Output Of Simulation Model Research Articles

Groundwater contaminant source identification based on an ensemble learning search framework associated with an auto xgboost surrogate

Groundwater contaminant source identification (GCSI) is commonly accompanied by search process which tweaks the unknown contaminant source information to match the simulation model outputs with the measurements. When solving identification task, search accuracy and time cost have always been challenges that must be tackled. In the present study, a novel ensemble learning search framework associated with auto extreme gradient boosting tree (xgboost) was proposed to solve GCSI. In particular, auto xgboost was employed to reduce the calculation burden caused by repeatedly running simulation model. To promote search efficiency, boosting strategy (BOS) was employed to sequentially concatenate iterative ensemble smoother, differential evolution particle filter (DEPF), and swarm evolution algorithm. The identification results indicated that: 1. Auto xgboost could substitute a numerical simulation model with desired accuracy and expeditious running speed. 2. BOS could achieve better search accuracy, but with the sacrifice of infinitesimal calculated time cost, when compared with bagging strategy.

Development of a digital model and metamodel to improve the performance of an automated manufacturing line

Digitalization in manufacturing is the conversion of information into digital format, the integration of this digital data and technologies into the manufacturing process and the use of those technologies (eg: simulation) to change a business model to provide new revenue and value-producing opportunities. Digitalization may be seen as the increased generation, analysis, and use of data to improve the efficiency of the overall manufacturing system. Simulation in manufacturing is often applied in situations where conducting experiments on a real system is impossible or very difficult due to cost or time to carry out the experiment is too long. A key input to the simulation model of automated equipment is the acquisition of valid data in relation to cycle time and reliability of various workstations on this line. As a consequence of being able to simulate equipment processes and interact with this validated simulation model, both the understanding of how the production system will perform under varying reliability and cycle time conditions is achieved. The simulation model then enables the experimentation of ‘what if scenarios’ that can be tested easily, while also providing a valuable tool to inform the maintenance personnel what station reliabilities they need to target in order to sustain a high performing manufacturing line. Simulation metamodeling is an approach to line design which is of great interest to design engineers and research experts. However, its application in automated medical devices manufacturing line design has never been well explored. The author has adopted an open-source simulation tool (JaamSim) to develop a digital model of an automated medical devices manufacturing line in the Johnson & Johnson Vision Care (JJVC) manufacturing facility. This paper demonstrates with a high level of rigour, fidelity and overall system design/approach, how a digital model along with the use of a metamodel can be used for the development of an automated manufacturing line in the medical devices industry. The digital model and metamodel can be used by manufacturing engineering teams to perform scenario testing during the design and development phase of the line or as part of the continuous improvement stage when the line is in full operation. The overall average absolute error when comparing the simulation model outputs to the metamodel outputs was 0.87% was achieved with the metamodel for the actual industrial application used by the author.

Capability of HYDRUS wetland module to simulate flow and nitrogen removal processes in pilot-scale treatment peatlands under frost and no-frost conditions

The HYDRUS wetland module is widely used together with the biokinetic model CWM1 to simulate reactive transport of contaminants in constructed wetlands. However, this approach has not been used previously to simulate processes in peat-based wetlands operating in cold climates and treating mining-influenced water. In this study, the goal was to clarify changes in flow, transport, and nitrogen removal processes in cold climate treatment peatlands by assessing the performance of HYDRUS-CWM1. Flow and non-reactive transport of tracer, and reactive transport of ammonium, nitrite, and nitrate, in two pilot wetlands operated under controlled conditions representing frozen (winter) and frost-free (summer) periods were simulated. Model simulation outputs were compared against data obtained from the pilot wetlands and from a full-scale treatment peatland treating mining-influenced water in an Arctic region. Initial peaks in tracer concentration were simulated satisfactorily, but transformation and transport of nitrogen species in treatment peatlands, especially under partially frozen conditions, were modeled with only limited success. Limitations of the model and the assumptions made for the simulations have been discussed to highlight the challenges in modeling of treatment peatlands.

Learning Summary Statistics for Bayesian Inference with Autoencoders

For stochastic models with intractable likelihood functions, approximate Bayesian computation offers a way of approximating the true posterior through repeated comparisons of observations with simulated model outputs in terms of a small set of summary statistics. These statistics need to retain the information that is relevant for constraining the parameters but cancel out the noise. They can thus be seen as thermodynamic state variables, for general stochastic models. For many scientific applications, we need strictly more summary statistics than model parameters to reach a satisfactory approximation of the posterior. Therefore, we propose to use a latent representation of deep neural networks based on Autoencoders as summary statistics. To create an incentive for the encoder to encode all the parameter-related information but not the noise, we give the decoder access to explicit or implicit information on the noise that has been used to generate the training data. We validate the approach empirically on two types of stochastic models.

Investigating stable oxygen and carbon isotopic variability in speleothem records over the last millennium using multiple isotope-enabled climate models

Abstract. The incorporation of water isotopologues into the hydrology of general circulation models (GCMs) facilitates the comparison between modeled and measured proxy data in paleoclimate archives. However, the variability and drivers of measured and modeled water isotopologues, as well as the diversity of their representation in different models, are not well constrained. Improving our understanding of this variability in past and present climates will help to better constrain future climate change projections and decrease their range of uncertainty. Speleothems are a precisely datable terrestrial paleoclimate archives and provide well-preserved (semi-)continuous multivariate isotope time series in the lower latitudes and mid-latitudes and are therefore well suited to assess climate and isotope variability on decadal and longer timescales. However, the relationships of speleothem oxygen and carbon isotopes to climate variables are influenced by site-specific parameters, and their comparison to GCMs is not always straightforward. Here we compare speleothem oxygen and carbon isotopic signatures from the Speleothem Isotopes Synthesis and Analysis database version 2 (SISALv2) to the output of five different water-isotope-enabled GCMs (ECHAM5-wiso, GISS-E2-R, iCESM, iHadCM3, and isoGSM) over the last millennium (850–1850 CE). We systematically evaluate differences and commonalities between the standardized model simulation outputs. The goal is to distinguish climatic drivers of variability for modeled isotopes and compare them to those of measured isotopes. We find strong regional differences in the oxygen isotope signatures between models that can partly be attributed to differences in modeled surface temperature. At low latitudes, precipitation amount is the dominant driver for stable water isotope variability; however, at cave locations the agreement between modeled temperature variability is higher than for precipitation variability. While modeled isotopic signatures at cave locations exhibited extreme events coinciding with changes in volcanic and solar forcing, such fingerprints are not apparent in the speleothem isotopes. This may be attributed to the lower temporal resolution of speleothem records compared to the events that are to be detected. Using spectral analysis, we can show that all models underestimate decadal and longer variability compared to speleothems (albeit to varying extents). We found that no model excels in all analyzed comparisons, although some perform better than the others in either mean or variability. Therefore, we advise a multi-model approach whenever comparing proxy data to modeled data. Considering karst and cave internal processes, e.g., through isotope-enabled karst models, may alter the variability in speleothem isotopes and play an important role in determining the most appropriate model. By exploring new ways of analyzing the relationship between the oxygen and carbon isotopes, their variability, and co-variability across timescales, we provide methods that may serve as a baseline for future studies with different models using, e.g., different isotopes, different climate archives, or different time periods.

Numerical modeling: the effect of land subsidence on hydrodynamic conditions and coastal morphology in Pekalongan

This study examines the effect of land subsidence on hydrodynamic conditions and coastal morphology through numerical modeling using MIKE21 with 30-day simulation time. Land subsidence is assumed to be 10 cm/year, which affects bathymetry. There are 2 modeling scenarios, scenario 1 before (2016) and scenario 2 after land subsidence (2021). River discharge is assumed to be constant at 10 m3/s. The model calibration result on water level elevation and current velocity of the model simulation output and field data comparison based on the variation of Chezy Number, the smallest error was obtained at Chezy Number 50 m0.5/s. The sediment transport model sensitivity test was conducted on parameters of model type, sediment grain size, and river discharge. The result of sensitivity test demonstrated that the sediment grain size is the most sensitive parameter. By comparing the two model scenario results show that the current velocity in scenario 1 is greater than scenario 2 by 20%, significant wave height in scenario 1 is smaller than scenario 2 up to 0.1 m, and sedimentation in Mangrove Park increases up to ± 0.01m. Land subsidence reduces the current velocity, increases the significant wave height and sedimentation.

Prognostication of scour around twin and three piers using efficient outlier robust extreme learning machine.

One of the most essential difficulties in the design and management of bridge piers is the estimation and modeling of scouring around the piers. The scour depth downstream of twin and three piers were simulated using a new outlier robust extreme learning machine (ORELM) model in this study. Furthermore, k-fold cross-validation with k = 4 was employed to validate the outcomes of numerical models. Four ORELM models with effective scouring parameters were first created to simulate scour depth. After then, the number of hidden layer neurons increased from two to thirty. The number of ideal hidden neurons was determined by examining the modeling results. The sigmoid activation function was also introduced as the best function. Furthermore, a sensitivity analysis was used to identify the superior model. The best model predicted scour depth as a function of the Froude number (Fr), the pier diameter to flow depth ratio (D/h), and the distance between the piers to flow depth ratio (d/h). The values of the objective function were accurately approximated by this model. As a result, using the ORELM model, the R2, scatter index, and Nash-Sutcliffe efficiency coefficient were calculated to be 0.953, 0.146, and 0.949, respectively. The most efficient parameters for simulating the scour depth were Fr and D/h, according to the modeling results. It is worth noting that nearly half of the superior model's simulated outputs had an inaccuracy of less than 10%. The superior model's performance has been underestimated, according to uncertainty analysis. After that, a simple and practical equation for calculating the scour depth was established for the superior model. Additionally, the influence of each input parameter on the objective function was assessed using a partial derivative sensitivity analysis.

Impact of coastal upwelling dynamics on the pCO2 variability in the southeastern Arabian Sea

The southeastern Arabian Sea (SEAS) experiences moderate to weak upwelling along the southwest coast of India during the southwest monsoon (SM). The coastal upwelling initiates from mid-May along the southern-most tip of India, and with the advancement of SM, it propagates towards the northern latitude. This study examines the impact of coastal upwelling dynamics on the spatio-temporal variability of pCO2 in SEAS. It aims to identify the factors controlling the variability of pCO2 using high-resolution, regional ocean-ecosystem model-simulated outputs while available in situ and ship-based observations are used to establish the capability of the model. The cold deeper water that rises to the surface during upwelling decreases surface ocean pCO2 by 50 ± 2.4 µatm, whereas the presence of carbon-rich upwelling waters to a significantly shallower depth increases pCO2 by 52 ± 1.5 µatm of SEAS during SM. The salinity component increases surface ocean pCO2 by 2.0 ± 1.6 µatm. It has relatively less impact when compared with the individual effects of temperature and dissolved inorganic carbon components in controlling surface ocean pCO2 variability. The biological activities are profound only in the southern part of SEAS where biology-driven changes decrease surface ocean pCO2 by 4.0 ± 0.4 µatm during SM. The total biology-driven changes consist of both soft and hard tissues decrease the pCO2 level of SEAS by 2.0 ± 0.2 µatm during SM. Therefore, the upwelling-driven physical dynamics dominate the biological processes in controlling the spatio-temporal variability of surface ocean pCO2 in SEAS during SM, which contrasts the physical-biological dynamics of the sea east of Sri Lanka, where the biological processes dominate over physical dynamics in controlling surface ocean pCO2 variability.

Drivers and physical processes of drought events over the State of São Paulo, Brazil

The State of São Paulo, Brazil (SSP) was impacted by severe water shortages during the intense austral summer drought of 2013/2014 and 2014/2015 (1415SD). This study seeks to understand the features and physical processes associated with these summer droughts in the context of other droughts over the region during 1961–2010. Thus, this study examines the spatio-temporal characteristics of anomalously low precipitation over SSP and the associated large-scale dynamics at seasonal timescales, using an observation-based dataset from the Climatic Research Unit (CRU) and model simulation outputs from the Met Office Hadley Centre Global Environment Model (HadGEM3-GA6 at N216 resolution). The study analyzes Historical and Natural simulations from the model to examine the role of human-induced climate forcing on droughts over SSP. Composites of large-scale fields associated with droughts are derived from ERA-20C and ERA-Interim reanalysis and the model simulations. HadGEM3-GA6 simulations capture the observed interannual variability of normalized precipitation anomalies over SSP, but with biases. Drought events over SSP are related to subsidence over the region. This is associated with reduced atmospheric moisture over the region as indicated by the analysis of the vertically integrated moisture flux convergence, which is dominated by reduced moisture flux convergence. The Historical simulations simulate the subsidence associated with droughts, but there are magnitude and location biases. The similarities between the circulation features of the severe 1415SD and other drought events over the region show that understanding of the dynamics of the past drought events over SSP could guide assessment of changes in risk of future droughts and improvements of model performance. The study highlights the merits and limitations of the HadGEM3-GA6 simulations. The model possesses the skills in simulating the large-scale atmospheric circulations modulating precipitation variability, leading to drought conditions over SSP.

A dependent multimodel approach to climate prediction with Gaussian processes

AbstractSimulations of future climate contain variability arising from a number of sources, including internal stochasticity and external forcings. However, to the best of our abilities climate models and the true observed climate depend on the same underlying physical processes. In this paper, we simultaneously study the outputs of multiple climate simulation models and observed data, and we seek to leverage their mean structure as well as interdependencies that may reflect the climate’s response to shared forcings. Bayesian modeling provides a fruitful ground for the nuanced combination of multiple climate simulations. We introduce one such approach whereby a Gaussian process is used to represent a mean function common to all simulated and observed climates. Dependent random effects encode possible information contained within and between the plurality of climate model outputs and observed climate data. We propose an empirical Bayes approach to analyze such models in a computationally efficient way. This methodology is amenable to the CMIP6 model ensemble, and we demonstrate its efficacy at forecasting global average near-surface air temperature. Results suggest that this model and the extensions it engenders may provide value to climate prediction and uncertainty quantification.

Information and material delays effect on price setting, operating contribution margins and cash conversion cycles in feed ingredients supply chain

PurposeThe purpose of this report was to evaluate the effectiveness and practicality of system dynamics modeling in integrating econometric equations to describe the effects of supply chain material and information delays on pricing decisions and consequent financial results in an animal feed export business.Design/methodology/approachAn empirical dynamic model, loaded with econometric theory of price effect on competitive demand, was used to describe the input data.FindingsThe model simulation outputs proved themselves relevant in analyzing the complex interconnections of multiple variables affecting the profitability in a commercial routine, supporting the decision process among sales managers. The impact of information delay on price decisions and business financial results were estimated using the model proposed.Originality/valueThis paper describes an empirical model, based on system dynamics, that predicts operating contribution margins and cash conversion cycles based on estimation of information and material delays in a supply chain. The method is pragmatic and simple for business routine implementation.

Gaussian Process Model-Based Performance Uncertainty Quantification of a Typical Turboshaft Engine

The gas turbine engine is a widely used thermodynamic system for aircraft. The demand for quantifying the uncertainty of engine performance is increasing due to the expectation of reliable engine performance design. In this paper, a fast, accurate, and robust uncertainty quantification method is proposed to investigate the impact of component performance uncertainty on the performance of a classical turboshaft engine. The Gaussian process model is firstly utilized to accurately approximate the relationships between inputs and outputs of the engine performance simulation model. Latin hypercube sampling is subsequently employed to perform uncertainty analysis of the engine performance. The accuracy, robustness, and convergence rate of the proposed method are validated by comparing with the Monte Carlo sampling method. Two main scenarios are investigated, where uncertain parameters are considered to be mutually independent and partially correlated, respectively. Finally, the variance-based sensitivity analysis is used to determine the main contributors to the engine performance uncertainty. Both approximation and sampling errors are explained in the uncertainty quantification to give more accurate results. The final results yield new insights about the engine performance uncertainty and the important component performance parameters.

Return of the Apex Predator — How Brown Trout (Salmo trutta) Re-Establishment Shapes an Ecosystem

Re-establishment of a declined apex predator fish species in a lake ecosystem may have dramatic effects on other fish and plankton community already inhabiting the ecosystem. We studied mechanistically potential impacts of re-establishment of the brown trout (Salmo trutta) in the west-central European Lake Constance focusing on two commercially important fish species: whitefish and Eurasian perch. We compared simulation model outputs from two versions of an allometric trophic network model for Lake Constance, one with and one without the trout as the apex predator. The re-establishment of the declined brown trout reduced the perch population directly by predation and indirectly by increased resource competition, whereas the whitefish population was directly affected by increased predation. The decrease in fish biomass densities was highly sensitive to trout larval survivability. Both species showed strong compensatory behaviour by achieving higher per capita resource consumption when the populations decreased in the presence of brown trout.

Physics-Aware Deep-Learning-Based Proxy Reservoir Simulation Model Equipped With State and Well Output Prediction

Data-driven methods have been revolutionizing the way physicists and engineers handle complex and challenging problems even when the physics is not fully understood. However, these models very often lack interpretability. Physics-aware machine learning (ML) techniques have been used to endow proxy models with features closely related to the ones encountered in nature; examples span from material balance to conservation laws. In this study, we proposed a hybrid-based approach that incorporates physical constraints (physics-based) and yet is driven by input/output data (data-driven), leading to fast, reliable, and interpretable reservoir simulation models. To this end, we built on a recently developed deep learning–based reduced-order modeling framework by adding a new step related to information on the input–output behavior (e.g., well rates) of the reservoir and not only the states (e.g., pressure and saturation) matching. A deep-neural network (DNN) architecture is used to predict the state variables evolution after training an autoencoder coupled with a control system approach (Embed to Control—E2C) along with the addition of some physical components (loss functions) to the neural network training procedure. Here, we extend this idea by adding the simulation model output, for example, well bottom-hole pressure and well flow rates, as data to be used in the training procedure. Additionally, we introduce a new architecture to the E2C transition model by adding a new neural network component to handle the connections between state variables and model outputs. By doing this, it is possible to estimate the evolution in time of both the state and output variables simultaneously. Such a non-intrusive data-driven method does not need to have access to the reservoir simulation internal structure, so it can be easily applied to commercial reservoir simulators. The proposed method is applied to an oil–water model with heterogeneous permeability, including four injectors and five producer wells. We used 300 sampled well control sets to train the autoencoder and another set to validate the obtained autoencoder parameters. We show our proxy’s accuracy and robustness by running two different neural network architectures (propositions 2 and 3), and we compare our results with the original E2C framework developed for reservoir simulation.

Groundwater contamination sources identification based on the Long-Short Term Memory network

When simulation–optimization (S/O) is used for groundwater contamination source identification (GCSI), to reduce the calculation load and time generated by calling the simulation model, a surrogate model is often used instead of the simulation model. However, when the conversion relationship between the simulation model inputs and outputs is complex and the model is highly nonlinear, the commonly used approach of building a surrogate model may lose its advantage. This study use and check a deep learning method with the long-short term memory (LSTM) network which has great potential for characterizing the input–output conversion relationship of complex nonlinear numerical simulations, to a surrogate model of the simulation model. The accuracy of the surrogate model developed by the LSTM method was compared with that of commonly used surrogate models developed by the Kriging method, the radial basis function network method, and the kernel extreme learning machine method. The surrogate model with the highest accuracy was linked to the optimization model, and the optimization model was solved to identify the contamination source information. Results show that compared with the other three methods, the surrogate model constructed by the LSTM method had the best accuracy and generalization performance. LSTM is therefore an effective method of building a surrogate model. Linking the LSTM surrogate model to an optimization model and then solving the optimization model can save approximately 99% of the computing load and time otherwise required.

Large-Eddy Simulation of Plume Dispersion in the Central District of Oklahoma City by Coupling with a Mesoscale Meteorological Simulation Model and Observation

Contaminant gas dispersion within an urban area resulting from accidental or intentional release is of great concern to public health and social security. When estimating plume dispersion in a built-up urban area under real meteorological conditions by computational fluid dynamics (CFD), a crucial issue is how to prescribe the input conditions. There are typically two approaches: using the outputs of a mesoscale meteorological simulation (MMS) model and meteorological observations (OBS). However, the influences of the different approaches on the simulation results have not been fully demonstrated. In this study, we conducted large-eddy simulations (LESs) of plume dispersion in the urban central district of Oklahoma City under real meteorological conditions by coupling with a MMS model and OBS obtained at a single stationary point, and evaluated the two different coupling simulations in comparison with the field experiments. The LES–MMS coupling showed better performance than the LES–OBS one. The latter one also showed a reasonable performance comparable to the acceptance criteria on the model prediction within a factor of two of the experimental data. These facts indicate that the approach using observations at a single stationary point still has enough potential to drive CFD models for plume dispersion under real meteorological conditions.

ASSESSING THE SIMILARITIES OF 3D SIMULATION MODEL OUTCOMES

Abstract. The recent advancement of simulation modeling to represent phenomena in three spatial dimensions (3D) requires the development of techniques that will allow comparison of the modeling outputs in multiple dimensions. However, many existing techniques for map comparison in two spatial dimensions (2D) have been developed from non-spatial method such Cohen’s Kappa. These techniques are not yet fully extended to deal with 3D map data or simulation outcomes. Therefore, the main objective of this study is to investigate the use of the 3D Accuracy and 3D Cohen’s Kappa coefficients to compare simulation model outputs in 3D. An existing agent-based model (ABM) of forest-fire smoke propagation was used to generate multiple scenarios for the purpose of comparing 3D simulation outputs. The results for 3D Accuracy and 3D Cohen’s Kappa produces meaningful values when comparing several scenarios with different 3D ABM outputs. This study emphasizes the need for the development of more advanced simulation output comparison techniques that operate in 3D and potentially over time (4D).

Hybrid homotopy-PSO global searching approach with multi-kernel extreme learning machine for efficient source identification of DNAPL-polluted aquifer

Groundwater pollution source identification (GPSI), which is critical for taking effective measures to protect groundwater resources, assess risks, and design remediation strategies, typically involves the solution of a nonlinear and ill-posed inverse problem. Regarding the inversion of dense non-aqueous phase liquid (DNAPL) sources, the special characteristics of pollutants render related research more complex. In the present study, homotopy-based optimization inverse theory and multi-kernel extreme learning machine (MK-ELM) were combined for efficiently solving GPSI problem while estimating aquifer parameters at a DNAPL-polluted site. The extreme learning machine incorporating multi kernels and whose parameters are obtained by means of a genetic algorithm (GA) was embedded in an optimization model for GPSI to replace the multiphase flow simulation model and to mitigate the considerable computational burdens of inversion iteration. The hybrid homotopy-particle swarm optimization (PSO) algorithm was constructed as a more efficient method for segmentally searching the global optimum in wide areas with low dependence on initial values. Results showed that the application of GA-based MK-ELM and hybrid homotopy-PSO effectively accomplish the simultaneous identification of source characteristics and aquifer parameters. The MK-ELM approximate the outputs of multiphase flow simulation model sufficiently with the certainty coefficient (R2) increased to 0.9982, whereas the mean relative error was limited to 1.5168%. Compared to the widely used PSO algorithm, the hybrid homotopy-PSO algorithm significantly reduced the mean relative error of identification results from 6.77% to 2.89%.

Application of artificial intelligence deep learning in numerical simulation of seawater intrusion.

Seawater intrusion not only causes fresh water shortages in coastal areas, but also has a negative impact on regional economic and social development. Global climate change will affect precipitation, sea level, and many other factors, which will in turn affect the simulation and prediction results for seawater intrusion. By combining groundwater numerical simulation technology, an atmospheric circulation model, artificial intelligence methods, and simulation optimization methods, this study coupled a numerical simulation model of seawater intrusion with an optimization model to optimize the groundwater exploitation scheme in the study area under the condition of climate change. As a result, a groundwater exploitation scheme was obtained for a typical study area, which provided a scientific basis and a reference for the rational development of effective groundwater resource solutions. The results of this study can be described as follows. (1) By introducing the theory and method of deep learning from artificial intelligence, the problem of complex nonlinear mapping between the inputs and outputs of a three-dimensional variable-density seawater intrusion numerical simulation model under the condition of limited number of training samples is effectively solved, and the approximation accuracy of the surrogate model with respect to the simulation model is improved. (2) By solving the optimization model, a reasonable groundwater exploitation scheme was obtained, which provided a scientific basis for the rational development and efficient use of groundwater resources in the study area.

Spatio‐temporal variability of summer monsoon surface air temperature over India and its regions using Regional Climate Model

AbstractIn this study, a dynamically downscaled regional climate model (RegCM4.3) is used to study the Indian summer monsoon (ISM) surface air temperature over the South‐Asia CORDEX domain using six convection schemes during 1986–2010. The spatial and temporal variability of mean surface air temperature has been analysed with reference to the India Meteorological Department (IMD) analysis data using various statistical scores. The sensitivity experiments in selecting the best convective parameterized schemes have been performed in simulating the surface air temperature during the summer monsoon season (June–September) over India and its five sub‐regions such as Northwest India, Northcentral India, West Peninsular India, Eastern Peninsular India, and Southern Peninsular India. The model results show the tendency of overestimation of surface air temperature mainly in four cumulus parameterization schemes (CPSs) that is, Tiedtke, Emanuel, Mix98, and Mix99 of RegCM4.3 during the JJAS, where Grell and Kuo CPSs show better agreement with the IMD data. Overall, Grell CPS has a close resemblance to the observation data with a minimum root mean square error, mean absolute error, lowest mean absolute percentage error (MAPE), and higher correlation coefficient. The model simulated results have also been investigated further using modified Nash Sutcliffe efficiency and modified Willmott's degree of index. These analyses confirm the potentiality of the Grell CPS followed by the Kuo CPS in simulating interannual variability of the surface air temperature over Indian and its five sub‐regions. The MAPE in Grell and Kuo CPSs are 0.004 and 0.013°C during monsoon season over India, respectively. The inter‐scheme difference in simulating surface air temperature is linked with the generation of low cloud convection and warming‐induced atmospheric moisture advection in the schemes. Therefore, Emanuel, Tiedtke, and Mix98 CPSs have shown a persistent nature of overestimation in surface air temperature variability during JJAS. It is also inferred that after removing the systematic mean bias from the RegCM4.3 model simulated outputs; the skill of Emanuel, Mix98, and Mix99 could be useful over the Indian subcontinent except for the southern peninsular region.