A norm indexes-based QSPR model for predicting the standard vaporization enthalpy and formation enthalpy of organic compounds

Yan, Xue; Lan, Tian; Jia, Qi; Yan, Fangyou; Wang, Qiang

doi:10.1016/j.fluid.2019.112437

Cited by 16 publications

(4 citation statements)

References 52 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The need to compute vapor pressure has long been an important technological issue, and a number of computational methods to predict P vap have been developed in recent years. These methods usually rely on quantitative structure–property relationship (QSPR) − or group-contribution (GC) − approaches. However, QSPR and GC methods rely on empirical models, which inherently lack predictive accuracy for entirely novel materials that significantly differ from the compounds in the training data set.…”

Section: Introductionmentioning

confidence: 99%

Ab Initio Prediction of Vapor Pressure for Diverse Atomic Layer Deposition Precursors

Odinokov,

Son,

Yakubovich

et al. 2024

J. Chem. Theory Comput.

View full text Add to dashboard Cite

Understanding the saturated vapor pressure (P vap ) is vital for evaluating atomic layer deposition (ALD) precursors, as it directly influences the ALD temperature window and, by extension, the processability of compounds. The early estimation of vapor pressure ranges is crucial during the initial stages of novel precursor design, reducing the reliance on empirical synthesis or experimentation. However, predicting vapor pressure through computer simulations is often impeded by the scarcity of suitable empirical force fields for molecular dynamics simulations. This challenge is further compounded by the diverse chemical substances and the introduction of new elements into modern ALD processes, necessitating robust force fields that can accommodate metals, organics, and halides. In response, this study introduces a novel approach utilizing a quantum mechanically derived force field for the prediction of vapor pressure across a wide spectrum of potential ALD precursors. This approach enables the creation of system-specific force fields through parametrization based on ab initio calculations for a single molecule. We develop a comprehensive workflow to simulate both liquid and gaseous equilibrium phases, allowing the calculation of vapor pressure across a wide temperature range. Our methodology has been validated with a diverse set of ALD precursors, demonstrating its robustness in predicting P vap at specified temperatures. The approach yields a Pearson's correlation coefficient (R 2 ) greater than 0.9 on a logarithmic scale and a root-meansquared deviation in self-solvation-free energies as low as 1.3 kcal mol −1 . This innovative workflow, which does not require any prior experimental data, marks a significant advancement in the computer-aided design of novel ALD precursors, paving the way for accelerating developments in technology.

show abstract

Section: Introductionmentioning

confidence: 99%

Ab Initio Prediction of Vapor Pressure for Diverse Atomic Layer Deposition Precursors

Odinokov,

Son,

Yakubovich

et al. 2024

J. Chem. Theory Comput.

View full text Add to dashboard Cite

show abstract

“…Quantitative structure-property relationships (QSPR) have been presented to predict fluid properties through chemical structure-based parameters, called as molecular descriptors. [35][36][37] The values of molecular descriptors can quantitatively describe the physical and chemical information of a molecule and thus construct models. 38 Inspired by the QSPR method, this work is dedicated to working fluid selection and performance prediction for a vortex tube at the macro properties level as well as micro molecular scale through molecular descriptors.…”

Section: Introductionmentioning

confidence: 99%

“…In depth, the properties of fluids are determined based on the molecule structure and interaction. Quantitative structure–property relationships (QSPR) have been presented to predict fluid properties through chemical structure‐based parameters, called as molecular descriptors 35–37 . The values of molecular descriptors can quantitatively describe the physical and chemical information of a molecule and thus construct models 38 .…”

Section: Introductionmentioning

confidence: 99%

Machine learning‐assisted analysis and prediction for the thermal effect of various working fluids in a vortex tube

Wang,

Li,

Zhong

et al. 2023

Asia-Pacific J Chem Eng

View full text Add to dashboard Cite

With the widespread application of vortex tube in various fields, it becomes essential to quantitatively explore the separation effect of different fluids (natural fluids, hydrocarbons, etc.) within the vortex tube and to promote its utilization. A new approach has been developed in this study to establish quantitative models for predicting the thermal effects of different fluids in a vortex tube. These models are based on both the macro properties of the working fluid and micro molecular descriptor through a molecular scale. A dataset of 11 numerical simulation results of hydrocarbons and hydrofluorocarbons refrigerants is employed. Three operating conditions, 10 property parameters, and 115 molecular descriptors are screened and identified using random forest feature analysis. Two types of models (micro and macro) have been developed by employing artificial neural network (ANN) modeling techniques. In the result, four key influencing fluid property parameters (the specific heat ratio γ, the multiplication of heat capacity and the molar weight cp·M, the kinematic viscosity ν, and the thermal conductivity λ) and nine molecular descriptors in affecting the thermal effect are identified and respectively chosen as the input in the macro and the micro ANN model establishment. Both types of developed models show a high correlation coefficient (R > .999) and a comparatively low mean square error (MSE). When R600 is employed in the validation, most of the relative error is less than 10%, suggesting both types of models can work effectively in predicting the thermal effect for other fluid. The findings contribute to a deeper understanding of the thermodynamic effect of vortex tubes and provide a valuable tool for selecting and optimizing working fluids in various applications.

show abstract

“…Quantitative Structure Property/Activity Relationship (QSPR/QSAR) models have been widely employed for several decades in chemistry-related fields to predict various endpoints of molecules (i.e., physico-chemical properties and biological activities, respectively) on the basis of their structure (e.g., descriptors, fingerprints, graphs), via mathematical methods. Successful QSPR/QSAR applications include very different endpoints such as critical temperature and pressure [1], normal boiling point [2], heat capacity [3], enthalpy of solvation [4]/vaporization [5,6], blood-brain barrier permeability [7], physico-chemical properties of polymers/fuels/ionic liquids [8][9][10][11][12][13][14][15], solubility [16][17][18][19][20][21], minimum ignition energy of combustible dusts [22] or antibacterial/antiviral properties [23,24].…”

Section: Introductionmentioning

confidence: 99%

On the Development of Descriptor-Based Machine Learning Models for Thermodynamic Properties: Part 1—From Data Collection to Model Construction: Understanding of the Methods and Their Effects

Trinh,

Tbatou,

Lasala

et al. 2023

Processes

View full text Add to dashboard Cite

In the present work, a multi-angle approach is adopted to develop two ML-QSPR models for the prediction of the enthalpy of formation and the entropy of molecules, in their ideal gas state. The molecules were represented by high-dimensional vectors of structural and physico-chemical characteristics (i.e., descriptors). In this sense, an overview is provided of the possible methods that can be employed at each step of the ML-QSPR procedure (i.e., data preprocessing, dimensionality reduction and model construction) and an attempt is made to increase the understanding of the effects related to a given choice or method on the model performance, interpretability and applicability domain. At the same time, the well-known OECD principles for the validation of (Q)SAR models are also considered and addressed. The employed data set is a good representation of two common problems in ML-QSPR modeling, namely the high-dimensional descriptor-based representation and the high chemical diversity of the molecules. This diversity effectively impacts the subsequent applicability of the developed models to a new molecule. The data set complexity is addressed through customized data preprocessing techniques and genetic algorithms. The former improves the data quality while limiting the loss of information, while the latter allows for the automatic identification of the most important descriptors, in accordance with a physical interpretation. The best performances are obtained with Lasso linear models (MAE test = 25.2 kJ/mol for the enthalpy and 17.9 J/mol/K for the entropy). Finally, the overall developed procedure is also tested on various enthalpy and entropy related data sets from the literature to check its applicability to other problems and competing performances are obtained, highlighting that different methods and molecular representations can lead to good performances.

show abstract

A norm indexes-based QSPR model for predicting the standard vaporization enthalpy and formation enthalpy of organic compounds

Cited by 16 publications

References 52 publications

Ab Initio Prediction of Vapor Pressure for Diverse Atomic Layer Deposition Precursors

Ab Initio Prediction of Vapor Pressure for Diverse Atomic Layer Deposition Precursors

Machine learning‐assisted analysis and prediction for the thermal effect of various working fluids in a vortex tube

On the Development of Descriptor-Based Machine Learning Models for Thermodynamic Properties: Part 1—From Data Collection to Model Construction: Understanding of the Methods and Their Effects

Contact Info

Product

Resources

About