Optimization of Ultrabroadband MXene-Based Surface Plasmon Resonance Solar Absorber Using Machine Learning for Renewable Energy Application

The solar absorber design is an effective design to be used as a renewable energy design which gives the sustainable option. The effectiveness of the design is enhanced by using the optimization method. Machine learning is used to optimize the results. The machine learning optimization gives a higher efficient design which is required for absorbing more radiation. The design results are also analyzed with AM 1.5 results and show minor energy losses. The current ultra-broadband structure can improve the performance of some solar applications such as heat transfers, generators, and photovoltaics in industrial use. The optimum design results are investigated for E-field analysis. The high absorption is visible in the substrate structure by high E-field in the same. Metamaterial analysis is also presented in this research. The optimum absorption of 99.9% is visible for numerous wavelengths. These optimized values are used to design the solar absorber which shows more than 92.37% average absorption for the solar spectral range of 200 to 3000 nm. The machine learning algorithm is applied for optimization having the highest R² value of 0.93. The superiority of the design is also shown by tabular investigation with other designs. The broad bandwidth of 2.8 µm is investigated in this tabular approach. The structure is also angularly stable for a wide angle of incidence. The solar thermal absorber structure investigated in this research can fulfill the industry’s energy demands using this renewable energy.