ExPaNDS webinar series to showcase achievements and look to the future

We’re pleased to announce our upcoming topic-based webinars which will take place during the coming month before the end of our grant in February 2023. The webinar topics have been selected with the help of our work package leaders and some of the highlighted use cases taken directly from the PaN community throughout our grant.

The series will provide a great opportunity to showcase some of the outcomes of our grant to the PaN facility user communities. We will present some key findings from the recently conducted data consultation, which was sent to over 14,000 PaN facility users.

The ongoing work of ExPaNDS has been very important to the PaN community and we have invited senior community figures to discuss the future needs and requirements for their respective discipline or technique to keep the momentum going beyond the grant.

We will have flash talks from our work packages with focus being on FAIR, data catalogue services, data analysis and an overview of the PaN training platform.

Read more on the ExPaNDS website

Image: Chairman of the DESY Board of Directors – Professor Dr Helmut Dosch

New software based on Artificial Intelligence helps to interpret complex data

Experimental data is often not only highly dimensional, but also noisy and full of artefacts. This makes it difficult to interpret the data. Now a team at HZB has designed software that uses self-learning neural networks to compress the data in a smart way and reconstruct a low-noise version in the next step. This enables to recognise correlations that would otherwise not be discernible. The software has now been successfully used in photon diagnostics at the FLASH free electron laser at DESY. But it is suitable for very different applications in science.

More is not always better, but sometimes a problem. With highly complex data, which have many dimensions due to their numerous parameters, correlations are often no longer recognisable. Especially since experimentally obtained data are additionally disturbed and noisy due to influences that cannot be controlled.

Helping humans to interpret the data

Now, new software based on artificial intelligence methods can help: It is a special class of neural networks (NN) that experts call “disentangled variational autoencoder network (β-VAE)”. Put simply, the first NN takes care of compressing the data, while the second NN subsequently reconstructs the data. “In the process, the two NNs are trained so that the compressed form can be interpreted by humans,” explains Dr Gregor Hartmann. The physicist and data scientist supervises the Joint Lab on Artificial Intelligence Methods at HZB, which is run by HZB together with the University of Kassel.

Read more on the HZB website

Calculating the “fingerprints” of molecules with artificial intelligence

With conventional methods, it is extremely time-consuming to calculate the spectral fingerprint of larger molecules. But this is a prerequisite for correctly interpreting experimentally obtained data. Now, a team at HZB has achieved very good results in significantly less time using self-learning graphical neural networks.

“Macromolecules but also quantum dots, which often consist of thousands of atoms, can hardly be calculated in advance using conventional methods such as DFT,” says PD Dr. Annika Bande at HZB. With her team she has now investigated how the computing time can be shortened by using methods from artificial intelligence.

The idea: a computer programme from the group of “graphical neural networks” or GNN receives small molecules as input with the task of determining their spectral responses. In the next step, the GNN programme compares the calculated spectra with the known target spectra (DFT or experimental) and corrects the calculation path accordingly. Round after round, the result becomes better. The GNN programme thus learns on its own how to calculate spectra reliably with the help of known spectra.

Read more on the HZB website

Image: The graphical neural network GNN receives small molecules as input with the task of determining their spectral responses. By matching them with the known spectra, the GNN programme learns to calculate spectra reliably.

Credit: © K. Singh, A. Bande/HZB