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."

arö

You might also be interested in

  • NETWORK DAY of the Alliance for Building-Integrated Photovoltaics on 14.02.
    News
    06.02.2023
    NETWORK DAY of the Alliance for Building-Integrated Photovoltaics on 14.02.
    The 2nd BIPV Alliance Network Day will take place on 14.02.2023 from 10 am to 4 pm. The HZB, a member of the BIPV Alliance, is pleased to host the industry-wide exchange. In addition to practical experiences from representatives from architecture, façade construction and applied research, the focus will be on direct exchange and discussion.

  • Stability of perovskite solar cells reaches next milestone
    Science Highlight
    27.01.2023
    Stability of perovskite solar cells reaches next milestone
    Perovskite semiconductors promise highly efficient and low-cost solar cells. However, the semi-organic material is very sensitive to temperature differences, which can quickly lead to fatigue damage in normal outdoor use. Adding a dipolar polymer compound to the precursor perovskite solution helps to counteract this. This has now been shown in a study published in the journal Science by an international team led by Antonio Abate, HZB. The solar cells produced in this way achieve efficiencies of well above 24 %, which hardly drop under rapid temperature fluctuations between -60 and +80 Celsius over one hundred cycles. That corresponds to about one year of outdoor use.
  • HZB physicist appointed to Gangneung-Wonju National University, South Korea
    News
    25.01.2023
    HZB physicist appointed to Gangneung-Wonju National University, South Korea
    Since 2016, accelerator physicist Ji-Gwang Hwang has been working at HZB in the department of storage rings and beam physics. He has made important contributions to beam diagnostics in several projects at HZB. He is now returning to his home country, South Korea, having accepted a professorship in physics at Gangneung-Wonju National University.