Filtern
Dokumenttyp
- Vortrag (5)
- Posterpräsentation (2)
- Zeitschriftenartikel (1)
Sprache
- Englisch (8)
Schlagworte
- Machine Learning (8) (entfernen)
Organisationseinheit der BAM
- 6 Materialchemie (8) (entfernen)
Bonds and local atomic environments are crucial descriptors of material properties. They have been used to create design rules and heuristics and as features in machine learning of materials properties. Implementations and algorithms (e.g., ChemEnv and LobsterEnv) for identifying local atomic environments based on geometrical characteristics and quantum-chemical bonding analysis are nowadays available. Fully automatic workflows and analysis tools have been developed to use quantum-chemical bonding analysis on a large scale. The lecture will demonstrate how our tools, that assess local atomic environments and perform automatic bonding analysis, help to develop new machine learning models and a new intuitive understanding of materials. Furthermore, the general trend toward automation in density functional-based materials science and some of our recent contributions will be discussed.
Bonds and local atomic environments are crucial descriptors of material properties. They have been used to create design rules and heuristics and as features in machine learning of materials properties. Implementations and algorithms (e.g., ChemEnv and LobsterEnv) for identifying local atomic environments based on geometrical characteristics and quantum-chemical bonding analysis are nowadays available. Fully automatic workflows and analysis tools have been developed to use quantum-chemical bonding analysis on a large scale. The lecture will demonstrate how our tools, that assess local atomic environments and perform automatic bonding analysis, help to develop new machine learning models and a new intuitive understanding of materials.[5,6] Furthermore, the general trend toward automation in density functional-based materials science and some of our recent contributions will be discussed.
Bonds and local atomic environments are crucial descriptors of material properties. They have been used to create design rules and heuristics and as features in machine learning of materials properties. Implementations and algorithms (e.g., ChemEnv and LobsterEnv) for identifying local atomic environments based on geometrical characteristics and quantum-chemical bonding analysis are nowadays available. Fully automatic workflows and analysis tools have been developed to use quantum-chemical bonding analysis on a large scale. The lecture will demonstrate how our tools, that assess local atomic environments and perform automatic bonding analysis, help to develop new machine learning models and a new intuitive understanding of materials. Furthermore, other recent workflow contributions to the Materials Project software infrastructure (pymatgen, atomate2) related to phonons and machine-learning potentials will be discussed.
An in-depth insight into the chemistry and nature of the individual chemical bonds is essential for understanding materials. Bonding analysis is thus expected to provide important features for large-scale data analysis and machine learning of material properties. Such chemical bonding information can be computed using the LOBSTER software package, which post-processes modern density functional theory data by projecting the plane wave-based wave functions onto an atomic orbital basis. With the help of a fully automatic workflow, the VASP and LOBSTER software packages are used to generate the data. We then perform bonding analyses on 1520 compounds (insulators and semiconductors) and provide the results as a database. The projected densities of states and bonding indicators are benchmarked on standard density-functional theory computations and available heuristics, respectively. Lastly, we illustrate the predictive power of bonding descriptors by constructing a machine learning model for phononic properties, which shows an increase in prediction accuracies by 27% (mean absolute errors) compared to a benchmark model differing only by not relying on any quantum-chemical bonding features.
Our aim is to develop a simple and inexpensive method for full field X-ray fluorescence imaging.We combine an energydispersive array detector with a coded aperture to obtain high resolut ion images. To obtain the information from the recorded image a reconstruction step is necessary. The reconstruction methods we have developed, were tested on simulated data and then applied to experimental data. The first tests were carried out at the BAMline @BESSY II. This method enables the simultaneous detection of multiple elements,which is important e.g. in the field of catalysis.
Getting more efficient – The use of Bayesian optimization and Gaussian processes at the BAMline
(2022)
For more than 20 years, BAM is operating the BAMline at the synchrotron BESSY II in Berlin Adlershof. During this time, the complexity of the setup and the amount of data generated have multiplied. To increase the effectiveness and in preparation for BESSY III, algorithms from the field of machine learning are increasingly used.
After a short introduction to BO and GP, the first example is the automatic alignment of our double multilayer monochromator (DMM).
The second example is the optimization of measurement time in XRF scanning.
Getting more efficient – The use of Bayesian optimization and Gaussian processes at the BAMline
(2022)
For more than 20 years, BAM is operating the BAMline at the synchrotron BESSY II in Berlin Adlershof. During this time, the complexity of the setup and the amount of data generated have multiplied. To increase the effectiveness and in preparation for BESSY III, algorithms from the field of machine learning are increasingly used.
In this paper, several examples in the areas of beamline alignment and measurement time optimization based on Bayesian optimization (BO) with Gaussian processes (GP) are presented. BO is a method for finding the global optimum of a function using a probabilistic model represented by a GP. The advantage of this method is that it can handle high-dimensional problems, does not depend on the initial estimate, and also provides uncertainty estimates.
After a short introduction to BO and GP, the first example is the automatic alignment of our double multilayer monochromator (DMM). To achieve optimal performance, up to three linear and two angular motor positions have to be optimized. To achieve this with a grid scan, at least 100^5 measurement points would be required. Assuming that all positions can be aligned independently, 100*5 points are still necessary. We show that with BO and GP less than 100 points are sufficient to achieve equal or better results.
The second example is the optimization of measurement time in XRF scanning. Here we will show the advantage of the BO GP approach over point-by-point scanning. As can be seen in Fig. 1, the number of points required and thus the measurement time can be reduced by a factor of 50, while the loss in image quality is acceptable. The advantages and limitations of this approach will be discussed.
In this talk an overview about artificial intelligence/machine learning applications @BAMline is given. In the first part, the use of neural networks for the quantification of XRF measurements and the decoding of coded-aperture measurements are shown. Then it is shown how Gaussian processes and Bayesian statistics can be used to achieve an optimal alignment of the set-up and in general for optimization of measurements.