var bibbase_data = {"data":"\"Loading..\"\n\n
\n\n \n\n \n\n \n \n\n \n\n \n \n\n \n\n \n
\n generated by\n \n \"bibbase.org\"\n\n \n
\n \n\n
\n\n \n\n\n
\n\n Excellent! Next you can\n create a new website with this list, or\n embed it in an existing web page by copying & pasting\n any of the following snippets.\n\n
\n JavaScript\n (easiest)\n
\n \n <script src=\"https://bibbase.org/show?bib=https%3A%2F%2Fbibbase.org%2Fnetwork%2Ffiles%2Fn9cGhwKu2bsFEXBsY&jsonp=1&noBootstrap=1&jsonp=1\"></script>\n \n
\n\n PHP\n
\n \n <?php\n $contents = file_get_contents(\"https://bibbase.org/show?bib=https%3A%2F%2Fbibbase.org%2Fnetwork%2Ffiles%2Fn9cGhwKu2bsFEXBsY&jsonp=1&noBootstrap=1\");\n print_r($contents);\n ?>\n \n
\n\n iFrame\n (not recommended)\n
\n \n <iframe src=\"https://bibbase.org/show?bib=https%3A%2F%2Fbibbase.org%2Fnetwork%2Ffiles%2Fn9cGhwKu2bsFEXBsY&jsonp=1&noBootstrap=1\"></iframe>\n \n
\n\n

\n For more details see the documention.\n

\n
\n
\n\n
\n\n This is a preview! To use this list on your own web site\n or create a new web site from it,\n create a free account. The file will be added\n and you will be able to edit it in the File Manager.\n We will show you instructions once you've created your account.\n
\n\n
\n\n

To the site owner:

\n\n

Action required! Mendeley is changing its\n API. In order to keep using Mendeley with BibBase past April\n 14th, you need to:\n

    \n
  1. renew the authorization for BibBase on Mendeley, and
    2. \n
  2. update the BibBase URL\n in your page the same way you did when you initially set up\n this page.\n
    3. \n
\n

\n\n

\n \n \n Fix it now\n

\n
\n\n
\n\n\n
\n \n \n
\n
\n  \n 2024\n \n \n (1)\n \n \n
\n
\n \n \n
\n \n\n \n \n \n \n \n \n Rxn-INSIGHT: fast chemical reaction analysis using bond-electron matrices.\n \n \n \n \n\n\n \n Dobbelaere, M. R.; Lengyel, I.; Stevens, C. V.; and Van Geem, K. M.\n\n\n \n\n\n\n Journal of Cheminformatics, 16(1): 37. March 2024.\n \n\n\n\n
\n\n\n\n \n \n \"Rxn-INSIGHT:Paper\n  \n \n\n \n \n doi\n  \n \n\n \n link\n  \n \n\n bibtex\n \n\n \n  \n \n abstract \n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n 
@article{dobbelaere_rxn-insight_2024,\n\ttitle = {Rxn-{INSIGHT}: fast chemical reaction analysis using bond-electron matrices},\n\tvolume = {16},\n\tissn = {1758-2946},\n\turl = {https://doi.org/10.1186/s13321-024-00834-z},\n\tdoi = {10.1186/s13321-024-00834-z},\n\tabstract = {The challenge of devising pathways for organic synthesis remains a central issue in the field of medicinal chemistry. Over the span of six decades, computer-aided synthesis planning has given rise to a plethora of potent tools for formulating synthetic routes. Nevertheless, a significant expert task still looms: determining the appropriate solvent, catalyst, and reagents when provided with a set of reactants to achieve and optimize the desired product for a specific step in the synthesis process. Typically, chemists identify key functional groups and rings that exert crucial influences at the reaction center, classify reactions into categories, and may assign them names. This research introduces Rxn-INSIGHT, an open-source algorithm based on the bond-electron matrix approach, with the purpose of automating this endeavor. Rxn-INSIGHT not only streamlines the process but also facilitates extensive querying of reaction databases, effectively replicating the thought processes of an organic chemist. The core functions of the algorithm encompass the classification and naming of reactions, extraction of functional groups, rings, and scaffolds from the involved chemical entities. The provision of reaction condition recommendations based on the similarity and prevalence of reactions eventually arises as a side application. The performance of our rule-based model has been rigorously assessed against a carefully curated benchmark dataset, exhibiting an accuracy rate exceeding 90\\% in reaction classification and surpassing 95\\% in reaction naming. Notably, it has been discerned that a pivotal factor in selecting analogous reactions lies in the analysis of ring structures participating in the reactions. An examination of ring structures within the USPTO chemical reaction database reveals that with just 35 unique rings, a remarkable 75\\% of all rings found in nearly 1 million products can be encompassed. Furthermore, Rxn-INSIGHT is proficient in suggesting appropriate choices for solvents, catalysts, and reagents in entirely novel reactions, all within the span of a second, utilizing nothing more than an everyday laptop.},\n\tnumber = {1},\n\tjournal = {Journal of Cheminformatics},\n\tauthor = {Dobbelaere, Maarten R. and Lengyel, István and Stevens, Christian V. and Van Geem, Kevin M.},\n\tmonth = mar,\n\tyear = {2024},\n\tpages = {37},\n}\n\n
\n
\n\n\n
\n The challenge of devising pathways for organic synthesis remains a central issue in the field of medicinal chemistry. Over the span of six decades, computer-aided synthesis planning has given rise to a plethora of potent tools for formulating synthetic routes. Nevertheless, a significant expert task still looms: determining the appropriate solvent, catalyst, and reagents when provided with a set of reactants to achieve and optimize the desired product for a specific step in the synthesis process. Typically, chemists identify key functional groups and rings that exert crucial influences at the reaction center, classify reactions into categories, and may assign them names. This research introduces Rxn-INSIGHT, an open-source algorithm based on the bond-electron matrix approach, with the purpose of automating this endeavor. Rxn-INSIGHT not only streamlines the process but also facilitates extensive querying of reaction databases, effectively replicating the thought processes of an organic chemist. The core functions of the algorithm encompass the classification and naming of reactions, extraction of functional groups, rings, and scaffolds from the involved chemical entities. The provision of reaction condition recommendations based on the similarity and prevalence of reactions eventually arises as a side application. The performance of our rule-based model has been rigorously assessed against a carefully curated benchmark dataset, exhibiting an accuracy rate exceeding 90% in reaction classification and surpassing 95% in reaction naming. Notably, it has been discerned that a pivotal factor in selecting analogous reactions lies in the analysis of ring structures participating in the reactions. An examination of ring structures within the USPTO chemical reaction database reveals that with just 35 unique rings, a remarkable 75% of all rings found in nearly 1 million products can be encompassed. Furthermore, Rxn-INSIGHT is proficient in suggesting appropriate choices for solvents, catalysts, and reagents in entirely novel reactions, all within the span of a second, utilizing nothing more than an everyday laptop.\n
\n\n\n
\n\n\n\n\n\n
\n
\n\n
\n
\n  \n 2023\n \n \n (2)\n \n \n
\n
\n \n \n
\n \n\n \n \n \n \n \n \n Active Machine Learning for Chemical Engineers: A Bright Future Lies Ahead!.\n \n \n \n \n\n\n \n Ureel, Y.; Dobbelaere, M. R.; Ouyang, Y.; De Ras, K.; Sabbe, M. K.; Marin, G. B.; and Van Geem, K. M.\n\n\n \n\n\n\n Engineering, 27: 23–30. August 2023.\n \n\n\n\n
\n\n\n\n \n \n \"ActivePaper\n  \n \n\n \n \n doi\n  \n \n\n \n link\n  \n \n\n bibtex\n \n\n \n  \n \n abstract \n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n \n \n \n \n \n \n \n \n \n \n\n\n\n
\n 
@article{ureel_active_2023,\n\ttitle = {Active {Machine} {Learning} for {Chemical} {Engineers}: {A} {Bright} {Future} {Lies} {Ahead}!},\n\tvolume = {27},\n\tissn = {2095-8099},\n\turl = {https://www.sciencedirect.com/science/article/pii/S2095809923002862},\n\tdoi = {10.1016/j.eng.2023.02.019},\n\tabstract = {By combining machine learning with the design of experiments, thereby achieving so-called active machine learning, more efficient and cheaper research can be conducted. Machine learning algorithms are more flexible and are better than traditional design of experiment algorithms at investigating processes spanning all length scales of chemical engineering. While active machine learning algorithms are maturing, their applications are falling behind. In this article, three types of challenges presented by active machine learning—namely, convincing the experimental researcher, the flexibility of data creation, and the robustness of active machine learning algorithms—are identified, and ways to overcome them are discussed. A bright future lies ahead for active machine learning in chemical engineering, thanks to increasing automation and more efficient algorithms that can drive novel discoveries.},\n\tjournal = {Engineering},\n\tauthor = {Ureel, Yannick and Dobbelaere, Maarten R. and Ouyang, Yi and De Ras, Kevin and Sabbe, Maarten K. and Marin, Guy B. and Van Geem, Kevin M.},\n\tmonth = aug,\n\tyear = {2023},\n\tkeywords = {Active learning, Active machine learning, Bayesian optimization, Chemical engineering, Design of experiments},\n\tpages = {23--30},\n}\n\n
\n
\n\n\n
\n By combining machine learning with the design of experiments, thereby achieving so-called active machine learning, more efficient and cheaper research can be conducted. Machine learning algorithms are more flexible and are better than traditional design of experiment algorithms at investigating processes spanning all length scales of chemical engineering. While active machine learning algorithms are maturing, their applications are falling behind. In this article, three types of challenges presented by active machine learning—namely, convincing the experimental researcher, the flexibility of data creation, and the robustness of active machine learning algorithms—are identified, and ways to overcome them are discussed. A bright future lies ahead for active machine learning in chemical engineering, thanks to increasing automation and more efficient algorithms that can drive novel discoveries.\n
\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n Bayesian tuned kinetic Monte Carlo modeling of polystyrene pyrolysis: Unraveling the pathways to its monomer, dimers, and trimers formation.\n \n \n \n \n\n\n \n Dogu, O.; Eschenbacher, A.; John Varghese, R.; Dobbelaere, M.; D'hooge, D. R.; Van Steenberge, P. H.; and Van Geem, K. M.\n\n\n \n\n\n\n Chemical Engineering Journal, 455: 140708. January 2023.\n \n\n\n\n
\n\n\n\n \n \n \"BayesianPaper\n  \n \n\n \n \n doi\n  \n \n\n \n link\n  \n \n\n bibtex\n \n\n \n  \n \n abstract \n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n\n\n\n
\n 
@article{dogu_bayesian_2023,\n\ttitle = {Bayesian tuned kinetic {Monte} {Carlo} modeling of polystyrene pyrolysis: {Unraveling} the pathways to its monomer, dimers, and trimers formation},\n\tvolume = {455},\n\tissn = {1385-8947},\n\turl = {https://www.sciencedirect.com/science/article/pii/S1385894722061885},\n\tdoi = {10.1016/j.cej.2022.140708},\n\tabstract = {The current kinetic models for polystyrene (PS) pyrolysis contain many simplifications to reduce their size and the corresponding simulation time. Moreover, they are often based on rate coefficients determined using non-ideal experimental data featuring ambiguous process conditions with respect to mixing and temperature uniformity. The practical interest of PS pyrolysis is the production of styrene monomer to be reused as a feedstock in the polymerization of styrene. In the present work, a lab-scale tree-based kinetic Monte Carlo (kMC) model is presented that differentiates between 18 reaction families and 26 end-group pairs to study the product yield variations for thermal degradation of PS. Model parameters follow from Bayesian optimization to experimental data recorded with an in-house micro-pyrolysis unit coupled with comprehensive two-dimensional gas chromatography. Low chain length (CL) anionic-made PS is specifically considered to gain an understanding of the role of specific end-groups. The experimental yields of the major products (monomer: 74.7–80.8 wt\\%, dimer: 5.1–5.5 wt\\%, trimer: 1.6–7.7 wt\\%) are well-predicted with the fine-tuned parameters. The main reaction pathway in the formation of styrene monomer is end-chain β-scission, while mid-chain β-scission is primarily involved in the formation of the styrene dimer and trimer. Our model shows that the pyrolysis of low CL anionic-made PS leads to better rate coefficients than those obtained from state-of-the-art pyrolysis of long CL PS, in which end-groups play a much smaller role.},\n\tjournal = {Chemical Engineering Journal},\n\tauthor = {Dogu, Onur and Eschenbacher, Andreas and John Varghese, Robin and Dobbelaere, Maarten and D'hooge, Dagmar R. and Van Steenberge, Paul H.M. and Van Geem, Kevin M.},\n\tmonth = jan,\n\tyear = {2023},\n\tkeywords = {Bayesian optimization, Chemical recycling, Diels-Alder dimerization, Kinetic modeling, Polystyrene, Thermal degradation},\n\tpages = {140708},\n}\n
\n
\n\n\n
\n The current kinetic models for polystyrene (PS) pyrolysis contain many simplifications to reduce their size and the corresponding simulation time. Moreover, they are often based on rate coefficients determined using non-ideal experimental data featuring ambiguous process conditions with respect to mixing and temperature uniformity. The practical interest of PS pyrolysis is the production of styrene monomer to be reused as a feedstock in the polymerization of styrene. In the present work, a lab-scale tree-based kinetic Monte Carlo (kMC) model is presented that differentiates between 18 reaction families and 26 end-group pairs to study the product yield variations for thermal degradation of PS. Model parameters follow from Bayesian optimization to experimental data recorded with an in-house micro-pyrolysis unit coupled with comprehensive two-dimensional gas chromatography. Low chain length (CL) anionic-made PS is specifically considered to gain an understanding of the role of specific end-groups. The experimental yields of the major products (monomer: 74.7–80.8 wt%, dimer: 5.1–5.5 wt%, trimer: 1.6–7.7 wt%) are well-predicted with the fine-tuned parameters. The main reaction pathway in the formation of styrene monomer is end-chain β-scission, while mid-chain β-scission is primarily involved in the formation of the styrene dimer and trimer. Our model shows that the pyrolysis of low CL anionic-made PS leads to better rate coefficients than those obtained from state-of-the-art pyrolysis of long CL PS, in which end-groups play a much smaller role.\n
\n\n\n
\n\n\n\n\n\n
\n
\n\n
\n
\n  \n 2022\n \n \n (3)\n \n \n
\n
\n \n \n
\n \n\n \n \n \n \n \n \n Speeding up turbulent reactive flow simulation via a deep artificial neural network: A methodology study.\n \n \n \n \n\n\n \n Ouyang, Y.; Vandewalle, L. A.; Chen, L.; Plehiers, P. P.; Dobbelaere, M. R.; Heynderickx, G. J.; Marin, G. B.; and Van Geem, K. M.\n\n\n \n\n\n\n Chemical Engineering Journal, 429: 132442. February 2022.\n \n\n\n\n
\n\n\n\n \n \n \"SpeedingPaper\n  \n \n\n \n \n doi\n  \n \n\n \n link\n  \n \n\n bibtex\n \n\n \n  \n \n abstract \n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n \n \n \n \n \n \n \n \n \n \n\n\n\n
\n 
@article{ouyang_speeding_2022,\n\ttitle = {Speeding up turbulent reactive flow simulation via a deep artificial neural network: {A} methodology study},\n\tvolume = {429},\n\tcopyright = {All rights reserved},\n\tissn = {1385-8947},\n\turl = {https://www.sciencedirect.com/science/article/pii/S1385894721040201},\n\tdoi = {10.1016/j.cej.2021.132442},\n\tabstract = {Turbulent reactive flow simulation often requires accounting for turbulence-chemistry interactions and the sub-grid phenomena. Their complexity leads to a trade-off between computational efficiency on one hand and computational accuracy on the other. We attempt to bridge this gap by coupling the power of machine learning with the turbulent reactive flow simulation, specifically in the form of a deep artificial neural network. The Lagrangian Monte Carlo method is chosen as a demonstration case as it is one of the most accurate models for turbulent reactive flow simulation, but also one of the most time-consuming. The workflow consists of training data generation, deep neural network construction, and implementation in ANSYS-Fluent, followed by an evaluation of model accuracy and efficiency, which results in an order of magnitude faster simulation without loss of accuracy thanks to our data-driven deep neural network. This approach can be of universal relevance in speeding up time-consuming models in the field of reactive flow simulation.},\n\tjournal = {Chemical Engineering Journal},\n\tauthor = {Ouyang, Yi and Vandewalle, Laurien A. and Chen, Lin and Plehiers, Pieter P. and Dobbelaere, Maarten R. and Heynderickx, Geraldine J. and Marin, Guy B. and Van Geem, Kevin M.},\n\tmonth = feb,\n\tyear = {2022},\n\tkeywords = {Artificial Neural Network, Lagrangian PDF Method, Sub-Grid Effect, Turbulence-Chemistry Interaction, Turbulent Reactive Flow Simulation},\n\tpages = {132442},\n}\n\n
\n
\n\n\n
\n Turbulent reactive flow simulation often requires accounting for turbulence-chemistry interactions and the sub-grid phenomena. Their complexity leads to a trade-off between computational efficiency on one hand and computational accuracy on the other. We attempt to bridge this gap by coupling the power of machine learning with the turbulent reactive flow simulation, specifically in the form of a deep artificial neural network. The Lagrangian Monte Carlo method is chosen as a demonstration case as it is one of the most accurate models for turbulent reactive flow simulation, but also one of the most time-consuming. The workflow consists of training data generation, deep neural network construction, and implementation in ANSYS-Fluent, followed by an evaluation of model accuracy and efficiency, which results in an order of magnitude faster simulation without loss of accuracy thanks to our data-driven deep neural network. This approach can be of universal relevance in speeding up time-consuming models in the field of reactive flow simulation.\n
\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n Machine Learning for Physicochemical Property Prediction of Complex Hydrocarbon Mixtures.\n \n \n \n \n\n\n \n Dobbelaere, M. R.; Ureel, Y.; Vermeire, F. H.; Tomme, L.; Stevens, C. V.; and Van Geem, K. M.\n\n\n \n\n\n\n Industrial & Engineering Chemistry Research, 61(24): 8581–8594. June 2022.\n Publisher: American Chemical Society\n\n\n\n
\n\n\n\n \n \n \"MachinePaper\n  \n \n\n \n \n doi\n  \n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n  \n \n 1 download\n \n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n 
@article{dobbelaere_machine_2022,\n\ttitle = {Machine {Learning} for {Physicochemical} {Property} {Prediction} of {Complex} {Hydrocarbon} {Mixtures}},\n\tvolume = {61},\n\tcopyright = {All rights reserved},\n\tissn = {0888-5885},\n\turl = {https://doi.org/10.1021/acs.iecr.2c00442},\n\tdoi = {10.1021/acs.iecr.2c00442},\n\tnumber = {24},\n\tjournal = {Industrial \\& Engineering Chemistry Research},\n\tauthor = {Dobbelaere, Maarten R. and Ureel, Yannick and Vermeire, Florence H. and Tomme, Lowie and Stevens, Christian V. and Van Geem, Kevin M.},\n\tmonth = jun,\n\tyear = {2022},\n\tnote = {Publisher: American Chemical Society},\n\tpages = {8581--8594},\n\tannote = {doi: 10.1021/acs.iecr.2c00442},\n}\n\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n Active learning-based exploration of the catalytic pyrolysis of plastic waste.\n \n \n \n \n\n\n \n Ureel, Y.; Dobbelaere, M. R.; Akin, O.; Varghese, R. J.; Pernalete, C. G.; Thybaut, J. W.; and Van Geem, K. M.\n\n\n \n\n\n\n Fuel, 328: 125340. November 2022.\n \n\n\n\n
\n\n\n\n \n \n \"ActivePaper\n  \n \n\n \n \n doi\n  \n \n\n \n link\n  \n \n\n bibtex\n \n\n \n  \n \n abstract \n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n \n \n \n \n \n \n \n \n \n \n\n\n\n
\n 
@article{ureel_active_2022,\n\ttitle = {Active learning-based exploration of the catalytic pyrolysis of plastic waste},\n\tvolume = {328},\n\tcopyright = {All rights reserved},\n\tissn = {0016-2361},\n\turl = {https://www.sciencedirect.com/science/article/pii/S0016236122021755},\n\tdoi = {10.1016/j.fuel.2022.125340},\n\tabstract = {Research in chemical engineering requires experiments, which are often expensive, time-consuming, and laborious. Design of experiments (DoE) aims to extract maximal information from a minimum number of experiments. The combination of DoE with machine learning leads to the field of active learning, which results in a more flexible, multi-dimensional selection of experiments. Active learning has not yet been applied in reaction modeling, as most active learning techniques still require an excessive amount of data. In this work, a novel active learning framework called GandALF that combines Gaussian processes and clustering is proposed and validated for yield prediction. The performance of GandALF is compared to other active learning strategies in a virtual case study for hydrocracking. Compared to these active learning methods, the novel framework outperforms the state-of-the-art and achieves a 33\\%-reduction in experiments. The proposed active learning approach is the first to also perform well for data-scarce applications, which is demonstrated by selecting experiments to investigate the ex-situ catalytic pyrolysis of plastic waste. Both a common DoE-technique, and our methodology selected 18 experiments to study the effect of temperature, space time, and catalyst on the olefin yield for the catalytic pyrolysis of LDPE. The experiments selected with active learning were significantly more informative than the regular DoE-technique, proving the applicability of GandALF for reaction modeling and experimental campaigns.},\n\tjournal = {Fuel},\n\tauthor = {Ureel, Yannick and Dobbelaere, Maarten R. and Akin, Oğuzhan and Varghese, Robin John and Pernalete, César G. and Thybaut, Joris W. and Van Geem, Kevin M.},\n\tmonth = nov,\n\tyear = {2022},\n\tkeywords = {Active learning, Catalytic pyrolysis, Design of experiments, Gaussian processes, Plastic waste recycling},\n\tpages = {125340},\n}\n\n
\n
\n\n\n
\n Research in chemical engineering requires experiments, which are often expensive, time-consuming, and laborious. Design of experiments (DoE) aims to extract maximal information from a minimum number of experiments. The combination of DoE with machine learning leads to the field of active learning, which results in a more flexible, multi-dimensional selection of experiments. Active learning has not yet been applied in reaction modeling, as most active learning techniques still require an excessive amount of data. In this work, a novel active learning framework called GandALF that combines Gaussian processes and clustering is proposed and validated for yield prediction. The performance of GandALF is compared to other active learning strategies in a virtual case study for hydrocracking. Compared to these active learning methods, the novel framework outperforms the state-of-the-art and achieves a 33%-reduction in experiments. The proposed active learning approach is the first to also perform well for data-scarce applications, which is demonstrated by selecting experiments to investigate the ex-situ catalytic pyrolysis of plastic waste. Both a common DoE-technique, and our methodology selected 18 experiments to study the effect of temperature, space time, and catalyst on the olefin yield for the catalytic pyrolysis of LDPE. The experiments selected with active learning were significantly more informative than the regular DoE-technique, proving the applicability of GandALF for reaction modeling and experimental campaigns.\n
\n\n\n
\n\n\n\n\n\n
\n
\n\n
\n
\n  \n 2021\n \n \n (2)\n \n \n
\n
\n \n \n
\n \n\n \n \n \n \n \n \n Learning Molecular Representations for Thermochemistry Prediction of Cyclic Hydrocarbons and Oxygenates.\n \n \n \n \n\n\n \n Dobbelaere, M. R.; Plehiers, P. P.; Van de Vijver, R.; Stevens, C. V.; and Van Geem, K. M.\n\n\n \n\n\n\n The Journal of Physical Chemistry A, 125(23): 5166–5179. June 2021.\n Publisher: American Chemical Society\n\n\n\n
\n\n\n\n \n \n \"LearningPaper\n  \n \n\n \n \n doi\n  \n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n  \n \n 2 downloads\n \n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n 
@article{dobbelaere_learning_2021,\n\ttitle = {Learning {Molecular} {Representations} for {Thermochemistry} {Prediction} of {Cyclic} {Hydrocarbons} and {Oxygenates}},\n\tvolume = {125},\n\tcopyright = {All rights reserved},\n\tissn = {1089-5639},\n\turl = {https://doi.org/10.1021/acs.jpca.1c01956},\n\tdoi = {10.1021/acs.jpca.1c01956},\n\tnumber = {23},\n\tjournal = {The Journal of Physical Chemistry A},\n\tauthor = {Dobbelaere, Maarten R. and Plehiers, Pieter P. and Van de Vijver, Ruben and Stevens, Christian V. and Van Geem, Kevin M.},\n\tmonth = jun,\n\tyear = {2021},\n\tnote = {Publisher: American Chemical Society},\n\tpages = {5166--5179},\n\tannote = {doi: 10.1021/acs.jpca.1c01956},\n}\n\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n Machine Learning in Chemical Engineering: Strengths, Weaknesses, Opportunities, and Threats.\n \n \n \n \n\n\n \n Dobbelaere, M. R.; Plehiers, P. P.; Van de Vijver, R.; Stevens, C. V.; and Van Geem, K. M.\n\n\n \n\n\n\n Engineering, 7(9): 1201–1211. September 2021.\n \n\n\n\n
\n\n\n\n \n \n \"MachinePaper\n  \n \n\n \n \n doi\n  \n \n\n \n link\n  \n \n\n bibtex\n \n\n \n  \n \n abstract \n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n \n \n \n \n \n \n \n \n\n\n\n
\n 
@article{dobbelaere_machine_2021,\n\ttitle = {Machine {Learning} in {Chemical} {Engineering}: {Strengths}, {Weaknesses}, {Opportunities}, and {Threats}},\n\tvolume = {7},\n\tcopyright = {All rights reserved},\n\tissn = {2095-8099},\n\turl = {https://www.sciencedirect.com/science/article/pii/S2095809921002010},\n\tdoi = {10.1016/j.eng.2021.03.019},\n\tabstract = {Chemical engineers rely on models for design, research, and daily decision-making, often with potentially large financial and safety implications. Previous efforts a few decades ago to combine artificial intelligence and chemical engineering for modeling were unable to fulfill the expectations. In the last five years, the increasing availability of data and computational resources has led to a resurgence in machine learning-based research. Many recent efforts have facilitated the roll-out of machine learning techniques in the research field by developing large databases, benchmarks, and representations for chemical applications and new machine learning frameworks. Machine learning has significant advantages over traditional modeling techniques, including flexibility, accuracy, and execution speed. These strengths also come with weaknesses, such as the lack of interpretability of these black-box models. The greatest opportunities involve using machine learning in time-limited applications such as real-time optimization and planning that require high accuracy and that can build on models with a self-learning ability to recognize patterns, learn from data, and become more intelligent over time. The greatest threat in artificial intelligence research today is inappropriate use because most chemical engineers have had limited training in computer science and data analysis. Nevertheless, machine learning will definitely become a trustworthy element in the modeling toolbox of chemical engineers.},\n\tnumber = {9},\n\tjournal = {Engineering},\n\tauthor = {Dobbelaere, Maarten R. and Plehiers, Pieter P. and Van de Vijver, Ruben and Stevens, Christian V. and Van Geem, Kevin M.},\n\tmonth = sep,\n\tyear = {2021},\n\tkeywords = {Artificial intelligence, Machine learning, Process engineering, Reaction engineering},\n\tpages = {1201--1211},\n}\n\n
\n
\n\n\n
\n Chemical engineers rely on models for design, research, and daily decision-making, often with potentially large financial and safety implications. Previous efforts a few decades ago to combine artificial intelligence and chemical engineering for modeling were unable to fulfill the expectations. In the last five years, the increasing availability of data and computational resources has led to a resurgence in machine learning-based research. Many recent efforts have facilitated the roll-out of machine learning techniques in the research field by developing large databases, benchmarks, and representations for chemical applications and new machine learning frameworks. Machine learning has significant advantages over traditional modeling techniques, including flexibility, accuracy, and execution speed. These strengths also come with weaknesses, such as the lack of interpretability of these black-box models. The greatest opportunities involve using machine learning in time-limited applications such as real-time optimization and planning that require high accuracy and that can build on models with a self-learning ability to recognize patterns, learn from data, and become more intelligent over time. The greatest threat in artificial intelligence research today is inappropriate use because most chemical engineers have had limited training in computer science and data analysis. Nevertheless, machine learning will definitely become a trustworthy element in the modeling toolbox of chemical engineers.\n
\n\n\n
\n\n\n\n\n\n
\n
\n\n
\n
\n  \n 2020\n \n \n (1)\n \n \n
\n
\n \n \n
\n \n\n \n \n \n \n \n \n Artificial Intelligence for Computer-Aided Synthesis In Flow: Analysis and Selection of Reaction Components.\n \n \n \n \n\n\n \n Plehiers, P. P.; Coley, C. W.; Gao, H.; Vermeire, F. H.; Dobbelaere, M. R.; Stevens, C. V.; Van Geem, K. M.; and Green, W. H.\n\n\n \n\n\n\n Frontiers in Chemical Engineering, 2. 2020.\n \n\n\n\n
\n\n\n\n \n \n \"ArtificialPaper\n  \n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n  \n \n abstract \n \n\n \n  \n \n 1 download\n \n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n 
@article{plehiers_artificial_2020,\n\ttitle = {Artificial {Intelligence} for {Computer}-{Aided} {Synthesis} {In} {Flow}: {Analysis} and {Selection} of {Reaction} {Components}},\n\tvolume = {2},\n\tcopyright = {All rights reserved},\n\tissn = {2673-2718},\n\turl = {https://www.frontiersin.org/articles/10.3389/fceng.2020.00005},\n\tabstract = {Computer-aided synthesis has received much attention in recent years. It is a challenging topic in itself, due to the high dimensionality of chemical and reaction space. It becomes even more challenging when the aim is to suggest syntheses that can be performed in continuous flow. Though continuous flow offers many potential benefits, not all reactions are suited to be operated continuously. In this work, three machine learning models have been developed to provide an assessment of whether a given reaction may benefit from continuous operation, what the likelihood of success in continuous flow is for a certain set of reaction components (i.e., reactants, reagents, solvents, catalysts, and products) and, if the likelihood of success is low, which alternative reaction components can be considered. The first model uses an abstract version of a reaction template, obtained via gaussian mixture modeling, to quantify its relative increase in publishing frequency in continuous flow, without relying on potentially ambiguously defined reaction templates. The second model is an artificial neural network that categorizes feasible and infeasible reaction components with a 75\\% success rate. A set of reaction components is considered to be feasible if there is an explicit reference to it being used in continuous synthesis in the database; all other reaction components are considered infeasible. While several cases that are “infeasible” by this definition, are classified as feasible by the neural network, further analysis shows that for many of these cases, it is at least plausible that they are in fact feasible – they simply have not been tested to (dis)prove this. The final model suggests alternative continuous flow components with a top-1 accuracy of 95\\%. Combined, they offer a black-box evaluation of whether a reaction and a set of reaction components can be considered promising for continuous syntheses.},\n\tjournal = {Frontiers in Chemical Engineering},\n\tauthor = {Plehiers, Pieter P. and Coley, Connor W. and Gao, Hanyu and Vermeire, Florence H. and Dobbelaere, Maarten R. and Stevens, Christian V. and Van Geem, Kevin M. and Green, William H.},\n\tyear = {2020},\n}\n\n
\n
\n\n\n
\n Computer-aided synthesis has received much attention in recent years. It is a challenging topic in itself, due to the high dimensionality of chemical and reaction space. It becomes even more challenging when the aim is to suggest syntheses that can be performed in continuous flow. Though continuous flow offers many potential benefits, not all reactions are suited to be operated continuously. In this work, three machine learning models have been developed to provide an assessment of whether a given reaction may benefit from continuous operation, what the likelihood of success in continuous flow is for a certain set of reaction components (i.e., reactants, reagents, solvents, catalysts, and products) and, if the likelihood of success is low, which alternative reaction components can be considered. The first model uses an abstract version of a reaction template, obtained via gaussian mixture modeling, to quantify its relative increase in publishing frequency in continuous flow, without relying on potentially ambiguously defined reaction templates. The second model is an artificial neural network that categorizes feasible and infeasible reaction components with a 75% success rate. A set of reaction components is considered to be feasible if there is an explicit reference to it being used in continuous synthesis in the database; all other reaction components are considered infeasible. While several cases that are “infeasible” by this definition, are classified as feasible by the neural network, further analysis shows that for many of these cases, it is at least plausible that they are in fact feasible – they simply have not been tested to (dis)prove this. The final model suggests alternative continuous flow components with a top-1 accuracy of 95%. Combined, they offer a black-box evaluation of whether a reaction and a set of reaction components can be considered promising for continuous syntheses.\n
\n\n\n
\n\n\n\n\n\n
\n
\n\n\n\n\n
\n\n\n \n\n \n \n \n \n\n
\n"}; document.write(bibbase_data.data);