. (In Russ.)
28. Ramazanov A.Sh., Valiullin R.A., Galliamov M.A. Radial temperature distribution in the well. IFZh, 2022, vol. 95, no. 3, pp. 657–664. (In Russ.)
29. Zakirov M.F., Valiullin R.A., Ramazanov A.Sh. Diagnostics of the overflow from above based on the results of well thermometry, Oilfield Business, 2024, no. 5 (665), pp. 31–37. (In Russ.)
30. Otnes R., Enokson L. Applied analysis of time series: basic methods. Moscow, Mir Publ., 1982. 428 p. (In Russ.)
31. Bilevich D.V., Popov A.A., Dobush I.M., Goryainov A.E., Novichkova Yu.A. Investigation of the smoothing algorithms for the preliminary processing of the microwave transistor noise figure measurement results when building a low-signal noise model. Vestnik of RGRTU, 2020, no. 71, pp. 34–44. (In Russ.) DOI: 10.21667/1995-4565-2020-71-34-44.
32. Valiullin R.A., Zakirov M.F. Using the vronskian to analyse the thermogram of a producing well. Georesursy, 2023, vol. 25 (4), pp. 260–266. DOI: 10.18599/grs.2023.4.22
33. Klyuev R.V., Morgoeva A.D., Gavrina O.A., Bosikov I.I., Morgoev I.D. Forecasting of the planned power consumption for the united power system with the help of machine learning. Notes of the Mining Institute, 2023, vol. 261, pp. 392–402. (In Russ.)
34. Bierens H.J. The Nadaraya–Watson kernel regression function estimator. Topics in Advanced Econometrics. New York, Cambridge University Press, 1994. pp. 212–247.
35. Scikit-learn: Machine Learning in Python. Available at: https://scikit-learn.org/stable (accessed 10 February 2025).
