Resource production forecasting
A method includes receiving data where the data include data for a plurality of factors associated with a plurality of wells; training a regression model based at least in part on the data and the plurality of factors; outputting a trained regression model; and predicting production of a well via the trained regression model.
1. A method comprising:
receiving data wherein the data comprise data for a plurality of factors associated with a plurality of wells;
training a regression model based at least in part on the data and the plurality of factors, wherein the regression model comprises a lateral length factor and a sine and cosine of mean azimuth of trajectory factor;
outputting a trained regression model; and
predicting production of a well via the trained regression model.
2. The method of claim 1 wherein the predicting comprises receiving production data for the well and inputting at least a portion of the production data to the trained regression model.
3. The method of claim 2 wherein the production data comprises production data for less than four months of production of the well as measured from initiation of production of the well.
4. The method of claim 3 wherein the predicting production comprises predicting production to at least twelve months of production of the well wherein at least six of the at least twelve months comprise future months.
5. The method of claim 1 wherein the well comprises an unconventional well.
6. The method of claim 1 wherein the well is in fluid communication with at least one hydraulic fracture.
7. The method of claim 1 wherein the regression model comprises a multiple factor tree model.
8. The method of claim 1 comprising training a plurality of regression models, outputting the plurality of trained regression models; and predicting production of a well via the plurality of trained regression models.
9. The method of claim 8 comprising fitting a decline curve to the predicted production of the well and predicting production of the well based on the fit decline curve.
10. The method of claim 8 wherein the plurality of regression models comprise multiple factor tree models.
11. The method of claim 1 wherein the regression model comprises at least one depth factor.
12. The method of claim 1 wherein the regression model comprises at least one water factor.
13. The method of claim 1 wherein the regression model comprises a depth factor.
14. The method of claim 1 comprising cleansing the data prior to the training.
15. The method of claim 14 wherein the cleansing comprises fitting a log curve to well production versus time data and including the well production versus time data or excluding the well production versus time data based at least in part on the fitting.
16. A system comprising:
a processor;
memory operatively coupled to the processor; and
instructions stored in the memory and executable by the processor to instruct the system to:
receive data wherein the data comprise data for a plurality of factors associated with a plurality of wells;
train a regression model based at least in part on the data and the plurality of factors, wherein the regression model comprises a lateral length factor and a sine and cosine of mean azimuth of trajectory factor;
output a trained regression model; and
predict production of a well via the trained regression model.
17. The system of claim 16 wherein the instructions comprise instructions to instruct the system to:
train a plurality of regression models;
output the plurality of trained regression models;
predict production of a well via the plurality of trained regression models;
fit a decline curve to the predicted production of the well; and
predict production of the well based on the fit decline curve.
18. One or more nontransitory computer-readable storage media comprising computer-executable instructions to instruct a computing system to:
receive data wherein the data comprise data for a plurality of factors associated with a plurality of wells;
train a regression model based at least in part on the data and the plurality of factors, wherein the regression model comprises a lateral length factor and a sine and cosine of mean azimuth of trajectory factor;
output a trained regression model; and
predict production of a well via the trained regression model.
19. The one or more nontransitory computer-readable storage media of claim 18 wherein the computer-executable instructions comprise computer-executable instructions to instruct the computing system to:
train a plurality of regression models;
output the plurality of trained regression models;
predict production of a well via the plurality of trained regression models;
fit a decline curve to the predicted production of the well; and
predict production of the well based on the fit decline curve.