Abstract: Methods for prediction and inhibition of calcium carbonate scale in hydrocarbon wells using machine learning include extracting training data including parameters from aqueous samples. Each aqueous sample is collected from a respective hydrocarbon well. The training data is classified in accordance with hydrocarbon production conditions of each hydrocarbon well. The classified training data is labeled in accordance with whether calcium carbonate scale has formed in each aqueous sample within a particular time period. A feature vector is determined from the labeled training data based on the parameters extracted from each aqueous sample. The feature vector is indicative of whether the respective hydrocarbon well contains calcium carbonate scale. A trained machine learning model is generated, wherein the machine learning model is trained based on the feature vector, to predict a number of the hydrocarbon wells containing calcium carbonate scale within the particular time period.

Abstract: A method of prioritizing candidate natural resource production wells for acid stimulation, including: receiving well testing information associated with a plurality of natural resource production wells; identifying a respective skin factor for each of the plurality of natural resource production wells; modeling an inflow performance relationship and a vertical lift performance for each of the plurality of natural resource production wells based on the identified respective skin factor; forecasting a post-stimulation production increase based on the modeled inflow performance relationship and vertical lift performance, and a predetermined skin factor adjustment; determining an incremental reserve over cost metric based on the forecasted post-stimulation production increase; ranking the plurality of natural resource production wells according to the determined incremental reserve over cost metric; and outputting one or more control signals adapted to initiate acid stimulation of one or more top-ranked natural r

Abstract: A system and method an acid corrosion inhibitor virtual laboratory is described. The method includes obtaining inputs comprising at least one of an acid concentration, exposure time, temperature, or any combinations thereof. A success or failure of a predefined minimum inhibitor loading value is predicted. A minimum inhibitor loading value that is a successful corrosion inhibitor loading is determined based on the inputs responsive to a failure of the predefined minimum inhibitor loading value.

Abstract: To control hydrostatic backpressure of disposal wells connected to a disposal plant surface network, density of water to be injected from a water disposal plant system into disposal wells formed in a subterranean zone, a density of a hydrostatic backpressure-modifying additive to modify a density of the water, a target total injection flow rate of the water, and a vertical depth of a portion of the subterranean zone through which the water is to be injected are identified. Injected water flow rate upstream of an injection point into the multiple disposal wells, wellhead injection pressure needed to achieve the target total injection flow rate and a total injection rate are periodically received. Based on these parameters, dosage rate of the additive to maintain the target total injection flow rate is periodically determined. An additive quantity is injected into the water and periodically modified based on the periodically determined dosage rate.

Abstract: Systems and methods include a computer-implemented method for predicting optimization scenarios. Health and defect categories are generated from historical well integrity survey data for surveyed wells. For each asset, a reference point in time and fixed analysis time durations are generated for the health and defect categories. A probability of defect (PD) cumulative distribution function (CDF) for predicting probabilities of defects over time is generated. A probability of health (PH) CDF for predicting health probabilities over time is generated. An overall probability of failure (Pf) function for predicting the Pf for the asset is determined. An overall age CDF for the asset is determined and is fitted to optimization scenarios for annual surveys of assets under different survey frequencies. A prediction for a number of failures is determined for each of the optimization scenarios. The predictions are provided to a user for selection of an optimization scenario.

Abstract: Techniques to determine wellbore leak crossflow rate between formations in an injection well are described. The techniques repurpose well performance principles to achieve the objective of cross flow rate quantification without the need to run a flowmeter.

Abstract: Methods for prediction and inhibition of calcium carbonate scale in hydrocarbon wells using machine learning include extracting training data including parameters from aqueous samples. Each aqueous sample is collected from a respective hydrocarbon well. The training data is classified in accordance with hydrocarbon production conditions of each hydrocarbon well. The classified training data is labeled in accordance with whether calcium carbonate scale has formed in each aqueous sample within a particular time period. A feature vector is determined from the labeled training data based on the parameters extracted from each aqueous sample. The feature vector is indicative of whether the respective hydrocarbon well contains calcium carbonate scale. A trained machine learning model is generated, wherein the machine learning model is trained based on the feature vector, to predict a number of the hydrocarbon wells containing calcium carbonate scale within the particular time period.

Abstract: Methods for prediction and inhibition of calcium carbonate scale in hydrocarbon wells include generating a confusion matrix for each of several machine learning methods. The confusion matrix is generated by executing a machine learning model trained to predict a number of hydrocarbon wells containing scale. A probabilistic model is generated indicating an uncertainty associated with using the machine learning method to predict the number of hydrocarbon wells containing scale based on the confusion matrix. A cost metric is generated indicating a cost of implementing a scale inhibition program using the machine learning method based on the probabilistic model. A machine learning method having a lowest cost metric is selected. It is determined whether the lowest cost metric is less than a base cost of implementing the scale inhibition program using a scale inhibition chemical.

Abstract: Provided are systems and method for operating and maintaining downhole inflow control valves (ICVs) of hydrocarbon wells, including monitoring the operations of ICVs to identify failure and non-failure times of defective and non-defective ICVs, respectively, determining a probability of failure of the ICVs (Pf) based on the failure and non-failure times, determining an operational stroking duration based on the probability of failure of the ICVs (Pf), and operating ICVs in accordance with the operational stroking duration determined.

Abstract: Provided are systems and method for operating and maintaining downhole inflow control valves (ICVs) of hydrocarbon wells, including monitoring the operations of ICVs to identify failure and non-failure times of defective and non-defective ICVs, respectively, determining a probability of failure of the ICVs (Pf) based on the failure and non-failure times, determining an operational stroking duration based on the probability of failure of the ICVs (Pf), and operating ICVs in accordance with the operational stroking duration determined.

Abstract: Techniques to determine wellbore leak crossflow rate between formations in an injection well are described. The techniques repurpose well performance principles to achieve the objective of cross flow rate quantification without the need to run a flowmeter.