E N

A B

LI N

G T

E C

H N

O LO

G IE

S

1 7 3 I H I G H L I G H T S 2 0 2 3

PRINCIPAL PUBLICATION AND AUTHORS

Closing the loop: autonomous experiments enabled by machine-learning-based online data analysis in synchrotron beamline environments , L. Pithan (a,e), V. Starostin (a), D. Mareček (b), L. Petersdorf (c), C. Völter (a), V. Munteanu (a), M. Jankowski (d), O. Konovalov (d), A. Gerlach (a), A. Hinderhofer (a), B. Murphy (c), S. Kowarik (b), F. Schreiber (a), J. Synchrotron Rad. 30, 1064- 1075 (2023); https:/doi.org/10.1107/S160057752300749X (a) University Tübingen, Tübingen (Germany) (b) University Graz, Graz (Austria) (c) University Kiel, Kiel (Germany) (d) ESRF, (e) DESY

REFERENCES

[1] https:/ www.daphne4nfdi.de [2] A. Hinderhofer et al., J. Appl. Cryst. 56, 3-11 (2023). [3] https:/ www.tango-controls.org, [4] https:/ bliss.gitlab-pages.esrf.fr/bliss [5] J.-F. Perrin, ESRF Highlights 2022, 158-159 (2022).

allows for multiple, different SLD profiles to correspond to the same curve within the bounds of measurement uncertainty. Fundamentally, this is related to the famous phase problem of scattering. Consequently, it is vital in reflectivity analysis to make use of the physical understanding of the investigated system in order to reduce the number of potential solutions and to identify the correct one. In this work, two methods to integrate existing physical knowledge into the ML model at runtime are highlighted: physics-based parameterisation, and the including of boundaries through open parameters as additional input to the neural network (Figure 136a).

Molecular thin films of AlQ3 were chosen for demonstration purposes. With the aim to grow molecular thin films of predefined thickness, an ML-based autonomous experiment took control over the growth process and terminated it once the target thickness was reached (Figures 136b and 137). Prior knowledge from preceding measurements (e.g. a plausible film thickness range) was provided as input of the ML model to achieve robust fitting for a large number of consecutive scans. Figure 137b shows the result of the closed-loop deposition control for several target thicknesses between 80 Å and 640 Å. As expected for well-functioning closed-loop control, the target thicknesses closely matched the reached thicknesses, except for one outlier. Overall, the chosen target thicknesses could be reached within ±2 Å average accuracy. The control software BLISS was used to store the ML analysis results together with the original raw data in one NeXus-compliant hdf5 file and to interact with the facility-provided electronic notebook.

This use case convincingly demonstrates the main advantages of using ML in this context. The ML approach gives reliable fit results both for simple two- to three-layer models as well as for complex multilayer models in the millisecond regime. The combined speed and reliability of the ML approach could not be achieved by simple fitting scripts or with reliance on human supervision. More widely, ML-based online data analysis has enormous potential to make publicly available datasets FAIR through enriching the raw archived data with scientifically relevant, real- time data analysis results (data + metadata).

Fig. 137: a) X-ray reflectivity measurement results and corresponding fits performed on-the-fly. b) The target

thicknesses are plotted on the x-axis, while the truly reached film thicknesses at which the deposition was terminated are given on the y-axis. In this representation, data on the diagonal line

illustrates the well-functioning closed-loop experiment.