Description:FORM 2 THE PATENTS ACT, 1970 (39 of 1970) & THE PATENT RULES, 2003 COMPLETE SPECIFICATION (See Section 10 and Rule 13) Title of invention: OPTIMIZATION AND SELF DIAGNOSIS OF CHEMICAL VAPOR DEPOSITION REACTOR FOR 2D TRANSITION METAL DICHALCOGENIDES (TMDCs) Applicant Tata Consultancy Services Limited A company Incorporated in India under the Companies Act, 1956 Having address: Nirmal Building, 9th floor, Nariman point, Mumbai 400021, Maharashtra, India Preamble to the description: The following specification particularly describes the invention and the manner in which it is to be performed. TECHNICAL FIELD The disclosure herein generally relates to a chemical vapor deposition (CVD) process of two-dimensional (2D) Transition metal Dichalcogenides (TMDCs) and, more particularly, to a method and a system for optimization and self-diagnosis of CVD reactor for 2D TMDCs. BACKGROUND The chemical vapor deposition (CVD) is process of depositing desired material on a substrate of a reactor by a set of precursors. The CVD is a scalable route to produce large-area two-dimensional (2D) Transition-metal dichalcogenide materials (TMDCs), wherein the 2D-TMDCs are an emerging class of materials with properties that make them highly attractive for fundamental studies of novel physical phenomena and for applications ranging from nanoelectronics and nano-photonics to sensing and actuation at the nanoscale. Further the 2D TMDCs have lately acquired enough attention in the field of storage, electronic and optoelectronic industries. CVD is the most viable method of producing TMDCs due to CVDs ability to control the chemical deposition process. The chemical deposition process can be controlled by subtle changes in inlet and operating conditions of the CVD. However, given the versatility of reactors and reactor conditions, it is not practical for operators to identify the chemical deposition process settings required for optimizing the chemical deposition process by varying input conditions and varying reactor configurations. In current industrial practice, process engineers and researchers accomplish the deposition of TMDCs using different set of industrial data from literature, trial-error of experiments to obtain the deposition rate. However, with wide variety of operating conditions such as temperature, pressure, inlet flowrate of inert gas and precursors, distance from precursor inlet to substrate, the trial-error process may not be very effective. Further data driven approaches along with physics-based modeling is a potential solution to this complex problem, however the physics-bases models are computationally expensive and time consuming. The current state of art techniques for monitoring includes placing a sensor in the upstream process that can lead to flow disruption. Data driven approaches along with physics-based modeling can help monitoring the CVD process, however this is limited to only certain vital dimensionless numbers-composition of reactants. Hence there is a requirement for robust and real time optimization and control of 2D TMDCs in a CVD reactor. SUMMARY Embodiments of the present disclosure present technological improvements as solutions to one or more of the above-mentioned technical problems recognized by the inventors in conventional systems. For example, in one embodiment, a method for optimization and self-diagnosis of CVD reactor for 2D TMDCs is provided. The system includes a memory storing instructions, one or more communication interfaces, and one or more hardware processors coupled to the memory via the one or more communication interfaces, wherein the one or more hardware processors are configured by the instructions to receive a plurality of inputs at a pre-determined frequency from a plurality of sources, via one or more hardware processors, wherein the plurality of inputs comprises a plurality of real-time data and a plurality of non-real-time data and the plurality of sources comprises a plurality of servers connected to a Chemical Vapor Deposition (CVD) reactor automation system and a CVD reactor data sources. The system is further configured to develop a plurality of soft sensors, via the one or more hardware processors, based on determining a first set of key performance indicators (KPIs)and a plurality of parameters using the plurality of inputs, wherein the plurality of first set of KPI s and the plurality of parameters are determined based on generating a physics-based model of the CVD reactor and generating a Design of experiment (DOE) for the CVD reactor. The system is further configured to predict a plurality of real-time KPIs and a plurality of real-time parameters, via the one or more hardware processors, using the plurality of real-time data and the plurality of soft sensors, wherein the predicted plurality of real-time KPIs comprises a deposition rate and an uniformity index. The system is further configured to recommend a set of optimal operating conditions, via the one or more hardware processors, based on optimizing the deposition rate and the uniformity index, wherein the optimization comprises configuring an optimization model and executing the optimization model based on a pre-configured configuration optimization problem associated with the deposition rate, and the uniformity index. The system is further configured to perform a self-diagnosis of the CVD reactor, via the one or more hardware processors, using the physics-based model of the CVD reactor and the plurality of soft sensors of the CVD reactor, wherein the self-diagnosis is performed based on identification of a drift, wherein the self-diagnosis comprises: identifying the drift based on a comparison of the plurality of real-time data, the predicted plurality of real-time KPIs and a plurality of real-time KPIs and the plurality of non-real time data, the predicted plurality of non-real-time KPIs, and a plurality of non-real time KPIs; identifying a root cause for the drift based on the plurality of soft sensors, the physics-based model, and the predicted plurality of real-time KPIs; and determining a diagnosed model of the CVD reactor by tuning one of (a) the physics-based model, (b) the plurality of soft sensors, and (c) the physics-based model and the plurality of soft sensors based on the drift. In another aspect, a method for optimization and self-diagnosis of CVD reactor for 2D TMDCs is provided. The method includes receiving a plurality of inputs at a pre-determined frequency from a plurality of sources, wherein the plurality of inputs comprises a plurality of real-time data and a plurality of non-real-time data and the plurality of sources comprises a plurality of servers connected to a Chemical Vapor Deposition (CVD) reactor automation system and a CVD reactor data source. The method further includes developing a plurality of soft sensors, based on determining a first set of key performance indicators (KPIs) and a plurality of parameters using the plurality of inputs, wherein the plurality of first set of KPI s and the plurality of parameters are determined based on generating a physics-based model of the CVD reactor and generating a Design of experiment (DOE) for the CVD reactor. The method further includes predicting a plurality of real-time KPIs and a plurality of real-time parameters, using the plurality of real-time data and the plurality of soft sensors, wherein the predicted plurality of real-time KPIs comprises a deposition rate and an uniformity index. The method further includes recommending a set of optimal operating conditions, based on optimizing the deposition rate and the uniformity index, wherein the optimization comprises configuring an optimization model and executing the optimization model based on a pre-configured configuration optimization problem associated with the deposition rate, and the uniformity index. The method further includes performing a self-diagnosis of the CVD reactor, using the physics-based model of the CVD reactor and the plurality of soft sensors of the CVD reactor, wherein the self-diagnosis is performed based on identification of a drift, wherein the self-diagnosis comprises: identifying the drift based on a comparison of the plurality of real-time data, the predicted plurality of real-time KPIs and a plurality of real-time KPIs and the plurality of non-real time data, the predicted plurality of non-real-time KPIs, and a plurality of non-real time KPIs; identifying a root cause for the drift based on the plurality of soft sensors, the physics-based model, and the predicted plurality of real-time KPIs; and determining a diagnosed model of the CVD reactor by tuning one of (a) the physics-based model, (b) the plurality of soft sensors, and (c) the physics-based model and the plurality of soft sensors based on the drift. In yet another aspect, a non-transitory computer readable medium for optimization and self-diagnosis of CVD reactor for 2D TMDCs is provided. The method includes receiving a plurality of inputs at a pre-determined frequency from a plurality of sources, wherein the plurality of inputs comprises a plurality of real-time data and a plurality of non-real-time data and the plurality of sources comprises a plurality of servers connected to a Chemical Vapor Deposition (CVD) reactor automation system and a CVD reactor data source. The method further includes developing a plurality of soft sensors, based on determining a first set of key performance indicators (KPIs)and a plurality of parameters using the plurality of inputs, wherein the plurality of first set of KPI s and the plurality of parameters are determined based on generating a physics-based model of the CVD reactor and generating a Design of experiment (DOE) for the CVD reactor. The method further includes predicting a plurality of real-time KPIs and a plurality of real-time parameters, using the plurality of real-time data and the plurality of soft sensors, wherein the predicted plurality of real-time KPIs comprises a deposition rate and an uniformity index. The method further includes recommending a set of optimal operating conditions, based on optimizing the deposition rate and the uniformity index, wherein the optimization comprises configuring an optimization model and executing the optimization model based on a pre-configured configuration optimization problem associated with the deposition rate, and the uniformity index. The method further includes performing a self-diagnosis of the CVD reactor, using the physics-based model of the CVD reactor and the plurality of soft sensors of the CVD reactor, wherein the self-diagnosis is performed based on identification of a drift, wherein the self-diagnosis comprises: identifying the drift based on a comparison of the plurality of real-time data, the predicted plurality of real-time KPIs and a plurality of real-time KPIs and the plurality of non-real time data, the predicted plurality of non-real-time KPIs, and a plurality of non-real time KPIs; identifying a root cause for the drift based on the plurality of soft sensors, the physics-based model, and the predicted plurality of real-time KPIs; and determining a diagnosed model of the CVD reactor by tuning one of (a) the physics-based model, (b) the plurality of soft sensors, and (c) the physics-based model and the plurality of soft sensors based on the drift. It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the invention, as claimed. BRIEF DESCRIPTION OF THE DRAWINGS The accompanying drawings, which are incorporated in and constitute a part of this disclosure, illustrate exemplary embodiments and, together with the description, serve to explain the disclosed principles: FIG.1 illustrates an exemplary system for optimization and self-diagnosis of CVD reactor for 2D TMDCs according to some embodiments of the present disclosure. FIG. 2 is a functional block diagram for optimization and self-diagnosis of CVD reactor for 2D TMDCs according to some embodiments of the present disclosure. FIGS. 3A to FIG.3B is a flow diagram illustrating a method (300) for optimization and self-diagnosis of CVD reactor for 2D TMDCs in accordance with some embodiments of the present disclosure. FIG.4 is a functional diagram of a CVD reactor for depositing Molybdenum Disulfide during the optimization and self-diagnosis of CVD reactor for 2D TMDCs in accordance with some embodiments of the present disclosure. FIG.5 is a flow diagram illustrating a method (500) for determination of the first set of KPIs and the determination of the plurality of parameters during the optimization and self-diagnosis of CVD reactor for 2D TMDCs in accordance with some embodiments of the present disclosure. FIG.6 is figure illustrating a variation of dimensionless numbers around the substrate inside the CVD reactor for varying temperatures of CVD reactor for 2D TMDCs in accordance with some embodiments of the present disclosure. FIG.7 is a graph illustrating predictions of the deposition rate from a prediction model in the CVD reactor for 2D TMDCs in accordance with some embodiments of the present disclosure. DETAILED DESCRIPTION OF EMBODIMENTS Exemplary embodiments are described with reference to the accompanying drawings. In the figures, the left-most digit(s) of a reference number identifies the figure in which the reference number first appears. Wherever convenient, the same reference numbers are used throughout the drawings to refer to the same or like parts. While examples and features of disclosed principles are described herein, modifications, adaptations, and other implementations are possible without departing from the scope of the disclosed embodiments. Referring now to the drawings, and more particularly to FIG. 1 through FIG.7, where similar reference characters denote corresponding features consistently throughout the figures, there are shown preferred embodiments and these embodiments are described in the context of the following exemplary system and/or method. FIG.1 is an exemplary block diagram of a system 100 for optimization and self-diagnosis of CVD reactor for 2D TMDCs in accordance with some embodiments of the present disclosure. In an embodiment, the system 100 includes a processor(s) 104, communication interface device(s), alternatively referred as input/output (I/O) interface(s) 106, and one or more data storage devices or a memory 102 operatively coupled to the processor(s) 104. The system 100 with one or more hardware processors is configured to execute functions of one or more functional blocks of the system 100. Referring to the components of the system 100, in an embodiment, the processor(s) 104, can be one or more hardware processors 104. In an embodiment, the one or more hardware processors 104 can be implemented as one or more microprocessors, microcomputers, microcontrollers, digital signal processors, central processing units, state machines, logic circuitries, and/or any devices that manipulate signals based on operational instructions. Among other capabilities, the one or more hardware processors 104 is configured to fetch and execute computer-readable instructions stored in the memory 102. In an embodiment, the system 100 can be implemented in a variety of computing systems including laptop computers, notebooks, hand-held devices such as mobile phones, workstations, mainframe computers, servers, a network cloud and the like. The I/O interface(s) 106 can include a variety of software and hardware interfaces, for example, a web interface, a graphical user interface, a touch user interface (TUI) and the like and can facilitate multiple communications within a wide variety of networks N/W and protocol types, including wired networks, for example, LAN, cable, etc., and wireless networks, such as WLAN, cellular, or satellite. In an embodiment, the I/O interface (s) 106 can include one or more ports for connecting a number of devices (nodes) of the system 100 to one another or to another server. The memory 102 may include any computer-readable medium known in the art including, for example, volatile memory, such as static random-access memory (SRAM) and dynamic random-access memory (DRAM), and/or non-volatile memory, such as read only memory (ROM), erasable programmable ROM, flash memories, hard disks, optical disks, and magnetic tapes. Further, the memory 102 may include a database 108 configured to include information regarding optimization and self-diagnosis of CVD reactor for 2D TMDCs. The memory 102 may comprise information pertaining to input(s)/output(s) of each step performed by the processor(s) 104 of the system 100 and methods of the present disclosure. In an embodiment, the database 108 may be external (not shown) to the system 100 and coupled to the system via the I/O interface 106. Functions of the components of system 100 are explained in conjunction with functional overview of the system 100 in FIG.2 and flow diagram of FIGS.3A to FIG.3B for optimization and self-diagnosis of CVD reactor for 2D TMDCs. The system 100 supports various connectivity options such as BLUETOOTH®, USB, ZigBee and other cellular services. The network environment enables connection of various components of the system 100 using any communication link including Internet, WAN, MAN, and so on. In an exemplary embodiment, the system 100 is implemented to operate as a stand-alone device. In another embodiment, the system 100 may be implemented to work as a loosely coupled device to a smart computing environment. The components and functionalities of the system 100 are described further in detail. FIG.2 is an example functional block diagram of the various modules of the system of FIG.1, in accordance with some embodiments of the present disclosure. As depicted in the architecture, the FIG.2 illustrates the functions of the modules of the system 100 that includes optimization and self-diagnosis of CVD reactor for 2D TMDCs. As depicted in FIG.2, the functional system 200 of system 100 system 200 is configured for optimization and self-diagnosis of CVD reactor for 2D TMDCs. The system 200 comprises input module 202 configured for receiving a plurality of inputs at a pre-determined frequency from a plurality of sources. The plurality of inputs comprises a plurality of real-time data and a plurality of non-real-time data. The plurality of sources comprises a plurality of servers connected to a Chemical Vapor Deposition (CVD) reactor automation system and a CVD reactor data source. The system 200 further comprises a soft sensor developer 204 configured developing a plurality of soft sensors based on determining a first set of key performance indicators (KPIs) and a plurality of parameters using the plurality of inputs. The plurality of first set of KPI s and the plurality of parameters are determined based on (a) generating a physics-based model of the CVD reactor and (b) generating a Design of experiment (DOE) for the CVD reactor. The system 200 further comprises a predictor 206 configured for predicting a plurality of real-time KPIs and a plurality of real-time parameters using the plurality of real-time data and the plurality of soft sensors. The predicted plurality of real-time KPIs comprises a deposition rate and a uniformity index. The system 200 further comprises a recommender 208 configured recommending a set of optimal operating conditions based on optimizing the deposition rate and the uniformity index. The optimization process comprises configuring an optimization model and executing the optimization model based on a pre-configured configuration optimization problem associated with the deposition rate, and the uniformity index. The system 200 further comprises a self-diagnosis 210 configured for performing a self-diagnosis of the CVD reactor using the physics-based model of the CVD reactor and the plurality of soft sensors of the CVD reactor. The self-diagnosis performed based on identification of a drift, identifying a root cause for the drift and determining a diagnosed model of the CVD reactor. The various modules of the system 100 and the functional blocks in FIG.2 are configured for optimization and self-diagnosis of CVD reactor for 2D TMDCs are implemented as at least one of a logically self-contained part of a software program, a self-contained hardware component, and/or, a self-contained hardware component with a logically self-contained part of a software program embedded into each of the hardware component that when executed perform the above method described herein. Functions of the components of the system 200 are explained in conjunction with functional modules of the system 100 stored in the memory 102 and further explained in conjunction with flow diagram of FIGS.3A-3B. The FIGS.3A-3B with reference to FIG.1, is an exemplary flow diagram illustrating a method 300 for optimization and self-diagnosis of CVD reactor for 2D TMDCs using the system 100 of FIG.1 according to an embodiment of the present disclosure. The steps of the method of the present disclosure will now be explained with reference to the components of the system 100 of FIG.1 for optimization and self-diagnosis of CVD reactor for 2D TMDCs and the modules 202-210 as depicted in FIG.2 and the flow diagrams as depicted in FIGS.3A-3B. Although process steps, method steps, techniques or the like may be described in a sequential order, such processes, methods and techniques may be configured to work in alternate orders. In other words, any sequence or order of steps that may be described does not necessarily indicate a requirement that the steps to be performed in that order. The steps of processes described herein may be performed in any order practical. Further, some steps may be performed simultaneously. At step 302 of the method 300, a plurality of inputs is received from a plurality of sources by the input module 202. The plurality of inputs comprises: a plurality of real-time data and a plurality of non-real-time data. The plurality of sources comprises a plurality of servers connected to a Chemical Vapor Deposition (CVD) reactor automation system and a CVD reactor data source. Most used reactors for depositing 2D TMDCs are in horizontal cold wall reactor configurations, wherein synergies between mass, energy and momentum transfers are existing in the reactor to achieve a desired deposition rate and a desired uniformity index. In an example scenario - a CVD of 2D TMDCs process, involves deposition of TMDCs such as MoS_2, Mo?Se?_2, ?WS?_2, ?WSe?_2 etc. by-passing corresponding precursors with inert gases like Argon, Nitrogen flowing upstream of the reactor. An example scenario of a CVD reactor configuration for depositing MoS_2 (Molybdenum Disulfide) is illustrated using FIG.4. The MoS_2 (Molybdenum Disulfide) is deposited by passing MoO_3 (Molybdenum trioxide) and Sulfur in the bottom with Argon as inert gas flowing upstream of the reactor. The MoO3 enters the reactor near the substrate while Sulfur inlet is kept at a distance of 23cm from the substrate. The distance from sulfur to substrate is generally varied from 15cm to 40 cm but not limited to that distance. The Argon flows upstream of the reactor to maintain a uniform concentration gradient of Sulfur across the reactor. The substrate is heated to reaction temperature and optimum pressure is maintained inside the reactor. The temperature and pressure are varied from 923K to 1173K and 50000 Pa to 101325 Pa respectively, but not limited to same. The MoO3 and Sulfur reach the substrate and sequences of gas phase and surface reaction occurs for the deposition to take place. The chemical reaction is given by 2MoO_3+7S?2MoS_2+3SO_2 (1) wherein, MoO3 is Molybdenum trioxide, MoS2 is Molybdenum disulfide, S representing sulfur and SO2 representing sulfur dioxide. The important parameter required to yield of the substrate are uniformity index and deposition rate. Deposition rate is the amount of material deposited over time while uniformity index represents how uniformly the material is deposited. Deposition rate is measured by performing characterization techniques like atomic force microscopy, electron microscopy etc. while uniformity index is measured by measuring deposition rate across the substrate and averaging it. In another example scenario the input module 202 is configured to receive the plurality of real-time data from the server and the plurality of non-real-time data from the CVD reactor data sources at a pre-determined frequency of once every 15 min, once in every 30 min and so on. In an embodiment, the plurality of real-time data comprises operations data such as temperature, operating pressure, inlet flow rates of precursors, argon flow rate and inlet temperatures of Sulphur etc. The plurality of real-time data also comprises environment data such as ambient temperature, atmospheric pressure, ambient humidity etc. The plurality of real-time data is obtained from reactor automation systems such as distributed control system (DCS) via a communication server such as OPC server or via an operations data source such as a historian. The plurality of non-real-time includes data from laboratory tests and maintenance activities. Laboratory data consists of data from Scanning electron microscope, Atomic force microscope, X-Ray Diffraction of wafer. The maintenance data includes details of planned and unplanned maintenance activities performed on one or more units of the reactor, and condition and health of the process and various units in the reactor. The plurality of non-real-time data is obtained from Laboratory Information Management System, Manufacturing Execution Services, historian, and other reactor maintenance databases. The plurality of real-time KPIs comprises a deposition rate and a uniformity index captured at a real-time and the plurality of non-real-time KPIs comprises the deposition rate and the uniformity index data captured at a historic time. At step 304 of the method 300, a plurality of soft sensors is a developed in the soft sensor developer 204. The soft sensors play an important role in measuring variables that are hard to measure/predict in a system without physically placing a sensor. Placing a physical sensor just before the substrate in a CVD reactor causes a disruption in flow and disturbs the reaction and movement of reactants to the substrate. However, it is essential to measure the hard to predict variables aids in accurate prediction of KPIs. The plurality of soft sensors are developed based on determining (a) a first set key performance indicators (KPIs)and (b) a plurality of parameters using the plurality of inputs. The plurality of first set of KPI s and the plurality of parameters are determined based on: generating a physics-based model of the CVD reactor and generating a Design of experiment (DOE) for the CVD reactor The determination of the first set of KPIs and the determination of the plurality of parameters is performed in several steps and is illustrated using FIG.5 as explained below: At step 502 of the method 500, a physics-based model of the CVD reactor is generated, and the physics-based model of the CVD reactor is tuned with experimental data. The physics based model is generated to investigate the effects of every individual parameter contributing the precise prediction of KPIs. Further the physics-based models are used to understand the effect of flow patterns, velocity profiles, temperature contours, deposition patterns that exists in the CVD reactor. In an embodiment, the physics-based model of the CVD reactor is generated like as experimental reactor to understand and investigate the effect of process parameters with KPIs. In an example scenario - in a CVD of MoS2, the physics based models are collected from plurality of models from model repository and boundary and initial conditions are ensured as in the real time conditions. The physics-based model is then validated with the plurality of non-real time (historical) data by tweaking model parameters such as the activation energies and pre-exponential factors of kinetics responsible for desired compound, specific heat constant values of various components in the reactor, etc. In an example scenario case, operating lines of experimental conditions are matched with simulated conditions. At step 504 of the method 500, a Design of experiment (DOE) is generated for the plurality of CVD operating conditions. In an embodiment, the design of experiment is generated to carry out more simulations and generate more data from the physics based model. Design of experiment can be performed by Quasi Monto Carlo sampler, Latin Hyper Cube, Central Composite Design, Full factorial design etc. DOE enables to create an optimal number of experiments to generate meaningful data. A Sample DOE data for depositing MoS2 is shown below using table 1. Temperature (K) Pressure (Pa) …. …… Flowrate of inert gas (slm) Design 1 923 50000 12 Design 2 1034 66000 66 .. .. Design 120 967 101325 164 Table 1: DOE data for depositing MoS2 At step 506 of the method 500, a set of simulated data is generated based on the DOE and the physics-based model of CVD reactor. The set of simulated data comprises a first set of KPI and a plurality of parameters. In an embodiment, the Design of experiment (DOE) for the CVD reactor is generated to carry out simulations for the physics-based models based on the obtained number of experiments are carried out by physics-based models and for every design, along with deposition rates and uniformity indices, plurality of parameters are collected. The plurality of parameters includes Grashof number, Reynolds number, composition (mole fractions) of important intermediate reactants at different locations around the substrate and on the substrate. The FIG.6 illustrates the variation of (Re) Reynolds number,(Gr/Re2) Grashof/Reynolds number at various locations near the substrate for different locations inside the CVD reactor. At step 508 of the method 500, a plurality of soft sensors is developed using the first set key performance indicators (KPIs)and a plurality of parameters. The generated Grashof number, Reynolds number, composition of reactants at different locations around the substrate and on the substrate are the potential soft sensors obtained from physics based models. However, the physics based models are computationally expensive and time consuming. Hence, models for these Grashof number, Reynolds number are generated by machine learning techniques from the data obtained from physics-based models which improves the relay time in predictions. The soft sensors are data driven models that are built using a plurality of machine learning and deep learning techniques, that include variants of regression (multiple linear regression, stepwise regression, forward regression, backward regression, partial least squares regression, principal component regression, Gaussian process regression, polynomial regression, etc.), decision tree and its variants (random forest, bagging, boosting, bootstrapping), support vector regression, k-nearest neighbors regression, spline fitting or its variants (e.g. multi adaptive regression splines), artificial neural networks and it variants (multi-layer perceptron, recurrent neural networks & its variants e.g. long short term memory networks, and convolutional neural networks) and time series regression models. The techniques for generating the soft sensors can be point models (that do not consider temporal relationship among data instances) or time series techniques (that consider temporal relationship among data instances). The data driven techniques for generating the soft sensors uses all the set of parameters in the module to generate models of the KPIs of the CVD reactor. At step 306 of the method 300, a plurality of real-time KPIs and a plurality of real-time parameters is predicted in the predictor 206. The plurality of real-time KPIs and the plurality of real-time parameters is predicted using the plurality of real-time data and the plurality of soft sensors. The predictions from prediction module 206 are real time and it predicts the deposition rate and the uniformity index of deposition in real time. The predicted plurality of real-time KPIs comprises a deposition rate and uniformity index. The soft sensors for predicting the plurality of real-time KPIs are built using machine learning and deep learning techniques that include variants of regression (multiple linear regression, stepwise regression, forward regression, backward regression, partial least squares regression, principal component regression, Gaussian process regression, polynomial regression, etc.), decision tree and its variants (random forest, bagging, boosting, bootstrapping), support vector regression, k-nearest neighbors regression, spline fitting or its variants (e.g. multi adaptive regression splines), artificial neural networks and it variants (multi-layer perceptron, recurrent neural networks & its variants e.g. long short term memory networks, and convolutional neural networks) and time series regression models. The techniques for generating the soft sensors can be point techniques (that do not consider temporal relationship among data instances) or time series techniques (that consider temporal relationship among data instances). In an embodiment, two separate models are created one for each (a) the deposition rate and (b) the uniformity index. The prediction module can be built by set of neural networks of one model or multiple machine learning models pinned together to predict and forecast the KPIs of the CVD reactor of 2D TMDCs. In an example scenario, in the case of prediction deposition rate of MoS2, the predictions from the soft sensors of Grashof number (at 2 cm before the substrate), Reynolds number (near the substrate), mole fraction of Sulfur (at 2cm before the substrate) are used to build the deposition rate prediction model. The FIG.7 illustrates the predictions versus ground truth data of the deposition rate predictions from the prediction model. At step 308 of the method 300, a set of optimal operating conditions is recommended in the recommender 208. The set of optimal operating conditions is recommended based on optimizing the deposition rate and the uniformity index. The optimization comprises configuring an optimization model and executing the optimization model based on a pre-configured configuration optimization problem associated with the deposition rate, and the uniformity index. In an embodiment, the recommender 208 comprises an optimization model configured to optimize a plurality of key performance indicators (KPIs) of the CVD reactor the deposition rate, and the uniformity index using the plurality of physics-based and the data-driven models of the soft sensors. The plurality of key performance parameters (KPI) of the CVD reactor are optimized by manipulating the decision variables comprising Temperature of the substrate, Pressure of the reactor, Flow rate of inert gas, distance between precursor inlet to substrate, composition of precursors etc. The optimization configuration enables configuring of optimization models/optimizer specific to the CVD reactor. The optimizer may be configured after a predefined time interval, when the key performance parameters of the CVD reactor cross the predefined thresholds, or by manual intervention. Configuration of the optimization problem involves choosing the type of optimization problem (single objective vs multi objective), direction of optimization (maximize or minimize), one or more objective functions, one or more constraints and their lower and upper limits, one or more manipulated variables and their lower and upper limits, and one or more groups of manipulated variables. Inputs for configuring the optimization model may be taken from the user via an user interface and the configured optimization models are stored in a model repository. The pre-configured configuration optimization problem associated with the deposition rate, and the uniformity index for which objective functions and constraint functions can be chosen from the plurality of key performance parameters of the CVD reactor. They can also be derived from or be a combination of the plurality of key performance parameters of the CVD reactor. A sample optimization problem for the CVD reactor is shared below: Optimization Configuration 1: ?Objective Function1: max???(Deposition rate)? Wherein, Constraints x^L