AI/ML-Optimised High-Temperature Thermal Energy Storage for Next-Gen Energy Efficiency

High-temperature thermal energy storage (HT-TES) is a critical enabler for industrial decarbonization, concentrated solar power (CSP), and waste heat recovery. By storing heat above 300 °C, HT-TES can supply process heat, generate power, or provide grid flexibility. adoption remains limited due to challenges in materials stability, system sizing, charge/discharge control, and long-term performance degradation. Optimizing these complex, non-linear systems using conventional methods is often slow, inaccurate, or impractical. Recent advances in artificial intelligence and machine learning (AI/ML) offer transformative potential to overcome these barriers and unlock the full value of HT-TES.This Research Topic aims to address the critical gap between HT-TES hardware development and intelligent system optimization. The problem is that current TES design and operation rarely leverage data-driven or adaptive control strategies, leading to suboptimal efficiency, higher costs, and reduced lifetime. Our goal is to gather cutting-edge research that applies AI/ML techniques—such as neural networks, reinforcement learning, genetic algorithms, and hybrid models—to optimise HT-TES across multiple scales: from material selection and component design to real-time operation and system integration. By doing so, we seek to demonstrate measurable improvements in round-trip efficiency, levelized cost of storage, thermal cycling stability, and demand-side response. We encourage contributions that validate AI/ML models with experimental or field data, as well as studies that benchmark against traditional optimization methods. The ultimate objective is to accelerate the commercial deployment of HT-TES in energy-intensive industries, renewable power plants, and district heating networks.We invite contributions addressing, but not limited to, the following themes:• ML-assisted design and selection of high-temperature storage materials;• AI-based predictive control of charging, storage, and discharging cycles for HT-TES;• Hybrid physics-informed ML models for degradation and lifetime prediction;• Solar collectors for thermal energy storage integration including Parabolic trough collectors, central receivers and linear Fresnel systems;• Advanced energy storage materials for high temperature applications;• Insulation and thermal loss reduction strategies. Topic editors: Dr Selvakumar Ponnusamy, Navid Nasajpour Esfahani, Ali Elkamel Source: https://www.frontiersin.org/research-topics/82178/aiml-optimised-high-temperature-thermal-energy-storage-for-next-gen-energy-efficiency