Muhammad Ihsan‐Ul‐Haq, Saad Naseem
Thermal energy storage (TES) is essential for renewable integration, industrial decarbonization, and flexible energy systems. In this chapter, we examine how artificial intelligence (AI) enhances TES development when combined with physics-based understanding and validated data. Sensible, latent, and thermochemical storage pathways are discussed through shared design trade-offs involving temperature range, energy density, heat transfer, and durability. AI methods are classified by function, spanning surrogate and reduced-order modeling, physics-informed learning, data-driven materials discovery, and forecasting and control for safe operation. Representative workflows demonstrate integrated simulation, data, and optimization approaches. Key challenges and priorities for trustworthy AI–TES deployment are outlined.