# Michele Ceriotti delivers E. Bright Wilson Prize Lecture December 04, 2024 - [ News ](/news-categories/news) On Tuesday, December 4, Michele Ceriotti, [Associate Professor at École Polytechnique Fédérale de Lausanne](https://people.epfl.ch/michele.ceriotti?lang=en), delivered his [E. Bright Wilson Prize Lecture](/e-bright-wilson-prize) entitled "Machine learning for chemistry: between physics and scaling." For over 50 years, [E. Bright Wilson, Jr.](https://chemistry.harvard.edu/files/chemistry/files/e._b._wilson_memorial_minute.pdf), was one of the most distinguished and admired professors of chemistry at Harvard. The E. Bright Wilson Prize has been awarded annually by CCB since 1983; this year Ceriotti was introduced by CCB Professor [Joonho Lee](/people/joonho-lee). Machine-learning techniques are often applied to perform "end-to-end" predictions, that is to make a black-box estimate of a property of interest using only a coarse description of the corresponding inputs. In contrast, atomic-scale modeling of matter is most useful when it allows one to gather a mechanistic insight into the microscopic processes that underlie the behavior of molecules and materials. In this talk Ceriotti provided an overview of the progress that has been made combining these two philosophies, using data-driven techniques to build surrogate models of the quantum mechanical behavior of atoms, enabling "bottom-up" simulations that reveal the behavior of matter in realistic conditions with uncompromising accuracy. He critically discussed two ways by which physical-chemical ideas can be integrated into a machine-learning framework. One way involves using physical priors, such as smoothness or symmetry of the structure-property relations, to inform the mathematical structure of a generic ML approximation - an approach that has become ubiquitous in the field, but that is increasingly challenged by the emergence of unconstrained models that can directly learn physical constraints from large amounts of data data. The other entails a deeper level of integration, in which explicit physics-based models and approximations are built into the model architecture. Ceriotti discussed several examples of the application of these ideas, from the calculation of electronic excitations to the design of solid-state electrolyte materials for batteries and high-entropy alloys for catalysis, emphasizing both the accuracy and the interpretability that can be achieved with a hybrid modeling approach, and providing an overview of the exciting research directions that are made available by these new modeling tools. Michele Ceriotti received his Ph.D. in Physics from ETH Zürich. He spent three years in Oxford as a Junior Research Fellow at Merton College. Since 2013 he leads the laboratory for Computational Science and Modeling, in the institute of Materials at EPFL, that focuses on method development for atomistic materials modeling based on statistical mechanics and machine learning. He is one of the core developers of several open-source software packages, including [http://ipi-code.org](http://ipi-code.org/) and [http://chemiscope.org](http://chemiscope.org/), and proudly serves the atomistic modeling community as an associate editor of the Journal of Chemical Physics, as a moderator of the physics.chem-ph section of the arXiv, and as an editorial board member of Physical Review Materials. Pictures below: ![Joonhoimg_8243jpg.jpg](/sites/g/files/omnuum7776/files/chemistry/files/img_8243jpg.jpg) ![JoonhoCeriottiimg_8244jpg.jpg](/sites/g/files/omnuum7776/files/chemistry/files/img_8244jpg.jpg) ![Ceriottiimg_8250jpg.jpg](/sites/g/files/omnuum7776/files/chemistry/files/img_8250jpg.jpg) ![Ceriottiimg_8253jpg.jpg](/sites/g/files/omnuum7776/files/chemistry/files/img_8253jpg.jpg) ![Ceriottiimg_8257jpg.jpg](/sites/g/files/omnuum7776/files/chemistry/files/img_8257jpg.jpg) ![Ceriottiimg_8258jpg.jpg](/sites/g/files/omnuum7776/files/chemistry/files/img_8258jpg.jpg) ![Ceriottiimg_8267jpg.jpg](/sites/g/files/omnuum7776/files/chemistry/files/img_8267jpg.jpg) ![Ceriottiimg_8273jpg.jpg](/sites/g/files/omnuum7776/files/chemistry/files/img_8273jpg.jpg) ![Ceriottiimg_8275jpg.jpg](/sites/g/files/omnuum7776/files/chemistry/files/img_8275jpg.jpg) ![Ceriottiimg_8277jpg.jpg](/sites/g/files/omnuum7776/files/chemistry/files/img_8277jpg.jpg) ![Ceriottiimg_8280jpg.jpg](/sites/g/files/omnuum7776/files/chemistry/files/img_8280jpg.jpg) ![Joonhoimg_8281jpg.jpg](/sites/g/files/omnuum7776/files/chemistry/files/img_8281jpg.jpg) ![JoonhoandCeriottiimg_8285jpg.jpg](/sites/g/files/omnuum7776/files/chemistry/files/img_8285jpg.jpg) ![img_8286jpg.jpg](/sites/g/files/omnuum7776/files/img_8286jpg.jpg) See also:- [ Lee ](/news-and-events-faculty/lee) - [ Prizes & Awards ](/news-type/prizes-awards) Share on:- [ Facebook ](#) - [ Twitter ](#) - [ Linkedin ](#)