Dimitrios Meimaroglou
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Dimitrios Meimaroglou has a total of 46 co-authors. Here are the top co-authors by number of shared publications:
Sandrine Hoppe
Laboratoire Réactions et Génie des Procédés, Université de Lorraine, CNRS, LRGP, Nancy, France
6 shared publicationsApostolos Krallis
Aristotle University of Thessaloniki & Chemical Process Engineering Research Institute
5 shared publicationsCostas Kiparissides
5 shared publications- Cindy Trinh
Université de Lorraine, CNRS, LRGP, F-54001 Nancy, France
4 shared publications - Prokopis Pladis
Chemical Process and Energy Resources Institute Centre for Research and Technology Hellas P.O. Box 60361 Thermi 57001 Thessaloniki Greece
4 shared publications - Sandrine Hoppe
Laboratoire Réactions et Génie des Procédés, Université de Lorraine, CNRS UMR7274, LRGP, F-54000 Nancy, France
4 shared publications
Latest Publications
- 6 November 2025
- Published by American Chemical Society (ACS) in Industrial & Engineering Chemistry Research
- Vol. 64 (46) , 22304-22320
A Novel Hybrid Modeling Framework for Polymer Reaction Engineering with Application to Real-Time Process Monitoring
- 6 November 2025
- Published by American Chemical Society (ACS) in Industrial & Engineering Chemistry Research
- Vol. 64 (46) , 22304-22320
A Novel Hybrid Modeling Framework for Polymer Reaction Engineering with Application to Real-Time Process Monitoring
- 24 April 2025
- Published by Wiley in The Canadian Journal of Chemical Engineering
- Vol. 103 (7) , 2968
Preface: Special series on the pathways to a circular economy of plastics
- 24 April 2025
- Published by Wiley in The Canadian Journal of Chemical Engineering
- Vol. 103 (7) , 2968
Preface: Special series on the pathways to a circular economy of plastics
- Open Access
- 18 December 2023
- Published by MDPI AG in Algorithms
- Vol. 16 (12) , 573
On the Development of Descriptor-Based Machine Learning Models for Thermodynamic Properties: Part 2—Applicability Domain and Outliers
This article investigates the applicability domain (AD) of machine learning (ML) models trained on high-dimensional data, for the prediction of the ideal gas enthalpy of formation and entropy of molecules via descriptors. The AD is crucial as it describes the space of chemical characteristics in which the model can make predictions with a given reliability. This work studies the AD definition of a ML model throughout its development procedure: during data preprocessing, model construction and model deployment. Three AD definition methods, commonly used for outlier detection in high-dimensional problems, are compared: isolation forest (iForest), random forest prediction confidence (RF confidence) and k-nearest neighbors in the 2D projection of descriptor space obtained via t-distributed stochastic neighbor embedding (tSNE2D/kNN). These methods compute an anomaly score that can be used instead of the distance metrics of classical low-dimension AD definition methods, the latter being generally unsuitable for high-dimensional problems. Typically, in low- (high-) dimensional problems, a molecule is considered to lie within the AD if its distance from the training domain (anomaly score) is below a given threshold. During data preprocessing, the three AD definition methods are used to identify outlier molecules and the effect of their removal is investigated. A more significant improvement of model performance is observed when outliers identified with RF confidence are removed (e.g., for a removal of 30% of outliers, the (Mean Absolute Error) of the test dataset is divided by 2.5, 1.6 and 1.1 for RF confidence, iForest and tSNE2D/kNN, respectively). While these three methods identify X-outliers, the effect of other types of outliers, namely Model-outliers and y-outliers, is also investigated. In particular, the elimination of X-outliers followed by that of Model-outliers enables us to divide and (Root Mean Square Error) by 2 and 3, respectively, while reducing overfitting. The elimination of y-outliers does not display a significant effect on the model performance. During model construction and deployment, the AD serves to verify the position of the test data and of different categories of molecules with respect to the training data and associate this position with their prediction accuracy. For the data that are found to be close to the training data, according to RF confidence, and display high prediction errors, tSNE 2D representations are deployed to identify the possible sources of these errors (e.g., representation of the chemical information in the training data).- 18 December 2023
- Published by MDPI AG in Algorithms
- Vol. 16 (12) , 573
Open AccessOn the Development of Descriptor-Based Machine Learning Models for Thermodynamic Properties: Part 2—Applicability Domain and Outliers
This article investigates the applicability domain (AD) of machine learning (ML) models trained on high-dimensional data, for the prediction of the ideal gas enthalpy of formation and entropy of molecules via descriptors. The AD is crucial as it describes the space of chemical characteristics in which the model can make predictions with a given reliability. This work studies the AD definition of a ML model throughout its development procedure: during data preprocessing, model construction and model deployment. Three AD definition methods, commonly used for outlier detection in high-dimensional problems, are compared: isolation forest (iForest), random forest prediction confidence (RF confidence) and k-nearest neighbors in the 2D projection of descriptor space obtained via t-distributed stochastic neighbor embedding (tSNE2D/kNN). These methods compute an anomaly score that can be used instead of the distance metrics of classical low-dimension AD definition methods, the latter being generally unsuitable for high-dimensional problems. Typically, in low- (high-) dimensional problems, a molecule is considered to lie within the AD if its distance from the training domain (anomaly score) is below a given threshold. During data preprocessing, the three AD definition methods are used to identify outlier molecules and the effect of their removal is investigated. A more significant improvement of model performance is observed when outliers identified with RF confidence are removed (e.g., for a removal of 30% of outliers, the (Mean Absolute Error) of the test dataset is divided by 2.5, 1.6 and 1.1 for RF confidence, iForest and tSNE2D/kNN, respectively). While these three methods identify X-outliers, the effect of other types of outliers, namely Model-outliers and y-outliers, is also investigated. In particular, the elimination of X-outliers followed by that of Model-outliers enables us to divide and (Root Mean Square Error) by 2 and 3, respectively, while reducing overfitting. The elimination of y-outliers does not display a significant effect on the model performance. During model construction and deployment, the AD serves to verify the position of the test data and of different categories of molecules with respect to the training data and associate this position with their prediction accuracy. For the data that are found to be close to the training data, according to RF confidence, and display high prediction errors, tSNE 2D representations are deployed to identify the possible sources of these errors (e.g., representation of the chemical information in the training data). - Open Access
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
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 ( 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.Open AccessOn 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
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 ( 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. - Open Access
A Comprehensive Study on the Styrene–GTR Radical Graft Polymerization: Combination of an Experimental Approach, on Different Scales, with Machine Learning Modeling
The study of the styrene–Ground Tire Rubber (GTR) graft radical polymerization is particularly challenging due to the complexity of the underlying kinetic mechanisms and nature of GTR. In this work, an experimental study on two scales (∼10 mL and ∼100 mL) and a machine learning (ML) modeling approach are combined to establish a quantitative relationship between operating conditions and styrene conversion. The two-scale experimental approach enables to verify the impact of upscaling on thermal and mixing effects that are particularly important in this heterogeneous system, as also evidenced in previous works. The adopted experimental setups are designed in view of multiple data production, while paying specific attention in data reliability by eliminating the uncertainty related to sampling for analyses. At the same time, all the potential sources of uncertainty, such as the mass loss along the different steps of the process and the precision of the experimental equipment, are also carefully identified and monitored. The experimental results on both scales validate previously observed effects of GTR, benzoyl peroxide initiator and temperature on styrene conversion but, at the same time, reveal the need of an efficient design of the experimental procedure in terms of mixing and of monitoring uncertainties. Subsequently, the most reliable experimental data (i.e., 69 data from the 10 mL system) are used for the screening of a series of diverse supervised-learning regression ML models and the optimization of the hyperparameters of the best-performing ones. These are gradient boosting, multilayer perceptrons and random forest with, respectively, a test of 0.91 ± 0.04, 0.90 ± 0.04 and 0.89 ± 0.05. Finally, the effect of additional parameters, such as the scaling method, the number of folds and the random partitioning of data in the train/test splits, as well as the integration of the experimental uncertainties in the learning procedure, are exploited as means to improve the performance of the developed models.Open AccessA Comprehensive Study on the Styrene–GTR Radical Graft Polymerization: Combination of an Experimental Approach, on Different Scales, with Machine Learning Modeling
The study of the styrene–Ground Tire Rubber (GTR) graft radical polymerization is particularly challenging due to the complexity of the underlying kinetic mechanisms and nature of GTR. In this work, an experimental study on two scales (∼10 mL and ∼100 mL) and a machine learning (ML) modeling approach are combined to establish a quantitative relationship between operating conditions and styrene conversion. The two-scale experimental approach enables to verify the impact of upscaling on thermal and mixing effects that are particularly important in this heterogeneous system, as also evidenced in previous works. The adopted experimental setups are designed in view of multiple data production, while paying specific attention in data reliability by eliminating the uncertainty related to sampling for analyses. At the same time, all the potential sources of uncertainty, such as the mass loss along the different steps of the process and the precision of the experimental equipment, are also carefully identified and monitored. The experimental results on both scales validate previously observed effects of GTR, benzoyl peroxide initiator and temperature on styrene conversion but, at the same time, reveal the need of an efficient design of the experimental procedure in terms of mixing and of monitoring uncertainties. Subsequently, the most reliable experimental data (i.e., 69 data from the 10 mL system) are used for the screening of a series of diverse supervised-learning regression ML models and the optimization of the hyperparameters of the best-performing ones. These are gradient boosting, multilayer perceptrons and random forest with, respectively, a test of 0.91 ± 0.04, 0.90 ± 0.04 and 0.89 ± 0.05. Finally, the effect of additional parameters, such as the scaling method, the number of folds and the random partitioning of data in the train/test splits, as well as the integration of the experimental uncertainties in the learning procedure, are exploited as means to improve the performance of the developed models. - 1 February 2022
- Published by Elsevier in Chemical Engineering Science
- Vol. 248, 117137
A kinetic modeling framework for the peroxide-initiated radical polymerization of styrene in the presence of rubber particles from recycled tires
- 1 February 2022
- Published by Elsevier in Chemical Engineering Science
- Vol. 248, 117137
A kinetic modeling framework for the peroxide-initiated radical polymerization of styrene in the presence of rubber particles from recycled tires
- Open Access
Machine Learning in Chemical Product Engineering: The State of the Art and a Guide for Newcomers
Chemical Product Engineering (CPE) is marked by numerous challenges, such as the complexity of the properties–structure–ingredients–process relationship of the different products and the necessity to discover and develop constantly and quickly new molecules and materials with tailor-made properties. In recent years, artificial intelligence (AI) and machine learning (ML) methods have gained increasing attention due to their performance in tackling particularly complex problems in various areas, such as computer vision and natural language processing. As such, they present a specific interest in addressing the complex challenges of CPE. This article provides an updated review of the state of the art regarding the implementation of ML techniques in different types of CPE problems with a particular focus on four specific domains, namely the design and discovery of new molecules and materials, the modeling of processes, the prediction of chemical reactions/retrosynthesis and the support for sensorial analysis. This review is further completed by general guidelines for the selection of an appropriate ML technique given the characteristics of each problem and by a critical discussion of several key issues associated with the development of ML modeling approaches. Accordingly, this paper may serve both the experienced researcher in the field as well as the newcomer.
Open AccessMachine Learning in Chemical Product Engineering: The State of the Art and a Guide for Newcomers
Chemical Product Engineering (CPE) is marked by numerous challenges, such as the complexity of the properties–structure–ingredients–process relationship of the different products and the necessity to discover and develop constantly and quickly new molecules and materials with tailor-made properties. In recent years, artificial intelligence (AI) and machine learning (ML) methods have gained increasing attention due to their performance in tackling particularly complex problems in various areas, such as computer vision and natural language processing. As such, they present a specific interest in addressing the complex challenges of CPE. This article provides an updated review of the state of the art regarding the implementation of ML techniques in different types of CPE problems with a particular focus on four specific domains, namely the design and discovery of new molecules and materials, the modeling of processes, the prediction of chemical reactions/retrosynthesis and the support for sensorial analysis. This review is further completed by general guidelines for the selection of an appropriate ML technique given the characteristics of each problem and by a critical discussion of several key issues associated with the development of ML modeling approaches. Accordingly, this paper may serve both the experienced researcher in the field as well as the newcomer.
- Open Access
A Novel Kinetic Modeling Framework for the Polycondensation of Sugars Using Monte Carlo and the Method of Moments
The kinetics of the hydrolysis and polycondensation reactions of saccharides have made the subject of numerous studies, due to their importance in several industrial sectors. The present work, presents a novel kinetic modeling framework that is specifically well-suited to reacting systems under strict moisture control that favor the polycondensation reactions towards the formation of high-degree polysaccharides. The proposed model is based on an extended and generalized kinetic scheme, including also the presence of polyols, and is formulated using two different numerical approaches, namely a deterministic one in terms of the method of moments and a stochastic kinetic Monte Carlo approach. Accordingly, the most significant advantages and drawbacks of each technique are clearly demonstrated and the most fitted one (i.e., the Monte Carlo method) is implemented for the modeling of the system under different conditions, for which experimental data were available. Through these comparisons it is shown that the model can successfully follow the evolution of the reactions up to the formation of polysaccharides of very high degrees of polymerization.
Open AccessA Novel Kinetic Modeling Framework for the Polycondensation of Sugars Using Monte Carlo and the Method of Moments
The kinetics of the hydrolysis and polycondensation reactions of saccharides have made the subject of numerous studies, due to their importance in several industrial sectors. The present work, presents a novel kinetic modeling framework that is specifically well-suited to reacting systems under strict moisture control that favor the polycondensation reactions towards the formation of high-degree polysaccharides. The proposed model is based on an extended and generalized kinetic scheme, including also the presence of polyols, and is formulated using two different numerical approaches, namely a deterministic one in terms of the method of moments and a stochastic kinetic Monte Carlo approach. Accordingly, the most significant advantages and drawbacks of each technique are clearly demonstrated and the most fitted one (i.e., the Monte Carlo method) is implemented for the modeling of the system under different conditions, for which experimental data were available. Through these comparisons it is shown that the model can successfully follow the evolution of the reactions up to the formation of polysaccharides of very high degrees of polymerization.
- 15 May 2020
- Published by Springer Nature in Journal of Thermal Analysis and Calorimetry
- Vol. 143 (4) , 3073-3084
Radical bulk polymerization of styrene in the presence of rubber particles from recycled tires: a kinetic study using DSC
- 15 May 2020
- Published by Springer Nature in Journal of Thermal Analysis and Calorimetry
- Vol. 143 (4) , 3073-3084
Radical bulk polymerization of styrene in the presence of rubber particles from recycled tires: a kinetic study using DSC
- 28 May 2018
- Published by Wiley in Macromolecular Reaction Engineering
- Vol. 12 (4)
A Dynamic Simulator for Slurry‐Phase Catalytic Olefin Copolymerization in a Series of CSTRs: Prediction of Distributed Molecular and Rheological Properties
A comprehensive mathematical model is developed to simulate the dynamic Ziegler–Natta ethylene‐α‐olefins copolymerization in a series of slurry‐phase continuous stirred tank reactors. A generalized multisite kinetic mechanism is considered to describe the molecular and compositional developments (joint molecular weight‐copolymer composition distribution) in a series of continuous stirred tank reactors (CSTRs). Dynamic macroscopic mole balances are derived to calculate the dynamic evolution of all species concentrations in three phases (i.e., gas, liquid, and polymer) of the multiphase system. The polymer molecular properties (i.e., molecular weight distribution, short chain branching distribution, etc.) are determined by two different approaches, namely, the method of double moments and a Monte Carlo algorithm. Detailed thermodynamic calculations are carried out to calculate the solubility of all species in the various phases. Particular emphasis is given to the calculation of mass transfer rates from the gas to the continuous liquid phase and from the liquid to the polymer swollen phase. Comparison of model predictions with experimental measurements has shown that the present plant simulator is capable of simulating the dynamic operation of ethylene with α‐olefins copolymerization over a broad range of operating conditions and, thus, can be used in future process and product optimization and control of lab‐, pilot‐, and industrial‐scale plants.
- 28 May 2018
- Published by Wiley in Macromolecular Reaction Engineering
- Vol. 12 (4)
A Dynamic Simulator for Slurry‐Phase Catalytic Olefin Copolymerization in a Series of CSTRs: Prediction of Distributed Molecular and Rheological Properties
A comprehensive mathematical model is developed to simulate the dynamic Ziegler–Natta ethylene‐α‐olefins copolymerization in a series of slurry‐phase continuous stirred tank reactors. A generalized multisite kinetic mechanism is considered to describe the molecular and compositional developments (joint molecular weight‐copolymer composition distribution) in a series of continuous stirred tank reactors (CSTRs). Dynamic macroscopic mole balances are derived to calculate the dynamic evolution of all species concentrations in three phases (i.e., gas, liquid, and polymer) of the multiphase system. The polymer molecular properties (i.e., molecular weight distribution, short chain branching distribution, etc.) are determined by two different approaches, namely, the method of double moments and a Monte Carlo algorithm. Detailed thermodynamic calculations are carried out to calculate the solubility of all species in the various phases. Particular emphasis is given to the calculation of mass transfer rates from the gas to the continuous liquid phase and from the liquid to the polymer swollen phase. Comparison of model predictions with experimental measurements has shown that the present plant simulator is capable of simulating the dynamic operation of ethylene with α‐olefins copolymerization over a broad range of operating conditions and, thus, can be used in future process and product optimization and control of lab‐, pilot‐, and industrial‐scale plants.