Predicting Electromagnetically Induced Transparency based Cold Atomic Engines using Deep Learning

TL;DR

This paper presents a deep learning model to predict the performance of electromagnetically induced transparency-based cold atomic quantum heat engines, revealing insights into their efficiency metrics and limitations.

Contribution

The authors develop a neural network to analyze and predict the performance of alkali-based cold atomic quantum heat engines, highlighting the limitations of radiation temperature as a performance metric.

Findings

High-performance engines predicted based on radiation temperature, work, and ergotropy.

Cs-based engine has higher output temperature but lower work and ergotropy than Rb-based engine.

Ergotropy exhibits a saturating exponential dependence on control Rabi frequency.

Abstract

We develop an artificial neural network model to predict quantum heat engines working within the experimentally realized framework of electromagnetically induced transparency. We specifically focus on {\Lambda}-type alkali-based cold atomic systems. This network allows us to analyze all the alkali atom-based engines' performance. High performance engines are predicted and analyzed based on three figures of merit output, radiation temperature, work and ergotropy. Contrary to traditional notion, the algorithm reveal the limitations of output radiation temperature as a stand alone metric for enhanced engine performance. In high output temperature regime, Cs based engine with a higher output temperature than Rb based engine is characterized by lower work and ergotropy. This is found to be true for different atomic engines with common predicted states in both high and low output temperature regimes. Additionally, the ergotropy is found to exhibit a saturating exponential dependency on the control Rabi frequency.