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.

Extracting core principles without prior knowledge

Google Deepmind had already proposed to use β-VAEs in 2017. Many experts assumed that the application in the real world would be challenging, as non-linear components are difficult to disentangle. "After several years of learning how the NNs learn, it finally worked," says Hartmann. β-VAEs are able to extract the underlying core principle from data without prior knowledge.

Photon energy of FLASH determined

In the study now published, the group used the software to determine the photon energy of FLASH from single-shot photoelectron spectra. "We succeeded in extracting this information from noisy electron time-of-flight data, and much better than with conventional analysis methods," says Hartmann. Even data with detector-specific artefacts can be cleaned up this way.

A powerful tool for different problems

"The method is really good when it comes to impaired data," Hartmann emphasises. The programme is even able to reconstruct tiny signals that were not visible in the raw data. Such networks can help uncover unexpected physical effects or correlations in large experimental data sets. "AI-based intelligent data compression is a very powerful tool, not only in photon science," says Hartmann.

Now plug and play

In total, Hartmann and his team spent three years developing the software. "But now, it is more or less plug and play. We hope that soon many colleagues will come with their data and we can support them."


You might also be interested in

  • HZB receives funding to make innovations usable more quickly
    HZB receives funding to make innovations usable more quickly
    The Helmholtz Association has selected three new innovation platforms that will now be funded. HZB is involved in two of them: The Innovation Platform on Accelerator Technologies HI-ACTS is intended to open up modern accelerators for a wide range of applications, while the Innovation Platform Solar TAP is intended to bring new ideas from the laboratories of photovoltaics research more quickly into an application. In total, HZB will receive 4.2 million euros in grants from the Pact for Research and Innovation over the next three years.

  • Green hydrogen: How photoelectrochemical water splitting may become competitive
    Science Highlight
    Green hydrogen: How photoelectrochemical water splitting may become competitive
    Sunlight can be used to produce green hydrogen directly from water in photoelectrochemical (PEC) cells. So far, systems based on this "direct approach" have not been energetically competitive. However, the balance changes as soon as some of the hydrogen in such PEC cells is used in-situ for a catalytic hydrogenation reaction, resulting in the co-production of chemicals used in the chemical and pharmaceutical industries. The energy payback time of photoelectrochemical "green" hydrogen production can be reduced dramatically, the study shows.
  • Perovskite solar cells from the slot die coater - a step towards industrial production
    Science Highlight
    Perovskite solar cells from the slot die coater - a step towards industrial production
    Solar cells made from metal halide perovskites achieve high efficiencies and their production from liquid inks requires only a small amount of energy. A team led by Prof. Dr. Eva Unger at Helmholtz-Zentrum Berlin is investigating the production process. At the X-ray source BESSY II, the group has analyzed the optimal composition of precursor inks for the production of high-quality FAPbI3 perovskite thin films by slot-die coating. The solar cells produced with these inks were tested under real life conditions in the field for a year and scaled up to mini-module size.