First-principles Model Research Articles

Impact of developmental temperature on neural growth, connectivity, and function.

Environmental temperature dictates the developmental pace of poikilothermic animals. In Drosophila, slower development at lower temperatures results in higher brain connectivity, but the generality of such scaling across temperatures and brain regions and its impact on function are unclear. Here, we show that brain connectivity scales continuously across temperatures, in agreement with a first-principle model that postulates different metabolic constraints for the growth of the brain and the organism. The model predicts brain wiring under temperature cycles and the nonuniform temporal scaling of neural development across temperatures. Developmental temperature has notable effects on odor-driven behavior. Dissecting the circuit architecture and function of neurons in the olfactory pathway, we demonstrate that developmental temperature does not alter odor encoding in first- and second-order neurons, but it shifts the specificity of connections onto third-order neurons that mediate innate behaviors. We conclude that while some circuit computations are robust to the effects of developmental temperature on wiring, others exhibit phenotypic plasticity with possible adaptive advantages.

Umbrella Sampling MD Simulations for Retention Prediction in Peptide Reversed-phase Liquid Chromatography.

Reversed-phase liquid chromatography (RPLC) is an essential tool for separating complex mixtures such as proteolytic digests in bottom-up proteomics. There is growing interest in methods that can predict the RPLC retention behavior of peptides and other analytes. Already, existing algorithms provide excellent performance based on empirical rules or large sets of RPLC training data. Here we explored a new type of retention prediction strategy that relies on first-principles modeling of peptide interactions with a C18 stationary phase. We recently demonstrated that molecular dynamics (MD) simulations can provide atomistic insights into the behavior of peptides under RPLC conditions (Anal. Chem. 2023, 95, 3892). However, the current work found that it is problematic to use conventional MD data for retention prediction, evident from a poor correlation between experimental retention times and MD-generated "fraction bound" values. We thus turned to umbrella sampling MD, a complementary technique that has previously been applied to probe noncovalent contacts in other types of systems. By restraining the peptide dynamic motions at various positions inside a C18-lined pore, we determined the free energy of the system as a function of peptide-stationary phase distance. ΔGbinding values determined in this way under various mobile phase conditions were linearly correlated with experimental retention times of tryptic test peptides. This work opens retention prediction avenues for novel types of stationary and mobile phases, and for peptides (or other analytes) having arbitrary chemical properties, without the need for RPLC reference data. Umbrella sampling can be used as a stand-alone tool, or it may serve to enhance existing retention prediction algorithms.

Norm-Conserving 5f-in-Core Pseudopotentials and Gaussian Basis Sets Optimized for Tri- and Tetra-Valent Actinides (An = Pa-Lr).

Relativistic pseudopotentials (PPs) and basis sets are the workhorses for modeling heavy elements of lanthanides and actinides. The norm-conserving Goedecker-Teter-Hutter (GTH) PP is advantageous for modeling lanthanide and actinide compounds and condensed systems because of its transferability and accuracy. In this work, we develop a set of well-benchmarked GTH-type 5f-in-core PPs with scalar-relativistic effects together with associated Gaussian basis sets for the most commonly encountered trivalent and tetravalent actinides [An(III), An(IV); An = Pa-Lr]. The 5f-in-core GTH PPs are constructed by placing 5f-subconfiguration 5fn of An(III) and 5fn-1 of An(IV) (n = 2-14) into the atomic core in the core-valence separation. The formalism of 5f-in-core GTH PPs circumvents the computational difficulty arising from the 5f open valence shell. The different performances of 5f-in-core GTH PPs for trivalent and tetravalent actinides are further analyzed from the chemical bonding features of actinides. We anticipate that the optimized 5f-in-core GTH PPs and Gaussian basis sets can be used to accelerate the costly first-principles modeling of structure-complicated actinide compounds and condensed-phase actinide systems.

Integration of Neural Networks and First-Principles Model for Optimizing l-Lactide Branched Polymerization.

Addressing the growing demand for sustainable materials, this research paves the way for the efficient consumption and sustainable production of branched polylactide (PLA). A novel hybrid modeling approach combines first-principles (FP) model with artificial neural network (ANN) for ring-opening polymerization (ROP). The hybrid ANN, trained with FP model data, demonstrated optimal performance with a hidden layer of 20 neurons, achieving a root mean square error (RMSE) of 0.004 and a regression coefficient (R2) of 0.99. The hybrid model accurately predicted key polymer properties, including average molecular weights (Mn and Mw), polydispersity index (PDI), degree of branching (DB), monomer conversion, and polymerization time. Validation was performed on various branched PLA compositions (PLLH80, PLLH94, and PLLH97). Multiobjective optimization (MOO) using NSGA-II showed strong agreement between FP model and hybrid ANN across six case studies, highlighting their effectiveness in predicting polymerization outcomes.

Investigation of ideal shear strength of dilute binary and ternary Ni-based alloys using first-principles calculations, CALPHAD modeling and correlation analysis

Investigation of ideal shear strength of dilute binary and ternary Ni-based alloys using first-principles calculations, CALPHAD modeling and correlation analysis

Menthol-Induced Chirality in Semiconductor Nanostructures: Chiroptical Properties of Atomically Thin 2D CdSe Nanoplatelets Capped with Enantiomeric L-(-)/D-(+)-Menthyl Thioglycolates.

Semiconductor colloidal nanostructures capped with chiral organic molecules are a research hotspot due to their wide range of important implications for photonic and spintronic applications. However, to date, the study of chiral ligands has been limited almost exclusively to naturally occurring chiral amino and hydroxy acids, which typically contain only one stereocenter. Here, we show the pronounced induction of chirality in atomically thin CdSe nanoplatelets (NPLs) by capping them with enantiopure menthol derivatives as multi-stereocenter molecules. L-(-)/D-(+)-menthyl thioglycolate, easily synthesized from L-(-)/D-(+)-menthol, is attached to Cd-rich (001) basal planes of 2- and 3-monolayer (ML) CdSe NPLs. We show the appearance of narrow sign-alternating bands in the circular dichroism (CD) spectra of 2 ML NPLs corresponding to heavy-hole (HH) and light-hole (LH) excitons with maximal dissymmetry g-factor up to 2.5 × 10-4. The most intense CD bands correspond to the lower-energy HH exciton, and in comparison with the N-acetyl-L-Cysteine ligand, the CD bands for L-(-)-menthyl thioglycolate have the opposite sign. The CD measurements are complemented with magnetic CD measurements and first-principles modeling. The obtained results may be of interest for designing new chiral semiconductor nanostructures and improving understanding of their chiroptical properties.

Carbon Nanomaterial Enabled Ultra High Conductivity Cu Composites for Advanced Conductors

Growing demand for electrical energy and increasing need for high power grid systems necessitates development of new conductors for enhanced electrical and thermal conductivity. The power losses associated with the electrical resistance of Cu adversely impact the efficiency and performance of all electric devices. Ballistic electrical transport in carbon nanotubes (CNTs) is expected to improve the conductivity of the Cu matrix with additional CNT-enabled benefits that can enable low-weight, flexibility, and better thermal management. By using scalable, cost-effective, and commercially viable processing methods, we demonstrate a novel technological platform to produce high-performance conductors that incorporates CNTs into the Cu matrix ― ultra-conductive metal composites (UCC), which promise significant technological and economic impact in all energy sectors, ranging from electrical vehicles to power grid. Our approach, which combines materials synthesis, characterization, and first-principles modeling, enables an efficient and systematic exploration of the multidimensional complex materials parameter space of Cu-CNT composites with dopants and identifies the key individual structural and interfacial components that govern the electronic transport properties of the UCC composites. Our experimental technology platform is concentrated on Cu tapes and involves processes from production of stable CNT dispersions, electrospinning techniques to deposit shear induced aligned CNT coatings along the direction of the current flow, post thermal treatment procedures, and homogeneous deposition of metal overlayers onto CNT coated tapes. Here, we demonstrate that the prototype UCC composites exhibit improved electrical conductivity (by > 5%), higher current carrying capacity (> 10%), and higher mechanical strength (> 10%) than the reference pure Cu counterparts.

Field-Driven Reactivity and Adsorbate Reorientation on Electrode Surfaces

Electric fields affect interfacial structure and reactivity during electrochemical reactions. First-principles modeling can be used to elucidate the electrostatic potential profiles at the electrode–electrolyte interface, where these potentials can be highly inhomogeneous due to the presence of electrolyte ions and molecular adsorbates. In this presentation, periodic density functional theory (DFT) calculations are used to understand field-driven proton-coupled electron transfer reactivity and adsorbate reorientation at heterogeneous electrochemical interfaces. These calculations show that field-driven protonation of graphite-conjugated organic acids is enabled by continuous electronic conjugation between solid carbon electrodes and molecular surface sites. The redox potentials for proton-coupled electron transfer in these systems are predicted computationally, showing close agreement with experimental voltammetry measurements. Constant-potential DFT calculations are also used to understand the adsorption structure of L-cysteine on Au(111) electrode surfaces. Using a classical electrolyte model, these calculations elucidate the interactions between the cysteine adsorbate, the electrode surface, and the electrolyte ions at different applied potentials. These studies shed light on the effects of interfacial electric fields on electrochemical reactivity and adsorption geometries at solid–liquid electrochemical interfaces.

Interpretation of PEMFC Impedance Response Using Continuum Modeling

The proton-exchange-membrane fuel cell (PEMFC) is an energy conversion technology developed to assist in the decarbonization of our energy infrastructure. Oxygen and hydrogen are electrochemically reacted to produce electricity, which can be used to power industrial processes like transportation and manufacturing. For hydrogen viability in heavy-duty transportation applications, PEMFC stacks are required to operate over long times scales, which prompts the development of more durable PEMFCs. Improving the durability of PEMFCs relies on understanding process variables and parameters that cause degradation and performance loss. A common diagnostic tool for electrochemical characterization is electrochemical impedance spectroscopy (EIS), where the current—potential relationship of an electrochemical cell is probed using sinusoidal perturbations, which yields the transfer function known as impedance.Due to the complex physics and chemistry occurring within a PEMFC, meaningful interpretation of impedance spectra is often challenging and relies on assumed equivalent-circuit models. The objective of this work is the development of mathematical continuum first-principle cell-level models capable of providing insight on the relationship between cell properties and measured impedance spectra. The mathematical model is based on a non-isothermal multi-scale continuum model of a PEMFC that accounts for multi-phase transport, where the impedance response is simulated about a steady-state operational mode.The mathematical model was used to simulate experimental measurements obtained from accelerated-stress tests on a commercially available PEMFC membrane-electrode assembly, as shown in Figure 1. Kinetic parameters obtained from a single EIS measurement were generalized to estimate overall cell performance, which was in good agreement with experimental polarization curves. The mathematical model represents the development of descriptive diagnostic tools capable of providing insights into the underlying governing physics and chemistry. Acknowledgements This research is supported by DOE Hydrogen and Fuel Cell Technologies Office, through the Million Mile Fuel Cell Truck (M2FCT) Consortia. Figure 1

(Invited) First-Principles Modeling of Degradation Mechanisms of the NaO2 Discharge Product in Na-O2 Battery Cells

The current climate crisis necessitates the development of improved electrochemical storage devices, such as aprotic alkali metal-O2 batteries (Li/Na-O2), which have greater than threefold higher thermodynamic gravimetric energy densities than Li-ion batteries. With a greater elemental abundance of sodium and low observed overpotential losses, Na-O2 batteries have become a focus of research interest. However, despite recent efforts, poor cell stability continues to plague Na-O2 cells, inhibiting commercial viability. A contributing factor to the poor cell stability is a degradation of the desired NaO2 discharge product at the cathode, resulting from undesirable interactions with the organic cell electrolyte under periods of cell idling where there is no charge transfer between the two electrodes. These undesirable interactions are hypothesized to degrade the NaO2 discharge product through two main pathways: (i) chemical transformation to hydrated sodium-oxygen species resulting from a chemical reaction with the electrolyte molecules and (ii) deleterious dissolution into the electrolyte. Thus far, practical solutions to improve stability have remained elusive, but elucidating molecular-level mechanistic details of these deleterious processes, using combined theory-driven and experimental approaches, could accelerate the discovery of practical design changes to overcome these stability bottlenecks.The goal of the present work is to couple computational and experimental studies to elucidate key molecular-level mechanistic insights of the undesirable interactions between the cell electrolyte and the surface of the NaO2 discharge product. We utilize periodic Density Functional Theory (DFT) calculations and ab initio molecular dynamics (AIMD) simulations to probe the two main NaO2 discharge product degradation mechanisms. To model the surface of the NaO2 discharge product, which in the case of high donor number electrolytes is deposited in a cubic confirmation, the cube faces and edges are represented as terrace and step facets, respectively, to capture the fact the undercoordinated cube edges could exhibit a different surface chemistry than the relatively pristine cube faces. At these two surface terminations, we elucidate the energetics that govern the degradation mechanisms of the NaO2 discharge product under cell idling conditions, as described below.To probe the chemical transformation of the NaO2 discharge product towards hydrated sodium-oxygen products, we elucidate the energetics of hydrogen abstractions from the electrolyte molecules to the NaO2 surface. With regards to the hydrogen coverage on the NaO2 surface, we find that there exists a plateau in the abstraction thermodynamics for the uptake of hydrogen, and at high coverages, the terrace NaO2 surface undergoes a series of favorable surface reconstructions towards sodium hydroxide species. Interestingly, we find that the free energy of activation for hydrogen abstraction from the electrolyte is not strongly influenced by the surface termination (terrace vs. step), as one would typically expect based on coordination number arguments. For the study of the deleterious dissolution of the NaO2 discharge product, we elucidate the energetics of elementary material loss mechanisms from the surface. We find that it is thermodynamically favorable for the surface to dissolute as individual NaO2 units, maintaining the NaO2 stoichiometry of the surface, with the thermodynamic surface penalty to undergo dissolution for the step facet being approximately ½ of the penalty for the pristine terrace facet. Further, we find the free energy of activation for dissolution of the step facet to be approximately ½ of the energy barrier of the terrace facet, suggesting that, unlike in the hydrogen abstraction process, the NaO2 cube edges drive the undesirable dissolution during idling. In closing, we comment how the current work lays the groundwork for future combined computational-experimental studies and how they may be used to propose practical design changes.

Development of hybrid first principles – Artificial intelligence models for transient modeling of power plant superheaters under load-following operation

This paper develops different approaches for synergistic integration of physics-based models with data-driven models for modeling of high temperature power plant superheaters. Two types of data-driven models are developed, namely all-nonlinear static-dynamic neural network models as well as models obtained using a Bayesian machine learning approach. Series, integrated, and parallel coupling of first-principles models and data-driven models are proposed. Algorithms for solving the training problems for the data-driven models and for simulation of the hybrid models are developed. The developed approach is applied to high temperature power plant superheaters that face considerable modeling and measurement challenges. Measurement challenges arise due to harsh operating conditions that not only make placement of sensors difficult, but life of the placed sensors very limited. Modeling challenges arise due to complex inhomogeneous spatial distribution of flue gas and steam flowrates, especially under load-following operation and uncertainties in heat transfer characteristics because of multiple factors such as stochastic spatio-temporal variation of ash deposits on the superheater tubes in coal-fired power plants, internal oxide scale formation in the tubes, etc. First-principles two-dimensional differential–algebraic equation models of two industrial superheaters, one from a natural gas combined cycle plant and another from a coal-fired power plant, are developed. The results from the models are compared against industrial operational data. For all cases studied in this work, it is observed that both for steady-state and dynamic data, the hybrid models have much higher accuracy than when only the respective first-principles models are used. For example, during prediction of the average outside tube wall temperature of superheater tubes at the combined cycle power plant, the root mean squared error observed for the standalone first-principles model improved from 12.3 °C to 0.5 °C post hybridization with data-driven models. Similarly, while predicting the main steam outlet temperature in the coal-fired plant, the hybrid models resulted in reduction of the root mean squared error value from 19.5 °C to around 2 °C. In addition, the hybrid models yield highly resolved spatio-temporal temperature profiles that can be helpful for developing monitoring approaches of these critical components under load-following operation.

Toward Implementation of the Pressure-regulated, Feedback-modulated Model of Star Formation in Cosmological Simulations: Methods and Application to TNG

Traditional star formation subgrid models implemented in cosmological galaxy formation simulations, such as that of V. Springel & L. Hernquist (hereafter SH03), employ adjustable parameters to satisfy constraints measured in the local Universe. In recent years, however, theory and spatially resolved simulations of the turbulent, multiphase, star-forming interstellar medium (ISM) have begun to produce new first-principles models, which when fully developed can replace traditional subgrid prescriptions. This approach has advantages of being physically motivated and predictive rather than empirically tuned, and allowing for varying environmental conditions rather than being tied to local-Universe conditions. As a prototype of this new approach, by combining calibrations from the TIGRESS numerical framework with the pressure-regulated feedback-modulated (PRFM) theory, simple formulae can be obtained for both the gas depletion time and an effective equation of state. Considering galaxies in TNG50, we compare the “native” simulation outputs with postprocessed predictions from PRFM. At TNG50 resolution, the total midplane pressure is nearly equal to the total ISM weight, indicating that galaxies in TNG50 are close to satisfying vertical equilibrium. The measured gas scale height is also close to theoretical equilibrium predictions. The slopes of the effective equations of states are similar, but with effective velocity dispersion normalization from SH03 slightly larger than that from current TIGRESS simulations. Because of this and the decrease in PRFM feedback yield at high pressure, the PRFM model predicts shorter gas depletion times than the SH03 model at high densities and redshift. Our results represent a first step toward implementing new, numerically calibrated subgrid algorithms in cosmological galaxy formation simulations.

Engineering Active Sites of Metal/Metal Oxide Catalysts by Oxide Ligand Overlayers.

Engineering sites of supported metal catalysts is essential to enhancing activity and selectivity. Such enhancement is typically achieved by particle size modification, surface alloying, or attaching molecular ligands. Yet, control strategies for complex, multifunctional molecules and catalysts, where selectivity is crucial, are lacking. Here, we demonstrate that submonolayer WOx with tunable coverage preferentially decorates well-coordinated Pt terrace sites as a stable ligand. By combining experimental kinetics with probe molecules, in situ spectroscopies, and first-principles modeling, we show that the WOx coverage on Pt modifies the metal-to-acid site balance while retaining the acid strength intact and results in optimal reactivity for metal-acid catalyzed reactions at a specific metal, size, and support-dependent WOx coverage. The oxide can also alter the reactant adsorption mode, reversing selectivity and pathways from terrace- to step-dominated, as evidenced in furfural decarbonylation and hydrogenation. The insights open avenues for improving metal/metal oxide catalysts beyond the specific system.

First-principles modeling of high-field transport in diamond

First-principles modeling of high-field transport in diamond

A hybrid predictive modeling approach for catalyzed polymerization reactors

Polymerization reactions are characterized by complex, nonlinear behaviors that pose significant challenges for conventional modeling techniques. Accurate and reliable models are crucial for advancing material science and enabling technological innovations across various industries. Conventional first-principles models often fall short in capturing the intricate dynamics of polymeric systems, leading to limitations in predictive accuracy. In this work, we propose a novel hybrid modeling approach that combines a conventional first-principles model with the strengths of a data-driven multi-layer perceptron (MLP) model and also a linear regression (LR) model to enhance the predictability of polymerization processes. Utilizing this hybrid approach significantly reduces the mean absolute error for predicting the concentrations of main reagents by 84% and 86%, respectively, in experiments with significantly deviant outcomes. Our results indicate that the model is capable of predicting the concentrations of both the main and side products with a maximum error margin of 3.5%.

Mathematical modeling and kinetics of batch and continuous electro-catalytic oxidation of pharmaceutical-contaminated wastewater

An accurate yet simple model is the key to the design and control of intricate electro-catalytic oxidation of pharmaceutical contaminated wastewater. For both batch and unsteady-state continuous flow stirred tank reactors (CSTR), batch reactor models have been used earlier. Further, these models do not correlate rate to the operating conditions, and consider pseudo-first/second-order kinetics. Here, first-principles models are proposed by formulating unsteady-state mass balances, modifying them to attain realistic final conditions, and incorporating fractional variable-order kinetics. Following integral analysis, analytical solutions are obtained. These are independently applicable to design, unlike a numerical solution. Nonlinear regression is performed to estimate the model parameters from the transient experimental data. The simulations yield markedly accurate model parameters together with a better fit to the experimental data of Ti/RuO2-mediated amoxicillin-trihydrate electro-oxidation, for CSTR and batch reactors. For the batch reactor, the operating conditions are varied one at a time. Their effects on the model parameters are elucidated based on the oxidant and transformation species formed. The computed optimum model parameters are: rate constant 3.318 × 10−3 mg−0.092 m1.276 min−1, order 1.092, initial rate 4.032 × 102 mg m−2 min−1, and final conversion 90.6% in 180 min. The corresponding operating conditions are: pH 2.0, feed 50 mg L−1, electrolyte 2 g L−1, and current 1 A. A simple generalized power-law correlation, associating rate to the operating conditions, is then estimated. Statistical analysis of these models using central composite design delivers R2 0.99, predicted R2 0.96, and optimum set close to the above. The corresponding sensitivity analysis and generalized correlation, both show applied current to be the most significant operating condition. The dynamic modeling approaches proposed here can be extended to model, control, and scale-up complex reaction systems.

First-principles modeling of electron-phonon scattering rates in graphene

Graphene, which has a high mobility of charge carriers, which exceeds the mobility of charge carriers for all known materials, is currently considered as one of the most promising materials for the creation of new semiconductor devices. The results of modeling of electron scattering rates are presented for the acoustic and optical phonons in a single layer of graphene without a substrate for small values of energy, which do not exceed 1 eV. When modeling these rates, variants of both emission and absorption of phonons are considered. The obtained dependences of the charge carrier scattering rates will allow us to study the main characteristics of charge carrier transport in semiconductor structures containing graphene layers by modeling using the Monte Carlo method. Characteristics and parameters of graphene can be used to create new heterostructure devices with improved output characteristics.

Simulations of the stationary Q = 10 and the exit phase from the flat-top of an ITER 15MA baseline scenario: predictive JINTRAC simulation with a consistent treatment of D and T in the whole plasma

Abstract Designing a robust termination scenario for a burning ITER plasma is a challenge that requires extensive core plasma and divertor modelling. The presented work consists of coupled core/edge/SOL/divertor simulations, performed with the JINTRAC code, to study the Q = 10 flat-top phase and exit phase of the ITER 15 MA/5.3 T DT scenario. The modelling utilizes the recently implemented option to treat deuterium and tritium separately in the SOL/divertor, enabling a consistent treatment of deuterium and tritium in the whole plasma volume, which is a unique capability of JINTRAC. In addition, these are the first JINTRAC simulations of this scenario that use a first-principles transport model to self-consistently model the ECRH power deposition and to include tungsten while keeping track of tungsten sputtering and accumulation. The flat-top simulations demonstrate the possibility of sustaining a steady state fusion Q of 10 using pure deuterium gas puffs together with DT mixed pellets, which is an option to make a more effective use of tritium. Simulations of the exit phase are set up sequentially, with each phase providing initial conditions for the next, starting with a density decay at full current and auxiliary power, and demonstrate the possibility of reducing the density robustly within a few seconds. Following the density decay, a subsequent auxiliary power ramp-down in H-mode is performed with a late H–L transition at low auxiliary power, which may provide an option for the optimization of the plasma termination. The final ramp-down phase consists of a current ramp-down in L-mode to 3.75 MA.

First-principle modeling of parallel-flow regenerative kilns and their optimization with genetic algorithm and gradient-based method

We present a one-dimensional first-principle model for parallel-flow regenerative kilns that accounts for the most important effects. These include the kinetics and thermal effects of the limestone decomposition as well as the heat transfer between the gaseous and solid phases. The model consists of two coupled equation systems for the upper and lower part of the kiln. The results of the model are validated qualitatively and are used to train an artificial neural network that predicts the conversion and the temperature in the crossover channel. The artificial neural network performs very well with values of the root mean squared error that are two to three orders of magnitudes lower than the range covered within the data. Finally, we use a genetic algorithm to optimize the feed mass flows such that the conversion and the fuel efficiency are improved in a Pareto-optimal manner. The results are compared to those of a gradient-based optimization method, which shows the usefulness and validity of the approach with the genetic algorithm.

Grey‐box modelling for estimation of optimum cut point temperature of crude distillation column

AbstractA grey‐box modelling framework was developed for the estimation of cut point temperature of a crude distillation unit (CDU) under uncertainty in crude composition and process conditions. First principle (FP) model of CDU was developed for Pakistani crudes from Zamzama and Kunnar fields. A hybrid methodology based on the integration of Taguchi method and genetic algorithm (GA) was employed to estimate the optimal cut point temperature for various sets of process variables. Optimised datasets were utilised to develop an artificial neural networks (ANN) model for the prediction of optimum values of cut points. The ANN model was then used to replace the hybrid framework of the Taguchi method and the GA. The integration of the ANN and FP model makes it a grey‐box (GB) model. For the case of Zamama crude, the GB model helped in the decrease of up to 38.93% in energy required per kilo barrel of diesel and an 8.2% increase in diesel production compared to the stand‐alone FP model under uncertainty. Similarly, for Kunnar crude, up to 18.87% decrease in energy required per kilo barrel of diesel and a 33.96% increase in diesel production was observed in comparison to the stand‐alone FP model.