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

  • Unconventional piezoelectricity in ferroelectric hafnia
    Science Highlight
    Unconventional piezoelectricity in ferroelectric hafnia
    Hafnium oxide thin films are a fascinating class of materials with robust ferroelectric properties in the nanometre range. While the ferroelectric behaviour is extensively studied, results on piezoelectric effects have so far remained mysterious. A new study now shows that the piezoelectricity in ferroelectric Hf0.5Zr0.5O2 thin films can be dynamically changed by electric field cycling. Another ground-breaking result is a possible occurrence of an intrinsic non-piezoelectric ferroelectric compound. These unconventional features in hafnia offer new options for use in microelectronics and information technology.
  • 14 parameters in one go: New instrument for optoelectronics
    Science Highlight
    14 parameters in one go: New instrument for optoelectronics
    An HZB physicist has developed a new method for the comprehensive characterisation of semiconductors in a single measurement. The "Constant Light-Induced Magneto-Transport (CLIMAT)" is based on the Hall effect and allows to record 14 different parameters of transport properties of negative and positive charge carriers. The method was tested now on twelve different semiconductor materials and will save valuable time in assessing new materials for optoelectronic applications such as solar cells.
  • Sodium-ion batteries: How doping works
    Science Highlight
    Sodium-ion batteries: How doping works
    Sodium-ion batteries still have a number of weaknesses that could be remedied by optimising the battery materials. One possibility is to dope the cathode material with foreign elements. A team from HZB and Humboldt-Universität zu Berlin has now investigated the effects of doping with Scandium and Magnesium. The scientists collected data at the X-ray sources BESSY II, PETRA III, and SOLARIS to get a complete picture and uncovered two competing mechanisms that determine the stability of the cathodes.