Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Study of Dangling Bond States in Magnetron-Sputtered a-Si Thin Films via Parametrization Using a Single UV-Vis-NIR Transmittance Spectrum.

Molecules (Basel, Switzerland)·2026
Same author

High-Accuracy Characterization of a Single Thin Film on a Substrate from One Transmittance Spectrum by an Advanced Envelope Method Addressing Voids, Tail Electron Transitions, and Deep-Level Electron Transitions in a-Si Films.

Nanomaterials (Basel, Switzerland)·2026
Same author

Investigating Structurally and Pigmentary Colored Featherworks via Noninvasive Methodologies.

ACS omega·2026
Same author

Optimizing atrial fibrillation detection through ECG feature selection using Extra-Trees and statistical association measures.

Journal of electrocardiology·2026
Same author

Predicting substance use behaviors with machine learning using small sets of judgment and contextual variables.

Npj mental health research·2026
Same author

Automated HFrEF Diagnosis Using an Optimized TimeSformer Model in Echocardiography.

Journal of imaging informatics in medicine·2025

Related Experiment Video

Updated: Jun 29, 2025

Subsurface Defect Localization by Structured Heating Using Laser Projected Photothermal Thermography
11:34

Subsurface Defect Localization by Structured Heating Using Laser Projected Photothermal Thermography

Published on: May 15, 2017

11.1K

A physics based machine learning model to characterize room temperature semiconductor detectors in 3D.

Srutarshi Banerjee1, Miesher Rodrigues2, Manuel Ballester3

  • 1Northwestern University, 2145 Sheridan Road, Evanston, IL, 60208, USA. srutarshibanerjee2022@u.northwestern.edu.

Scientific Reports
|April 2, 2024
PubMed
Summary

A new physics-based machine learning model characterizes room temperature semiconductor radiation detectors (RTSD) in 3D. This approach models charge transport properties within sub-pixel voxels for improved detector performance and advanced imaging applications.

More Related Videos

Thermal Measurement Techniques in Analytical Microfluidic Devices
08:29

Thermal Measurement Techniques in Analytical Microfluidic Devices

Published on: June 3, 2015

9.6K
Fiber Optic Distributed Sensors for High-resolution Temperature Field Mapping
09:48

Fiber Optic Distributed Sensors for High-resolution Temperature Field Mapping

Published on: November 7, 2016

12.0K

Related Experiment Videos

Last Updated: Jun 29, 2025

Subsurface Defect Localization by Structured Heating Using Laser Projected Photothermal Thermography
11:34

Subsurface Defect Localization by Structured Heating Using Laser Projected Photothermal Thermography

Published on: May 15, 2017

11.1K
Thermal Measurement Techniques in Analytical Microfluidic Devices
08:29

Thermal Measurement Techniques in Analytical Microfluidic Devices

Published on: June 3, 2015

9.6K
Fiber Optic Distributed Sensors for High-resolution Temperature Field Mapping
09:48

Fiber Optic Distributed Sensors for High-resolution Temperature Field Mapping

Published on: November 7, 2016

12.0K

Area of Science:

  • Physics
  • Materials Science
  • Machine Learning

Background:

  • Room temperature semiconductor radiation detectors (RTSD), particularly Cadmium Zinc Telluride (CZT), are crucial for X-ray and gamma-ray detection in fields like medical imaging and astrophysics.
  • Current characterization methods for RTSDs often assume bulk homogeneity and lack detailed 3D sub-pixel resolution, hindering advanced event reconstruction.

Purpose of the Study:

  • To introduce a novel physics-based machine learning (PBML) model for detailed 3D characterization of RTSDs at a sub-pixel level.
  • To enable precise modeling of charge transport properties within individual voxels of a discretized detector volume.

Main Methods:

  • The study discretizes the RTSD into 3D voxels, modeling charge transport phenomena (drift, trapping, detrapping, recombination) as trainable weights within each voxel.
  • A second-order non-linear drift model is incorporated to accurately represent observed charge movement.
  • The PBML model is trained using electron-hole pair injections as input and electrode signals as output, with weights determined via backpropagation of a loss function.

Main Results:

  • The PBML model successfully characterizes 3D charge transport properties within voxelized detector volumes.
  • The trained model weights establish a direct correlation with the actual physical charge transport characteristics in each voxel.
  • This represents the first comprehensive 3D charge transport model for RTSDs.

Conclusions:

  • The developed PBML model offers an unprecedented level of detail for RTSD characterization in 3D space.
  • This approach overcomes the limitations of traditional bulk characterization, paving the way for enhanced sub-pixel level analysis.
  • The findings are expected to advance the performance of RTSDs in critical applications requiring high-resolution radiation detection.