Abstract: Implementations described and claimed herein provide systems and methods for developing resources from a reservoir. In one implementation, obtaining nuclear magnetic resonance (NMR) log data is obtained for one or more wells of the reservoir. The NMR data is captured using one or more logging tools. An interpreted NMR log is generated by quantifying one or more fluid producibility parameters. The one or more fluid producibility parameters are quantified by processing the NMR log data using automated unsupervised machine learning. A production characterization of the reservoir is generated based on the interpreted NMR log, with the reservoir being developed based on the production characterization.

Abstract: Systems and method for nuclear magnetic resonance (NMR) well logging use an inversion pulse sequence with a Carr-Purcell-Meiboom-Gill (CPMG) pulse sequence to improve spin magnetization calculations. Improved Bloch equation-based calculations consider conditions where a longitudinal relaxation time and a transverse relaxation time of the hydrogen nuclei (e.g., of a subterranean hydrocarbon pool and/or water) are within an order of magnitude of pulse durations for the inversion pulse sequence and the CPMG pulse sequence. Accordingly, an NMR response to the inversion pulse sequence and the CPMG pulse can be detected and used to calculate one or more spin magnetization values with higher accuracy amplitudes. Reservoir characteristics are determined based on the one or more spin magnetization values. As such, improved well operations (e.g., selecting a drilling site, determining a drilling depth, and the like) can be performed.

Abstract: Implementations described and claimed herein provide systems and methods for determining surfactant impact on reservoir wettability. In one implementation, a nuclear magnetic resonance T1 measurement of a sample is obtained before surfactant imbibition is applied to the sample, and a second nuclear magnetic T2 measurement of the sample is made after forced imbibition of the surfactant. Moreover, another nuclear magnetic resonance T1 measurement (e.g., omitting surfactant imbibition) can be obtained simultaneously with the nuclear magnetic resonance T2 measurement using a twin core sample. The nuclear magnetic resonance T1 measurement and the nuclear magnetic resonance T2 measurement are captured under simulated reservoir conditions. A fluid typing map is generated using the nuclear magnetic resonance T1 measurement and the nuclear magnetic resonance T2 measurement. An impact of the surfactant on fluid producibility is determined based on the fluid typing map.

Abstract: A method and system for estimating native hydrocarbons from oil-based drilling muds with the aid of NMR data. Adaptive echo stacking may be used to balance between precision and sensitivity to changes in the fluid composition. Apparent T2 decay time and effective diffusion constants derived from the NMR data may be transformed into an indication of native hydrocarbon type, using known diffusion constants, fuzzy logic, and neural networks.