Tag: teaching

Jan 21 2025

Machine Learning and Artificial Intelligence in modern materials science

  • Filed under blog

  • January 21, 2025

One of the most joyful parts of teaching, is when you read a student paper and see their joy of the research shine through.

This year was the second year I taught the course “Machine Learning and Artificial Intelligence in modern materials science“, an elective course in the second master materiomics program. As with my other computational courses, there is a strong hands-on component present in this course: a semester long homework assignment, culminating in a paper and presentation of the work done. The basic idea behind the assignment is simple: Take the QM9 dataset and study it using machine learning and artificial intelligence, incorporating things you learn during the course. In practice this means a lot of coding with for example scikit-learn in combination with using every ounce of physical and chemical intuition they gathered during their previous courses. The absolute freedom generally results in some initial trepidation, but intermediate feedback and the growing understanding that the journey is the the actual goal results in some amazing work.

At the end of the semester, I had three papers before me, which could only be written by these three students (Materiomics is a new program, so having 3 of the 7 students picking a rather hard core computational course is good 😉 ). You could feel their own backgrounds and interests seeping through, as well as the fun they had doing so. There was the engineer who approached the problem from a pipeline perspective, the chemist comparing the efficacy of various fingerprints as features, and the physicist who build a new small fingerprint from scratch creating a linear regression model that outperformed all else having R² =1. The last one is a very nice example of frugal computing, of which we do need more in a world suffering climate change. It was also interesting to see also how three totally different stories also hint at the same underlying properties of the dataset (same target being the hardest to predict), a consistency which provides a level of meta-validation of the results. The students themselves also learned to be critical of their own work by comparing the results of different methods used to attack their own research question.

At the end of this course, it is clear they learned more about artificial intelligence than what is possible by just reading about it. The understood the entire workflow of which training is merely a small part, they learned directly the importance of having good quality data and features, and most importantly they learned that they themselves need to be the I in AI, to be successful…and finally, maybe us four should put our heads together and combine this work into a real research paper, as to celebrate the great research done as a “mere homework-assignment”.

Permanent link to this article: https://dannyvanpoucke.be/machine-learning-and-artificial-intelligence-in-modern-materials-science/

Dec 22 2023

Materiomics Chronicles: week 13 & 14

Weeks eleven and twelve gave some rest, needed for the last busy week of the semester: week 13. During this week, I have an extra cameo in the first year our materiomics program at UHasselt.

NightCafe's response to the prompt: "Professor teaching quantum chemistry."

NightCafe’s response to the prompt: “Professor teaching quantum chemistry.”

Within the Bachelor of chemistry, the courses introduction to quantum chemistry and quantum and computational chemistry draw to a close, leaving just some last loose to tie up. For the second bachelor students in chemistry, this meant diving into the purely mathematical framework describing the quantum mechanical angular momentum and discovering spin operators are an example, though they do not represent an actual rotating object. Many commutators were calculated and ladder operators were introduced. The third bachelor students in chemistry dove deeper in the quantum chemical modeling of simple molecules, both in theory as well as in computation using a new set of jupyter notebooks during an exercise session.

In the first master materiomics, I had gave the students a short introduction into high-throughput modeling and computational screening approaches during a lecture and exercise class in the course Materials design and synthesis. The students came into contact with materials project via the web-interface and the python API. For the course on Density Functional Theory there was a final guest response lecture, while in the course Machine learning and artificial intelligence in modern materials science a guest lecture on optimal control was provided. During the last response lecture, final questions were addressed.

With week 14 coming to a close, the first semester draws to an end for me. We added another 15h of classes, ~1h of video lecture, and 3h of guest lectures, putting our semester total at 133h of live lectures (excluding guest lectures, obviously). January and February brings the exams for the second quarter and first semester courses.

I wish the students the best of luck with their exams, and I happily look back at surviving this semester.

Permanent link to this article: https://dannyvanpoucke.be/materiomics-chronicles-week-13-14/

Dec 10 2023

Materiomics Chronicles: week 11 & 12

After the exam period in weeks nine and ten, the eleventh and twelfth week of the academic year bring the second quarter of our materiomics program at UHasselt for the first master students. Although I’m not coordinating any courses in this quarter, I do have some teaching duties, including being involved in two of the hands-on projects.

As in the past 10 weeks, the bachelor students in chemistry had lectures for the courses introduction to quantum chemistry and quantum and computational chemistry. For the second bachelor this meant they finally came into contact with the H atom, the first and only system that can be exactly solved using pen and paper quantum chemistry (anything beyond can only be solved given additional approximations.) During the exercise class we investigated the concept of aromatic stabilization in more detail in addition to the usual exercises with simple Schrödinger  equations and wave functions. For the third bachelor, their travel into the world of computational chemistry continued, introducing post-Hartree-Fock methods with also include the missing correlation energy. This is the failure of Hartree-Fock theory, making it a nice framework, but of little practical use for any but the most trivial molecules (e.g. H2 for example already being out of scope). We also started looking into molecular systems, starting with simple diatomic molecules like H2+.

SnV split vacancy defect in diamond.

SnV split vacancy defect in diamond.

In the master materiomics, the course Machine learning and artificial intelligence in modern materials science hosted a guest lecture on Large Language Models, and their use in materials research as well as an exercise session during which the overarching ML study of the QM9 dataset was extended. During the course on  Density Functional Theory there was a second lab, this time on conceptual DFT. For the first master students, the hands-on project kept them busy. One group combining AI and experiments, and a second group combining DFT modeling of SnV0 defects in diamond with their actual lab growth. It was interesting to see the enthusiasm of the students. With only some mild debugging, I was able to get them up and running relatively smoothly on the HPC. I am also truly grateful to our experimental colleagues of the diamond growth group, who bravely set up these experiments and having backup plans for the backup plans.

At the end of week 12, we added another 12h of classes, ~1h of video lecture, ~2h of HPC support for the handson project and 6h of guest lectures, putting our semester total at 118h of live lectures. Upwards and onward to weeks 13 & 14.

Permanent link to this article: https://dannyvanpoucke.be/materiomics-chronicles-week-11-12/

Nov 26 2023

Materiomics Chronicles: week 9 & 10

With the end of the first quarter in week eight, the nine and tenth week of the academic year were centered around the first batch of exams for the first master students of our materiomics program at UHasselt. For the other students in the second master and bachelor, academic life continued with classes.

Coefficients of the 63-1G basis set for the H and He atom.

Coefficients of the 63-1G basis set for the H and He atom.

The course introduction to quantum chemistry starts to hone in on the first actual fully realistic system: the H atom. But before we get there, the students of the second bachelor chemistry extended their particle on a ring model system to an infinite number of ring systems: i.e. discs, spheres, and balls. Separation of variables has no longer any secrets for them. Now they are ready for reality after many weeks of abstract toy models. The third bachelor students on the other hand had their first ever contact with real practical quantum chemistry (i.e. computational chemistry) during the course quantum and computational chemistry. They learned about Hartree-Fock, the self-consistent field method, basis sets and slater orbitals. They entered this new world with a practical exercise class where, using jupyter notebooks and the psi4 package, they performed their first even quantum chemical calculations. Starting with the trivial H and He atom systems as a start, since for these we have calculated exact solutions during the classes of this course. This way, we learned about the quality of different basis sets and the time of calculations.

In the master materiomics, the first master students had their exams on Fundamentals of materials modeling, and Properties of functional materials, where all showed they understood the topics presented to sufficient degree making them ready for the second quarter. For the second master students, the course on Density Functional Theory held a lecture on the limitations of DFT and a guest lecture on conceptual DFT.

With week 10 drawing to a close, we added another 15h of classes, ~1h of video lecture and 2h of guest lectures, putting our semester total at 106h of live lectures. Upwards and onward to weeks 11 & 12.

Permanent link to this article: https://dannyvanpoucke.be/materiomics-chronicles-week-9-10/

Nov 12 2023

Materiomics Chronicles: week 8

After the complexities of week seven, week eight brings the last lecture week of the first quarter of the academic year. After this week, the students of our materiomics program at UHasselt will start studying for a first batch of exams. It also means with this week, their basic courses come to an end and they have all been brought up to speed and to a similar level, needed for the continuation of their study in the materiomics program.

In the bachelor program, the third bachelor chemistry students ended their detailed study of the He atom in the course quantum and computational chemistry with the investigation of its excited states. They learned about the splitting of in singlet and triplet states as well as Fermi-holes and heaps.

Vulcanoplot

Vulcano-plot of small data model quality of model instances in a large ensemble. Taken from our paper “Small Data Materials Design with Machine Learning: When the Average Model Knows Best“, J. Appl. Phys. 128, 054901 (2020)

The first mater materiomics students got their last lecture in the course Fundamentals of materials modeling, where we looked into some examples of application of machine learning in materials research. We also brought all levels of the course together and imagined how to link these in a multiscale project. Starting from the example of a windmill we discussed the application of computational materials modeling at different scales. For the course Properties of functional materials, the third and final presentation and discussion was held, now focusing on characterization methods. The second master students had response lectures for the courses on Density Functional Theory and Machine learning and artificial intelligence in modern materials science where the various topics of the self study were discussed (e.g., concepts of Neural Networks in case of the latter).

At the end of this week, we have added another 8h of live lectures, putting our semester total at 99h of live lectures. With the workload of the first master materiomics coming to an end, the following chronicles will be biweekly. Upwards and onward to week 9&10.

 

Permanent link to this article: https://dannyvanpoucke.be/materiomics-chronicles-week-8/

Nov 05 2023

Materiomics Chronicles: week 7

After a relatively chill week six, the seventh week of the academic year ended up being complicated. As it was fall-break the week only consisted of two class days at university. However, primary schools are closed entirely so our son was at home having a holiday, while both parents were trying to juggle classes and project proposal deadlines as well as additional administrative reporting. A second evaluation meeting with the students of our materiomics program at UHasselt took place (second master this time), and also these students appreciated the effort put into creating their classes.

Although there were only two days of teaching, this did not mean there was little work there. The students of the second bachelor in chemistry extended their knowledge of a particle in a box to the model of a particle on a ring, during the course introduction to quantum chemistry. Similar as for a particle in a box, this can be considered a simplified model for a circular molecule like benzene, allowing us to estimate the first excitation quite accurately.

For the course Fundamentals of Materials Modeling, there was a lecture introducing the first master students materiomics into the very basics of machine learning, as well as an exercise session. During these, the students learned about linear regression, decision trees and support vector machines. This class was also open to students of the bachelor programs to get a bit of an idea of the content of the materiomics program. Finally, the first master students also presented the results of their lab on finite element modeling as part of the course Fundamentals of Materials Modeling. They presented flow studies around arrows, reef and car models, as well as heat transfer in complex partially insulated systems, as well as sinking boats. They showed they clearly gained insight through this type of hands-on tasks, which is always a joy to note, resulting in grades reflecting their efforts and insights.

Though this week was rather short, we added another 6h of classes, putting our semester total at 91h of live lectures. Upwards and onward to week 8.

Permanent link to this article: https://dannyvanpoucke.be/materiomics-chronicles-week-7/

Oct 29 2023

Materiomics Chronicles: week 6

After surviving week five, the sixth week of the academic year feels almost relaxing. However, all the effort is worth it, and I was happy to hear the students of our materiomics program at UHasselt appreciate the effort put into creating their classes, during an evaluation meeting.

The evolution of the Z position of a Be atom on Graphene. Periodic cell with 10 Angstrom vacuum along z direction. Z position is given in direct coordinates (0...1), with the graphene sheet positioned at z=0 (=1). The Be atom is van der Waals bonded, and moves through the vacuum to attach to the "bottom" side of the sheet, though originally positioned at the "top" side.

The evolution of the Z position of a Be atom on Graphene. Periodic cell with 10 Angstrom vacuum along z direction. Z position is given in direct coordinates (0…1), with the graphene sheet positioned at z=0 (=1). The Be atom is van der Waals bonded, and moves through the vacuum to attach to the “bottom” side of the sheet, though originally positioned at the “top” side.

Though the week was not as intense as the week before does not mean there were no classes at all. The second bachelor students in chemistry continued their studies of particles in simple potentials though the study of a particle in a square infinite potential well during the course introduction to quantum chemistry. During the course quantum and computational chemistry, the third bachelor chemistry, the He atom was now studied by means of the variational method, introducing the concepts of effective nuclear charge and shielding in a natural way.

While the bachelor students could take a backseat approach during the lectures (except for calculating some bbracket integrals), the master materiomics students had to do most of the heavy lifting during their classes. For the course on Density Functional Theory there was response lecture as well as a lab-session where they studied the dynamics of Be on and around graphene, while the first master students had their second presentation & discussion session on the computational aspects of the papers studied in the course Properties of functional materials.

At the end of this week, we added another 11h of live classes and ~2h of video lectures, putting our semester total at 85h of live lectures. Upwards and onward to week 7.

Permanent link to this article: https://dannyvanpoucke.be/materiomics-chronicles-week-6/

Oct 22 2023

Materiomics Chronicles: week 5

After week four, this fifth week of the academic year is most arguably the most intense and hectic week of teaching. With 22h of classes and still two classes that needed to be prepared from scratch (even including weekends time was running out), I’m tired but happy it is over. However, all the effort is worth it, and I was happy to hear the students of our materiomics program at UHasselt appreciate the effort put into creating their classes, during an evaluation meeting.

The corral is an artificial structure created from 48 iron atoms (the sharp peaks) on a copper surface. The wave patterns in this scanning tunneling microscope image are formed by copper electrons confined by the iron atoms. Don Eigler and colleagues created this structure in 1993 by using the tip of a low-temperature scanning tunneling microscope (STM) to position iron atoms on a copper surface, creating an electron-trapping barrier. This was the first successful attempt at manipulating individual atoms and led to the development of new techniques for nanoscale construction.source: https://www.nisenet.org/catalog/scientific-image-quantum-corral-top-view

The corral is an artificial structure created from 48 iron atoms (the sharp peaks) on a copper surface. The wave patterns in this scanning tunneling microscope image are formed by copper electrons confined by the iron atoms. Don Eigler and colleagues created this structure in 1993 by using the tip of a low-temperature scanning tunneling microscope (STM) to position iron atoms on a copper surface, creating an electron-trapping barrier. This was the first successful attempt at manipulating individual atoms and led to the development of new techniques for nanoscale construction.
source: https://www.nisenet.org/catalog/scientific-image-quantum-corral-top-view

For the second bachelor students in chemistry the introduction to quantum chemistry finally put them into contact with some “real” quantum mechanics when they were introduced into the world of potential barriers, steps, and wells. Though these are still abstract and toy-model in nature, they provide a first connection with reality, where they can be seen as crude approximations of the potential experienced by valence electrons near the surface, or STM experiments. They were also introduced to my favorite quantum system related to this course: the quantum corral. Without any effort it can be used in half a dozen situations with varying complexity to show and learn basic quantum mechanics. For the third bachelor chemistry students the course quantum and computational chemistry finally provided them the long promised first example of a non-trivial quantum chemical object: The Helium atom. With it’s two electrons, we break free of the H-atom(-like)  world. Using perturbation theory and Slater determinant wave functions, we made our first approximations of its energy. In addition, these students also had a seminar for their course Introductory lectures in preparation to the bachelor project (Kennismakingstraject m.b.t. stage en eindproject, in Dutch). During this lecture I gave a brief introduction and overview of the work I did in the past and the work we do in our research group QuATOMs, which although “quantum” is quite different of what the students experience during their courses on quantum chemistry.

In the materiomics program, the first master students continued their travels into the basics of force-fields during the lecture of the course Fundamentals of materials modelling. The exercise class of this week upped the ante by moving from ASE to LAMMPS for practical modeling of alkane chains, which was also the topic of their second lab session. In the course Properties of functional materials, we investigated the ab initio modelling of vibrations. During the exercise classes we investigated precalculated phonon spectra in the materials-project database, as well as calculated our own vibrational spectrum at the gamma-point of the first Brillouin zone. During the second master course Machine learning and artificial intelligence in modern materials science the central theme was GIGO (Garbage-In-Garbage-Out). How can we make sure our data is suitable and good enough for our models to return useful results. We therefore looked into data-preparation & cleaning, as well as  clustering methods.

At the end of this week, we have added another 22h of live lectures and ~1h of video lectures, putting our semester total at 74h of live lectures. Upwards and onward to week 6.

Permanent link to this article: https://dannyvanpoucke.be/materiomics-chronicles-week-5/

Oct 15 2023

Materiomics Chronicles: week 4

Week four of the academic year at the chemistry and materiomics programs of UHasselt, we are stepping up the pace a bit…at least for me. The students continue to dive deeper into the various subjects furthering their knowledge gained in the previous weeks.

In the bachelor chemistry program, the third bachelor chemistry extended their knowledge of variational theory to excited states, in the course quantum and computational chemistry. They also saw some first glimpses of the mathematical setup which makes the use of computational methods so important and powerful in quantum chemistry.  Finally they proved the Hellmann-Feynman Theorem which makes structure optimization in quantum chemistry practically feasible. For the second bachelor chemistry, the course introduction to quantum chemistry was focused on the time-dependent Schrödinger equation and the uncertainty principle.

In the first master materiomics, I was the  main player this week (and will also be so next week) teaching the classes of two of the three courses. In the course Properties of functional materials, the second module started, which is centered on the computational (quantum mechanical) modeling of materials properties. Here the students build on their recently acquired expertise in DFT to gain further insights into electronic structure calculations both in theory and in practice. In addition, the students also had their first seminar presentation where they present their understanding after studying two papers within the context of the concepts presented during the first module of the course. In the course Fundamentals of materials modelling, we moved to a new level of modeling: atomistic modeling using force-fields. The freshly gained knowledge was also here directly applied through the modeling of bulk aluminum using the ASE library in a jupyter notebook. (For many a first contact with python.) Finally, the students of the second master learned about “dynamical” modeling, in the course on Density Functional Theory, covering NEB calculations for energy barriers as well as basic molecular dynamics (with examples such as the water molecule below).

 

At the end of this week, we have added another 17h of live lectures and ~1h of video lectures, putting our semester total at 52h of live lectures. Upwards and onward to week 5.

Permanent link to this article: https://dannyvanpoucke.be/materiomics-chronicles-week-4/

Oct 07 2023

Materiomics Chronicles: week 3

In week three of the academic year at the chemistry and materiomics programs of UHasselt, the students started to put their freshly gained new knowledge of weeks 1 and 2 into practice with a number of exercise classes.

For the second bachelor chemistry students, this meant performing their first calculations within the context of the course introduction to quantum chemistry. At this point this is still very mathematical (e.g., calculating commutators) and abstract (e.g., normalizing a wave function or calculating the probability of finding a particle, given a simple wave function), but this will change, and chemical/physical meaning will slowly be introduced into the mathematical formalism. For the third bachelor chemistry, the course quantum and computational chemistry continued with perturbation theory, and we started with the variational method as well. The latter was introduced through the example of the H atom, for which the exact variational ground state was recovered starting from a well chosen trial wave function.

Infinite polymethylene glycol (POM) chain.

Ball-and-stick representation of an infinite polymethylene glycol (POM) chain.

In the master materiomics, the first master course fundamentals of materials modelling, dove into the details underpinning DFT introducing concepts like pseudo-potentials, the frozen-core approximation, periodic boundary conditions etc. This knowledge was then put into practice during a second exercise session working on the supercomputer, as a last preparation for the practical lab exercise the following day. During this lab, the students used the supercomputer to calculate the Young modulus of two infinite linear polymers. An intense practical session which they all executed with great courage (remember 2 weeks ago they never heard of DFT, nor had they accessed a supercomputer). Their report for this practical will be part of their grade.

For the second master materiomics, the course focused on Density Functional Theory consisted of a discussion lecture, covering the topics the students studied during their self study assignments. In addition, I recorded two video lectures for the blended learning part of the course. For the course Machine learning and artificial intelligence in modern materials science self study topics were covered in such a discussion lecture as well. In addition, the QM9 data set was investigated during an exercise session, as preparation for further detailed study.

At the end of this week, we have added another 16h of live lectures and ~1h of video lectures, putting our semester total at 35h of live lectures. Upwards and onward to week 4.

Permanent link to this article: https://dannyvanpoucke.be/materiomics-chronicles-week-3/