Abstract: Methods for determination of mechanical properties of geological formations using deep learning include receiving, by a computer system, data acquired during drilling a geological formation. The computer system generates features of the data acquired during drilling. The features are indicative of mechanical properties of the geological formation. The computer system segments the features of the data acquired during drilling into sequences readable by a trained temporal convolutional network (TCN). The computer system determines the mechanical properties of the geological formation using the TCN based on the sequences obtained from the features of the data. A display device of the computer system generates a graphical representation of the mechanical properties of the geological formation.

Abstract: Methods for determination of mechanical properties of geological formations using deep learning include receiving, by a computer system, data acquired during drilling a geological formation. The computer system generates features of the data acquired during drilling. The features are indicative of mechanical properties of the geological formation. The computer system segments the features of the data acquired during drilling into sequences readable by a trained temporal convolutional network (TCN). The computer system determines the mechanical properties of the geological formation using the TCN based on the sequences obtained from the features of the data. A display device of the computer system generates a graphical representation of the mechanical properties of the geological formation.

Abstract: Techniques for controlling a hydrocarbon production system include determining a first estimate of a prior FVC detectability probability map based on a plurality of reservoir data that includes four-dimensional (4D) seismic data of a subterranean reservoir; determining a second estimate of the prior FVC detectability probability map under seismic data noise conditions; determining an updated detectable FVC probability based on the 4D seismic data; determining an updated FVC probability based on the updated detectable FVC probability and the first and second estimates of the prior FVC detectability probability maps; and generating a control instruction for at least one of a fluid injection system or a hydrocarbon production assembly based on the updated FVC probability.

Abstract: A method of continuous seismic reservoir monitoring includes receiving a plurality of seismic data sets associated with a reservoir during a period, where the plurality of seismic data sets corresponds to seismic data received at different times during the period. The reservoir includes a plurality of reflectors, where each reflector has a reflection coefficient. For each of the plurality of seismic data sets, the reflection coefficients of the plurality of reflectors are determined by iteratively updating common focus point (CFP) operators associated with the plurality of reflectors and a plurality of acquisition surface locations. The reflection coefficients corresponding to different seismic data sets are compared to determine changes of the reflection coefficients during the period. The changes of the reflection coefficients are displayed.

Abstract: Techniques for controlling a hydrocarbon production system include determining a first estimate of a prior FVC detectability probability map based on a plurality of reservoir data that includes four-dimensional (4D) seismic data of a subterranean reservoir; determining a second estimate of the prior FVC detectability probability map under seismic data noise conditions; determining an updated detectable FVC probability based on the 4D seismic data; determining an updated FVC probability based on the updated detectable FVC probability and the first and second estimates of the prior FVC detectability probability maps; and generating a control instruction for at least one of a fluid injection system or a hydrocarbon production assembly based on the updated FVC probability.

Abstract: A method of continuous seismic reservoir monitoring includes receiving a plurality of seismic data sets associated with a reservoir during a period, where the plurality of seismic data sets corresponds to seismic data received at different times during the period. The reservoir includes a plurality of reflectors, where each reflector has a reflection coefficient. For each of the plurality of seismic data sets, the reflection coefficients of the plurality of reflectors are determined by iteratively updating common focus point (CFP) operators associated with the plurality of reflectors and a plurality of acquisition surface locations. The reflection coefficients corresponding to different seismic data sets are compared to determine changes of the reflection coefficients during the period. The changes of the reflection coefficients are displayed.

Abstract: An method of constructing a geological model of a subsoil formation constrained by seismic data having application to petroleum reservoir development is disclosed. Logs relative to geological properties are acquired and a seismic facies cube is constructed. Logs relative to geological properties and logs relative to seismic facies are then simulated. Then distribution of proportions is estimated at any point on the subsoil by means of the acquired logs in the well and of the simulated logs. A seismic constraint is then defined by constructing a lithologic facies average proportion cube from these estimated proportion distributions. Finally, a geological model wherein the geological properties are constrained by this lithologic facies average proportion cube is constructed.

Abstract: The invention is a method for facilitating recognition of objects, using a discriminant analysis technique to classify the objects into predetermined categories. A learning base comprising objects that have already been recognized and classified into predetermined categories is formed with each category being defined by variables of known statistical characteristics. A classification function using a discriminant analysis technique, which allows distribution among the categories the various objects to be classified from measurements available on a number of parameters, is constructed by reference to the learning base. This function is formed by determining the probabilities of the objects belonging to the various categories by taking account of uncertainties about the parameters as intervals of variable width. Each object is then assigned, if possible, to one or more predetermined categories according to the relative value of the probability intervals.

Abstract: A method for facilitating monitoring, in the course of time, of the evolution of the physical states of a zone of an underground formation such as a reservoir by using and interpreting 4D seismic data. The method uses seismic pattern recognition, more particularly a fuzzy discriminant analysis technique allowing to integrate the uncertainties on the seismic measurements in the interpretation. The uncertainties taken into account are evaluated on parts of seismic traces obtained during successive seismic surveys, corresponding to zones of the underground formation (outside the reservoir) where the physical states monitored have undergone no significant change. The invention is useful for monitoring of the evolution of a hydrocarbon reservoir during production.

Abstract: Method for facilitating monitoring, in the course of time, of the evolution of the physical states of a zone of an underground formation such as a reservoir by using and interpreting 4D seismic data.

Abstract: Method for facilitating recognition of objects, using a discriminant analysis technique to classify them into predetermined categories.