Fluid inflow characterization using hybrid DAS/DTS measurements

1. A method of determining fluid inflow rates within a wellbore extending within a subterranean formation, the method comprising:

determining a plurality of temperature features from a distributed temperature sensing signal originating in a wellbore, wherein each temperature feature of the plurality of temperature features is a statistical variation of a temperature measurement along the wellbore through depth or both time and depth;

determining one or more frequency domain features from an acoustic signal originating in the wellbore, wherein the one or more frequency domain features are obtained from a frequency domain representation of the acoustic signal; and

using at least one temperature feature of the plurality of temperature features as an input to a first machine learning model and using at least one frequency domain feature of the one or more frequency domain features as an input to a second machine learning model to identify one or more fluid inflow locations along the wellbore and to determine a fluid inflow rate at the one or more fluid inflow locations, wherein the fluid inflow rate comprises a rate of fluid flowing into the wellbore from the subterranean formation.

2. The method of claim 1 , wherein using the at least one temperature feature and using the at least one frequency domain feature comprises:

using the first machine learning model to identify the one or more fluid inflow locations; and

using the second machine learning model to determine the fluid inflow rate at the one or more fluid inflow locations.

3. The method of claim 2 , wherein the first machine learning model comprises one or more multivariate models, and wherein the output from each multivariate model of the one or more multivariate model comprises an indication of the one or more fluid inflow locations.

4. The method of claim 3 , wherein the second machine learning model comprises a regression model, and wherein the output from the regression model comprises an indication of a fluid inflow rate at the one or more fluid inflow locations.

5. The method of claim 2 , further comprising combining an output from the first machine learning model an output from the second machine learning model to form a combined output.

6. The method of claim 5 , further comprising:

receiving an indication of a fluid flow rate from the wellbore; and

allocating a portion of the fluid flow rate from the wellbore to the one or more fluid inflow locations based on the determined fluid inflow rate at the one or more fluid inflow locations based on the combined output.

7. The method of claim 1 , wherein the fluid inflow rate is the liquid inflow rate at one or more locations along the wellbore.

8. The method of claim 1 , wherein the plurality of temperature features comprise at least two of: a depth derivative of temperature with respect to depth, a temperature excursion measurement, a baseline temperature excursion, or a peak-to-peak value.

9. The method of claim 1 , wherein the plurality of temperature features comprise a temperature excursion measurement, and wherein the temperature excursion measurement comprises a difference between a temperature reading at a first depth and a smoothed temperature reading over a depth range, wherein the first depth is within the depth range.

10. The method of claim 1 , wherein the plurality of temperature features comprise a derivative of a baseline excursion with depth, and wherein the baseline temperature excursion comprises a derivative of a baseline excursion with depth, wherein the baseline excursion comprises a difference between a baseline temperature profile and a smoothed temperature profile.

11. The method of claim 1 , wherein the plurality of temperature features comprise a peak-to-peak value, and wherein the peak-to-peak value comprises a derivative of a peak-to-peak difference with depth, wherein the peak-to-peak difference comprises a difference between a peak high temperature reading and a peak low temperature reading with an interval.

12. The method of claim 1 , wherein the one or more frequency domain features comprise at least one of: a spectral centroid, a spectral spread, a spectral roll-off, a spectral skewness, a root mean square (RMS) band energy, a total RMS energy, a spectral flatness, a spectral slope, a spectral kurtosis, a spectral flux, or a spectral autocorrelation function.

13. A method of determining fluid inflow rates along a wellbore extending within a subterranean formation, the method comprising:

determining a plurality of temperature features from a distributed temperature sensing signal originating in a wellbore, wherein the plurality of temperature features comprise at least two of: a depth derivative of temperature with respect to depth, a temperature excursion measurement, a baseline temperature excursion, or a peak-to-peak value;

determining one or more frequency domain features from an acoustic signal originating in the wellbore;

using at least one temperature feature of the plurality of temperature features as an input to a first machine learning model to determine an indication of one or more locations along the wellbore; and

after using the at least one temperature features to determine the indication of the one or more locations, using at least one frequency domain feature of the one or more frequency domain features as an input to a second machine learning model to determine a fluid inflow rate at each of the one or more locations, wherein the fluid inflow rate comprises a rate of fluid flowing into the wellbore from the subterranean formation.

14. The method of claim 13 , wherein the one or more frequency domain features comprise at least one of: a spectral centroid, a spectral spread, a spectral roll-off, a spectral skewness, a root mean square (RMS) band energy, a total RMS energy, a spectral flatness, a spectral slope, a spectral kurtosis, a spectral flux, or a spectral autocorrelation function.

15. The method of claim 13 , further comprising:

combining an output from the first machine learning model and an output from the second machine learning model to form a combined output; and

determining an identification of the one or more locations and the fluid inflow rate at each of the one or more locations based on the combined output.

16. The method of claim 15 , wherein the first machine learning model comprises one or more multivariate models, and wherein the output from each multivariate model of the one or more multivariate model comprises an indication of the one or more locations along the wellbore.

17. The method of claim 16 , wherein the second machine learning model comprises a regression model, and wherein the output from the regression model comprises an indication of a fluid inflow rate at the one or more locations along the wellbore, and wherein combining the output from the first machine learning model with the output from the second machine learning model comprises determining the combined output as a function of: 1) the output from the first machine learning model, and 2) the output from the second machine learning model.

18. The method of claim 13 , further comprising:

receiving an indication of a fluid flow rate from the wellbore; and

allocating a portion of the fluid flow rate from the wellbore to the one or more locations along the wellbore based on the determined fluid inflow rate at the one or more locations based on the combined output.

19. A system of determining fluid inflow rates within a wellbore extending within a subterranean formation, the system comprising:

a processor;

a memory; and

an analysis program stored in the memory, wherein the analysis program is configured, when executed on the processor, to:

receive a distributed temperature sensing signal and an acoustic signal, wherein the temperature sensing signal and the acoustic signal originated within the wellbore;

determine a plurality of temperature features from the distributed temperature sensing signal, wherein each temperature feature of the plurality of temperature features is a statistical variation of a temperature measurement along the wellbore through depth or both time and depth;

determine one or more frequency domain features from the acoustics signal;

determine an identification of one or more locations along the wellbore by providing at least one temperature feature of the plurality of temperature features to a first machine learning model; and

determine a fluid inflow rate at each of the one or more locations by providing at least one frequency domain feature of the one or more frequency domain features to a second machine learning model, wherein the fluid inflow rate comprises a rate of fluid flowing into the wellbore from the subterranean formation.

20. The system of claim 19 , wherein the analysis program is further configured to:

combine an output from the first machine learning model and an output from the second machine learning model to form a combined output; and

determine the identification of the one or more locations and the fluid inflow rate at each of the one or more locations based on the combined output.

21. The system of claim 20 , wherein the first machine learning model comprises one or more multivariate models, and wherein the output from each multivariate model of the one or more multivariate model comprises an indication of the one or more locations.

22. The system of claim 21 , wherein the second machine learning model comprises a regression model, and wherein the output from the regression model comprises an indication of a fluid inflow rate at the one or more locations along the wellbore, and wherein the analysis program is further configured to:

combine the output from the first machine learning model with the output from the second machine learning model as a function of: 1) the output from the first machine learning model, and 2) the output from the second machine learning model.

23. The system of claim 19 , wherein the analysis program is further configured to:

receive an indication of a fluid flow rate from the wellbore; and

allocate a portion of the fluid flow rate from the wellbore to the one or more locations along the wellbore based on the determined fluid inflow rate at the one or more locations based on the combined output.

24. The system of claim 19 , wherein the plurality of temperature features comprise at least two of: a depth derivative of temperature with respect to depth, a temperature excursion measurement, a baseline temperature excursion, or a peak-to-peak value.