AI-Assisted Detector Calibration and Characterization

Sensor systems, from individual units to complex networks and bespoke instruments, pervade a wide range of government, industry, and scientific applications. With advances in artificial intelligence and machine learning, there is heightened interest in signals from sensors being interpreted by AI, either to provide automated agent behaviour or in the form of an augmented intelligence system that retains a human in the loop. While radiation detection and nuclear measurements are central to this collection, sensor systems across particle physics, astronomy, and safeguarding share the same core need: using AI to interpret complex detector signals, automate calibration, and handle high data rates.Calibration and characterization workflows must continuously account for complex sensor response dynamics, including gain drift, baseline shifts, dead-time compensation, and spatial non-uniformities. In multi-sensor arrays and distributed detection systems, traditional static calibration routines struggle with operational scale and high-rate data acquisition. AI, computer vision, and machine learning techniques offer powerful solutions for real-time baseline restoration, automated cross-calibration, noise reduction, and continuous anomaly detection.This Research Topic brings together researchers and engineers developing and applying AI and machine learning methods across detector calibration, characterization, commissioning, and automated sensor processing. We welcome contributions demonstrating algorithmic advances, simulation studies, benchmarking against classical analytical methods, and hardware-level experimental implementations.Key themes and areas of interest include, but are not limited to:- Machine learning and deep neural network approaches for non-uniformity correction, dead-time compensation, baseline restoration, and gain drift tracking- AI and computer vision models for multi-dimensional sensor output, denoising, signal-to-noise ratio enhancement, and raw pulse feature extraction- Sensor fusion strategies for multi-detector arrays, distributed sensor networks, and automated cross-calibration- Real-time automated commissioning, anomaly detection, and data quality validation in detector operations- Fault-tolerant and radiation-hard sensor processing, including edge-AI deployments and automated agent behaviour- Benchmarking studies comparing AI-driven calibration against classical analytical calibration frameworks- Radiation detection systems applied to safeguarding, civil nuclear monitoring, and environmental sensing- Sensor networks and detector instrumentation across particle physics, nuclear physics, astronomy, and non-destructive testing Topic editors: Adrian Bevan, Paul Sellin, Antonio Di Buono, G. (Shahab) Anbarjafari, Abdallah Hussein Sham Source: https://www.frontiersin.org/research-topics/87212/ai-assisted-detector-calibration-and-characterization