Curriculum Vitae
Download it from here
Education
- Ph.D Data-driven thermodynamics, Technical University of Denmark, Denmark, 2023
- 3-months stay at the Institute of Thermal Separation Processes, Hamburg University of Technology, 2023
- M.S. Chemical and biochemical engineering (honors), Technical University of Denmark, Denmark, 2019
- 6-months at Monash University, Melbourne, Australia, 2018
- B.Eng Chemistry and biotechnology, Technical University of Denmark, Denmark, 2017
Research experience
- Postdoc - (June 2023 - June 2024)
- Process systems engineering center (PROSYS), Technical university of Denmark, Denmark
- Part of the MLEEP project with Assoc. Prof. Jakob Kjøbsted Huusom
- Industrial data preprocessing, data analytics, data visualization, mechanistic modelling of various processes (heat exchangers, evaporators and distillation columns)
- Part of the AIM-Bio project with Prof. Krist Gernaey
- Investigate the potential of digital-twins for pilot scale liquid-chromatography
- Doctoral researcher - (December 2019- April 2023)
- Process systems engineering center - PROSYS, Technical university of Denmark (DTU), Denmark
- PIs: Prof. Gürkan Sin and Assoc. Prof. Jens Abildskov
- Machine learning and deep learning application for new and improved property prediction
- Research Assistant - (December 2021 - April 2022)
- Process systems engineering center - PROSYS, Technical university of Denmark (DTU), Denmark
- PI: Prof. Gürkan Sin
- Deep-Learning for nitrous oxide emission characterization: modelling & uncertainty/sensitivity analysis
- Research Assistant - (August 2019 - September 2019)
- Github University
- PI: Emeri. Kaj Thomsen
- Thermodynamic modelling of carbon capture systems (CO2-MDEA-H2O).
Skills
- Process modelling
- Thermodynamic modelling
- Programming (Python, Matlab, GAMS, Pytorch, Scikit-learn)
- Machine learning (ML)
- Molecular property modelling
- Computer-aided molecular design (CAMD)
Teaching
M.Sc. Theses supervised
- 2024 Thomas Swagerman (TBD), Development of a Streamlined Modelling Platform for Chemical Property Prediction
- 2024 Paul Gerard R Seghers (TBD), Hybrid modelling using graph neural networks for molecular properties
- 2024 Yitong Yang (TBD), Extending ranges of property prediction methods using machine learning
- 2023 Alessandro Cogliati (TBD), Development and deployment of Deep-learning based property models
- 2022 Nicolai Dynweber Bruhn (TBD), AI Assisted reverse engineering of molecules
- 2022 Fan Fan (TBD), Graph neural networks and uncertainty analysis for pure compound properties
- 2021 Esther Mang Zing (TBD), Application of Graph Neural Networks for chemical property prediction
B.Eng. Theses supervised
- 2022 Nichlas Uhrenholt Nielsen (M.SC. student at DTU), Deep-Learning modelling for nitrous oxide emission characterization
- 2021 Amalie Elsborg Andersen (now Development scientist Novo Nordisk), Modeling of Biochemical Reaction Equilibria, DTU.
Special Courses supervised
- 2024 Felix Oscar Ærtebjerg (M.Sc. student at DTU), Data-driven feature extraction and prediction using Deep Neural Networks
- 2021 Amalie Elsborg Andersen (now Development scientist Novo Nordisk), Stability analysis of liquid mixtures
- 2021 Fan Fan (TBD), Machine Learning for property prediction
Publications
Towards Self-Consistent Graph Neural Networks for Predicting the Ideal Gas Heat Capacity, Enthalpy, and Entropy
Aouichaoui, A. R., Müller, S., & Abildskov, J. (2024). Towards Self-Consistent Graph Neural Networks for Predicting the Ideal Gas Heat Capacity, Enthalpy, and Entropy. In Computer Aided Chemical Engineering (Vol. 53, pp. 2833-2838). Elsevier.
Scoping and Identifying Data-Driven Optimization Prospects in the Danish Processing Industry
Aouichaoui, A. R., Ernstsson, B. B., Jul-Rasmussen, P., Iversen, N. H., Vermue, L., & Huusom, J. K. (2024). Scoping and Identifying Data-Driven Optimization Prospects in the Danish Processing Industry. In Computer Aided Chemical Engineering (Vol. 53, pp. 451-456). Elsevier.
Energy- and process real-time optimization through hybrid modeling - a case from Viking Malt A/S
Jul-Rasmussen, P., Aouichaoui, A. R., Korzepa, M., Engelbrecht, K., Kongsgaard, K., & Huusom, J. K. (2024). Energy-and process real-time optimization through hybrid modeling-a case from Viking Malt A/S. In Computer Aided Chemical Engineering (Vol. 53, pp. 1645-1650). Elsevier.
S-GNN: State-Dependent Graph Neural Networks for Functional Molecular Properties
Aouichaoui, A. R., Cogliati, A., Abildskov, J., & Sin, G. (2023). S-GNN: State-Dependent Graph Neural Networks for Functional Molecular Properties. In Computer Aided Chemical Engineering (Vol. 52, pp. 575-581). Elsevier.
Application of interpretable group-embedded graph neural networks for pure compound properties
Aouichaoui, A. R., Fan, F., Abildskov, J., & Sin, G. (2023). Application of interpretable group-embedded graph neural networks for pure compound properties. Computers & Chemical Engineering, 176, 108291.
Application of Outlier Treatment Towards Improved Property Prediction Models
Aouichaoui, A. R., Mansouri, S. S., Abildskov, J., & Sin, G. (2022). Application of Outlier Treatment Towards Improved Property Prediction Models. In Computer Aided Chemical Engineering (Vol. 51, pp. 1357-1362). Elsevier.
On The Interpretability of Graph Neural Networks in QSPR Modeling
Fan, F., Aouichaoui, A. R., & Sin, G. (2022). On The Interpretability of Graph Neural Networks in QSPR Modeling. In Computer Aided Chemical Engineering (Vol. 51, pp. 1393-1398). Elsevier.
Molecular representations in deep-learning models for chemical property prediction
Aouichaoui, A. R., Fan, F., Mansouri, S. S., & Sin, J. A. G. (2022). Molecular representations in deep-learning models for chemical property prediction. In Computer Aided Chemical Engineering (Vol. 49, pp. 1591-1596). Elsevier.
DeepGSA: Plant Data-Driven Global Sensitivity Analysis using Deep Learning
Aouichaoui, A. R., Al, R., & Sin, G. (2022). DeepGSA: Plant Data-Driven Global Sensitivity Analysis using Deep Learning. In Computer Aided Chemical Engineering (Vol. 49, pp. 1759-1764). Elsevier.
Combining Group-Contribution concept and graph neural networks toward interpretable molecular property models
Aouichaoui, A. R., Fan, F., Mansouri, S. S., Abildskov, J., & Sin, G. (2023). Combining Group-Contribution concept and graph neural networks toward interpretable molecular property models. Journal of Chemical Information and Modeling, 63(3), 725-744.
Uncertainty estimation in deep learning‐based property models: Graph neural networks applied to the critical properties
Aouichaoui, A. R., Mansouri, S. S., Abildskov, J., & Sin, G. (2022). Uncertainty estimation in deep learning‐based property models: Graph neural networks applied to the critical properties. AIChE Journal, 68(6), e17696.
Comparison of group-contribution and machine learning-based property prediction models with uncertainty quantification
Aouichaoui, A. R., Al, R., Abildskov, J., & Sin, G. (2021). Comparison of group-contribution and machine learning-based property prediction models with uncertainty quantification. In Computer Aided Chemical Engineering (Vol. 50, pp. 755-760). Elsevier.
Analysis and evaluation of periodic separations using COPS trays
Nielsen A., Alvarez E.C., Carlsen N., Azizi H., Jorgensen S.B., Abildskov J., 2018, Analysis and evaluation of periodic separations using cops trays, Chemical Engineering Transactions, 69, 733-738
Talks
Towards Self-Consistent Graph Neural Networks for Predicting the Ideal Gas Heat Capacity, Enthalpy, and Entropy
Talk at ESCAPE-33, Florence, Italy
State-aware graph neural networks for temperature-dependent propertie
Talk at ESCAPE-33, Athens, Greece
Combining Functional Groups and Graph Neural Networks Towards Interpretable Molecular Property Models
Talk at AIChE annual meeting 2022, Pheonix, USA
Integrating Chemistry Knowledge and Graph Neural Networks Towards Interpretable Molecular Property Models
Poster at DDSA-2022, Billund, Denmark
DeepGSA: Plant Data-Driven Global Sensitivity Analysis using Deep Learning
Poster at ESCAPE-32, Kyoto, Japan
Molecular Representations in Deep-Learning Models for Chemical Property Prediction
Poster at ESCAPE-32, Kyoto, Japan
Application of Outlier Treatment Towards Improved Property Prediction Models
Poster at ESCAPE-32, Toulouse, France
An Interpretable Graph Neural Network-based Property Prediction
Talk at ESCAPE-32, Toulouse, France
Prediction of Nitrous Oxide Concentration in Wastewater Treatment Plants: Application and Benchmarking of Deep-Learning Models
Poster at AIChE Annual meeting 2021, Boston, USA
Multi-Task Property Prediction: Importance of the “Chemist-in-the-Loop” in Model
Poster at AIChE Annual meeting 2021, Boston, USA
Benchmarking Uncertainty Quantification Methods for Property Prediction Models: Application to Group-Contribution Models
Keynote lecture at the 13th European Congress of Chemical Engineering (ECCE), Berlin, Germany
Data Scarcity in Developing Property Prediction Models: Application of Multi-Task Transfer
Poster at 21st Symposium on thermophysical properties, Colorado, USA
Comparison of Group-Contribution and Machine Learning-based Property Prediction Models with Uncertainty Quantification
Poster at ESCAPE-31, Istanbul, Turkey
Importance of Outlier Treatment for Property Prediction Models
Talk at CAPE Forum 2020, Lyngby, Denmark