Automated real-time scale inhibition

An automated system for real-time scale indexing and inhibitor treatment addresses rapid frac water changes, ensuring accurate and timely scale prevention, enhancing well productivity.

WO2026240865A1PCT designated stage Publication Date: 2026-11-19HALLIBURTON ENERGY SERVICES INC
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
PCT/US2026/019065
Authority / Receiving Office
WO · WO
Patent Type
Applications
Current Assignee / Owner
Priority Date
2025-05-16
Filing Date
2026-03-13
Publication Date
2026-11-19

AI Technical Summary

Technical Problem

Frac water conditions can change rapidly, leading to inaccurate scale risk analysis and equipment damage due to scaling, which reduces well productivity and causes formation damage.

Method used

An automated system using real-time scale indexing and empirical models to calculate ion composition and scaling index, allowing for immediate adjustment of scale inhibitor treatment based on water chemistry parameters.

Benefits of technology

Enables accurate and timely scale inhibitor application, reducing equipment failure and improving well productivity by preventing scale formation in wellbores and reservoirs.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure US2026019065_19112026_PF_FP_ABST
    Figure US2026019065_19112026_PF_FP_ABST
Patent Text Reader

Abstract

A system for inhibiting scale in a hydraulic fracturing operation includes a sensor system configured to measure data, and a controller configured to receive, in real time, the data measured by the sensor system; use a first model to estimate, in real time, ion composition in the fracturing fluid, based on the data measured by the sensor system and one or both of a geographical location of the hydraulic fracturing operation or a geographical location of a fluid source of the hydraulic fracturing operation; use a second model to estimate, in real time, a scaling index of a scale species in the fracturing fluid based on the estimated ion composition; determine a treatment parameter of one or more scale inhibitors based on the estimated scaling index of the scale species; and control addition of the one or more scale inhibitors to the fracturing fluid according to the treatment parameter.
Need to check novelty before this filing date? Find Prior Art

Description

Atty. Docket No.: 2024INV112484W001-64001AUTOMATED REAL-TIME SCALE INHIBITION BACKGROUND

[0001] Frac water conditions can change greatly in a single pad. A job could start with highly fresh water and change to highly produced water in a single day, or even a single stage. There may also be sudden changes in pH, Oxidation-Reduction Potential (ORP), temperature, chemical reaction, pressure, contact time (e.g., due to pump rate), evaporation, and / or ionic compositions. Scale risk analysis is conventionally done by spot sampling and laboratory work. However, if there is significant delay between the sampling time and the laboratory result, it could render the analysis inaccurate if there is a rapid change in water quality. Most, if not all, water in frac operations has scaling tendency. Scaling generally refers to the coating of surfaces of pipes and tubing, typically caused when dissolved minerals precipitate from aqueous solutions. When scaling happens in surface equipment, it can cause an increase in non-productive time and equipment failure. When scaling happens in the wellbore, it can reduce the cross-sectional area of the wellbore, which can reduce the productivity of the well. If scaling happens in the reservoir, it can cause formation damage by clogging fractures and pore spaces with mineral deposits, reducing permeability and flow capacity. The system and method of the present disclosure may address one or more of these issues.BRIEF DESCRIPTION OF THE DRAWINGS

[0002] For a more complete understanding of the present disclosure, reference is now made to the following brief description, taken in connection with the accompanying drawings and detailed description, wherein like reference numerals represent like parts.

[0003] FIG. 1A is a schematic diagram of a well system, according to an embodiment of the present disclosure;

[0004] FIG. IB is a schematic diagram of a well system, according to another embodiment;

[0005] FIG. 2 is a schematic diagram of a well system, according to an embodiment;

[0006] FIG. 3 is a schematic diagram of a well system, according to another embodiment;

[0007] FIG. 4A is a schematic diagram of a system for automated injection of scale inhibitor, according to an embodiment;

[0008] FIG. 4B is a schematic diagram of a system for automated injection of scale inhibitor, according to another embodiment;

[0009] FIG. 4C is a schematic diagram of a system for automated injection of scale inhibitor, according to yet another embodiment;Atty. Docket No.: 2024INV112484W001-64001

[0010] FIG. 5 is a schematic diagram of a system for automated injection of scale inhibitor, according to another embodiment;

[0011] FIG. 6 is a flow diagram of a method of sulfate scale risk assessment, according to an embodiment;

[0012] FIG. 7 is a flow diagram of a method of carbonate scale risk assessment, according to an embodiment;

[0013] FIG. 8 is a flow diagram of a method for sulfate scale treatment, according to an embodiment;

[0014] FIG. 9 is a flow diagram of a method for carbonate scale treatment, according to an embodiment; and

[0015] FIG. 10 is a flow diagram of an exemplary method for automated addition of scale inhibitors.DETAILED DESCRIPTION

[0016] It should be understood at the outset that although illustrative implementations of one or more embodiments are illustrated below, the disclosed systems and methods may be implemented using any number of techniques, whether currently known or not yet in existence. The description that follows includes example systems, methods, techniques, and program flows that embody aspects of the disclosure. However, it is understood that this disclosure may be practiced without these specific details. For brevity, well-known steps, protocols, structures, and techniques have not been shown in detail in order not to obfuscate the description. The disclosure should in no way be limited to the illustrative implementations, drawings, and techniques illustrated below, but may be modified within the scope of the appended claims along with their full scope of equivalents.

[0017] As used herein the terms “uphole”, “upwell”, “above”, “top”, and the like refer directionally in a wellbore towards the surface, while the terms “downhole”, “downwell”, “below”, “bottom”, and the like refer directionally in a wellbore towards the toe of the wellbore (e.g. the end of the wellbore distally away from the surface). Orientation terms “upstream” and “downstream” are defined relative to the direction of flow of fluid, for example relative to flow of well fluid in the well. As used herein, orientation terms “upstream,” “downstream,” “up,” and “down” are defined relative to the direction of flow of well fluid in the well casing. “Upstream” is directed counter to the direction of flow of well fluid, towards the source of well fluid (e.g., towards perforations in well casing through which hydrocarbons flow out of a subterranean formation and into the casing). “Downstream” is directed in the direction of flow of well fluid, away from the source of well fluid. “Down” is directedAtty. Docket No.: 2024INV112484W001-64001counter to the direction of flow of well fluid, towards the source of well fluid. “Up” is directed in the direction of flow of well fluid, away from the source of well fluid.

[0018] The term “real time” will be recognized by those skilled in the art to mean that events (e.g., a measurement action, a modeling action, a decision, and / or a control action or other response) in relation to a system or process of interest, to take place in substantially the same time frame, as appropriate to the context of the system or process of interest, instead of following a delay or depending upon other events whose timing(s) are not intended to conform to the timing requirements of the system or process. For example, in some contexts, “real time” may mean substantially contemporaneous, ignoring transmission latencies. In other contexts, “real time” may include allowance for latencies that represent less time than the time of the overall response of the well system being treated. For example, the term “real time” may mean during a pumping stage or interval. In other examples, the term “real time” may mean that a response occurs within 1 day, within 2 hours, within 1 hour, within 30 minutes, within 10 minutes, within 1 minute, within 30 seconds, within 10 seconds, within 1 second, within 0.1 seconds, within 0.01 seconds, or within 0.001 seconds. In some examples, a process takes place in “real time” where decisions to modify an operation are made based at least in part on measurements taken during the same operation. In some examples, “real time” may mean during a first portion of a pumping activity, where there are subsequent portions of the pumping activity that may benefit from adjustments made in the first portion.

[0019] In some embodiments, some or all calculations and / or operations are performed at a wellsite. At the wellsite may mean proximate a wellhead of one or more wells penetrating a subterranean formation. For example, at the wellsite, may mean within 1 mile, 0.5 miles, 0.25 miles, 200 yards, or 100 yards from the wellhead. For example, at the wellsite may mean on a pad of the wellsite. The wellsite may mean the area available for the positioning or location of equipment while carrying out a wellbore servicing operation. In some embodiments, the process is automated (e.g., there may be a control loop at the website with sensors and an injection point. Automated may mean without user input and / or a user approves suggestions generated autonomously by the system. The term “in-line” refers to in the line or flow path of a parameter being measured. In some embodiments, the system and method of the present disclosure does not include sending samples to the lab and / or analyzing samples at the lab.

[0020] Scale indexing (e.g., automated and / or real time) may be performed by an empirical model based on historical data using one or more water-property readings from a single sensor or an array of in-line water sensors as the input. Once the scale indexing is done, another model can generate theAtty. Docket No.: 2024INV112484W001-64001treatment design to avoid scale formation. This may involve a system that diagnoses scaling tendency of water coming to location in real time. The system may generate and optimize scale inhibitor treatment design in real time based on the water coming to location. This may also involve a method comprising the step of reading multiple parameters — such as salinity, pH, temperature, and pressure. These parameters may be obtained from wellsite application module skid data. The data may, for example, be obtained simultaneously, in-line, and in real time. These variables may be input into two empirical models: a first model and a second model.

[0021] The first model (e.g., lon-TDS model) may calculate the ion composition of the water using historical ion distribution of each specific geographic region / location, in which “TDS” refers to “Total Dissolved Solids.” The historical data may be obtained from testing done in a lab to obtain the concentrations of the individual ions from samples with known salinity and region. The historical data may be used to improve speed at which the ion composition may be calculated. The model may calculate the ion composition in the water — including the total ion concentration and / or individual concentration of particular ion species — without a direct measurement by referencing the historical data that contains samples from the same geographical area with similar TDS measurements (e.g., total TDS of all ions). The historical data may be updated with new data. The lon-TDS model may be constructed based on historical data of ion composition of the water. The model can be different from one geographic region to another (e.g., from one location to another). The input may be salinity, and the output may be ion composition at the given salinity. The model may be a machine learning model. The model may be periodically updated with additional data from the operation to help ensure that the model is up to date.

[0022] The second model (e.g., SI model) may use the in-line measurement results and the result from the first model to calculate the scaling index of different scale species, in which “SI” refers to “Scale Index” or “Scaling Index.” The scaling index refers to the potential for minerals to precipitate out of a fluid (e.g., aqueous solution) onto surfaces, such as of pipes, tubing, and wellbore, among others. The scale index may indicate the potential for scale formation, which occurs when mineral salts precipitate from water. It may be a unitless value calculated from water chemistry parameters (e.g. one or more of pH, temperature, TDS, calcium, and alkalinity). The index may range, for example, from -2.0 to +2.0, where negative values indicate undersaturation (no scale risk), zero denotes equilibrium, and positive values suggest supersaturation and a risk of scale deposition. Higher saturation levels of minerals may increase the index, indicating greater scale-forming potential. The output from the second model may be in any form that indicates risk of scaling. Alternatively, theAtty. Docket No.: 2024INV112484W001-64001scaling index may be on a scale of risk described in words rather than numbers (e.g., high risk, moderate risk, low risk). In some embodiments, additional parameters may be input and / or considered by the model, such as materials for which there is a concern of scaling. For example, materials of manifolds, piping, completion equipment, and / or formation rocks may be input and / or considered by the model.

[0023] The pressure input to the second model can also be provided from various pressure transducers in a frac spread, allowing for scale indices at different sections of the frac spread to be calculated. The SI model may be constructed based on an output of a third model (e.g., a historical SI model). The input to the second model may be salinity, pH, temperature, pressure, and / or ion composition. Other possible inputs to the SI model may be ORP, chemical reaction data, pressure data, contact time, pump rate, evaporation rate, and / or ionic composition. The models may allow for real-time and in-line calculations by avoiding the need for an iterative offline process. The output of the SI model (e.g., one or more numerical values that indicate tendency for scaling) can then be used to select one or more scale inhibitors and dosing in real-time. Additionally, new data may be captured into a cloud database and stored in remote server. The data may be used to train machine learning models. The scale indices output can then be used to autonomously determine the type and quantity of scale inhibitor to be added. The system can be applied to various applications, e.g., a producing well. For example, an initial dosing selection may be made, which may come from historical learning, and then the dosing may be fine-tuned (see FIG. 8). Addition of scale inhibitors can be controlled in real time (e g., during wellbore servicing (e.g., fracturing) operations, for example during pumping of a wellbore servicing (e.g., fracturing) fluid, or during the operation of a geothermal power plant) based on the type and quantity of scale inhibitor, as determined based on the output from the second model. For example, addition of scale inhibitors can be added according to the system and method of the present disclosure to water drive production, enhanced oil recovery (EOR) sweeps, and / or steambased production.

[0024] Referring FIGS. 1-2, a well system 105 (e.g., a fracturing spread or frac spread) is shown, comprising exemplary mixing equipment 140 and a frac pumping manifold 150. The frac pumping manifold 150 comprises one or fracturing pumps 100 and one or more manifolds 102. The mixing equipment 140 may be in fluid communication with pumps 100 via feed / suction lines of a manifold 102, which may be in fluid communication with a wellhead 104 via wellbore supply conduit 113 (e.g., frac iron). In the frac pumping manifold 150, low pressure suction lines feeding pumps 100 and high-pressure discharge lines from pumps 100 may be connected to the manifold 102. The pumps 100 mayAtty. Docket No.: 2024INV112484W001-64001pump fracturing fluid, which may include water, proppant, and / or other abrasive material. The proppant may be sand, for example. The manifold 102 may be a trailer system that transfers high-pressure fracturing fluid from the pumps 100 to a wellhead 104 and downhole to a perforated zone for fracturing.

[0025] The mixing equipment may include a water source 108, a scale inhibitor adder 136, a proppant supply 112, and a blender 106. The scale inhibitor adder 136 may further include one or more storage containers and pumps. The manifold 102 may transfer low-pressure fracturing fluid from the blender 106 via feed / suction lines to the pumps 100. The blender 106 may combine water with scale inhibitors and / or other chemicals from the scale inhibitor adder 136 and / or proppant from the proppant supply 112. At the blender 106, proppant may be metered from the proppant supply 112 into the mixture to become fracturing fluid that feeds into the pumps 100. There may be a sensor manifold 163 upstream of the blender 106. Additionally or alternatively, one or more sensor manifolds may be located at any other suitable position, such as in water storage tanks or pods, in proppant supply 112, inside the blender 106, inside the manifold 102, inside one or more of the pumps 100, inside scale inhibitor adder 136, at or near the wellhead 104 or injection point, and / or within the wellbore. The sensor manifold 163 may measure salinity (such as by TDS or conductivity), pH, temperature, and / or pressure, for example. In other examples, the sensor manifold 163 may measure ORP, chemical reactions, pressure, contact time, flowrate, pump rate, evaporation rate, and / or ionic composition. The sensor manifold 163 may contain a single sensor or multiple sensors. Scale inhibitor(s) may be dispensed based on the data from the sensor manifold 163. The scale inhibitor(s) may be stored in the scale inhibitor adder 136 and fed into the blender 106 (as shown in FIG. 1 A). Alternatively, the scale inhibitor may be added at any other suitable position, for example, upstream of the blender 106, at / in the blender 106, downstream of the blender 106, at a downhole injection location, and / or into produced water (as shown in FIG. IB).

[0026] Referring to FIG. 2, an exemplary well system 105 that may be used to introduce inj ection fluid and / or proppant 116 into fractures 101 is shown. The well system 105 of FIG. 2 can be used in combination with any of the frac spread embodiments of FIG. 1. The well system 105 may include the mixing equipment 140, the frac pumping manifold 150, and / or a wellbore supply conduit 113. The frac pumping manifold 150 may be fluidly coupled with the wellbore supply conduit 113 to wellhead 104 to pump a fracturing fluid, which may include proppant, into the wellbore 114.

[0027] The well system 105 may pump the fracturing fluid 117 into the subterranean formation 120 surrounding the wellbore 114. The wellbore 114 may include horizontal, vertical, slanted, curved,Atty. Docket No.: 2024INV112484W001-64001and / or other types of wellbore geometries and orientations, and the proppant may generally be applied to the subterranean formation 120 surrounding any portion of the wellbore 114, including the fractures 101. The wellbore 114 may include the casing 103 which may be cemented (or otherwise secured) to the wall of the wellbore 114 by a cement sheath 122. Perforations 123 may allow communication between the wellbore 114 and the subterranean formation 120. The perforations 123 may penetrate the casing 103 and the cement sheath 122, allowing communication between the interior of the casing 103 and the fractures 101. A plug 124 may be disposed in wellbore 114 below the perforations 123.

[0028] A perforated interval of interest (e.g., an interval of the wellbore 114 including the perforations 123) may be isolated with the plug 124. A pad or pre-pad fluid (e.g., a clean fluid such as slick water) may be pumped into the subterranean formation 120 at a pumping rate and pressure at or above the fracture gradient to create and maintain at least one fracture 101 in subterranean formation 120. Then, proppant 116 may be mixed with an aqueous-based fluid via mixing equipment 140, thereby forming a fracturing fluid (e.g., a dirty fluid). The fracturing fluid may be pumped via the frac pumping manifold 150 and wellbore supply conduit 113 to the wellhead 104 and down the interior of the casing 103 and into subterranean formation 120 at or above a fracture gradient of the subterranean formation 120. Pumping the fracturing fluid at or above the fracture gradient of the subterranean formation 120 may create (or enhance) at least one fracture (e.g., fractures 101) extending from the perforations 123 into the subterranean formation 120, wherein the proppant 116 is placed into the fractures and remains therein to prop open the fractures upon reduction of pumping pressure upon completion of the fracturing stage / job.

[0029] Referring to FIG. 3, the system and method of the present disclosure may also be applied to wells for geothermal applications. For example, fractures may be formed in the subterranean formation 120 to bring horizontal portions of two wellbores 114 into fluid communication. One of the wellbores 114 may be an injection wellbore and the other may be a production wellbore. Although FIG. 3 illustrates fracturing of a geothermal well, the system and method described herein can also be applied to a producing geothermal well (e.g., a geothermal well that is currently being used to produce electric power). The system and method may continuously monitor salinity of injection or produced water and adjust scale inhibitor accordingly to prevent or mitigate scale buildup in the geothermal well.

[0030] Referring to FIGS. 1-2 and 4-5, a system 105 for inhibiting scale in a hydraulic fracturing operation comprises a sensor. Although hydraulic fracturing is used as an example, the system 105 can be used in any wellbore servicing operation such as drilling, fracking, cementing, and producing.Atty. Docket No.: 2024INV112484W001-64001The system 105 can also be used in wellbore servicing operations for geothermal power plants. Tn an embodiment, the sensor may be a salinity sensor, which may be part of sensor manifold 163, and configured to measure salinity data of fracturing fluid for the hydraulic fracturing operation (e.g., fracturing fluid pumped into the wellhead 104 by the pumps 100). The system 105 may further include a controller 170 configured to: receive in real time the data (e.g., salinity data, pH data, pressure data, temperature data, flow rate data, TDS, conductivity, etc.) from / measured by the sensor manifold 163 (e.g., by a wired or wireless signal); estimate in real time, using a first model 181, ion composition (e.g., concentrations of individual ions) in the fracturing fluid based on the data measured from the sensor (e.g., salinity data and a geographical region (e.g., location, GPS coordinates, area, town, county, state, etc.)); estimate in real time, using a second model 182 and data from sensor manifold 163 (e.g., one or more of pH, pressure, and temperature), scaling index of scale species in the fracturing fluid based on the estimated ion composition (e.g., the scaling index being a quantity indicating expected severities of scaling of the respective scale species); determine / adjust a treatment parameter (e.g., type, quantity, composition, etc.) of a scale inhibitor based on the estimated scaling index of the scale species; and control addition of the scale inhibitor (e.g., via a control signal from the controller 170 to the scale inhibitor adder 136) to the fracturing fluid according to the treatment parameter. Adjusting the treatment parameter may include adjusting a selection of a single scale inhibitor, adjusting a selection of a plurality of scale inhibitors, altering a composition of a single scale inhibitor, altering a composition of a plurality of scale inhibitors, altering a dosage of a single scale inhibitor, and / or altering dosages of a plurality of scale inhibitors.

[0031] Referring to FIGS. 4-5, the system 105 may further include a turbidity meter 166. In an embodiment, turbidity meter 166 may be disposed downstream of a location at which the scale inhibitor(s) are added to the fracturing fluid. The turbidity meter 166 may measure turbidity data of the fracturing fluid and / or produced fluid. The controller 170 may adjust one or more treatment parameters based on the turbidity data. For example, in response to the turbidity meter 166 sensing a turbidity level above a threshold, the controller 170 may increase the amount of scale inhibitor being added. The controller 170 may weigh the turbidity measurements against the estimated scale risk (e.g., scale index) when determining how much to increase the amount of scale inhibitor. In some embodiments, in addition to or instead of the turbidity meter, there may be a pipe (e.g., a small diameter pipe) and a pressure gauge that measures pressure inside the pipe. Greater pressure inside the pipe may indicate the presence of scale buildup in the pipe. The controller 170 may adjust an amount of scale inhibitor based on the pressure inside the pipe. For example, the controller 170 mayAtty. Docket No.: 2024INV112484W001-64001increase the amount of scale inhibitor in response to the pressure inside the pipe (as measured by the pressure sensor) exceeding a threshold.

[0032] The sensor manifold 163 may be configured to measure pH data, temperature data, and / or pressure data. The controller 170 may be configured to receive sensor data from the sensor manifold 163, including pH data, the temperature data, and the pressure data, and estimate (e.g., in real time) the ion composition in the fracturing fluid based on the salinity data, the region of the hydraulic fracturing operation, the pH data, the temperature data, and / or the pressure data. The ion composition can include the total ion concentration and / or individual concentration of particular ion species. The first model 181 may be based on historical data comprising historical salinity, historical ion composition, and historical geographical region of other hydraulic fracturing operations. For example, the first model 181 may be created based on or trained by data tagged to geographical locations. The data may include salinity data (e.g., TDS or conductivity) and ion composition (e.g., concentrations of individual ions) corresponding to the salinity data. The first model 181 may be used to estimate individual ion concentrations based on the geographical location and the salinity data. The controller 170 may be configured to estimate in real time the ion composition in the fracturing fluid by matching the geographical region of the hydraulic fracturing operation with a geographical region from the historical data. The first model 181 may include a machine learning model (e.g., a neural network) that is trained on the historical data. The model may be, for example, a generalized linear model, a random forest, a decision tree, or an XGBoost. For example, the historical data set can include information about inhibitor categories such as polyacrylic or polymaleic salts or their derivatives, sulfonated co- or ter- polymers, diethylenetriamine penta(methylenephosphonic salts - delta, bis(hexamethylene)triamine penta(methylenephosphonic salts) - BHMT, and / or polyamino polyether methylenephosphonic salts. The estimated ion composition may include respective total dissolved solid quantities of individual ions in the fracturing fluid. The individual ions may include, for example, monatomic cations (e.g., calcium Ca2+, magnesium Mg2+, barium Ba2+, strontium Sr2+, iron Fe2+), monatomic anions (e.g., chloride CT), polyatomic ions (e.g., carbonate CCh2' , bicarbonate HCCh', and / or sulfate SO42), and other types of ions. Inputs to the first model may be, for example, pH, ORP, temperature, chemical reactions, pressure, contact time, flowrate pump rate, evaporation, and / or ion compositions. In some embodiments, the output of the first model includes numerical quantities for the ion composition of the fluid.

[0033] The second model 182 may generate scaling indices in real time. To enable the real-time generation of scale indices by the second model 182, the third model 183 may be generated fromAtty. Docket No.: 2024INV112484W001-64001empirical equation of scale indices based on each scale solubility coefficient. The empirical equation may be a set of implicit equations and may be simplified by fitting a linear-explicit model on the precalculated equation on a large range of values for salinity (TDS), ion composition, pH, pressure, and temperature, for example. This linear-explicit model may be used as the second model 182. Real-time generation of scale indices then can be performed by using the output of the first model 181 (e.g., realtime ion composition) and sensor data from sensor manifold 163 (e.g., total salinity, pH, pressure, and temperature) as the input of the second model 182. Calculation using the first model 181 and second model 182 may be performed by controller 170. This calculation may then estimate the scaling index of the scale species based on the scaling indices and / or the ion composition (e.g., mass per volume of the scale-forming constituents).

[0034] The second model 182 may be based on a third model 183, and the third model 183 may be based on the historical data (e.g., the same historical data used by the first model 181). The third model 183 use the historical data to pre-generate outputs that the second model 182 can use to achieve real-time output of scaling index, and the first model 181 may use the historical data to estimate the ion composition. The third model 183 may be a historical scale index model (e.g., from lab samples). The third model 183 may generate a profile of scale indices (e.g., concentrations of individual ions) for each geographic region based on a large range of variables (e.g., salinity, pH, temperature, pressure). Each geographic region may have a homogeneous trend. The output of the third model 183 may contain an interpolation and / or an extrapolation model of the historical data. The new interpolation and / or extrapolation model based on the third model 183 that is generated from historical data can be used as the second model.

[0035] In some embodiments, the first model 181 may be a model component; the second model 182 may be a second model component; and the third model 183 may be a third model component. The model components can be combined into a single model or in separate models. The model components may be combined in the same program / code or separate programs / codes. The model components may operate on the same or different computers.

[0036] Real-time generation of scale indices then can be performed by using the output of the first model 181 (real-time ion composition) and sensor data from sensor manifold 163 (total salinity, pH, pressure, and temperature) as the input of the second model 182. Calculation of the first model 181 and second model 182 may happen in controller 170. This calculation may then estimate the scaling index of the scale species based on the scaling indices and / or the mass per volume of the scale-forming constituents.Atty. Docket No.: 2024INV112484W001-64001

[0037] The scaling species presented in the output of the second model 182 may include sulfate and carbonate. The scale-forming constituents output by the second model 182 may include calcite, barite, gypsum, celestite, anhydrate, and iron carbonate (FeCCh). The output of the second model 182 may be int the form of a Langelier Saturation Index or a Ryznar Index, for example. The adjusting of the treatment parameter (e.g., selection and dosage of one or more scale inhibitors) may be done in real time. The controller 170 may control the addition of the scale inhibitors by controlling in real time a scale inhibitor adder 136 (e.g., an injector and / or a chemical storage) to inject the scale inhibitors into a blender 106 of the hydraulic fracturing operation (see FIG. 1). As shown in FIG. 5, outputs from the second model 182 may include calcite PTB, FeCCh PTB, gypsum PTB, anhydrate PTB, barite PTB, celestite PTB, calcite SI, FeCCh SI, gypsum SI, anhydrate SI, barite SI, and / or celestite PTB.

[0038] Referring to FIG. 6, the controller may estimate the scaling index of sulfate using the second model. Based on inputs of barite scale index (SI), CaSC>4 SI, celestite SI, barite mass of precipitation in pounds per thousand barrels of water produced (PTB), CaSC>4 PTB, and celestite PTB, the controller may estimate the scaling index for sulfate, for example, using a neural network or an empirical model. The SI may be a unitless quantity that indicates likeliness for scaling. In response to determining that the SI of each individual scale type is less than a first threshold (e g., 0.3) or the total PTB is less than a total PTB threshold (e.g., 20), the controller may determine that there is no scaling risk of sulfate. In response to determining that the SI is between the first threshold and a third threshold (e.g., 0.3-1.0,) the controller may determine that there is a low scaling risk of sulfate. In response to determining that the SI is between the third threshold and a fourth threshold (e.g., 1.0-2.0), the controller may determine that there is a moderate scaling risk of sulfate. In response to determining that the SI is greater than the fourth threshold (e.g., 2.0) and the PTB is greater than a fifth threshold (e.g., 50), the controller may determine that there is a high scaling risk of sulfate. In some embodiments, the risk of sulfate is quantified (e.g., given a numerical value for scaling index) rather than being in terms of low, medium, and high.

[0039] Referring to FIG. 7, the controller may estimate the scaling index of carbonate using the second model. In this embodiment, the decision tree represents the second model and shows the logical steps the controller may implement to output whether the carbonate scaling risk is non-existent, low, moderate, or high. Based on inputs of concentrations of Calcite SI, FeCCh SI, CaCCh PTB, and FeCCh PTB, the controller may estimate the scaling index for carbonate. For example, in response to determining that the SI is less than a first threshold (e.g., 0.5) or the total PTB is less than a second threshold (e.g., 20), the controller may determine that there is no scaling risk of carbonate. In responseAtty. Docket No.: 2024INV112484W001-64001to determining that the SI is between the first threshold and a third threshold (e.g., 0.5-1.0), the controller may determine that there is low scaling risk of carbonate. In response to determining that SI is between the third threshold and a fourth threshold (e.g., 1.0-1.5), the controller may determine that there is moderate scaling risk of carbonate. In response to determining that the SI is greater than the fourth threshold (e.g., 1.5) and the total PTB is greater than a fifth threshold (e g., 100), the controller may determine that there is high scaling risk of carbonate. In some embodiments, the risk of carbonate is quantified (e.g., rated on a numerical scale) rather than being in terms of low, moderate, and high.

[0040] Referring to FIG. 8, the controller 170 may set and adjust a treatment parameter of scale inhibitor(s) based on the estimated scaling index of the scale species. Inputs to setting and adjusting the treatment parameter(s) (e.g., scale inhibitor selection and dosing) to prevent sulfate scale risk may include sulfate risk (e.g., risk of sulfates forming), TDS, Fe concentration, temperature, and / or historical case info. The controller may compare Fe concentration to a first threshold (e.g., 50 ppm), compare TDS to a second threshold (e.g., 150k ppm), and compare temperature to a third threshold (e.g., 250 F), and select a scale inhibitor, a scale inhibitor combination, or a scale inhibitor list of preferences (e.g., from SI to S5) based on the result. In response to determining that Fe concentration is greater than a first threshold, TDS is greater than a second threshold, and temperature is greater than a third threshold, the controller may select an inhibitor S2. In response to determining that Fe concentration is greater than the first threshold, TDS is greater than the second threshold, and temperature is less than the third threshold, the controller may select the inhibitor S2, S3 (order of preference). In response to determining Fe concentration is greater than the first threshold, TDS is less than the second threshold, and temperature is greater than the third threshold, the controller may select the inhibitor S2, SI, S4 (order of preference). In response to determining that Fe concentration is greater than the first threshold, TDS is less than the second threshold, and temperature is less than the third threshold, the controller may select the inhibitor SI, S3 (order of preference). In response to determining that Fe concentration is less than the first threshold, TDS is greater than the second threshold, and temperature is greater than the third threshold, the controller may select S2, SI (order of preference). In response to determining that Fe concentration is less than the first threshold, TDS is greater than the second threshold, and temperature is greater than the third threshold, the controller may select the inhibitors S 1, S3 (order of preference). In response to determining that Fe concentration is less than the first threshold, TDS is greater than the second threshold, and temperature is less than the third threshold, the controller may select SI, S3 (order of preference). In response to determiningAtty. Docket No.: 2024INV112484W001-64001that Fe is less than the first threshold, TDS is less than the second threshold, and temperature is greater than the third threshold, the controller may select S2, SI, S4 (order of preference). In response to determining that Fe is less than the first threshold, TDS is less than the second threshold, and temperature is less than the third threshold, the controller may select SI, S3 (order of preference). The order of preference may be the order of estimated efficacy in fighting each individual scale case. The user may select one scale inhibitor if there is more than one suggested scale inhibitor, for example, based on availability.

[0041] In some embodiments, SI is Polyacrylic or Polymaleic salts or their derivatives, S2 is Sulfonated co- or ter-polymers, S3 is Diethylenetriamine Penta(methylenephosphonic salts) - Deta, S4 is Bis(hexamethylene)triamine Penta(methylenephosphonic salts) - BHMT, and / or S5 is Polyamino Polyether Methylenephosphonic salts.

[0042] The controller 170 may set the initial treatment dosage based on the scaling index. In response to the scaling index being high, the controller may set the initial treatment dosage to greater than a first value (e.g., above 100 ppm). In response to the scaling index being medium (middle), the controller may set the initial treatment dosage to between a second value (e.g., 50 ppm) and a third value (e.g., 100 ppm). In response to the scaling index being low, the controller may set that initial treatment dosage to below a fourth value (e.g., below 50 ppm). Initial treatment dosage may be compared to a historical case. Each geographic region or well may have its own “a” multiplier (alpha multiplier), which is a multiplier applied to the initial treatment dosage. To become a final treatment recommendation, the alpha multiplier may be constantly corrected based on field data that indicates whether the treatment is successful or not. Stated another way, the selection of the initial treatment dosage may be based on empirical data and estimates from empirical data. The final treatment dosage may be calculated by multiplying the initial treatment dosage by the alpha multiplier, which may be region-dependent, or in some case may be well -dependent. The loop may happen if the final dosage was determined to be insufficient. The determination of insufficiency may be based on observation at the field, e.g., observing scale still forming on location. Then the alpha multiplier may be adjusted again (e.g., increased) until scale is not observed. Another way of observing scale formation can be from the turbidity sensor, where higher turbidity shows that scale is still forming. Another way of observing scale formation may be from pressure drop. Higher pressure drops may signal severe scale formation as the pipe wall gets thicker, which limits the flow. Sensors that can be used for detecting actual deposition could include, for example, an ultrasonic sensor, a turbidity meter, a differential pressure sensor, an ultrasonic sensor, and / or a conductivity probe. For example, in response to sensingAtty. Docket No.: 2024INV112484W001-64001increased turbidity by the turbidity meter, the controller may determine that scale crystal is forming in the water. In response to the differential pressure sensor detecting increased pressure drop, the controller may determine that the pipe diameter decreases due to scale deposition. In response to ultrasonic sensor measurements, the controller may determine that there is scale. In response to a conductivity probe detecting a reduction in conductivity, the controller may determine that there is a reduction in scale-forming ions that are dissolved in the water.

[0043] Referring to FIG. 9, the method for setting and adjusting treatment composition and dosage for preventing carbonate scale may be analogous to that for preventing sulfate scale, but at least some of the inhibitor selections may be different. If there are mixed scales (e.g., of carbonate and sulfate), requirements for sulfate treatment may be generally followed unless there is additional information such as failure or special needs that indicates a combination of both carbonate and sulfate treatment is necessary.

[0044] Any of the operations disclosed herein as being performed by the controller may be performed by one or more processors. The processors need not be at the same location. For example, some or all of the operations may take place in the cloud. Referring to FIG. 10, a method 1000 for inhibiting scale in a hydraulic fracturing operation may include the step 1010 of measuring data of fracturing fluid for the hydraulic fracturing operation, wherein the data comprises any combination of any two or more of salinity data, pH data, pressure data, temperature data, or flowrate data; the step 1020 of using a first model to estimate, in real time, ion composition in the fracturing fluid, based on the measured data and one or both of a geographical location of the hydraulic fracturing operation or a geographical location of a fluid source of the hydraulic fracturing operation; the step 1030 of using a second model to estimate, in real time, scaling index of a scale species in the fracturing fluid based on the estimated ion composition; the step 1040 of determining a treatment parameter of one or more scale inhibitors based on the estimated scaling index of the scale species; and the step 1050 of controlling addition of the one or more scale inhibitors to the fracturing fluid according to the treatment parameter. The method 1000 may further include measuring turbidity data of the fracturing fluid at a location downstream of a location at which the scale inhibitors are added to the fracturing fluid, and adjusting the treatment composition based on the turbidity data. The first model may be based on historical data, and the second model may be based on outputs from a third model, which may be based on the historical data. In the first model, the historical data may be used to generate an output of ion composition, and in the third model, the historical data may be used to pre-generate outputsAtty. Docket No.: 2024INV112484W001-64001enable the second model to output scaling index in real-time. Any of these method steps may be performed by a controller and / or one or more processors.

[0045] The system and method of the present disclosure may allow for analysis of scaling propensity to be performed in-line and in real time. The system and method may be applied to frac process, production, and / or other applications sensitive to scale deposition such as geothermal wells. There may be a cloud-based database and a trained, integrated machine learning model, thus enabling instantaneous treatment decisions to be reliably generated.

[0046] The system and method of the present disclosure may enable more accurate and more responsive scale inhibitor treatment compared to the conventional art. By allowing individual ion compositions to be estimated without the need for lab testing, scaling index of scale species can be more reliably assessed, which enables selection and implementation of an effective treatment of scale inhibitor. The assessment of the scaling index of the scale species may be continuously updated as real-time data continues to stream in from the sensor and is processed according to the method of the present disclosure, thus enabling effective and timely adaptation to changing conditions. The more effective treatment of scale inhibitor may reduce downhole scaling (e.g., scaling in the wellbore, scaling in the reservoir, or both). This can improve flow capacity as compared with the related art.

[0047] The following are non-limiting, specific embodiments in accordance with the present disclosure:

[0048] In a first embodiment, a system for inhibiting scale in a hydraulic fracturing operation, comprises a sensor system configured to measure salinity, pH, pressure, and temperature data of fracturing fluid for the hydraulic fracturing operation; and a controller configured to: receive in real time the salinity data, the pH data, the pressure data, and the temperature data from the sensor system; estimate in real time, using a first model, ion composition in the fracturing fluid based on the salinity data, the pH data, the pressure data, the temperature data, and a geographical location of the hydraulic fracturing operation; estimate in real time, using a second model, scaling risk of a scale species in the fracturing fluid based on the estimated ion composition; adjust a treatment parameter of a scale inhibitor based on the estimated scaling risk of the scale species; and control addition of the scale inhibitor to the fracturing fluid according to the treatment parameter.

[0049] A second embodiment can include the system of the first embodiment, further comprising a device that measures the ion composition of the fracturing fluid in-line and in real-time without the need of the first model in the first embodiment. This device may be an electro-chemical -based sensor,Atty. Docket No.: 2024INV112484W001-64001chromatography-based sensor / device, spectrometry -based sensor / device, etc. This device may be part of sensor manifold 163.

[0050] A third embodiment can include the system of the first or second embodiments, further comprising a turbidity meter disposed downstream of a location at which the scale inhibitor is added to the fracturing fluid, wherein the turbidity meter is configured to measure turbidity data of the fracturing fluid, and wherein the controller is further configured to adjust the treatment parameter based on the turbidity data.

[0051] A fourth embodiment can include the system of any of the first through third embodiments, wherein the sensor system comprises (e.g., is part of a sensor manifold) configured to measure pH data, temperature data, and pressure data, and the controller is further configured to receive the pH data, the temperature data, and the pressure data, and estimate in real time the ion composition in the fracturing fluid based on the salinity data, the location of the hydraulic fracturing operation, the pH data, the temperature data, and the pressure data.

[0052] A fifth embodiment can include the system of any of the first through fourth embodiments, wherein the first model is based on historical data comprising historical salinity, historical ion composition, and historical geographical location of other hydraulic fracturing operations.

[0053] A sixth embodiment can include the system of any of the first through fifth embodiments, wherein the controller is further configured to estimate in real time the ion composition in the fracturing fluid by matching the geographical location of the hydraulic fracturing operation with a geographical location from the historical data.

[0054] A seventh embodiment can include the system of any of the first through sixth embodiments, wherein the first model comprises a neural network that is trained on the historical data.

[0055] An eighth embodiment can include the system of any of the first through seventh embodiments, wherein the estimated ion composition comprises respective total dissolved solid quantities of individual ions in the fracturing fluid.

[0056] A ninth embodiment can include the system of any of the first through eighth embodiments, wherein the ions comprise any combination of any two or more of monatomic cations (e.g., calcium Ca2+, magnesium Mg2+, barium Ba2+, strontium Sr2+, iron Fe2+), monatomic anions (e.g., chloride Cl'), polyatomic ions (e.g., carbonate CCh2' , bicarbonate HCCh', and / or sulfate SC>42'), and other types of ionsd.Atty. Docket No.: 2024INV112484W001-64001

[0057] A tenth embodiment can include the system of any of the first through ninth embodiments, wherein the second model is based on a third model, which is based on solubility coefficients empirical model.

[0058] An eleventh embodiment can include the system of any of the first through tenth embodiments, wherein the second model is based on a third model, which is based on the historical data.

[0059] A twelfth embodiment can include the system of any of the first through eleventh embodiments, wherein the third model comprises a historical scale index model.

[0060] A thirteenth embodiment can include the system of any of the first through twelfth embodiments, wherein the controller is further configured to estimate in real time the scaling risk of the scale species in the fracturing fluid by matching the estimated ion composition with an ion composition of the historical scale index model to estimate scaling indices or mass per volume of scale-forming constituents, and estimating the scaling risk of the scale species based on the scaling indices or the mass per volume of the scale-forming constituents.

[0061] A fourteenth embodiment can include the system of any of the first through thirteenth embodiments, wherein the second model comprises a neural network that is trained on an output of the historical scale index model.

[0062] A fifteenth embodiment can include the system of any of the first through fourteenth embodiments, wherein the scale species comprise sulfate or carbonate.

[0063] A sixteenth embodiment can include the system of any of the first through fifteenth embodiments, wherein the scale-forming constituents comprise any combination of any two or more of calcite, barite, gypsum, anhydrate, celestite, and FeCCh.

[0064] A seventeenth embodiment can include the system of any of the first through sixteenth embodiments, wherein the adjustment of the treatment parameter comprises any one or any combination of any two or more of adjusting a selection of a single scale inhibitor, adjusting a selection of a plurality of scale inhibitors, altering a composition of a single scale inhibitor, altering a composition of a plurality of scale inhibitors, altering a dosage of a single scale inhibitor, and altering dosages of a plurality of scale inhibitors.

[0065] An eighteenth embodiment can include the system of any of the first through seventeenth embodiments, wherein the controller is further configured to control the addition of the scale inhibitor by controlling in real time a chemical storage to inj ect the scale inhibitor into a blender of the hydraulic fracturing operation.Atty. Docket No.: 2024INV112484W001-64001

[0066] In a nineteenth embodiment, a processor-implemented method for inhibiting scale in a hydraulic fracturing operation, comprising: measuring salinity data, pH data, pressure data, and temperature data of fracturing fluid for the hydraulic fracturing operation; estimating in real time, using a first model ion composition in the fracturing fluid based on the salinity data, the pH data, the pressure data, and the temperature data and a geographical location of the hydraulic fracturing operation; estimating in real time, using a second model, scaling risk of a scale species in the fracturing fluid based on the estimated ion composition; adjusting a treatment parameter of a scale inhibitor based on the estimated scaling risk of the scale species; and controlling addition of the scale inhibitor to the fracturing fluid according to the treatment parameter.

[0067] A twentieth embodiment can include the method of the nineteenth embodiment, further comprising measuring turbidity data of the fracturing fluid at a location downstream of a location at which the scale inhibitor is added to the fracturing fluid, and adjusting the treatment parameter based on the turbidity data.

[0068] A twenty-first embodiment can include the method of any of the nineteenth or twentieth embodiments, wherein the first model is based on historical data, and the second model is based on a third model, which is based on the historical data.

[0069] In a twenty-second embodiment, a non-transitory computer-readable medium storing instructions that, when executed by a processor, cause the processor to perform the method of any of the nineteenth through twenty -first embodiments.

[0070] In a twenty-third embodiment, a system for inhibiting scale in a hydraulic fracturing operation comprises: a sensor system configured to measure data, wherein the data comprises salinity data, pH data, pressure data, temperature data of fracturing fluid for the hydraulic fracturing operation, flow rate data of the fracturing fluid for the hydraulic fracturing operation, or any combination thereof; and a controller configured to: receive, in real time, the data from the sensor system; estimate, in real time, using a first model, ion composition in the fracturing fluid, based on the data and a geographical location of the hydraulic fracturing operation, a geographical location of a fluid source of the hydraulic fracturing operation, or both; estimate, in real time, using a second model, scaling risk of a scale species in the fracturing fluid based on the estimated ion composition; adjust a treatment parameter of one or more scale inhibitors based on the estimated scaling risk of the scale species; and control addition of the one or more scale inhibitors to the fracturing fluid according to the treatment parameter.

[0071] A twenty-fourth embodiment can include the system of the twenty-third embodiment, further comprising a turbidity meter disposed downstream of a location at which the one or more scaleAtty. Docket No.: 2024INV112484W001-64001inhibitors is added to the fracturing fluid, wherein the turbidity meter is configured to measure turbidity data of the fracturing fluid, and wherein the controller is further configured to adjust the treatment parameter based on the turbidity data.

[0072] A twenty-fifth embodiment can include the system of the twenty-third or twenty-fourth embodiment, wherein the controller is further configured to estimate in real time the ion composition in the fracturing fluid based on the data, the geographical location of the hydraulic fracturing operation, and the geographical location of the fluid source of the hydraulic fracturing operation.

[0073] A twenty-sixth embodiment can include the system of any of the twenty-third through twenty-fifth embodiments, wherein the first model is based on historical data comprising historical salinity, historical ion composition, and historical geographical locations of other hydraulic fracturing operations, historical geographical locations of a fluid source of the other hydraulic fracturing operations, or both.

[0074] A twenty-seventh embodiment can include the system of any of the twenty-third through twenty-sixth embodiment, wherein the controller is further configured to estimate in real time the ion composition in the fracturing fluid by matching the geographical location of the hydraulic fracturing operation with a geographical location from the historical data.

[0075] A twenty-eighth embodiment can include the system of any of the twenty-third through twenty-seventh embodiments, wherein the first model comprises a neural network that is trained on the historical data.

[0076] A twenty-ninth embodiment can include the system of any of the twenty-third through twenty-eighth embodiments, wherein the estimated ion composition comprises respective total dissolved solid quantities of individual ions in the fracturing fluid.

[0077] A thirtieth embodiment can include the system of any of the twenty-third through twentyninth embodiments, wherein the ions comprise Ca2+, Mg2+, Ba2+, Sr2, Fe2+, Cl', I ICOv, SC>42', ions that cause formation of insoluble inorganic minerals through the system, or any combination thereof.

[0078] A thirty-first embodiment can include the system of any of the twenty-third through thirtieth embodiments, wherein the second model is based on a third model, which is based on a solubility coefficients empirical model.

[0079] A thirty-second embodiment can include the system of any of the twenty-third through thirty-first embodiments, wherein the second model is based on a third model, which is based on the historical data.Atty. Docket No.: 2024INV112484W001-64001

[0080] A thirty -third embodiment can include the system of any of the twenty -third through thirty-second embodiments, wherein the third model comprises a historical scale index model.

[0081] A thirty-fourth embodiment can include the system of any of the twenty-third through thirty-third embodiments, wherein the controller is further configured to estimate in real time the scaling risk of the scale species in the fracturing fluid by matching the estimated ion composition with an ion composition of the historical scale index model to estimate scaling indices or mass per volume of scale-forming constituents, and estimate the scaling risk of the scale species based on the scaling indices or the mass per volume of the scale-forming constituents.

[0082] A thirty -fifth embodiment can include the system of any of the twenty -third through thirtyfourth embodiments, wherein the second model comprises a neural network that is trained on an output of the historical scale index model.

[0083] A thirty-sixth embodiment can include the system of any of the twenty -third through thirtyfifth embodiments, wherein the scale species comprise sulfate or carbonate.

[0084] A thirty-seventh embodiment can include the system of any of the twenty-third through thirty-sixth embodiments, wherein the scale-forming constituents comprise calcite, barite, gypsum, anhydrate, celestite, FeCCh, or any combination thereof.

[0085] A thirty-eighth embodiment can include the system of any of the twenty-third through thirty-seventh embodiments, wherein the adjustment of the treatment parameter comprises any one or any combination of any two or more of adjusting a selection of a single scale inhibitor, adjusting a selection of a plurality of scale inhibitors, altering a composition of a single scale inhibitor, altering a composition of a plurality of scale inhibitors, altering a dosage of a single scale inhibitor, altering dosages of a plurality of scale inhibitors, and altering downhole scale inhibition injection.

[0086] A thirty-ninth embodiment can include the system of any of the twenty-third through thirty-eighth embodiments, wherein the controller is further configured to control the addition of the one or more scale inhibitors by controlling in real time a chemical storage to inject the scale inhibitor into a blender of the hydraulic fracturing operation.

[0087] In a fortieth embodiment, a processor-implemented method for inhibiting scale in a hydraulic fracturing operation comprises: measuring data, wherein the data comprises salinity data, pH data, pressure data, temperature data of fracturing fluid for the hydraulic fracturing operation, flow rate data of the fracturing fluid for the hydraulic fracturing operation, or any combination thereof; estimating, in real time, using a first model, ion composition in the fracturing fluid, based on the data and a geographical location of the hydraulic fracturing operation, a geographical location of a fluidAtty. Docket No.: 2024INV112484W001-64001source of the hydraulic fracturing operation, or both; estimating, in real time, using a second model, scaling risk of a scale species in the fracturing fluid based on the estimated ion composition; adjusting a treatment parameter of one or more scale inhibitors based on the estimated scaling risk of the scale species; and controlling addition of the one or more scale inhibitors to the fracturing fluid according to the treatment parameter.

[0088] A forty-first embodiment can include the method of the fortieth embodiment, further comprising measuring turbidity data of the fracturing fluid at a location downstream of a location at which the one or more scale inhibitors is added to the fracturing fluid, and adjusting the treatment parameter based on the turbidity data.

[0089] A forty-second embodiment can include the method of the fortieth or forty-first embodiments, wherein the first model is based on historical data, and the second model is based on a third model, which is based on the historical data.

[0090] A forty-third embodiment can include the method of any of the fortieth through forty-second embodiments, wherein the adjusting of the treatment parameter comprises any one or any combination of any two or more of adjusting a selection of a single scale inhibitor, adjusting a selection of a plurality of scale inhibitors, altering a composition of a single scale inhibitor, altering a composition of a plurality of scale inhibitors, altering a dosage of a single scale inhibitor, altering dosages of a plurality of scale inhibitors, and altering downhole scale inhibition injection.

[0091] A forty-fourth embodiment can include the method of any of the fortieth through forty-third embodiments, wherein the input and / or output of the first and / or second and / or third model is pH, ORP, temperature, chemical reaction, pressure, contact time, pump rate, evaporation, and / or ionic composition.

[0092] A forty -fifth embodiment can include the method of any of the fortieth through forty -fourth embodiments, wherein the method prevents or mitigates downhole scaling (e.g., scaling within the wellbore and / or the reservoir).

[0093] In a forty-sixth embodiment, a system for inhibiting scale in a hydraulic fracturing operation comprises: a sensor system configured to measure data, wherein the data comprises salinity data, pH data, pressure data, temperature data of fracturing fluid for the hydraulic fracturing operation, flow rate data of the fracturing fluid for the hydraulic fracturing operation, or any combination thereof; and a controller configured to: receive, in real time, the data measured by the sensor system; use a first model to estimate, in real time, (e.g., autonomously / automatically) ion composition in the fracturing fluid, based on the data measured by the sensor system and one or both of a geographical location ofAtty. Docket No.: 2024INV112484W001-64001the hydraulic fracturing operation or a geographical location of a fluid source of the hydraulic fracturing operation; use a second model to estimate, in real time, (e.g., autonomously / automatically) a scaling index of a scale species in the fracturing fluid based on the estimated ion composition; determine a treatment parameter of one or more scale inhibitors based on the estimated scaling index of the scale species; and control (e.g., autonomously / automatically) addition of the one or more scale inhibitors to the fracturing fluid according to the treatment parameter.

[0094] A forty-seventh embodiment can include the system of the forty-sixth embodiment, further comprising a turbidity meter disposed downstream of a location at which the one or more scale inhibitors is added to the fracturing fluid, wherein the turbidity meter is configured to measure turbidity data of the fracturing fluid, and wherein the controller is further configured to adjust the treatment parameter based on the turbidity data (e.g., autonomously / automatically).

[0095] A forty-eighth embodiment can include the system of any of the forty-sixth through fortyseventh embodiments, wherein the scale inhibitors comprise polyacrylic or polymaleic salts or their derivatives, sulfonated co- or ter-polymers, diethylenetriamine penta(methylenephosphonic salts), bis(hexamethylene)triamine penta(methylenephosphonic salts), polyamino polyether methylenephosphonic salts, or combinations thereof.

[0096] A forty -ninth embodiment can include the system of any of the forty-sixth through fortyeighth embodiments, wherein the first model is based on historical data comprising historical salinity, historical ion composition and one or both of historical geographical locations of other hydraulic fracturing operations or historical geographical locations of a fluid source of the other hydraulic fracturing operations.

[0097] A fiftieth embodiment can include the system of any of the forty-sixth through forty-ninth embodiments, wherein the controller is further configured to estimate in real time the ion composition in the fracturing fluid by matching the geographical location of the hydraulic fracturing operation with a geographical location from the historical data.

[0098] A fifty-first embodiment can include the system of any of the forty-sixth through fiftieth embodiments, wherein the first model comprises a neural network that is trained on the historical data.

[0099] A fifty-second embodiment can include the system of any of the forty-sixth through fifty-first embodiments, wherein the estimated ion composition comprises respective total dissolved solid quantities of individual ions in the fracturing fluid.Atty. Docket No.: 2024INV112484W001-64001

[0100] A fifty-third embodiment can include the system of any of the forty-sixth through fifty-second embodiments, wherein the ions comprise Ca2+, Mg2+, Ba2+, Sr2, Fe2+, Cl', HCO ', SC>42', or CO32ions, or any combination thereof.

[0101] A fifty -fourth embodiment can include the system of any of the forty-sixth through fifty-third embodiments, wherein the second model is based on an output from a third model, which is based on a scale solubility coefficients empirical model.

[0102] A fifty-fifth embodiment can include the system of any of the forty-sixth through fiftyfourth embodiments, wherein the second model is based on a third model, which is based on the historical data.

[0103] A fifty-sixth embodiment can include the system of any of the forty-sixth through fiftyfifth embodiments, wherein the third model comprises a historical scale index model.

[0104] A fifty-seventh embodiment can include the system of any of the forty-sixth through fiftysixth embodiments, wherein the controller is further configured to estimate in real time the scaling index of the scale species in the fracturing fluid by matching the estimated ion composition with an ion composition of the historical scale index model, and estimate the scaling index of the scale species based on the scaling indices or the mass per volume of the scale-forming constituents.

[0105] A fifty -eighth embodiment can include the system of any of the forty-sixth through fiftyseventh embodiments, wherein the second model comprises a neural network that is trained on an output of the historical scale index model.

[0106] A fifty-ninth embodiment can include the system of any of the forty-sixth through fiftyeighth embodiments, wherein the scale species comprise sulfate or carbonate.

[0107] A sixtieth embodiment can include the system of any of the forty-sixth through fifty-ninth embodiments, wherein the scale-forming constituents comprise any combination of any two or more of calcite, barite, gypsum, anhydrate, celestite, or feCCf.

[0108] A sixty-first embodiment can include the system of any of the forty-sixth through sixtieth embodiments, wherein the adjustment of the treatment parameter comprises any one or any combination of any two or more of adjusting a selection of a single scale inhibitor, adjusting a selection of a plurality of scale inhibitors, altering a composition of a single scale inhibitor, altering a composition of a plurality of scale inhibitors, altering a dosage of a single scale inhibitor, altering dosages of a plurality of scale inhibitors, altering downhole scale inhibition injection, or any combination thereof.Atty. Docket No.: 2024INV112484W001-64001

[0109] A sixty-second embodiment can include the system of any of the forty-sixth through sixty-first embodiments, wherein the controller is further configured to control the addition of the one or more scale inhibitors by controlling in real time a chemical storage to inject the scale inhibitor into a blender of the hydraulic fracturing operation.

[0110] In a sixty-third embodiment, a processor-implemented method for inhibiting scale in a hydraulic fracturing operation, comprises: measuring data of fracturing fluid for the hydraulic fracturing operation, wherein the data comprises any combination of any two or more of salinity data, pH data, pressure data, temperature data, or flowrate data; using a first model to estimate, in real time, ion composition in the fracturing fluid, based on the measured data and one or both of a geographical location of the hydraulic fracturing operation or a geographical location of a fluid source of the hydraulic fracturing operation; using a second model to estimate, in real time, scaling index of a scale species in the fracturing fluid based on the estimated ion composition; determining a treatment parameter of one or more scale inhibitors based on the estimated scaling index of the scale species; and controlling addition of the one or more scale inhibitors to the fracturing fluid according to the treatment parameter.

[0111] A sixty -fourth embodiment can include the method of the sixty -third embodiment, further comprising measuring turbidity data of the fracturing fluid at a location downstream of a location at which the one or more scale inhibitors is added to the fracturing fluid, and adjusting the treatment parameter based on the turbidity data.

[0112] A sixty-fifth embodiment can include the method of the sixty-third or sixty-forth embodiments, wherein the first model is based on historical data, and the second model is based on a third model, which is based on the historical data.

[0113] A sixty-sixth embodiment can include the method of any of the sixty third through sixtyfifth embodiments, wherein the adjusting of the treatment parameter comprises adjusting a selection of one or more scale inhibitors, altering a composition of one or more scale inhibitors, altering a dosage of one or more scale inhibitors, or any combination thereof.

[0114] A sixty-seventh embodiment can include the method of any of the sixty-third through sixty-sixth embodiments, further comprising informing or calibrating or pinning one or more of the models with lab data in addition to the real time data.

[0115] A sixty-eighth embodiment can include the method of any of the sixty -third through sixtyseventh embodiments, further comprising pumping the fluid comprising the scale inhibitor down the wellbore.Atty. Docket No.: 2024INV112484W001-64001

[0116] A sixty -ninth embodiment can include the method of any of the sixty-third through sixtyeighth embodiments, wherein the controlling step comprises sending a control system in a closed-loop control system.

[0117] A seventieth embodiment can include the method of any of the sixty-third through sixtyninth embodiments, wherein geographical water is used to determine ion concentration, then the second model is used to determine scale-index, and then the dose of SI is selected accordingly. Preinjection and post-injection sensors may be used to collect the data (e.g., sensors upstream and downstream of the injection point).

[0118] A seventy-first embodiment can include the method of any of the sixty-third through seventieth embodiments, wherein water is produced that has scale properties, and water is treated according to the method for further processing downhole of the well (e.g., treating to protect midstream, surface processing equipment at wellsite). For example, the method may prevent downhole scaling.

[0119] In a seventy-second embodiment, a system for inhibiting scale in a wellbore servicing operation, comprises: a sensor system configured to measure data, wherein the data comprises at least one of salinity data, pH data, pressure data, temperature data, or flow rate data; and a controller configured to: receive the data measured by the sensor system; use a first model component to estimate ion composition in fluid for the operation, based on the data measured by the sensor system and one or both of a geographical location of the operation or a geographical location of a fluid source of the operation; use a second model component to estimate a scaling index of a scale species in the fluid based on the estimated ion composition; determine a treatment parameter of one or more scale inhibitors based on the estimated scaling index of the scale species; and control addition of the one or more scale inhibitors to the fluid according to the treatment parameter.

[0120] A seventy-third embodiment can include the system of the seventy-second embodiment, further comprising a turbidity meter disposed downstream of a location at which the one or more scale inhibitors is added to the fluid, wherein the turbidity meter is configured to measure turbidity data of the fluid, and wherein the controller is further configured to adjust the treatment parameter based on the turbidity data.

[0121] A seventy-fourth embodiment can include the system of the seventy-second or seventy-third embodiments, wherein the scale inhibitors comprise polyacrylic or polymaleic salts or their derivatives, sulfonated co- or ter-polymers, diethylenetriamine penta(methylenephosphonic salts),Atty. Docket No.: 2024INV112484W001-64001bis(hexamethylene)triamine penta(methylenephosphonic salts), polyamino polyether methylenephosphonic salts, or combinations thereof.

[0122] A seventy-fifth embodiment can include the system of any of the seventy-second through seventy-fourth embodiments, wherein the first model component is based on historical data comprising historical salinity, historical ion composition and one or both of historical geographical locations of other operations or historical geographical locations of a fluid source of the other operations.

[0123] A seventy-sixth embodiment can include the system of any of the seventy-second through seventy-fifth embodiments, wherein the controller is further configured to estimate the ion composition in the fluid by relating the geographical location of the operation to a geographical location from the historical data.

[0124] A seventy-seventh embodiment can include the system of any of the seventy-second through seventy-sixth embodiments, wherein the first model component comprises a neural network that is trained on the historical data.

[0125] A seventy-eighth embodiment can include the system of any of the seventy-second through seventy-seventh embodiments, wherein the estimated ion composition comprises respective total dissolved solid quantities of individual ions in the fluid.

[0126] A seventy -ninth embodiment can include the system of any of the seventy-second through seventy-eighth embodiments, wherein the ions comprise Ca2+, Mg2+, Ba2+, Sr2, Fe2+, Cl', HCCh', SO42', or CO32' ions, or any combination thereof.

[0127] An eightieth embodiment can include the system of any of the seventy-second through seventy-ninth embodiments, wherein the second model component is based on an output from a third model component, which is based on a scale solubility coefficients empirical model.

[0128] An eighty-first embodiment can include the system of any of the seventy-second through eightieth embodiments, wherein the second model component is based on a third model component, which is based on the historical data.

[0129] An eighty-second embodiment can include the system of any of the seventy-second through eighty-first embodiments, wherein the third model component comprises a historical scale index model.

[0130] An eighty-third embodiment can include the system of any of the seventy-second through eighty-second embodiments, wherein the controller is further configured to estimate the scaling index of the scale species in the fluid by matching the estimated ion composition with an ion compositionAtty. Docket No.: 2024INV112484W001-64001of the historical scale index model, and estimate the scaling index of the scale species based on the scaling indices or the mass per volume of the scale-forming constituents.

[0131] An eighty-fourth embodiment can include the system of any of the seventy-second through eighty -third embodiments, wherein the second model component comprises a neural network that is trained on an output of the historical scale index model.

[0132] An eighty-fifth embodiment can include the system of any of the seventy-second through eighty-fourth embodiments, wherein the scale species comprise sulfate or carbonate.

[0133] An eighty-sixth embodiment can include the system of any of the seventy-second through eighty-fifth embodiments, wherein the scale-forming constituents comprise any combination of any two or more of calcite, barite, gypsum, anhydrate, celestite, or FeCCh.

[0134] An eighty-seventh embodiment can include the system of any of the seventy-second through eighty-sixth embodiments, wherein the adjustment of the treatment parameter comprises any one or any combination of any two or more of adjusting a selection of a single scale inhibitor, adjusting a selection of a plurality of scale inhibitors, altering a composition of a single scale inhibitor, altering a composition of a plurality of scale inhibitors, altering a dosage of a single scale inhibitor, altering dosages of a plurality of scale inhibitors, altering downhole scale inhibition injection, or any combination thereof.

[0135] An eighty-eighth embodiment can include the system of any of the seventy-second through eighty-seventh embodiments, wherein the controller is further configured to control the addition of the one or more scale inhibitors by controlling a chemical storage to inject the scale inhibitor into a blender of the operation.

[0136] In an eighty -ninth embodiment, a processor-implemented method for inhibiting scale in a wellbore servicing operation, comprises: receiving data of fluid for the operation, wherein the data comprises any combination of any two or more of salinity data, pH data, pressure data, temperature data, or flowrate data; using a first model component to estimate ion composition in fluid for the operation, based on the measured data and one or both of a geographical location of the operation or a geographical location of a fluid source of the operation; using a second model component to estimate scaling index of a scale species in the fluid based on the estimated ion composition; determining a treatment parameter of one or more scale inhibitors based on the estimated scaling index of the scale species; and outputting a signal based on the determined treatment parameter.

[0137] A ninetieth embodiment can include the method of the eighty -ninth embodiment, wherein the outputting of the signal comprises controlling addition of the one or more scale inhibitors to theAtty. Docket No.: 2024INV112484W001-64001fluid according to the treatment parameter, or issuing a control advisory for addition of the one or more scale inhibitors to the fluid according to the treatment parameter.[001381 A ninety-first embodiment can include the method of the eighty-ninth or ninetieth embodiments, further comprising measuring turbidity data of the fluid at a location downstream of a location at which the one or more scale inhibitors is added to the fluid, and adjusting the treatment parameter based on the turbidity data, wherein the first model component is based on historical data, and the second model component is based on a third model component, which is based on the historical data.

[0139] A ninety-second embodiment can include the method of any of the eighty-ninth through ninety-first embodiments, wherein the adjusting of the treatment parameter comprises adjusting a selection of one or more scale inhibitors, altering a composition of one or more scale inhibitors, altering a dosage of one or more scale inhibitors, or any combination thereof.

[0140] In a ninety-third embodiment, a processor-implemented method for inhibiting scale in a wellbore servicing operation, comprises: collecting data of water properties during the wellbore servicing operation; using one or more models to predict scale formation based on the collected data and historical data; and modifying a chemical treatment of fluid for the wellbore servicing operation based on the predicted scale formation.

[0141] A ninety-fourth embodiment can include the method of the ninety-third embodiment, further comprising pumping the fluid with the modified chemical treatment downhole, using a hydraulic fracturing pump, to fracture a formation.

[0142] A ninety-fifth embodiment can include the method of the ninety-third or ninety-fourth embodiments, further comprising circulating the fluid with the modified chemical treatment, using a pump, through a geothermal loop.

[0143] A ninety-sixth embodiment can include the method of any of the ninety-third through ninety-fifth embodiments, wherein the modifying of the chemical treatment is performed by a controller.

[0144] While embodiments have been shown and described, modifications thereof can be made by one skilled in the art without departing from the spirit and teachings of this disclosure. The embodiments described herein are exemplary only and are not intended to be limiting. Many variations and modifications of the embodiments disclosed herein are possible and are within the scope of this disclosure. For example, the various elements or components may be combined or integrated in another system or certain features may be omitted or not implemented. Also, techniques, systems,Atty. Docket No.: 2024INV112484W001-64001subsystems, and methods described and illustrated in the various embodiments as discrete or separate may be combined or integrated with other techniques, systems, subsystems, or methods without departing from the scope of this disclosure. Other items shown or discussed as directly coupled or connected or communicating with each other may be indirectly coupled, connected, or communicated with. Method or process steps set forth may be performed in a different order. The use of terms, such as “first,” “second,” “third” or “fourth” to describe various processes or structures is only used as a shorthand reference to such steps / structures and does not necessarily imply that such steps / structures are performed / formed in that ordered sequence (unless such requirement is clearly stated explicitly in the specification).

[0145] Where numerical ranges or limitations are expressly stated, such express ranges or limitations should be understood to include iterative ranges or limitations of like magnitude falling within the expressly stated ranges or limitations. For example, whenever a numerical range with a lower limit, Ri, and an upper limit, Ru, is disclosed, any number falling within the range is specifically disclosed. In particular, the following numbers within the range are specifically disclosed: R=Ri +k* (Ru-Ri), wherein k is a variable ranging from 1 percent to 100 percent with a 1 percent increment, i.e., k is 1 percent, 2 percent, 3 percent, 4 percent, 5 percent ... 50 percent, 51 percent, 52 percent ... 95 percent, 96 percent, 97 percent, 98 percent, 99 percent, or 100 percent. Moreover, any numerical range defined by two R numbers as defined in the above is also specifically disclosed. Language of degree used herein, such as “approximately,” “about,” “generally,” and “substantially,” represent a value, amount, or characteristic close to the stated value, amount, or characteristic that still performs a desired function or achieves a desired result. For example, the language of degree may mean a range of values as understood by a person of skill or, otherwise, an amount that is + / -10%.

[0146] Disclosure of a singular element should be understood to provide support for a plurality of the element. It is contemplated that elements of the present disclosure may be duplicated in any suitable quantity.

[0147] Use of broader terms such as comprises, includes, having, etc. should be understood to provide support for narrower terms such as consisting of, consisting essentially of, comprised substantially of, etc. The use of terms such as “high-pressure” and “low-pressure” is intended to only be descriptive of the component and their position within the systems disclosed herein. That is, the use of such terms should not be understood to imply that there is a specific operating pressure or pressure rating for such components. For example, the term “high-pressure” describing a manifold should be understood to refer to a manifold that receives pressurized fluid that has been dischargedAtty. Docket No.: 2024INV112484W001-64001from a pump irrespective of the actual pressure of the fluid as it leaves the pump or enters the manifold. Similarly, the term “low-pressure” describing a manifold should be understood to refer to a manifold that receives fluid and supplies that fluid to the suction side of the pump irrespective of the actual pressure of the fluid within the low-pressure manifold.

[0148] Accordingly, the scope of protection is not limited by the description set out above but is only limited by the claims which follow, that scope including all equivalents of the subject matter of the claims. Each and every claim is incorporated into the specification as embodiments of the present disclosure. Thus, the claims are a further description and are an addition to the embodiments of the present disclosure. Any discussion of a reference herein is not an admission that it is prior art. Any disclosures of all patents, patent applications, and / or publications cited herein are hereby incorporated by reference, to the extent that they provide exemplary, procedural, or other details supplementary to those set forth herein.

[0149] As used herein, terms such as parallel, perpendicular, vertical, horizontal, and coincident are not intended to mean exactly parallel, exactly perpendicular, exactly vertical, exactly horizontal, and exactly coincident. Rather, those terms are intended to mean what those of ordinary skill in the art would recognize as parallel, perpendicular, vertical, horizontal, and coincident. Those and similar terms may cover a structural configuration even when there is some imperfection, variation, or deviation from an exact relationship.

[0150] As used herein, the term “or” does not require selection of only one element. Thus, the phrase “A or B” is satisfied by either one or both elements from the set {A, B}. A clause that recites “A or B” can be infringed with only one of the listed items, both of the listed items, multiples of the listed items, and one or both of the listed items and another item not listed. The phrase “A, B, or C” is satisfied by any one or any combination of any two or more from the set {A, B, C}. A clause that recites “A, B, or C” can be infringed with only one of the listed items, multiples of the listed items, and one or more of the items from the list and another item not listed.

[0151] As used herein, the article “a” means “one or more.” As used herein, the article “an” means “one or more.” As used herein, the article “the” when referring to a singular noun means “the one or more.” Thus, the phrase “an element” means “one or more elements;” and the phrase “the element” means “the one or more elements.”

[0152] As used herein, the term “and / or” includes any combination of the elements associated with the “and / or” term. Thus, the phrase “A, B, and / or C” includes any of A alone, B alone, C alone, A and B together, B and C together, A and C together, or A, B, and C together.

Claims

Atty. Docket No.: 2024INV112484W001-64001CLAIMSWhat is claimed is:

1. A system for inhibiting scale in a wellbore servicing operation, comprising:a sensor system configured to measure data, wherein the data comprises at least one of salinity data, pH data, pressure data, temperature data, or flow rate data; anda controller configured to:receive the data measured by the sensor system;use a first model component to estimate ion composition in fluid for the operation, based on the data measured by the sensor system and one or both of a geographical location of the operation or a geographical location of a fluid source of the operation;use a second model component to estimate a scaling index of a scale species in the fluid based on the estimated ion composition;determine a treatment parameter of one or more scale inhibitors based on the estimated scaling index of the scale species; andcontrol addition of the one or more scale inhibitors to the fluid according to the treatment parameter.

2. The system of claim 1, further comprising a turbidity meter disposed downstream of a location at which the one or more scale inhibitors is added to the fluid, wherein the turbidity meter is configured to measure turbidity data of the fluid, and wherein the controller is further configured to adjust the treatment parameter based on the turbidity data.

3. The system of claim 1, wherein the scale inhibitors comprise polyacrylic or polymaleic salts or their derivatives, sulfonated co- or ter-polymers, diethylenetriamine penta(methylenephosphonic salts), bis(hexamethylene)triamine penta(methylenephosphonic salts), polyamino polyether methylenephosphonic salts, or combinations thereof.

4. The system of claim 1, wherein the first model component is based on historical data comprising historical salinity, historical ion composition and one or both of historical geographical locations of other operations or historical geographical locations of a fluid source of the other operations.Atty. Docket No.: 2024INV112484W001-640015. The system of claim 4, wherein the controller is further configured to estimate the ion composition in the fluid by relating the geographical location of the operation to a geographical location from the historical data.

6. The system of claim 4, wherein the first model component comprises a neural network that is trained on the historical data.

7. The system of claim 1, wherein the estimated ion composition comprises respective total dissolved solid quantities of individual ions in the fluid.

8. The system of claim 7, wherein the ions comprise Ca2+, Mg2+, Ba2+, Sr2+, Fe2+, CT, HCO3 , SO42", or CO32’ ions, or any combination thereof.

9. The system of claim 4, wherein the second model component is based on an output from a third model component, which is based on a scale solubility coefficients empirical model.

10. The system of claim 4, wherein the second model component is based on a third model component, which is based on the historical data.

11. The system of claim 9, wherein the third model component comprises a historical scale index model.

12. The system of claim 11, wherein the controller is further configured to estimate the scaling index of the scale species in the fluid by matching the estimated ion composition with an ion composition of the historical scale index model, and estimate the scaling index of the scale species based on the scaling indices or the mass per volume of the scale-forming constituents.

13. The system of claim 11, wherein the second model component comprises a neural network that is trained on an output of the historical scale index model.

14. The system of claim 1, wherein the scale species comprise sulfate or carbonate.Atty. Docket No.: 2024INV112484W001-6400115. The system of claim 12, wherein the scale-forming constituents comprise any combination of any two or more of calcite, barite, gypsum, anhydrate, celestite, or FeCCh.

16. The system of claim 1, wherein the adjustment of the treatment parameter comprises any one or any combination of any two or more of adjusting a selection of a single scale inhibitor, adjusting a selection of a plurality of scale inhibitors, altering a composition of a single scale inhibitor, altering a composition of a plurality of scale inhibitors, altering a dosage of a single scale inhibitor, altering dosages of a plurality of scale inhibitors, altering downhole scale inhibition injection, or any combination thereof.

17. The system of claim 1, wherein the controller is further configured to control the addition of the one or more scale inhibitors by controlling a chemical storage to inject the scale inhibitor into a blender of the operation.

18. A processor-implemented method for inhibiting scale in a wellbore servicing operation, comprising:receiving data of fluid for the operation, wherein the data comprises any combination of any two or more of salinity data, pH data, pressure data, temperature data, or flowrate data;using a first model component to estimate ion composition in fluid for the operation, based on the measured data and one or both of a geographical location of the operation or a geographical location of a fluid source of the operation;using a second model component to estimate scaling index of a scale species in the fluid based on the estimated ion composition;determining a treatment parameter of one or more scale inhibitors based on the estimated scaling index of the scale species; andoutputting a signal based on the determined treatment parameter.

19. The method of claim 18, wherein the outputting of the signal comprises controlling addition of the one or more scale inhibitors to the fluid according to the treatment parameter, or issuing a control advisory for addition of the one or more scale inhibitors to the fluid according to the treatment parameter.Atty. Docket No.: 2024INV112484W001-6400120. The method of claim 18, further comprising measuring turbidity data of the fluid at a location downstream of a location at which the one or more scale inhibitors is added to the fluid, and adjusting the treatment parameter based on the turbidity data, wherein the first model component is based on historical data, and the second model component is based on a third model component, which is based on the historical data.

21. The method of claim 18, wherein the adjusting of the treatment parameter comprises adjusting a selection of one or more scale inhibitors, altering a composition of one or more scale inhibitors, altering a dosage of one or more scale inhibitors, or any combination thereof.

22. A processor-implemented method for inhibiting scale in a wellbore servicing operation, comprising:collecting data of water properties during the wellbore servicing operation;using one or more models to predict scale formation based on the collected data and historical data; andmodifying a chemical treatment of fluid for the wellbore servicing operation based on the predicted scale formation,wherein the steps of the method are conducted in real time.

23. The method of claim 22, further comprising pumping the fluid with the modified chemical treatment downhole, using a hydraulic fracturing pump, to fracture a formation.

24. The method of claim 22, further comprising circulating the fluid with the modified chemical treatment, using a pump, through a geothermal loop.

25. The method of claim 22, wherein the modifying of the chemical treatment is performed by a controller.