The design of broadband, high-efficiency solar absorbers remains challenging due to the complex and ill-posed inverse mapping from the target optical responses to the physical structures in inverse design optimization. To address this, we propose a joint forward–inverse deep learning framework that enables the rapid and accurate optimization of multilayer metamaterial absorbers. This method integrates an inverse network based on a Modified Swin Transformer with a Multilayer Perceptron forward proxy and performs end-to-end training in a consistency-driven cycle. This strategy reduces the one-to-many ambiguity in inverse design and improves the prediction accuracy, with normalized test mean squared errors of 7.2 × 10−5 (inverse) and 6.8 × 10−5 (forward). Using this framework, we optimized an absorber comprising W/SiO2 hyperbolic metamaterial stacks and TiO2/SiO2 anti-reflection coatings, achieving 97.4% average absorptivity across the 400–1750 nm solar spectrum, along with polarization insensitivity and robust wide-angle performance up to 60° incidence. The outdoor solar heating tests showed that the fabricated absorber reaches a peak temperature of 86.3 °C under natural sunlight, with an irradiance peak of about 850 W/m2 at noon. This work shows that combining forward and reverse deep learning provides a powerful and scalable paradigm for accelerating the intelligent design of high-performance solar thermal metamaterials.
Wu et al. (Thu,) studied this question.