Chris Patrick writes that SLAC researchers have built a neural-network method for compressing large scientific datasets while preserving fine details that conventional compression erases. The approach uses wavelet analysis to separate data features by scale, then encodes each scale separately through a neural network, enabling 10- to 100-fold file size reductions and selective decompression of only the regions a researcher needs.
- Published in Nature Machine Intelligence (August 24, 2026)
- Motivated by upcoming LCLS upgrades that will generate nearly one terabyte of data per second
- Tested successfully on X-ray diffraction data, solar magnetic field measurements, and photographs
- Neural networks trained on Perlmutter at NERSC (Lawrence Berkeley National Lab)
- Co-developers include researchers from UC Davis and Carnegie Mellon University
- Published in Nature Machine Intelligence (August 24, 2026)
- Motivated by upcoming LCLS upgrades that will generate nearly one terabyte of data per second
- Tested successfully on X-ray diffraction data, solar magnetic field measurements, and photographs
- Neural networks trained on Perlmutter at NERSC (Lawrence Berkeley National Lab)
- Co-developers include researchers from UC Davis and Carnegie Mellon University
Researchers have demonstrated that megaelectronvolt MeV electrons induce a strong, ultrafast nonlinear optical response in semiconductors on timescales below 10 picoseconds. This effect is driven by highly localized charge carriers generated during inelastic collisions along ionization trajectories rather than through homogeneous volume deposition. In materials like CdSe, the interaction causes a bandgap shift via band filling, while ZnTe exhibits bandgap renormalization. These findings enable high-precision spatiotemporal detection of ionizing radiation at room temperature, which could enhance medical imaging and plasma monitoring technologies.
* Discovery of sub-10 ps optical modulation from MeV electrons
* Identification of localized charge carrier generation as the driving mechanism
* Observation of band filling and bandgap renormalization in different semiconductors
* Potential for high-precision radiation detection applications
* Discovery of sub-10 ps optical modulation from MeV electrons
* Identification of localized charge carrier generation as the driving mechanism
* Observation of band filling and bandgap renormalization in different semiconductors
* Potential for high-precision radiation detection applications
