Computer-implemented method and system for optimizing a solvent extraction process

Abstract

A computer-implemented method for controlling a parameter in a solvent extraction process by receiving first set of input data 402 from at least one first data source associated with at least one parameter of the solvent extraction process and predicting 404 at least one state associated with solvent extraction process based on this first set of input data using a pre-trained predictive domain model. Receiving a second set of input data 406 associated with an extractant used in the solvent extraction process from at least one second data source and executing a pre-trained predictive domain model using the predicted state and the second set of input data to predict equilibrium isotherms 408 for the solvent extraction process. The value of the parameter is controlled 412 using the equilibrium isotherms and desired state information for the solvent extraction process.

Description

TECHNICAL FIELD The present disclosure relates to computer-implemented methods for optimizing solvent extraction processes. Moreover, the present disclosure relates to systems for optimizing solvent extraction processes. Furthermore, the present disclosure relates to computer-readable storage mediums comprising software applications comprising instructions for optimizing solvent extraction processes. BACKGROUND The solvent extraction (SX) process is a widely used technique in hydrometallurgical operations for the separation and purification of metals (such as copper, nickel, cobalt, uranium, and rare earth elements) from complex aqueous solutions by passing it through various extraction, washing / scrubbing and stripping stages in one or more mixer-settler units of an on-site Solvent Extraction (SX) circuit as shown in FIGs. 1, 2 and 3 (prior art). Typically, the on-site SX circuit faces challenges in maintaining organic phase-continuity stability, primarily attributed to operational factors, such as fluctuations in upstream pregnant leach solution (PLS) inventory, entrainment of aqueous phase in organic phase, and so on. Moreover, many on-site SX circuits do not have the luxury of an inline loaded organic flow meter, therefore, SX operators have a lack of visibility on what state (i.e., phase continuity) the on-site SX circuit is operating in. In this regard, conventionally, the SX operators rely heavily on visual monitoring of the "surface texture" of the organic in the settlers as a guideline as to whether the associated mixers are running in stable organic-continuous mode or not. Typically, the SX operators rely on regular manual organic-to-aqueous (O / A) mixing ratio measurements to ensure sufficient loaded organic and stripped organic is advancing through the SX circuit. This makes the SX process time-consuming, labour-intensive and prone to errors. Moreover, there exists no solutions that provide real time analysis of different steps involved in the SX process. Thus, resulting in a challenging situation to ascertain stable organic-continuous mixing operation and difficulties in making timely adjustments. Therefore, in light of the foregoing discussion, there exists a need to overcome the aforementioned drawbacks. SUMMARY The aim of the present disclosure is to provide a computer-implemented method and a system for real time monitoring of different stages of the solvent extraction process and optimizing (or managing) physical stability within solvent extraction circuits at a plant site by utilizing virtual sensors, alerts and notifications. The aim of the present disclosure is achieved by a computer-implemented method and a system for optimizing a solvent extraction process as defined in the appended independent claims to which reference is made to. Advantageous features are set out in the appended dependent claims. Throughout the description and claims of this specification, the words "comprise", "include", "have", and "contain" and variations of these words, for example "comprising" and "comprises", mean "including but not limited to", and do not exclude other components, items, integers or steps not explicitly disclosed also to be present. Moreover, the singular encompasses the plural unless the context otherwise requires. In particular, where the indefinite article is used, the specification is to be understood as contemplating plurality as well as singularity, unless the context requires otherwise. BRIEF DESCRIPTION OF THE DRAWINGS FIGs. 1, 2 and 3 (Prior Art) are illustrations of exemplary implementations of a solvent extraction circuit, in accordance with an embodiment of the present disclosure; FIG. 4 is an illustration of a flowchart depicting steps of a computer-implemented method for optimizing a solvent extraction process, in accordance with an embodiment of the present disclosure; FIG. 5A is an illustration of a schematic representation of steps of a computer-implemented method for optimizing a solvent extraction process, in accordance with an embodiment of the present disclosure; FIG. 5B is an illustration of a schematic representation of steps of a computer-implemented method for a volumetric and mass-flow dynamics reconciliation, in accordance with an embodiment of the present disclosure; FIG. 6 is an illustration of a workflow diagram of a volumetric and massflow dynamics reconciliation module, in accordance with an embodiment of the present disclosure; FIG. 7A-E are illustrations of various user-interactive data corresponding to first set of input data and at least one parameter of a solvent extraction process as estimated by the at least one first data source, in accordance with an embodiment of the present disclosure; FIG. 8 is an illustration of a graphical representation of a confidence band of an organic-to-aqueous (O / A) mixing ratio virtual sensor, in accordance with an embodiment of the present disclosure; and FIG. 9 is an illustration of a block diagram of a system for optimizing a solvent extraction process, in accordance with an embodiment of the present disclosure. DETAILED DESCRIPTION OF EMBODIMENTS The following detailed description illustrates embodiments of the present disclosure and ways in which they can be implemented. Although some modes of carrying out the present disclosure have been disclosed, those skilled in the art would recognize that other embodiments for carrying out or practising the present disclosure are also possible. In a first aspect, the present disclosure provides a computer-implemented method for optimizing a solvent extraction process, the method comprising: - receiving a first set of input data from at least one first data source, wherein the first set of input data is associated with at least one parameter of the solvent extraction process; - predicting at least one state associated with the solvent extraction process, based on the first set of input data, by executing at least one pre-trained predictive domain model; - receiving a second set of input data from at least one second data source, wherein the second set of input data is associated with extractants for use in the solvent extraction process; - predicting equilibrium isotherms for the solvent extraction process, based on the at least one predicted state and the second set of input data, by executing at least one pre-trained predictive domain model; - receiving desired state information associated with the solvent extraction process; and - determining at least one change required in at least one parameter for optimizing the solvent extraction process, based on the equilibrium isotherms and the desired state information. The method provides scalability and adaptability across all conventional mixer-settler SX circuits. It also offers SX operators the opportunity to manage the physical stability within the SX circuit and associated SX tank farm, irrespective of the target extraction metal species. In this regard, the method employs data from various data sources to provide near-real time visibility into organic-to-aqueous (O / A) mixing ratios in mixers, and alerts generation for providing information on mixer organic-continuous operation mixing regime stability. In a second aspect, the present disclosure provides a system for optimizing a solvent extraction process, the system comprising: - at least one first data source configured to monitor the solvent extraction process; - at least one second data source; and - at least one processor communicably coupled to the at least one first data source and the at least one second data source via a data communication network, wherein the at least one processor is configured to: - receive a first set of input data from at least one first data source, wherein the first set of input data is associated with at least one parameter of the solvent extraction process; - predict at least one state associated with the solvent extraction process, based on the first set of input data, by executing at least one pre-trained predictive domain model; - receive a second set of input data from at least one second data source, wherein the second set of input data is associated with extractants for use in the solvent extraction process; - predict equilibrium isotherms for the solvent extraction process, based on the at least one predicted state and the second set of input data, by executing at least one pre-trained predictive domain model; - receive desired state information associated with the solvent extraction process; and - determine at least one change required in the at least one parameter for optimizing the solvent extraction process, based on the equilibrium isotherms and the desired state information. The system employs pre-trained predictive modules, virtual sensors and associated alerts to optimize the SX process by providing real time (or near-real time) monitoring of the SX process and scalability and adaptability across all conventional mixer-settler SX circuits. Throughout the present disclosure, the term "solvent extraction process" as used herein refers to an industrial process for separating or extracting one or more elements (or substance(s)) from a mixture based on their solubility in different phases. Optionally, the solvent extraction process is employed in chemicals, pharmaceuticals, food processing, and mining industries, for example. It may be appreciated that different phases for solubility are two immiscible phases. Moreover, herein the term 'optimizing' pertains to all aspects of managing the solvent extraction process, for example, monitoring the solvent extraction process, detecting possible issues or drawbacks in the solvent extraction process, finding solutions for the solvent extraction process, implementing the solutions for the solvent extraction process to achieve a desired stability, and so forth. Optionally, an extracted element is selected from any of: copper, cobalt, nickel, iron, free acid, salts, sulphates, manganese, silicon, calcium, aluminium, organophosphorus compounds, a combination thereof, or any other element. Notably, copper, cobalt, nickel, iron, zinc, manganese, calcium and aluminium are metals that are often extracted using solvent extraction process in the mining industry. Free acid refers to unbound or unconjugated acidic substances that may be present in a solution, and need to be selectively removed or concentrated using the solvent extraction process. Similarly, the solvent extraction process may be employed to separate or concentrate specific salts, organophosphorus compounds and sulphates from a solution. Optionally, the solvent extraction process may be employed to extract a combination of the mentioned elements or compounds, such as a mixture of copper, cobalt, nickel, zinc, iron, acids, salts, and other substances or elements. Beneficially, the solvent extraction process may be employed in a wide range of applications to selectively separate or concentrate specific components and / or elements from a mixture. Moreover, high-grade extraction of metals such as copper, cobalt, nickel, iron, manganese, zinc, calcium and aluminium are essential as these metals are crucial industrial metals used in various applications including, but not limited to, electrical wiring, electronics, construction, transportation, manufacturing (such as semiconductor, steel manufacturing), aeros\pace, automotive, agriculture, water treatment processes, management of acidic waste and pollution control, chemical and pharmaceutical production. The solvent extraction process typically involves selecting a solvent depending on specific properties of the elements to be extracted. Optionally, the solvent includes organic compounds like hexane, ethanol, methanol, water, and so on depending on the nature of the solutes. The target element (normally dispersed in a mixture) is brought into contact with the selected solvent such that the target element distributes itself between the two immiscible phases (usually a liquid and a solid or two liquids). Notably, the distribution depends on the solubility of the target element in each phase. Subsequently, the two phases are allowed to separate such that the solvent now contains the dissolved target element (i.e., solvent-rich phase). The solvent-rich phase is then processed (such as evaporation or other separation techniques) to recover the solvent. The recovered solvent is further processed, using additional separation techniques, such as distillation or crystallization, to obtain a concentrated form of the target element. Subsequently, further purification steps may be performed to obtain a high-purity target element. Typically, the solvent extraction process is performed using a solvent extraction circuit installed at a plant site (or client site). The term "solvent extraction circuit" refers to the series of unit operations and equipment used in the solvent extraction process. The solvent extraction circuit normally comprises at least one mixer-settler units that are configured for various steps, namely, mixing, stripping, evaporating, washing, extraction, and so on, of the solvent extraction process. Herein, the term "extraction" refers to transfer of a target elemental species from a pregnant leach solution (PLS) into the synthetic organic phase (extractant solution), by for example a chemical reaction between the dissolved target elemental species and the organic phase. The term "wash" as used herein refers to removal of any unwanted physical entrained leach aqueous from the target elemental species-loaded organic phase, before advancing the loaded organic phase to a strip-duty mixer-settler unit. The term "strip" as used herein refers to transfer of the target elemental species from the washed, loaded organic phase into a high-purity dissolved target elemental species aqueous phase in the strip-duty mixersettler unit, to achieve a selective transfer of the dissolved target elemental species from an impure pregnant leach solution (PLS) into a high-purity advance aqueous phase for further processing of the target elemental species via electrolytic deposition (electrowinning), crystallization or neutralization precipitation, and so on. The mixer unit or mixer tank is designed for containing and contacting the incoming aqueous phase with incoming organic phase (namely, extractant), entering via a mixer unit false bottom chamber. The aqueous phase and the organic phase contact each other in the mixer unit due to an electrically driven mechanical mixer fitted onto the top of the mixer unit. The mixer is used to disperse the aqueous and organic phases in the mixer unit in order to maximize organic-aqueous surface area contact for mass transfer of the target elemental species from one liquid phase to the other. The settler unit provides a large-surface-area-design to dissipate the mixing energy input during the mixing of the two liquid phases, once the mixed phases discharge from the mixer via a mixer unit overflow. The primary duty of the settler unit is to separate the two liquid phases (organic and aqueous) as completely as possible, before the two phases exit the settler unit via respective discharge launders, namely an organic overflow launder and an Aqueous underflow launder and discharge weir, extending across the width of the settler unit, at the opposite end of the settler unit, furthest away from the mixer unit. The two liquid phases (organic and aqueous) are separated in the settler unit through a settler picket fence. The settler picket fence is a slotted vertical cross-sectional plate extending across the width of the settler unit, and is used to "hold back" the mixed organic-aqueous (O / A) phase emulsion, in order to offer additional separation time of the two liquid phases. Optionally, the mixer unit is operated in an organic-continuous mixing mode. The organic-continuous mixing mode of operation results in lowest operational risk of aqueous entrainment in the post-mixing advancing organic phase, hence preferred. The term "input data" as used herein refers to a collection of data or information which is used as an input for the at least one predictive domain model. The input data is optionally expressed as numerical values indicative of the at least one parameter of the solvent extraction process at a given time instant. Optionally, the input data is presented in a tabular pattern, wherein each column corresponds to a given parameter and each row corresponds to a given time instant. Optionally, the input data is predictive of at least one state of the solvent extraction process. Optionally, the first set of input data comprises at least one of: historic data, real time data, of the solvent extraction process. The historic data refers to collected data pertaining to past events that have transpired during one or more operations of the solvent extraction circuit. For example, the historic data may comprise data pertaining to a drill for a mining solvent extraction process from 1 week ago. Optionally, the historic data is used for training the at least one predictive domain model for optimizing the solvent extraction process. Beneficially, such historic data provides information regarding how the solvent extraction process is conducted and issues that may have occurred in the past. Moreover, using such data allows the at least one predictive domain model to learn possible scenarios from historical occurrences. The real time data refers to collected data pertaining to instantaneous changes in the solvent extraction process. Such real time data is instantaneously available as soon as it is created and / or acquired. Optionally, the real time data is used for optimizing the solvent extraction process. Beneficially, such real time data provides information pertaining to the execution of the solvent extraction process, such that if there are any discrepancies, the at least one predictive domain model can identify the same and suggest appropriate changes required, in near-real time. Optionally, the at the least one parameter is selected from at least one of: volumetric flows of at least one feed stream, at least one inter-stage, at least one product stream, at least one target elemental species, at least one organic flow rate, at least one aqueous flow rate, volumetric flows of at least one organic stream and aqueous stream, at least one jump, a total organic volume, at least one linear velocity, a loaded organic tank volume and geometry, a volume of aqueous phase in the loaded organic tank, a loaded organic tank dynamic volumetric inventory, at least one pump data, at least one conductivity reading, an upstream pregnant leach solution inventory, a spent electrolyte flow, a loaded organic inventory, a vessel geometry, a settler geometry, at least one mixer live volume, at least one settler organic volume, an organic consumption rate. The term "parameter" as used herein refers to a characteristic of the solvent extraction process, which is useful for evaluating at least a performance, a status, or condition of the solvent extraction process. In this regard, the volumetric flows of at least one feed stream refers to the rates of flow of different streams in the process, including feed streams, inter-stage streams, product streams, organic streams, and aqueous streams. The target elemental species refer to the specific target element or elements that are the focus of extraction in the solvent extraction process. As mentioned above, the target elemental species or the extracted elements and / or compounds may be a metal, compound, or any element of interest. The organic and aqueous flow rates refer to rates at which the organic solvent and the aqueous (water-containing) phase flow through the extraction circuit, respectively. The jumps refer to a change or transition in conductivity or current consumed between different stages or phases within the solvent extraction process. The conductivity reading provides measurement of electrical conductivity in the solution, which can provide information about the concentration of ions therein. The total organic volume refers to cumulative volume of the organic solvent used in each solvent extraction process. The at least one linear velocity refers to speed of movement of the solvent or other phases through a given section of the solvent extraction circuit, such as at least one settler. The loaded organic tank volume and geometry describes the volume and shape of the tank that holds the organic solvent after it has been loaded with the extracted element, i.e., transfer from the aqueous phase into the organic phase for example. The loaded organic tank dynamic volumetric inventory indicates the changing inventory or content of the loaded organic tank over time. The volume of aqueous phase in the loaded organic tank refers to the volume occupied by the aqueous phase in the tank containing the loaded organic solvent, resulting from an entrainment event. The pump data provides information related to the pumps used in the process, including flow rates, pressure, and other relevant parameters. The upstream pregnant leach solution (PLS) inventory describes the inventory or content of the solution or mixture comprising the at least one target elemental species before entering the solvent extraction process. The spent electrolyte flow refers to the flow of electrolyte solution that has been depleted or spent in a previous stage of the solvent extraction process. The loaded organic inventory is the total amount or inventory of loaded organic solvent containing the extracted element. The vessel and settler geometries describe the physical shape and dimensions of vessels used in the process, such as the mixer-settler unit, etc. The mixer live volume refers to the volume of the mixer unit that is actively involved in the mixing process. Similarly, the settler organic volume is the volume of the settler unit that is dedicated to the organic phase. The organic consumption rate is the rate at which the organic solvent is consumed in the extraction process. Notably, the aforementioned parameters collectively describe the various aspects and conditions of the solvent extraction process critical to the efficiency and control of the extraction operation. Optionally, additionally, the at least one parameter of the solvent extraction process may include a pressure parameter, a motion parameter, a light parameter, a flow parameter, a temperature parameter, an optical parameter, a magnetic parameter, a proximity parameter, an infrared parameter, a level parameter. Beneficially, measuring the at least one parameter of the solvent extraction process is essential for ensuring efficiency, safety, and effectiveness of the overall solvent extraction process. Moreover, real time monitoring and control of the solvent extraction process helps optimize the solvent extraction process, ensuring consistent and reproducible results. Optionally, the first set of input data comprises at least one of an organic-to-aqueous-mixing ratios, a mixer phase instability jump data and an entrainment data. It may be appreciated that the first set of input data is derived from the at least one parameter of the solvent extraction process. The organic-to-aqueous-mixing ratio refers to a ratio of organic solvent to aqueous (water-based) solution in the mixing phase of the solvent extraction process. Notably, the organic-to-aqueous-mixing ratio may influence the efficiency and selectivity of the solvent extraction process. For example, the organic-to-aqueous-mixing ratio impacts mass transfer of the target elemental species from the aqueous phase to the organic phase by affecting contact area and residence time between the two phases. Moreover, the organic-to-aqueous-mixing ratio impacts reaction kinetics (by influencing the concentration gradients and phase contact) and selectivity (by affecting the competitive extraction of different elements). The mixer phase instability jump relates to phase instability jumps that may occur in the mixer unit of the solvent extraction process. A phase instability jump is a sudden change or transition in the behaviour of the phases being mixed. It may be appreciated that sudden changes in phase behaviour (namely, jumps) may lead to an incomplete (or non-uniform) mixing, a reduction in the contact area and residence time between the phases and, consequently, affect the efficiency of mass transfer. Moreover, the mixer phase instability jump may impact the rate at which the target element is transferred from the aqueous phase to the organic phase, affecting the overall efficiency of the extraction. The entrainment refers to an unintentional carryover of one phase into another in a mixing or separation process. The entrainment data, which provides information about the extent of entrainment, can have a significant impact on the efficiency and selectivity of the solvent extraction process. Entrainment typically leads to loss of the target elemental species as some of the target elements may be carried over from one phase to the other, thereby resulting in incomplete extraction and reduced overall efficiency of the solvent extraction process. Notably, entrainment may be a fast entrainment or a slow entrainment. Fast entrainment is a sudden accumulation of aqueous phase in the loaded organic tank as a result of excessive aqueous phase still being entrained in the loaded organic phase exiting the extraction-duty settler unit, via the organic overflow launder. By "sudden", it is meant that the level goes up by several percentage units in less than five minutes, for example. Slow entrainment is a gradual accumulation of aqueous phase in the loaded organic tank as a result of excessive aqueous phase gradually being entrained over an extended period of solvent extraction process operational time, in the loaded organic phase exiting the extraction-duty settler unit, via the organic overflow launder. By "gradual", it is meant that the level goes up by fractions of the percentage unit in more than a couple of minutes, for example. Beneficially, by understanding and controlling entrainment, operators of the solvent extraction circuit can improve the efficiency and selectivity of the solvent extraction process, resulting in a more reliable and cost-effective extraction operation. The term "data source" as used herein refers to a memory which is configured to store at least the input data. Specifically, the at least one first data source is configured to store the first set of input data. Optionally, the at least one first data source may be configured to measure the at least one parameter, determine the first set of input data therefrom and store the determined first set of input data therein. Optionally, the at least one first data source is implemented as at least one of: a virtual sensor, a physical sensor, a device. Typically, the virtual sensor is a sensor which is virtually deployed to sense the at least one parameter in the solvent extraction process. Such virtual sensors are trained using historical data to sense the at least one parameter and are not placed physically within a system. Optionally, such virtual sensors are built using principles of physics and chemistry. It will be appreciated that the virtual sensor is often a result of a model. Herein, the model calculates a series of criteria (i.e., parameters), pertaining to a given process (such as, for example, temperature, pressure, flow, and so forth). In an example, the solvent extraction process involves a set of interconnected mixer-settler units, wherein some parameters between individual mixer-settler units are not physically measured, and merely an intake of a first mixer-settler unit and an output of a last mixer-settler units are measured using the virtual sensors. Beneficially, the virtual sensors eliminate the need for deploying potential physical sensors (such as, for example, a flow sensor) and therefore reduces the overall implementation and maintenance cost of the solvent extraction process. The physical sensor is typically an electromechanical device which senses the at least one parameter in the solvent extraction process, based on which the first set of input data may be calculated using known mathematical (or physics-related) relations. Such physical sensors are deployed by being physically placed within the solvent extraction process. Examples of the physical sensor include, but are not limited to, a pressure sensor, a motion sensor, a light sensor, a flow sensor, a temperature sensor, an optical sensor, a magnetic sensor, a proximity sensor, an infrared sensor, a level sensor. The device is an electromechanical device capable of capturing, storing and / or sharing the input data. Herein, the device may be implemented as: a device of the solvent extraction process, an external device, a user device. The device of the solvent extraction process is a device embedded within the solvent extraction process, the external device is a device which is not embedded within the solvent extraction process but provides some insight into the solvent extraction process, and the user device is a device associated with a user and which is capable of capturing, storing, and sharing data. Beneficially, the above-mentioned implementations of the at least one first data source provide valuable insights into the solvent extraction process. Optionally, the virtual sensor is implemented as: an organic-to-aqueous (O / A) mixing ratio virtual sensor, an organic dynamic volumetric inventory virtual sensor, a loaded organic flow virtual sensor, and a mixer phase instability jump detector, and wherein the physical sensor is implemented as a pregnant leach solution and spent electrolyte flow inline sensor. Virtual sensors use algorithms and models to estimate or calculate important parameters, providing valuable information for control and monitoring. In this regard, the organic-to-aqueous (O / A) mixing ratio virtual sensor is designed to estimate or calculate the organic-to-aqueous mixing ratio by using available data, such as the at least one parameter fed as a historical data or real time data into the at least one pre-trained predictive domain model and algorithms to virtually infer or compute this ratio. The organic dynamic volumetric inventory virtual sensor is designed to estimate the dynamic volumetric inventory of the organic phase. Moreover, the organic dynamic volumetric inventory may provide a virtual representation of the volume of the organic solvent in the extraction system over time. The loaded organic flow virtual sensor is designed to estimate or calculate the flow rate of the loaded organic solvent, which contains the extracted elements. The loaded organic flow virtual sensor utilizes the developed O / A ratio virtual sensor models and reference to PLS and spent electrolyte flow inline sensor real time measurements to derive the loaded organic flow virtual sensor for the pumped loaded organic from the loaded organic tank as well as settler-to-mixer interstage loaded organic flows. In this regard, the organic dynamic volumetric inventory virtual sensor is configured to use data corresponding to the solvent extraction plant design, parameters and manual measurements together with the virtual sensors as described in the present disclosure to derive the organic volumetric inventory virtual sensor. Optionally, data corresponding to the solvent extraction plant design, parameters and manual measurements include, but do not limit to, solvent extraction mixer unit live volume and solvent extraction settler unit cross sectional area (calculated from design drawings), solvent extraction settler unit volume occupied by the organic phase (calculated from the organic depth manual readings per shift), solvent extraction real time mixer unit O / A ratio estimates (converting the 0 part of the ratio into a dynamic mixer organic inventory volume), loaded organic tank dynamic volumetric inventory (calculated from loaded organic tank dimensions and online tank level sensor, aqueous entrainment extent). Notably, the solvent extraction circuit organic inventory dynamic volume serves as the basis for developing the solvent extraction circuit organic consumption rate (expressed in kg / month) as a first output of the solvent extraction process. Beneficially, the loaded organic flow virtual sensor helps in assessing the efficiency of the solvent extraction process, by offering significant additional monitoring, organic consumption assessment and organic inventory top-up scheduling insight, and is useful for process optimization. The mixer phase instability jump detector is designed to detect the phase instability jumps in the mixer unit by using algorithms or mathematical models to identify sudden changes or disruptions in the phase behaviour during mixing. In this regard, the mixer phase instability jump detector monitors the current drawn by the mixer motor, which is a metric that is monitored across all solvent extraction plant-sites. The mixer phase instability jump detector examines the characteristics of the mixer current draw, from which it deduces whether the mixer is undergoing phase "flipping" using statistical techniques. Moreover, the mixer phase instability jump detector is configured to generate an alert notification if the phase continuum in a mixer unit of a mixer-settler unit "flips" or is about to "flip" to the opposite phase continuum. Beneficially, such alert notifications give time to the operator to act immediately to avert this instability by adjusting available control mechanisms, which would otherwise be impossible without continuous human visual supervision. Optionally, other virtual sensors configured for monitoring, measuring and generating alert notifications may be present. For example, a settler unit phase linear velocity flow monitoring virtual sensor is configured to convert the volumetric flows of the organic and aqueous phases entering the solvent extraction mixer-settler units into linear velocities of flow in the associated settler unit, based on data corresponding to the settler unit design dimensions, to generate near-real time settler unit organic and aqueous phases flow regimes (turbulent / laminar) with associated risk profiles for varying operational depths of organic and aqueous phases within each settler unit. The settler unit phase linear velocity flow monitoring virtual sensor indicates linear velocity flow regime risk profiling for 5 scenarios of organic depth in settler profiles (5cm, 10cm, 15cm, 20cm, 25cm and 30cm), which the user can use to make heuristic decisions to adjust organic depths in the settler units to minimize turbulent organic flow regimes and therefore reduce aqueous entrainment to organic phase transfer. In an example, if there is 5 cm of organic depth in the settler unit, the risk profile of aqueous entrainment to loaded organic phase will be elevated. Beneficially, the settler unit phase linear velocity flow monitoring virtual sensor further improves the opportunities for users to stabilize the solvent extraction circuit, physically. The physical sensors, on the other hand, directly measure specific variables in real time, offering accurate and direct data about the conditions within the solvent extraction process. The PLS and spent electrolyte flow inline sensor are physical sensors that are configured to directly measure the flow rates of the PLS and spent electrolyte in real time as they move through the solvent extraction circuit. The PLS typically contains the extracted substances, and the spent electrolyte is the solution depleted of the extracted elements. Beneficially, incorporating a combination of the virtual sensors and the physical sensors. This of virtual and physical sensors allows for comprehensive monitoring, control, and optimization of the solvent extraction process. Moreover, the data gathered from these sensors aids in making informed decisions and adjustments (namely, optimization) to ensure efficient and effective solvent extraction process. Optionally, the method comprises generating control signals for controlling the solvent extraction process in real time. The term "control signal" as used herein refers to a signal which represents a control command for controlling the solvent extraction process. Optionally, the solvent extraction process is controlled in near real time, i.e., as soon as a real time monitoring of the at least one parameter is performed and processed using the at least one predictive domain model. In such cases when real time data cannot be instantaneously implemented, the control signals for controlling the solvent extraction process are generated by the at least one data source in near real time. The term "predictive domain mode!" as used herein refers to a model which predicts future events or outcomes in the solvent extraction process by analysing patterns using the at least one digital twin of the solvent extraction process and the first set of input data. Optionally, the predictive domain model can be implemented for simulating a portion or the whole of the solvent extraction process. Examples of the at least one predictive domain model include, but are not limited to, a classification model, a clustering model, a forecast model, an outliers model, a time series model. It will be appreciated that the at least one predictive domain model leverages the input data to optimize the solvent extraction process. Notably, the at least one predictive domain model is a pre-trained model. Furthermore, the at least one predictive domain model may include, but not be limited to, a standard solvent extraction process model, a tested solvent extraction operation model, and so forth. In an example, the at least one predictive domain model may include a machine learning model and / or an artificial intelligence model to pre-train the at least one predictive domain model, which predicts the at least one state of the solvent extraction process based on the execution of the at least one predictive domain model on the first set of input data and the at least one digital twin. Herein the prediction of the at least one state is a cumulative process of translating the first set of input data to the at least one digital twin and executing the at least one predictive domain model in tandem. It will be appreciated that the at least one predictive domain model auto generates determining steps based at least one of: a given input data, a given data source, an ideal (or desired) solvent extraction process, a reoccurrence, a combination thereof. The term "predicted state" refers to a state of the solvent extraction process which is predicted based on the first set of input data. Furthermore, the at least one predicted state may be interpreted as a step of a conventional solvent extraction process. Herein, the step of the conventional solvent extraction process may include a portion of the step, a prior step which has already been executed, a future step which has to be executed. In an example, the at least one predicted state may include an increase in the mixing rate of the organic and aqueous phases in the mixer unit, a reduction in the linear velocity in the settler unit, and so on, like in the conventional solvent extraction process. Optionally, the at least one pre-trained predictive domain model comprises at least one of: a volumetric and mass-flow dynamics reconciliation module; a dynamic equilibrium isotherm module. Herein, the "volumetric and mass-flow dynamics reconciliation module" refers to a computational system or module designed to derives near-real time volumetric and mass flow dynamic reconciliations across the solvent extraction circuit. The volumetric and mass flow dynamic reconciliation module is configured to reconcile and optimize predictions related to volumetric and mass-flow dynamics of the solvent extraction process in near-real time. Typically, the volumetric and mass-flow dynamics relate to the behaviour and movement of fluids in terms of its volume (volumetric) and rate of flow (mass-flow). Herein, the term "reconciliation" refers to the process of comparing, adjusting, or aligning predicted values or state of the solvent extraction process with observed values or state of the solvent extraction process. The near-real time volumetric and mass-flow dynamics reconciliation module includes a dynamic reconciliation of the solvent extraction circuit organic inventory, to monitor total organic consumption rates as well as act as an indicator to monitor minimum organic inventory impact on the target elemental species' extraction transfer efficiencies. In this regard, beneficially, the volumetric and mass-flow dynamics reconciliation module, by way of derived virtual sensors and alerts, gives additional insight to operators of the solvent extraction process with regards to target elemental species and impurity deportment in the solvent extraction feed streams, interstage and product streams. Additionally, beneficially, the volumetric and mass-flow dynamics reconciliation module minimizes discrepancies between the predicted values or state of the solvent extraction process and the observed values or state of the solvent extraction process, and improves the accuracy of predictions. Herein, the "dynamic equilibrium isotherm module" refers to a computational component or module within a system that deals with dynamic equilibrium isotherms. The dynamic equilibrium isotherm module incorporates mathematical models or algorithms to simulate the dynamic equilibrium conditions such as flow rates, concentrations, and temperature of the solvent extraction process. Herein, the dynamic equilibrium isotherm module combines data sets from the volumetric and mass-flow dynamics reconciliation module together with the data sets from the at least one second data source (such as BASF LIX reagent chemistry) to monitor in near-real time the solvent extraction circuit equilibrium extraction and equilibrium stripping isotherms. The dynamic equilibrium isotherm module may also predict equilibrium isotherm trends for a given maximum time period in the future. The dynamic equilibrium isotherm module is also configured to run various simulation models, based upon certain data control input changes. Optionally, the volumetric and mass-flow dynamics reconciliation module has an average error of ±5-10%. Herein, the average error in the volumetric and mass-flow dynamics reconciliation module refers to the average discrepancy between predicted or calculated values generated by the volumetric and mass-flow dynamics reconciliation module and the actual observed values in the physical solvent extraction circuit. For example, the average error ranges from -10, -8, -5, -2, -0, +2, +5 or +8 up to -8, -5, -2, -0, +2, +5, +8 or +10%. In an example, the average error is 10%. It may be appreciated that in some cases, a small average error may be critical, while in others, a higher error may still be acceptable. In this regard, the method may comprise monitoring average errors over time or during model development, for iterative improvement by adjustments made to the at least one data entry corresponding to the first set of input data or at least one parameter to minimize errors and enhance predictive accuracy. Beneficially, managing average errors is crucial in optimizing the solvent extraction process based on the performance of the volumetric and mass-flow dynamics reconciliation module in predicting or simulating the solvent extraction process. In other words, the disclosed method is configured to estimate the state of the solvent extraction process with about 90% accuracy. Optionally, the above-mentioned process is repeated until an acceptable value of a confidence factor is achieved. The confidence factor is indicative of an accuracy of prediction and / or function. The acceptable value of the confidence factor demonstrates efficient functioning of the solvent extraction process. In this regard, it will be appreciated, that the at least one pre-trained predictive domain model is continually executed with updated values of the first set of input data until a required accuracy is achieved. Herein, the terms "second set of input data" and "second data source" refer to information or data associated with one or more extractants for use in the solvent extraction process and a database for storing the same, respectively. Notably, the first set of input data and the second set of input data are distinct from each other, and similarly, the at least one first data source and the at least one second data source are distinct from each other. The at least one second data source may include for example, (r) BASF's LIX (Liquid Ion Exchange), ChemSpider (Royal Society of Chemistry), PubChem (National Center for Biotechnology Information (NCBI)), SciFinder (Chemical Abstracts Service (CAS)), Reaxys, NIOSH Pocket Guide (National Institute for Occupational Safety and Health (NIOSH)), ChemicalBook, ACD / Labs, and the like. Optionally, the at least one second data source includes the second set of input data selected from at least one of: chemical composition of extractants, concentration of extractants in the solvent phase, physical characteristics of the extractants, selectivity of extractants, stability and reactivity of the extractants, solubility characteristics of extractants in both organic and aqueous phases, supplier information, application guidelines, regulatory compliance, historical performance data. The extractants are solvents or substances added to the solvent to enhance the selectivity of the solvent extraction process. Notably, the extractants are chosen based on their ability to selectively extract the target elemental species from the aqueous phase. The choice of extractant depends on factors such as the composition of the feed solution, the desired level of the target elemental species extraction, and economic considerations. Examples of the extractants may include, but do not limit to, LIX series extractants (e.g., LIX 64N, LIX 84-IC, LIX 622), DEHPA (Di-2-ethylhexyl phosphoric acid; a phosphoric acid derivative), D2EHPA (Di-2-ethylhexyl phosphoric acid; an organophosphorus extractant), N,N-Di(2-ethylhexyl)amine (D2EHA; an amine-based extractant), cyanex extractants (e.g., Cyanex 272, Cyanex 302;organophosphorus compounds), alamine extractants (e.g., Alamine 336; tertiary amines), acorga series (e.g., Acorga M5640, Acorga K2000; organophosphorus compounds), and so on. Notably, the aforementioned extractant examples are suitable for copper extraction. According to an embodiment of the present disclosure, the at least one predicted state is represented through the first set of input data and the second set of input data of the solvent extraction process, based on execution of the at least one predictive domain model. The term "equilibrium isotherm" relate to the relationship between the concentration of a solute in the organic phase and the concentration thereof in the aqueous phase at equilibrium under specific conditions. Notably, the choice of extractant affects the equilibrium isotherms of the solvent extraction process, hence, based on the at least one predicted state and the second set of input data, the at least one pre-trained predictive domain model predicts the equilibrium isotherms for the solvent extraction process. For example, the concentration of a copper ion in the organic phase is 0.005 molar (M), and in the aqueous phase is 0.1 M, an equilibrium constant or distribution ratio of the aforementioned example is a ratio of concentration of copper ion in the organic phase to that in the aqueous phase, i.e., 0.005 / 0.1 or 0.05. Thus, at equilibrium, the concentration of copper ions in the organic phase is 0.05 times the concentration in the aqueous phase. The term "desired state information" refers to a desired output data of the solvent extraction process. The desired state may indicate at least one of: an ideal state, a standard procedural state, a position, in the solvent extraction process. Furthermore, the desired state may be referenced from a conventional solvent extraction plan, or an established solvent extraction data obtained from experimental setups and experimental data. Herein, the at least one predicted state and the desired state of the solvent extraction process are mapped to find similarities and / or dissimilarities in two or more solvent extraction processes. Optionally, the desired state data is received from an operator of the solvent extraction process who is responsible for the operation, control, and maintenance of the solvent extraction circuit. Optionally, the desired state data is manually fed by the operator or obtained automatically from a historic data. The term "at least one change" refers to an iteration in the at least one parameter of the solvent extraction process, which results in a deviation of the overall solvent extraction process. Herein, the at least one change would be required to change the at least one predicted state to the desired state. It may be appreciated that the at least one predictive domain model is continually executed with at least one change in the at least one parameter, resulting in updated values of the first set of input data, until a required accuracy of the solvent extraction process, namely, the desired state of the solvent extraction process, is achieved. In other words, once the at least one change is implemented such as by an operator, the at least one predicted state and the desired state must be similar. When the at least one predicted state is similar to the desired state, the at least one predicted state will mimic the desired state, and provide outputs akin to a local sensor installed within the solvent extraction process. Optionally, the computer-implemented method further comprises initiating at least one process action in response to the determined at least one change for optimizing the solvent extraction process. The term "process action" refers to an action which is to be performed in real time in the solvent extraction process. In some cases where the solvent extraction process is physically deployed, the at least one process action is a physical action. In other cases where the solvent extraction process is virtually deployed, the at least one process action is a virtual action. Optionally, the at least one process action is initiated autonomously or semi-autonomously. Herein, when the at least one process action is initiated autonomously, no approvals or verifications are required from the operator, however, when the at least one process action is initiated semi-autonomously, an approval and / or verification is required from the operator. Optionally, the at least one change is as at least one of: a change in volumetric flows of at least one organic stream and aqueous stream, a change in at least one pump frequency, a change in potential or current, a change in an upstream pregnant leach solution inventory, a spent electrolyte flow, a change in a loaded organic inventory, a change in a vessel geometry and / or a settler geometry, a change in an organic consumption rate, and wherein the at least one process action pertains to controlling flux; controlling at least one of: the aqueous flow rate, the organic flow rate. In this regard, the at least one change in the at least one parameter of the solvent extraction process changes the first set of input data and hence the at least one state overall solvent extraction process. Examples of the at least one process action include, but are not limited to, changing or controlling flow rates of the organic and aqueous phases, changing the at least one linear velocity, changing or controlling the viscosity of the PLS, changing or controlling mixing characteristics (such as mixing time, mixing speed, and so on), changing or controlling the extractant, changing or controlling the current drawn at different stages of the solvent extraction process. Beneficially, implementing the at least one change by initiating the at least one process action optimizes the solvent extraction process. In an example, the solvent extraction process involves the recovery of copper ions from the pregnant leach solution (PLS) having a copper ions concentration of 0.2 M, using an organic extractant. Based on the copper ions concentration in the aqueous phase (PLS) and the second set of input data corresponding to the organic extractant, the equilibrium isotherms predict a distribution ratio (D) 0.02 at the current state of the solvent extraction process. The received desired state depicts an increase in the efficiency of copper extraction from the PLS as compared to the current low distribution ratio of 0.02. Based on these data (i.e., the equilibrium isotherms and desired state information), the method requires a change in the solvent extraction process, to improve the efficiency thereof. In this regard, the at least one change that the operator may decide to implement to adjust operating conditions. In an example, the operator may implement at least one change corresponding to increasing contact time or mixing time or residence time in the mixer-settler units to enhance the contact between the aqueous and organic phases, allowing more copper ions to transfer to the organic phase. In another example, the operator may implement at least one change corresponding to optimizing extractant concentration by adjusting the concentration of the organic extractant to optimize its efficiency in selectively extracting copper ions. It may be appreciated that after implementing said changes, via at least one process action manually by the operator for example, the new equilibrium isotherms predict an increased distribution ratio (D) of for example, 0.1, indicating that a larger fraction of copper ions is now transferring to the organic phase. Thus, based on the equilibrium isotherms along with adjustments to at least one parameter, the solvent extraction process may be optimized to achieve the desired state thereof. Optionally, the method comprises sending, via a notification module associated with the at least one data source, a notification to at least one device associated with an entity, wherein the notification is indicative of at least one change in the at least one parameter associated with the solvent extraction process from a pre-defined threshold therefor, and wherein the entity performs at least one change to optimize the solvent extraction process. Herein, the at least one change is being implemented semi-autonomously since the at least one predictive domain model is being utilized to determine the at least one change but the at least one change is eventually performed by the entity. The term "entity" refers to a physical entity capable of performing the at least one change. Optionally, the entity is at least one of: a person, a robot, that can operate the solvent extraction circuit. The at least one device associated with the entity refers to a communication device capable of receiving and accessing the notification. Optionally, the notification is implemented as at least one of: a visual notification, an audio notification, a haptic notification, a text notification. It will be appreciated that the notification is sent to the at least one device associated with the entity, such that the entity performs or implements the at least one change in the at least one parameter. Beneficially, sending the notification in a timely manner enables a near-real time optimization of the solvent extraction process, by timely resolution of issues in the solvent extraction process. Optionally, the computer-implemented method further comprises - creating at least one digital twin of the solvent extraction process based on the at least one parameter associated with the solvent extraction process; and - updating the at least one digital twin while the solvent extraction process is being executed, based on at least one of: the first set of input data, the at least one predicted state, the equilibrium isotherms, the at least one process action. In this regard, the term "digital twin" as used herein refers to a virtual representation of a real-world asset, herein, the solvent extraction process and / or solvent extraction circuit, which serves as a real time digital counterpart. This means that, the at least one digital twin is updated in real time during its entire lifecycle, depending on changes observed in the at least one real-world asset. Moreover, the at least one digital twin utilises at least one of: simulation, machine learning and reasoning technologies for assisting in decision-making. The at least one digital twin is created using the at least one parameter pertaining to the solvent extraction process. For example, the at least one digital twin may comprise equal number of virtual mixer-settler unit as the number of physical mixer-settler unit in the solvent extraction circuit at the plant site. Moreover, the at least one digital twin is dynamically updated, which means that any changes being observed in the solvent extraction process are updated in the at least one digital twin while the solvent extraction process is being updated in near-real time. Beneficially, the dynamic updating of the at least one digital twin allows potential shortcomings in the solvent extraction process to be identified before significant damage occurs, and thereby be resolved in a timely manner for improving performance and accuracy. In an example, the at least one digital twin may be dynamically updated by removing existing data values, and / or replacing the existing data values with new (i.e., updated or changed) data values. Optionally, the at least one digital twin may not be updated in real time. Herein, a process of the at least one digital twin may be slowed down to provide an output at desired time intervals, such that information may be derived from the at least one digital twin for training of the at least one predictive domain model, for example. In this manner, small changes may be captured which assist in optimising the solvent extraction process. Moreover, the process of the at least one digital twin may be accelerated to anticipate behaviour and performance. Optionally, the computer-implemented method further comprises at least one of: - predicting the equilibrium isotherms of the solvent extraction process for a predefined time period, based on the at least one predicted state of the solvent extraction process and the second set of input data; - running at least one simulation model, based on the at least one change and the predicted equilibrium isotherms, for optimizing a solvent extraction process. In this regard, the equilibrium isotherms of the solvent extraction process are predicted over a specified duration, such as 1 day, 1 week, and so on. Notably, the equilibrium isotherms predicted over a given predefined time period provides an estimate of how the concentrations of substances may vary in each phase over the given predefined time period. Beneficially, such predictive capability of the disclosed method is valuable for planning, optimizing, and understanding the behaviour of the solvent extraction process over time. The simulation model is typically a mathematical or computational representation of the system or process that imitates the behaviour, dynamics, and interactions of the real-world system over time. The simulation model is used to analyse and understand complex systems, predict their behaviour, and test different scenarios without the need for real-world experimentation. The simulation model may be implemented using software tools, mathematical equations, or a combination thereof. Optionally, the simulation model may be a part of the at least one digital twin. Alternatively, the simulation model may be installed in a separate system distinct from the at least one digital twin, wherein the separate system distinct may be communicably coupled to the at least one digital twin. Optionally, when determining the at least one change, the method comprises: - determining at least one proposed change based on the at least one predicted state and the desired state information; - simulate the at least one proposed change in the at least one digital twin of the solvent extraction process to generate a simulated output state information; - assess whether the simulated output state information is similar to the desired state information; and - when the simulated output state information is similar to the desired state information, implement the at least one proposed change as the at least one change required in the solvent extraction process. The at least one proposed change refers to at least one change proposed by the at least one pre-trained predictive domain model for changing the at least one predicted state to the desired state. The at least one proposed change is determined by mapping similarities and differences of the at least one predicted state and the desired state. Thereon, the at least one proposed change is simulated in the at least one digital twin to anticipate an output state of the solvent extraction process when the at least one proposed change is implemented. Since the at least one proposed change is simulated, it beneficially saves costs and effort while providing insights with respect to the at least one proposed change being simulated. The simulated output state is mapped with the desired state by comparing similarities and differences of the same. Notably, the at least one proposed change is implemented as the at least one change required in the solvent extraction process only when the simulated output is similar to the at least one required state. It will be appreciated that such determination of the at least one change required in the solvent extraction process is efficient, sustainable and saves excessive costs since it simulates the at least one proposed change in the at least one digital twin before applying the at least one change to the solvent extraction process. Herein, if any issues are flagged during the simulation, those are sought out and the at least one proposed change is altered until it provides a desired result. Optionally, the method comprises: - calculating an uncertainty of the at least one process action for implementing the at least one change; - comparing the uncertainty with a predefined uncertainty threshold; and - when the uncertainty is greater than the predefined uncertainty threshold, blocking at least one data entry from the first set of input data. The term "uncertainty" refers to an epistemic situation involving imperfect or unknown information. Such uncertainty is applicable to predictions of future events, predetermined physical measurements, an unknown, and so forth. Optionally, the uncertainty is implemented as at least one of: a state uncertainty, an effect uncertainty, a response uncertainty. In operation, the uncertainty is caused by the at least one data entry of the first set of input data. The at least one data entry refers to a data entry of the first set of input data which causes a discrepancy and increases the uncertainty. Such data entry is often unreliable and thereby jeopardizes the prediction of the at least one change. Optionally, the at least one data entry is utilized to train the at least one predictive domain model. The uncertainty is calculated by mapping if the at least one process action would implement the at least one change. When excessive disparity, i.e., a significant difference in the uncertainty from the predefined uncertainty threshold, is observed between the two, it may be assumed that the at least one change is unreliable and thereby a corresponding process action is not implemented. The term "predefined uncertainty threshold" refers to a predetermined level or limit of uncertainty that serves as a criterion for decision-making or analysis within the system or process. The predefined uncertainty threshold is typically established in advance based on the acceptable level of uncertainty that can be tolerated in the optimization of the solvent extraction process. Beneficially, blocking the at least one data entry from the first set of input data removes the uncertainty since the uncertainty was being caused by the at least one data entry. Moreover, calculating the uncertainty and thereon blocking the at least one data entry is beneficial since it safeguards the solvent extraction method against unreliable data. Notably, the predefined uncertainty threshold may be iteratively adjusted, based on the outcomes and feedback from the solvent extraction process, to reflect evolving conditions or changing risk tolerances. Optionally, the method further comprises employing a Monte Carlo dropout algorithm to estimate the uncertainty. The Monte Carlo dropout algorithm refers to a class of computational algorithms that rely on repeated random sampling to obtain a distribution of a numerical quantity. Optionally, when the uncertainty is greater than the predefined uncertainty threshold, the method further comprises sending an alert to the at least one device associated with the entity. In such cases, the determination of the at least one change is halted, and the entity is to overlook the solvent extraction process until the uncertainty is not reduced to a value equal to or lower than the predefined uncertainty threshold. Optionally, the computer-implemented method further comprises providing, to the at least one device associated with the entity, a user-interactive data corresponding to the optimized solvent extraction process. Herein, the term "user-interactive data" refers to a data corresponding to the optimized solvent extraction process, that can be manipulated, explored, or engaged with by the user. Such user engagement with the data may involve data visualizations, data representations by means of charts, graphs, or other interactive elements, and so on, that allow the user to interact with and understand the data provided. In this regard, optionally, the method comprises at least one of: calculating and presenting key performance metrics related to the solvent extraction process, such as extraction efficiency, yields, or resource utilization; developing visual representations of the optimized solvent extraction process to depict the at least one parameter that has been optimized over time; allowing the user to interact with the data easily, over a graphical user interface (GUI) or a dashboard; providing a mechanism for the user to provide feedback, ask questions, or make further adjustments based on the presented data. Beneficially, the user-interactive data corresponding to the optimized solvent extraction process is informative and allows for user interaction, understanding, and potential engagement with the ongoing optimization efforts. Optionally, the method further comprises creating the at least one pretrained predictive domain model using at least one machine learning algorithm and the first set of input data and / or the at least one parameter associated with the solvent extraction process, at least one process action. The machine learning algorithm typically refers to an algorithm which creates the at least one predictive domain model, such that it is able to learn and predict outcomes without being explicitly trained to do so. Moreover, the at least one predictive domain model is thereby trained using the first set of input data, at least one parameter and / or at least one process action, which may be labelled, allowing the at least one predictive domain model to learn and grow accurate over time. Examples of the at least one machine learning algorithm include, but are not limited to, a linear regression algorithm, a logistic regression algorithm, a decision tree algorithm, a support vector machine (SVM) algorithm, a Naive Bayes algorithm, a k-nearest neighbours (KNN) algorithm, a K-means algorithm, a random forest algorithm. Optionally, the predictive domain model is implemented using artificial intelligence. Optionally, the predictive domain model is based on a predictive algorithm. Examples of the predictive algorithm include, but are not limited to, a random forest algorithm, a generalized linear model (GLM) algorithm, a gradient boosted model (GBM) algorithm, a K-means algorithm, a prophet algorithm. Beneficially, the at least one predictive domain model is created and trained herein such that the at least one predictive domain model is pre-trained for use in optimizing the solvent extraction process. Optionally, the computer-implemented method further comprises calibrating the at least one pre-trained predictive domain model based on at least one of: the first set of input data, the at least one predicted state, the equilibrium isotherm, at least one process action. Calibrating or adjusting or fine-tuning the at least one pre-trained predictive domain model is typically performed to improve the accuracy of the at least one pre-trained predictive domain model and ensure that it aligns well with the current or specific conditions of the physical system it is applied to. It may be appreciated that the at least one pre-trained predictive domain model may be calibrated multiple times until it produces the desired state of the solvent extraction process. In this regard, each calibration step employs a new set of data (i.e., that was not used during the training of the at least one pre-trained predictive domain model) selected from the first set of input data, the at least one predicted state and / or the equilibrium isotherm, at least one process action. Optionally, the computer-implemented method further comprises validating the calibrated the at least one pre-trained predictive domain model, based on a separate set of data that was not used during either the training or calibration phases. Beneficially, validating the calibrated the at least one pre-trained predictive domain model helps assess the model's generalization ability. Optionally, the method comprises obtaining (namely, monitoring) the first set of input data in real time by the at least one first data source by employing at least one machine learning algorithm. In this regard, the at least one machine learning algorithm processes (such as by analysing and deriving insights) the incoming first set of input data in real time. Beneficially, obtaining first set of input data in real time ensures making timely and informed decisions, automating processes, and responding dynamically to changes in the environment or input data. The present disclosure also relates to the system as described above. Various embodiments and variants disclosed above, with respect to the aforementioned computer-implemented method, apply mutatis mutandis to the system. The term "at least one processor" as used herein refers to a computational element that is operable to respond to and processes instructions that drive the system. Optionally, the processor includes, but is not limited to, a microprocessor, a microcontroller, a complex instruction set computing (CISC) microprocessor, a reduced instruction set (RISC) microprocessor, a very long instruction word (VLIW) microprocessor, or any other type of processing circuit. Furthermore, the term "processor" may refer to one or more individual processors, processing devices and various elements associated with a processing device that may be shared by other processing devices. Additionally, the one or more individual processors, processing devices and elements are arranged in various architectures for responding to and processing the instructions that drive the system. In other words, the processor is a strategic organization and deployment of various servers and computing resources within a cloud infrastructure to support the operations of the system using a data communication network. The term "data communication network" as used herein refers to means for communication between the processor and other components of the system, such as the data sources (namely, the first and second data sources), a digital twin, and so on, in order to receive and subsequently process the data related to the functioning of the system. Notably, the data communication network refers to an arrangement of interconnected, programmable and / or non-programmable components that, when in operation, facilitate data communication between one or more electronic devices and / or databases. Furthermore, the data communication network may include, but is not limited to, a peer-to-peer (P2P) network, a hybrid peer-to-peer network, local area networks (LANs), radio access networks (RANs), metropolitan area networks (MANs), wide area networks (WANs), all of or a portion of a public network such as global computer network known as the Internet®, a private network, a cellular network and any other communication system. Additionally, the data communication network employs wired or wireless communication that can be carried out via one or more known protocols. Moreover, the at least one processor is configured to perform the steps of the computer-implemented method of the first aspect. Optionally, the at least one pre-trained predictive domain model comprises at least one of: a volumetric and mass-flow dynamics reconciliation module; a dynamic equilibrium isotherm module. Optionally, the system further comprises a notification module, associated with the at least one data source, configured to send a notification to at least one device associated with an entity, wherein the notification is indicative of at least one change in the at least one parameter associated with the solvent extraction process from a predefined threshold therefor, and wherein the entity performs at least one change to optimize the solvent extraction process. Optionally, the at least one first data source is configured to generate control signals for controlling the solvent extraction process in real time. Optionally, the at least one first data source is implemented as at least one of: a virtual sensor, a physical sensor, a device, wherein the virtual sensor is implemented as: an organic-to-aqueous (O / A) mixing ratio virtual sensor, an organic dynamic volumetric inventory virtual sensor, a loaded organic flow virtual sensor, and a mixer phase instability jump detector, and wherein the physical sensor is implemented as a pregnant leach solution and spent electrolyte flow inline sensor. Optionally, the at least one processor is further configured to initiate at least one process action in response to the determined at least one change for optimizing the solvent extraction process. Optionally, the at least one processor is configured to create the at least one pre-trained predictive domain model using at least one machine learning algorithm and the first set of input data and / or the at least one parameter associated with the solvent extraction process, at least one process action. Optionally, the at least one processor is further configured to: create at least one digital twin of the solvent extraction process based on the at least one parameter associated with the solvent extraction process; and dynamically update the at least one digital twin while the solvent extraction process is executed by the solvent extraction circuit, based on at least one of: the first set of input data, the at least one predicted state, the equilibrium isotherms, the at least one process action. Optionally, the at least one processor is further configured to: - predict the equilibrium isotherms of the solvent extraction process for a predefined time period, based on the at least one predicted state of the solvent extraction process and the second set of input data; - run at least one simulation model, based on the at least one change and the predicted equilibrium isotherms, for optimizing a solvent extraction process. Optionally, when determining the at least one change, the at least one processor is configured to: - determine at least one proposed change based on the at least one predicted state and the desired state information; - simulate the at least one proposed change in the at least one digital twin of the solvent extraction process to generate a simulated output state information; - assess whether the simulated output state information is similar to the desired state information; and - when the simulated output state information is similar to the desired state information, implement the at least one proposed change as the at least one change required in the solvent extraction process. Optionally, the at least one processor is further configured to: - calculate an uncertainty of the at least one process action for implementing the at least one change; - compare the uncertainty with a predefined uncertainty threshold; and - when the uncertainty is greater than the predefined uncertainty threshold, block at least one data entry from the first set of input data. Optionally, the at least one change is as at least one of: a change in volumetric flows of at least one organic stream and aqueous stream, a change in at least one pump frequency, a change in potential or current, a change in an upstream pregnant leach solution inventory, a spent electrolyte flow, a change in a loaded organic inventory, a change in a vessel geometry and / or a settler geometry, a change in an organic consumption rate, and wherein the at least one process action pertains to controlling flux; controlling at least one of: the aqueous flow rate, the organic flow rate. Optionally, the at least one processor is further configured to calibrate the at least one pre-trained predictive domain model based on at least one of: the first set of input data, the at least one predicted state, the equilibrium isotherm, at least one process action. Optionally, the at least one processor is further configured to provide, to the at least one device associated with the entity, a user-interactive data corresponding to the optimized solvent extraction process. Optionally, the volumetric and mass-flow dynamics reconciliation module has an average error of ±5-10%. Optionally, the at least one first data source employs at least one machine learning algorithm to obtain the first set of input data in real time. The present disclosure also relates to the computer-readable storage medium as described above. Various embodiments and variants disclosed above, with respect to the aforementioned computer-implemented method and the aforementioned system, apply mutatis mutandis to the computer-readable storage medium. EXPERIMENTALPART A plant site SX circuit was assessed over an operational time period of 8 months. During said operational time period daily extraction copper mass transfer efficiencies was monitored and expressed as a mass percentage, based upon the extraction of copper from the PLS into the organic phase. The plant site SX circuit was operated without the implementation of disclosed SX Application a period of about 6 months to provide insights into virtual O / A ratio sensors and phase continuity jump detector alerts. During a first assessment period, there was an elevated state of flux for the plant site SX circuit operational stability. During this period of operation, an average of 47% extraction efficiency was realized. The main contributor to the lowering of extraction efficiencies during this period of SX operation was the SI strip mixer flipping to aqueous continuous and the resulting deportment of high acid high copper electrolyte aqueous to the extraction stages. During a second assessment period, performing a combination of managing solids impurities in the PLS and electrowinning circuit resulted in an average copper extraction mass transfer efficiency of 86%. During a third assessment period, the results showed an average copper extraction mass transfer efficiency of 95%. DETAILED DESCRIPTION OF THE DRAWINGS Referring to FIGs. 1, 2 and 3 (Prior Art), illustrated are exemplary implementations of a solvent extraction circuit 100, 200 and 300, respectively, in accordance with an embodiment of the present disclosure. FIG. 1 (Prior Art) illustrates a side-view of a conventional solvent extraction circuit 100. As shown, the solvent extraction circuit 100 is implemented as a single mixer-settler unit. The single mixer-settler unit comprises a mixer unit 102 (or mixer tank) and a settler unit 104. The mixer unit 102 is a high-fluid energy zone. The mixer unit 102 comprises a mixer 106, a mixer unit false bottom chamber 108 for receiving an organic phase (depicted as solid squares) and an aqueous phase (depicted as checks) entering therein, and a mixer unit overflow point 110 for removing an organic-aqueous (O / A) emulsion from the mixer unit 102 into the settler unit 104. The settler unit 104 is a low-fluid energy zone. The settler unit 104 comprises an organic-aqueous (O / A) emulsion band 112 and a settler picket fence 114. The settler picket fence 114 is an energy dissipating zone. The organic phase and the aqueous phase separate in the settler unit 104. The separated organic phase exits the settler unit 104 from an organic overflow launder 116. The separated aqueous phase exits the settler unit 104 from an aqueous underflow launder and aqueous discharge weir 118. FIG. 2 (Prior Art) illustrates a schematic illustration of a conventional solvent extraction circuit 200. As shown, the multiple mixer-settler units are implemented as a multiple mixer-settler unit comprising two extraction-duty mixer-settler units 202 and 204 and a strip-duty mixersettler unit 206. The solvent extraction circuit 200 further comprises a mixer 208 attached to each of the multiple mixer-settler units, pumps 210, 212 and 214, and output tanks 216, 218 and 220, and input tanks 222 and 224. As shown, the input tank 222 (PLS tank) receive a pregnant leach solution (PLS) from a PLS dam 226. The PLS comprises target elemental species, focus of the solvent extraction phase, dissolved in an aqueous phase. The input tank 222 supplies, via a first pump 210, the PLS to a first extraction-duty mixer-settler unit 202, in which the PLS is mixed with an organic phase or a partially-loaded organic phase 204A received from a second extraction-duty mixer-settler unit 204 to carry out a first-stage extraction of target elemental species. The first-stage extracted target elemental species-loaded organic phase 202A is discharged from the first extraction-duty mixer-settler unit 202 and collected in a first output tank 216 (loaded organic tank). The remaining partially extracted PLS is transferred from the first extraction-duty mixer-settler unit 202 to the second extraction-duty mixer-settler unit 204, in which the remaining partially extracted PLS is mixed with an organic phase or a stripped organic phase 206A received from the strip-duty mixer-settler unit 206 to carry out a second-stage extraction of the target elemental species. The target elemental species-barren aqueous phase is discharged from the second extraction-duty mixer-settler unit 204 and collected in a second output tank 218 (raffinate tank). The target elemental species-barren aqueous phase is recycled back to the PLS dam 226 via a leach circuit 228. The strip-duty mixer-settler unit 206 receives a high-purity target elemental species-loaded aqueous phase form a second input tank 224 (spent electrolyte tank), via a second pump 212, and target elemental species-loaded organic phase from the first output tank 216 (loaded organic tank), via a third pump 214, to achieve efficient stripping of any potentially remaining target elemental species. A high-purity target elemental species-loaded aqueous phase is extracted from the strip-duty mixer-settler unit 206 and collected into a third output tank 220 (advance electrolyte tank). The high-purity target elemental species-loaded aqueous phase is advanced for further downstream processing, such as via an electrowinning circuit 230. FIG. 3 (Prior Art) illustrates a schematic illustration of an integrated solvent extraction circuit 300 with multiple mixer-settler units. As shown, the multiple mixer-settler units are implemented as a multiple mixersettler unit comprising two high-grade (HG) extraction-duty mixer-settler units 302 and 304, two low-grade (LG) extraction-duty mixer-settler units 306 and 308, two strip-duty mixer-settler unit 310 and 312, and a wash-duty mixer-settler unit 314. The solvent extraction circuit 300 further comprises a mixer 316 attached to each of the multiple mixersettler units, pumps 318, 320, 322, 324 and 326, and output tanks 328, 330, 332 and 334, and input tanks 336, 338, 340 and 342. As shown, a first input tank 336 (High-grade PLS dam) supplies, via a first pump 318, a high-grade (HG) PLS, comprising a high concentration of a target elemental species, focus of the solvent extraction phase, dissolved in an aqueous phase, to a first HG extraction-duty mixer-settler unit 302, in which the PLS is mixed with an organic phase or a partially-loaded organic phase 304A received from a second HG extraction-duty mixer-settler unit 304 to carry out a first-stage HG extraction of target elemental species. The first-stage HG extracted target elemental species-loaded organic phase is discharged from the first HG extraction-duty mixer-settler unit 302 and collected in a first output tank 328 (loaded organic tank). The remaining partially extracted PLS is transferred from the first HG extraction-duty mixer-settler unit 302 to the second HG extraction-duty mixer-settler unit 304, in which the remaining partially extracted PLS is mixed with an organic phase or a partially-loaded organic phase 306A received from the first LG extraction-duty mixer-settler unit 306 to carry out a second-stage HG extraction of the target elemental species. The HG target elemental species-barren aqueous phase is discharged from the second HG extraction-duty mixer-settler unit 304 and collected in a second output tank 330 (HG raffinate tank). The target elemental species-barren aqueous phase is recycled back to the first input tank 336 via a leach circuit 344. Moreover, a second input tank 338 (Low-grade PLS dam) supplies, via a second pump 320, a low-grade (LG) PLS, comprising a low concentration of the target elemental species, focus of the solvent extraction phase, dissolved in an aqueous phase, to a first LG extraction-duty mixer-settler unit 306, in which the LG PLS is mixed with an organic phase or a partially-loaded organic phase 308A received from a second LG extraction-duty mixer-settler unit 308. The remaining partially extracted LG PLS is transferred from the first LG extraction-duty mixer-settler unit 306 to the second LG extraction-duty mixer-settler unit 308, in which the remaining partially extracted LG PLS is mixed with an organic phase or a stripped organic phase 310A received from the first strip-duty mixersettler unit 310 to carry out a second-stage LG extraction of the target elemental species. The LG target elemental species-barren aqueous phase is discharged from the second LG extraction-duty mixer-settler unit 308 and collected in a third output tank 332 (LG raffinate tank). The LG target elemental species-barren aqueous phase is recycled back to the second input tank 338 via a CCD circuit 346. Moreover, a first strip-duty mixer-settler unit 310 receives a high-purity target elemental species-loaded aqueous phase form a third input tank 340 (spent electrolyte tank), via a third pump 322, and an organic phase or a partially-loaded organic phase 312A received from a second stripduty mixer-settler unit 312. The remaining partially extracted PLS is transferred from the first strip-duty mixer-settler unit 310 to the second strip-duty mixer-settler unit 312, in which the remaining partially extracted PLS is mixed with a washed organic phase 314A received from a wash-duty mixer-settler unit 314 to carry out a second-stage electrolyte extraction comprising high-purity target elemental species in aqueous phase. The high-purity target elemental species in aqueous phase is discharged from the second strip-duty mixer-settler unit 312 and collected in a fourth output tank 334 (advance electrolyte tank). The high-purity target elemental species in aqueous phase is advanced for further downstream processing, such as via an electrowinning circuit ”3 AO jtfO. The wash-duty mixer-settler unit 314 receives a wash solution from a fourth input tank 342 (wash solution tank), via a fourth pump 324, and the target elemental species-loaded organic phase from the first output tank 328 (loaded organic tank), via a fifth pump 326, to achieve efficient stripping of any potentially remaining target elemental species. A spent wash solution 350 is collected and may be recycled back to the fourth input tank 342. The washed organic phase 314A is transferred to the second strip-duty mixer-settler unit 312. Referring to FIG. 4, illustrated is a flowchart depicting steps of a computer-implemented method for optimizing a solvent extraction process, in accordance with an embodiment of the present disclosure. At step 402, a first set of input data is received from at least one first data source, wherein the first set of input data is associated with at least one parameter of the solvent extraction process. At step 404, at least one state associated with the solvent extraction process is predicted, based on the first set of input data, by executing at least one pre-trained predictive domain model. At step 406, a second set of input data is received from at least one second data source, wherein the second set of input data is associated with extractants for use in the solvent extraction process. At step 408, equilibrium isotherms for the solvent extraction process are predicted, based on the at least one predicted state and the second set of input data, by executing at least one pre-trained predictive domain model. At step 410, desired state information associated with the solvent extraction process is received. At step 412, at least one change required in the at least one parameter is determined for optimizing the solvent extraction process, based on the equilibrium isotherms and the desired state information. Referring to FIG. 5A, illustrated is schematic representation of steps of a computer-implemented method for optimizing a solvent extraction process, in accordance with an embodiment of the present disclosure. As shown, the pre-trained predictive domain model employs data sets from a volumetric and mass-flow dynamics reconciliation module, a dynamic equilibrium isotherm module, and a solvent extraction simulator for optimization of solvent extraction process. Referring to FIG. 5B, illustrated is schematic representation of steps of a computer-implemented method for a volumetric and mass-flow dynamics reconciliation, in accordance with an embodiment of the present disclosure. As shown, data from the solvent extraction circuit organic inventory dynamic volume virtual sensor and the solvent extraction circuit aqueous steam volumetric flows are used to generate a baseline solvent extraction volumetric flow dynamic reconciliation module. The user's analytical database pertaining to the solvent extraction circuit feed and product streams is subsequently applied to the baseline solvent extraction volumetric flow dynamic reconciliation module to generate the final volumetric and mass-flow dynamics reconciliation module. Moreover, the elemental mass flow reconciliation combines the volumetric flow reconciliation module with plant-site laboratory assay data to infer solvent extraction process stream elemental species (Cu, Fe, free acid, SOv, Mn, Si, Ca, Al and others) mass flow deportment. This offers near-real time insight into copper and impurity deportment in incoming solvent extraction process streams, internal transfer process streams and exiting product streams, which collectively assists users to assess the overall performance of the solvent extraction circuit at any given time of operation. Referring to FIG. 6, illustrated is a workflow diagram 600 of a volumetric and mass-flow dynamics reconciliation module, in accordance with an embodiment of the present disclosure. An organic-to-aqueous (O / A) mixing ratio virtual sensor, employed by the volumetric and mass-flow dynamics reconciliation module, return real-time estimates of the organic-aqueous (O / A) mixing ratios in a mixer unit of a mixer-settler unit with an average relative error of + / -10%, to help operators of a plant-site solvent extraction circuit to set optimal conditions in the mixer units to maximize target elemental species transfer from one phase to another and to contribute to the solvent extraction circuit running at an elevated level of equilibrium physical stability. As shown, the volumetric and mass-flow dynamics reconciliation module employs live data 602 corresponding to loaded organic pumps 602A of at least one extraction-duty mixer-settler unit (El, E2) and strip-duty mixer-settler unit (SI) (namely, status, speed, current draw, etc.) as well as aqueous pump flow rate 602B, loaded organic tank level 602C, and so on. The information corresponding to the loaded organic pumps 602A and other live data 602 is employed by the organic-to-aqueous (O / A) mixing ratio virtual sensor 604 to estimate the organic-to-aqueous (O / A) mixing ratio 604A. The estimated organic-to-aqueous (O / A) mixing ratio 604A and the live data corresponding to the aqueous pump flow rate 602B are employed by a loaded organic flow virtual sensor 606 to estimate an organic flow rate 606A. The estimated organic flow rate 606A along with data corresponding to the loaded organic tank level 602C, vessel geometry 608, and the estimated organic-to-aqueous (O / A) mixing ratio 604A is employed by an organic dynamic volumetric inventory virtual sensor 610 to estimate the organic phase volume 610A exiting the mixer-settler units. Moreover, the estimated organic flow rate 606A along with settler geometry 612 are employed by a settler flow regime virtual sensor 614 to determine linear velocities 614A in the settler unit. Furthermore, live data corresponding to current drawn 602D by mixer motors of El, E2 and SI is received by mixer phase instability jump detector 616 to determine if there is a flip 616A. Furthermore, live data corresponding to corresponding to loaded organic pumps 602A and loaded organic tank level 602C are received by at least one loaded organic tank aqueous entrainment detector 618 configured to detect fast or slow entrainment activity 618A. Referring to FIG. 7A-E, illustrated are various user-interactive data corresponding to first set of input data and at least one parameter of a solvent extraction process as estimated by the at least one first data source, in accordance with an embodiment of the present disclosure. As shown in FIG. 7A, for different time periods (such as 3PM, 6PM, and so on as provided in the X-axis) of a day (as shown in A, B and C) and months (D and E), a system of the present disclosure is configured to provide to a user thereof, information pertaining to first set of input data and at least one parameter of a solvent extraction process, such as O / A ratio (as shown in A and D), organic flow rates (as shown in B) and mixer stability jumps (as shown in C and E) in extraction-duty mixer-settler units (El and E2) and a strip-duty mixer-settler unit (SI). FIG. 7B illustrates graphical representations of total organic dynamic volumetric inventory of a solvent extraction process. As shown, the total organic dynamic volumetric inventory is constant due to the continuous operational conditions. FIG. 7C illustrates graphical representations of fast and slow entrainment alerts generated by a loaded organic entrainment detector, in accordance with an embodiment of the present disclosure. As shown, the solid vertical bars indicate the fast and slow entrainment alerts during fast and slow entrainment events, respectively. FIG. 7D illustrates organic linear velocity profile scenarios for various organic depths for an extraction-duty settler unit. Shown are linear velocity flow regime risk profiling for 5 scenarios of organic depth in settler profiles (5cm, 10cm, 15cm, 20cm, 25cm and 30cm). As shown, if there is 5 cm of organic depth in the settler, the risk profile of aqueous entrainment to loaded organic will be elevated, as depicted by a black triangle pointing to higher risk vale of approximately 5.4. FIG. 7E illustrates the daily extraction copper mass transfer efficiencies expressed as a mass percentage, based upon the extraction of copper from the PLS into the organic phase. For the period indicated in A, a first assessment period, there was an elevated state of flux for the plant site SX circuit operational stability. During this period of operation, an average of 47% extraction efficiency was realized. The main contributor to the lowering of extraction efficiencies during this period of SX operation was the SI strip mixer flipping to aqueous continuous and the resulting deportment of high acid high copper electrolyte aqueous to the extraction stages. For the period indicated in B, a second assessment period, performing a combination of managing solids impurities in the PLS and electrowinning circuit resulted in an average copper extraction mass transfer efficiency of 86%. For the period indicated in C, during a third assessment period, the results showed an average copper extraction mass transfer efficiency of 95%. Referring to FIG. 8, illustrated is a graphical representation 800 of a confidence band of an organic-to-aqueous (O / A) mixing ratio virtual sensor, in accordance with an embodiment of the present disclosure. As shown, an O / A mixing ratio in extraction-duty mixer-settler unit (El O / A ratio) depicted using line 802 as measured by a physical sensor and an O / A mixing ratio depicted using line 804 as estimated by a virtual sensor falls between a 90% confidence band as depicted by lines 806 and 808. This shows that the virtual sensors employed by the pre-trained predictive domain model of the present method and system accurately estimate the organic-to-aqueous (O / A) mixing ratio to a confidence factor of 90%. Referring to FIG. 9, illustrated is a system 900 for optimizing a solvent extraction process, in accordance with an embodiment of the present disclosure. The system 900 comprises at least one first data source 902 configured to monitor the solvent extraction process; at least one second data source 904; and at least one processor 906 communicably coupled to the at least one first data source 902 and the at least one second data source 902 via a data communication network 908. The at least one processor 906 is configured to: receive a first set of input data from the at least one first data source 902, wherein the first set of input data is associated with at least one parameter of the solvent extraction process; predict at least one state associated with the solvent extraction process, based on the first set of input data, by executing at least one pre-trained predictive domain model 910; receive a second set of input data from at least one second data source 904, wherein the second set of input data is associated with extractants for use in the solvent extraction process; predict equilibrium isotherms for the solvent extraction process, based on the at least one predicted state and the second set of input data, by executing at least one pre-trained predictive domain model 910; receive 50 desired state information associated with the solvent extraction process; and determine at least one change required in the at least one parameter for optimizing the solvent extraction process, based on the equilibrium isotherms and the desired state information. 5 Optionally, the processor 906 employs a notification module 912, associated with the at least one first data source 902 and the at least one second data source 904, to send notifications to at least one device 914 associated with an entity 916. The at least one device 914 is communicably coupled to at least one processor 906 and is configured 10 to show at least one digital twin 918 of the solvent extraction process.

Claims

1. A computer-implemented method for optimizing a solvent extraction process, the method comprising:- receiving a first set of input data from at least one first data source 902, wherein the first set of input data is associated with at least one parameter of the solvent extraction process;- predicting at least one state associated with the solvent extraction process, based on the first set of input data, by executing at least one pre-trained predictive domain model 910;- receiving a second set of input data from at least one second data source 904, wherein the second set of input data is associated with extractants for use in the solvent extraction process;- predicting equilibrium isotherms for the solvent extraction process, based on the at least one predicted state and the second set of input data, by executing at least one pre-trained predictive domain model;- receiving desired state information associated with the solvent extraction process; and- determining at least one change required in the at least one parameter for optimizing the solvent extraction process, based on the equilibrium isotherms and the desired state information.

2. The computer-implemented method of claim 1, wherein the first set of input data comprises at least one of an organic-to-aqueous-mixing ratio, a mixer phase instability jump data and an entrainment data.

3. The computer-implemented method of claim 1 or 2, wherein the at the least one parameter is selected from at least one of: volumetric flows of at least one feed stream, at least one inter-stage, at least one product stream, at least one target elemental species, at least one organic flow rate, at least one aqueous flow rate, volumetric flows of at least one organic stream and aqueous stream, at least one jump, a total organic volume, at least one linear velocity, a loaded organic tank volume andgeometry, a volume of aqueous phase in the loaded organic tank, a loaded organic tank dynamic volumetric inventory, at least one pump data, at least one conductivity reading, an upstream pregnant leach solution inventory, a spent electrolyte flow, a loaded organic inventory, a vessel geometry, a settler geometry, at least one mixer live volume, at least one settler organic volume, an organic consumption rate.

4. The computer-implemented method of any of the preceding claims, wherein the method comprises sending, via a notification module 912 associated with the at least one data source, a notification to at least one device 914 associated with an entity 916, wherein the notification is indicative of at least one change in the at least one parameter associated with the solvent extraction process from a pre-defined threshold therefor, and wherein the entity performs at least one change to optimize the solvent extraction process.

5. The computer-implemented method of any of the preceding claims, further comprising initiating at least one process action in response to the determined at least one change for optimizing the solvent extraction process.

6. The computer-implemented method of any of the preceding claims, further comprising- creating at least one digital twin 918 of the solvent extraction process based on the at least one parameter associated with the solvent extraction process; and- updating the at least one digital twin while the solvent extraction process is being executed, based on at least one of: the first set of input data, the at least one predicted state, the equilibrium isotherms, the at least one process action.

7. The computer-implemented method of claim 6, further comprising at least one of:- predicting the equilibrium isotherms of the solvent extraction process for a predefined time period, based on the at least one predicted state of the solvent extraction process and the second set of input data;- running at least one simulation model, based on the at least one change and the predicted equilibrium isotherms, for optimizing a solvent extraction process.

8. The computer-implemented method of any of the preceding claims, wherein the at least one change is as at least one of: a change in volumetric flows of at least one organic stream and aqueous stream, a change in at least one pump frequency, a change in potential or current, a change in an upstream pregnant leach solution inventory, a spent electrolyte flow, a change in a loaded organic inventory, a change in a vessel geometry and / or a settler geometry, a change in an organic consumption rate,and wherein the at least one process action pertains to controlling flux; controlling at least one of: the aqueous flow rate, the organic flow rate.

9. The computer-implemented method of any of the preceding claims, further comprising calibrating the at least one pre-trained predictive domain model based on at least one of: the first set of input data, the at least one predicted state, the equilibrium isotherm, at least one process action.

10. The computer-implemented method of method of any of the preceding claims, wherein an extracted element is selected from any of: copper, iron, free acid, salts, sulphates, manganese, silicon, calcium, aluminium, organophosphorus compounds, a combination thereof, or any other element.

11. The computer-implemented method of any of the claims 4-10, wherein when determining the at least one change, the method comprises:- determining at least one proposed change based on the at least one predicted state and the desired state information;- simulate the at least one proposed change in the at least one digital twin 918 of the solvent extraction process to generate a simulated output state information;- assess whether the simulated output state information is similar to the desired state information; and- when the simulated output state information is similar to the desired state information, implement the at least one proposed change as the at least one change required in the solvent extraction process.

12. The computer-implemented method of any of the preceding claims, wherein the method comprises:- calculating an uncertainty of the at least one process action for implementing the at least one change;- comparing the uncertainty with a predefined uncertainty threshold; and - when the uncertainty is greater than the predefined uncertainty threshold, blocking at least one data entry from the first set of input data.

13. The computer-implemented method of any of the preceding claims, wherein the method comprises generating control signals for controlling the solvent extraction process in real time.

14. The computer-implemented method of any of the preceding claims, further comprising providing, to the at least one device 914 associated with the entity 916, a user-interactive data corresponding to the optimized solvent extraction process.

15. A system 900 for optimizing a solvent extraction process, the system comprising:- at least one first data source 902 configured to monitor the solvent extraction process;- at least one second data source 904; and- at least one processor 906 communicably coupled to the at least one first data source and the at least one second data source via a data communication network 908, wherein the at least one processor is configured to:- receive a first set of input data from the at least one first data source, wherein the first set of input data is associated with at least one parameter of the solvent extraction process;- predict at least one state associated with the solvent extraction process, based on the first set of input data, by executing at least one pre-trained predictive domain model;- receive a second set of input data from at least one second data source, wherein the second set of input data is associated with extractants for use in the solvent extraction process;- predict equilibrium isotherms for the solvent extraction process, based on the at least one predicted state and the second set of input data, by executing at least one pre-trained predictive domain model;- receive desired state information associated with the solvent extraction process; and- determine at least one change required in the at least one parameter for optimizing the solvent extraction process, based on the equilibrium isotherms and the desired state information.

16. The system 900 of claim 15, wherein the at least one pre-trained predictive domain model 910 comprises at least one of: a volumetric and mass-flow dynamics reconciliation module; a dynamic equilibrium isotherm module.

17. The system 900 of claim 15 or 16, further comprising a notification module 912, associated with the at least one data source, configured to send a notification to at least one device 914 associated with an entity 916, wherein the notification is indicative of at least one change in the at least one parameter associated with the solvent extraction processfrom a pre-defined threshold therefore, and wherein the entity performs at least one change to optimize the solvent extraction process.

18. The system 900 of any of the claims 15-17, wherein the at least one first data source is configured to generate control signals for controlling the solvent extraction process in real time.

19. The system 900 of any of the claims 15-18, wherein the at least one first data source 902 is implemented as at least one of: a virtual sensor, a physical sensor, a device, wherein the virtual sensor is implemented as: an organic-to-aqueous (O / A) mixing ratio virtual sensor, an organic dynamic volumetric inventory virtual sensor, a loaded organic flow virtual sensor, and a mixer phase instability jump detector, and wherein the physical sensor is implemented as a pregnant leach solution and spent electrolyte flow inline sensor.

20. The system 900 of any of the claims 15-19, wherein the at least one processor 906 is further configured to initiate at least one process action in response to the determined at least one change for optimizing the solvent extraction process.

21. The system 900 of any of the claims 15-20, wherein the at least one processor 906 is configured to create the at least one pre-trained predictive domain model 910 using at least one machine learning algorithm and the first set of input data and / or the at least one parameter associated with the solvent extraction process, at least one process action.

22. The system 900 of any of the claims 15-21, wherein the at least one processor 906 is further configured to:create at least one digital twin 918 of the solvent extraction process based on the at least one parameter associated with the solvent extraction process; anddynamically update the at least one digital twin while the solvent extraction process is executed by the solvent extraction circuit, based onat least one of: the first set of input data, the at least one predicted state, the equilibrium isotherms, the at least one process action.

23. The system 900 of claim 16, wherein the volumetric and mass-flow dynamics reconciliation module has an average error of ±5-10%.5 24. The system 900 of any of the claims 15-23, wherein the at least onefirst data source 902 employs at least one machine learning algorithm to obtain the first set of input data in real time.

25. A computer-readable storage medium comprising at least one software application comprising instructions for optimizing a solvent 10 extraction process, which when executed by a processing arrangement, causes the processing arrangement to execute steps of a computer-implemented method of claim 1-14.

Images