Mohammed, Hayder I.Rashid, Farhan LaftaTogun, HusseinAgyekum, Ephraim BonahAmeen, ArmanHammoodi, Karrar A.Abbas, Walaa Nasser2025-09-152025-09-1520251872-91180306-261910.1016/j.apenergy.2025.1265762-s2.0-105012614220https://doi.org/10.1016/j.apenergy.2025.126576https://hdl.handle.net/20.500.14517/8359The growing demand for clean energy and the limitations of conventional thermal systems necessitates the integration of advanced technologies to enhance efficiency, adaptability, and sustainability. This review critically examines recent advancements in the application of nanotechnology and artificial intelligence for optimizing thermal energy systems, including solar collectors, heat exchangers, and latent heat storage units. Nanotechnology (particularly the use of nano-enhanced phase change materials and nanofluids such as Al₂O₃ and CuO) has shown to improve thermal conductivity by up to 28.8 %, accelerating energy absorption and storage rates. Concurrently, artificial intelligence algorithms, especially artificial neural networks and particle swarm optimization, enable predictive modelling, real-time system control, and fault detection, with some models achieving prediction accuracies above 97 % under complex operational conditions. The review emphasizes the synergistic potential of combining these technologies to create intelligent, self-regulating thermal energy systems. However, the paper also identifies critical challenges including computational overhead, cost of nanoparticle synthesis, lack of reproducibility in artificial intelligence implementations, and insufficient validation under extreme scenarios. Commercial deployment case studies (such as artificial intelligence-driven phase change material-based heating, ventilation, and air conditioning systems in smart buildings) are discussed to illustrate practical viability, reporting energy savings of up to 28 % with return-on-investment periods under three years. The paper concludes by proposing integrated research directions that combine multiscale material innovation with robust artificial intelligence training on dynamic datasets. This dual approach is essential to developing scalable, cost-effective, and resilient thermal energy systems capable of supporting global energy transitions. © 2025 Elsevier B.V., All rights reserved.eninfo:eu-repo/semantics/closedAccessEnergy EfficiencyEnergy Storage OptimizationMachine Learning in Energy SystemsNanofluidsPhase Change MaterialsAir ConditioningCost EffectivenessEnergy TransitionHeat StorageIntelligent BuildingsInteractive Computer SystemsInvestmentsLearning SystemsNanotechnologyNeural NetworksParticle Swarm Optimization (PSO)Real Time SystemsStorage (Materials)Thermal ConductivityThermal EnergyEnergyEnergy Storage OptimizationEnergy SystemsMachine Learning in Energy SystemMachine-LearningNanofluidsPhase ChangeStorage OptimizationThermal Energy SystemsEnergy EfficiencyPhase Change MaterialsAbsorptionAir ConditioningArtificial IntelligenceEnergy EfficiencyEnergy StorageMachine LearningNanoparticleNanotechnologyThermal ConductivityArticleQ1Q1400