Servizio momentaneamente sospeso per manutenzione.


Personale Strutture


Professore Associato





Pierantonio Facco is Associate Professor at the Department of Industrial Engineering of the University of Padova. He is a Chemical Engineer and PhD in Industrial Engineering.
His research interests deal with the development of data-driven methodologies to support chemical and process engineering activities for: process and product quality monitoring; product formulation and process development; process understanding and troubleshooting; process continuous improvement; process, product and technology scale-up/down and transfer; statistical and model-based design of experiments; data fusion. His main activities are concerned with data analytics, machine learning, deep learning, hybrid modelling, multivariate statistical process and quality monitoring and control, Quality-by-Design, process and product development, adaptive soft-sensing, process analytical technologies, development of artificial vision systems, development of methodologies to deal with -omics data.
He is author of 100+ publications, among which 55 papers in peer reviewed journals, also as corresponding author, with the following bibliometric indices: H-index=20 on Scopus with 1031 citations in 809 documents; 23 on Google Scholar with 1336 citations; 19 on Web of Science with 887 citations in 680 documents [data assessed on January 19th 2024]. He attended several international congresses, presenting different works, also as an invited speaker. He is referee of several prestigious scientific journals. He is involved in national and international academic collaborations (Imperial College London, University College London, Louisiana State University, Polytechnic University of Valencia, Pukyong National University, Rutgers University) and industrial partnerships (GlaxoSmithKline, Buhler, BASF, Casale, Versalis-Eni, Eli Lilly, Pfizer, Newchem, Fresenius Kabi, Merial/Sanofi, Novamont, Safilo, Unox, Sirca).
Dr. Facco currently teaches Machine learning for process industry for the curriculum of Chemical and Process Engineering, Quality control and data analytics in food production for the curriculum of Food and Health, and Transport phenomena for the curriculum in Environmental Engineering at the University of Padova.
The main skills of Dr. Facco’s are: the ability to transfer research innovations to the industrial world, good communication ability, great attitude to teamwork and to conceive innovative solutions and to develop new research ideas.


Orari di ricevimento

  • Il Venerdi' dalle 10:00 alle 11:00
    presso My office at DII: via Marzolo 9, Padova
    Please, contact me by email ( to schedule a meeting. Telematic meetings can be sheduled, as well.


1. Cenci, F., A. Pankajakshan, P. Facco, F. Galvanin (2023). An exploratory model-based design of experiments approach to aid parameters identification and reduce model prediction uncertainty. Comp. Chem. Eng., 177, 108353
2. Botton, A., G. Barberi, P. Facco (2022). Data augmentation to support biopharmaceutical process development through digital models – A proof of concept. Processes, 10, 1796
3. Arnese Feffin, E., P. Facco, F. Bezzo, M. Barolo (2022). Digital design of new products: accounting for output correlation via a novel algebraic formulation of the latent-variable model inversion problem. Chemom. Intell. Lab. Sys., 227, 104610
4. Barberi, G., A. Benedetti, P. Diaz-Fernandez, D. C. Sévin, J. Vappiani, G. Finka, F. Bezzo, M. Barolo, P. Facco (2022). Integrating metabolomic dynamics and process data in the cell line selection for biopharm process development - A machine learning strategy. Metabolic Engineering, 72, 353-364
5. Cenci, F., G. Bano, C. Christodoulou, Y. Vueva, S. Zomer, M. Barolo, F. Bezzo, P. Facco (2022). Streamlining tablet lubrication design via model-based design of experiments. Int. J. Pharmaceutics, 614, 121435
6. Facco, P., S. Zomer, R. Rowland-Jones, D. Marsh, P. Diaz-Fernandez, G. Finka, F. Bezzo, M. Barolo (2020). Using data analytics to accelerate biopharmaceutical process scale-up. Biochem. Eng. J., 164, 107791
7. Destro, F., P. Facco, S. García-Muñoz, F. Bezzo, M. Barolo (2020). A hybrid framework for process monitoring: enhancing data-driven methodologies with state and parameter estimation. J. Process Control., 92, 333-351.
8. Palacì-López, D., P. Villalba, P. Facco, M. Barolo, A. Ferrer (2020). Improved formulation of the Latent Variable Model Inversion-based optimization problem for Quality by Design applications. J. Chem., 34, e3230
9. Palacì-López, D., P. Facco, A. Ferrer, M. Barolo (2019). New tools for the design and manufacturing of new products based on Latent Variable Model Inversion. Chemom. Intell. Lab. Sys., 194, 103848
10. Facco, P., F. Dal Pastro, N. Meneghetti, F. Bezzo, M. Barolo (2015). Bracketing the design space within the knowledge space in pharmaceutical product development. Ind. Eng. Chem. Res., 54, 5128-5138
11. Facco, P., M. Largoni, E. Tomba, F. Bezzo, M. Barolo (2014). Transfer of process monitoring models between plants: batch systems. Chemical Engineering Research and Design, 92, 273-284
12. Facco, P., A. Masiero, A. Beghi (2013). Advances on Multivariate Image Analysis for Product Quality Monitoring. J. Process Control, 23, 89-98
13. Facco, P., E. Tomba, F. Bezzo, S. García-Muñoz, M. Barolo (2012). Transfer of process monitoring models between different plants using latent variable techniques. Ind. Eng. Chem. Res., 51, 7327-7339
14. Facco, P., F. Bezzo, M. Barolo (2010). Nearest neighbor method for the automatic maintenance of multivariate statistical soft sensors in batch processing. Ind. Eng. Chem. Res., 49, 2336-2347
15. Facco, P., F. Doplicher, F. Bezzo, M. Barolo (2009). Moving-average PLS soft sensor for online product quality estimation in an industrial batch polymerization process. J. Process Control, 19, 520-529.
Facco, P., N. Meneghetti, F. Bezzo, M. Barolo (2018). Mining information from developmental data: process understanding, design space identification, and product transfer. In: Multivariate Analysis in the Pharmaceutical Industry, Elsevier, 267-292.

Area di ricerca

Current and future research interests involve:
• development of innovative techniques for the quality monitoring of high value-added products through multivariate and multiresolution methodologies, including: artificial vision systems for the characterization of materials, such as, granulated powders and nanostructured materials (semiconductors, nanofiber membranes); development and implementation of adaptive systems for the multivariate statistical models updating to new process and plant conditions; anti-fraud and anti-sophistication technologies for pharmaceutical, manufacturing and food industries; Quality-by-Design methodologies for the exploration and the characterization of the design space in the pharmaceutical industry
• development and implementation of methodologies for Machine learning in the Industry 4.0 perspective: data analytics, machine learning and deep learning for process understanding and data mining, pattern recognition and product/process classification, predictive and prescriptive purposes (data compression and visualization, real-time updating of models, model parameter uncertainty characterization)
• development of digital models and digital twins for: process scale-up and scale-down; data augmentation and in-silico experimentation; real time monitoring;
• development of methodologies for the study of –omics data and their integration with process data in the biopharmaceutical industry: definition of a host-specific culture management to condition the cell behavior to the desired performance through specific process settings and feeding strategies; development of a methodology to identify targets for host engineering in terms of metabolites and metabolic pathways;
• data augmentation for process monitoring and scale-up;
• definition of optimal experimental protocols from design of experiments (DoE), dynamic design of experiments and model-based DoE (streamlining drug substance and the drug product development in the pharmaceutical industry; reducing the cost of the experimental campaigns)
• development of hybrid models;
• development of novel methodologies for both the product formulation and the process, product and technology transfer between different production scales or different industrial sites

Tesi proposte

• Development of a machine learning framework for the multivariate monitoring of a continuous direct compression manufacturing process.
• Enhancing the understanding of CHO cell culture metabolic traits through integrated first-principle modelling and data-based parameter estimation
• Development of machine learning methods for the characterization of the product quality in the production of resins – An industrial case study.
• Formulation of polyurethane foams through multivariate machine learning (in italian).
• De’ Longhi logistic flux redefinition through a “just-in-time” strategy
• Process understanding of the centrifugation of an active principle for the production of antibiotics through machine learning
• Optimization on biopharmaceutical production protocols through dynamic Design of Experiments on digital twins.
• Data augmentation through digital twins to support quality monitoring in the biopharmaceutical industry.
• Development of an industrial process of low-delamination pharmaceutical glass vials forming.
• Development of deep learning methodologies to diagnose serious diseases.
• LLDPE-C4 spot price prediction to plan the purchase strategies through machine learning (in Italian).
• Comparison between different multivariate regression techniques for quality real-time estimation of product quality in batch processes.
• Development of multivariate statistical techniques for data reconciliation in refinery heat exchangers.
• Data-driven reaction modelling to accelerate drug substance development.
• Multivariate and multi-resolution soft-sensor development in fed-batch fermenters for the production of penicillin. (in Italian)