ML Model Characterizes Solid-State Detectors and Reduces Defect Levels
Summary
USPTO published patent application US20260093984A1 by Srutarshi Banerjee et al. describing a physics-based neural network model that learns trapping, detrapping, and charge transport properties in solid-state detectors on a voxel-by-voxel basis. The invention reduces experimental data requirements by using electrode signals or free charge data alone to train the model, with regularization techniques to handle reduced training data.
What changed
This patent application discloses a machine learning method for characterizing solid-state radiation detectors. The physics-based network learns detector material properties including trapping, detrapping, and charge transport on a voxel-by-voxel basis. The key innovation reduces data requirements by training with just electrode signals or free charge data, using equivalency methods to combine multiple trapping centers and regularization in loss calculations.
Patent applications do not create compliance obligations. Entities developing or using solid-state detectors for imaging applications (medical, industrial, security) may reference this technology for detector characterization. No regulatory deadlines or penalties apply. This publication is informational for IP tracking purposes.
Archived snapshot
Apr 2, 2026GovPing captured this document from the original source. If the source has since changed or been removed, this is the text as it existed at that time.
SOLID-STATE DETECTOR CHARACTERIZATION BY MACHINE LEARNING-BASED PHYSICAL MODEL WITH REDUCED DEFECT LEVELS
Application US20260093984A1 Kind: A1 Apr 02, 2026
Inventors
Srutarshi Banerjee, Miesher Rodrigues, Alexander Hans Vija, Aggelos Katsaggelos
Abstract
A physics-based network model is trained to learn weights such as trapping, detrapping, and/or transport of holes and/or electrons, as well as voltage distribution on a voxel-by-voxel basis throughout a solid-state detector model. The physics-based network may be used to estimate material property variation throughout the voxels. To reduce the number of experimental setups and information needed to train the models, the models may be trained using more easily acquired ground truth. Just the electrode signals or just the free charge data is used to train the model to characterize the solid-state detector. With this reduced data, the detector may be characterized using equivalency, such as combining multiple trapping centers to an equivalent trapping center. Regularization may be used in the loss calculation, such as where just the electrode signals are used, to deal with the reduced data available as ground truth.
CPC Classifications
G06N 3/08
Filing Date
2025-12-05
Application No.
19410502
Named provisions
Related changes
Get daily alerts for USPTO Patent Applications - AI & Computing (G06N)
Daily digest delivered to your inbox.
Free. Unsubscribe anytime.
Source
About this page
Every important government, regulator, and court update from around the world. One place. Real-time. Free. Our mission
Source document text, dates, docket IDs, and authority are extracted directly from USPTO.
The plain-English summary, classification, and "what to do next" steps are AI-generated from the original text. Cite the source document, not the AI analysis.
Classification
Who this affects
Taxonomy
Browse Categories
Get alerts for this source
We'll email you when USPTO Patent Applications - AI & Computing (G06N) publishes new changes.