Calibrating for the Future:Enhancing Calorimeter Longevity with Deep Learning

TL;DR

A Wasserstein GAN inspired methodology is developed that adeptly calibrates the misalignment in calorimeter data due to aging or other factors, and requires a significantly lower number of events and resources to achieve high precision, minimizing absolute errors effectively.

Abstract

In the realm of high-energy physics, the longevity of calorimeters is paramount. Our research introduces a deep learning strategy to refine the calibration process of calorimeters used in particle physics experiments. We develop a Wasserstein GAN inspired methodology that adeptly calibrates the misalignment in calorimeter data due to aging or other factors. Leveraging the Wasserstein distance for loss calculation, this innovative approach requires a significantly lower number of events and resources to achieve high precision, minimizing absolute errors effectively. Our work extends the operational lifespan of calorimeters, thereby ensuring the accuracy and reliability of data in the long term, and is particularly beneficial for experiments where data integrity is crucial for scientific discovery.

Figures (6)

• Figure 1: Distribution of aging coefficients
• Figure 2: Energy Sum Distribution in damaged vs. undamaged Calorimeters
• Figure 3: Architecture of the WGAN-inspired network used for calibrating the calorimeter.
• Figure 4: Scatter plot of true aging coefficients versus predicted aging coefficients. The closer to line, the more consistent with true values the predictions are.
• Figure 5: Mean Absolute Error (MAE) of aging coefficients. The MAE decreases consistently, stabilizing around 0.0074 after 100 epochs, with R2 value of 0.88, demonstrating the model's potential to tune aging coefficients.