Using a Novel Transfer Learning Method for Designing Thin Film Solar Cells with Enhanced Quantum Efficiencies

Abstract

In this study a new method for design optimization is proposed that is based on “transfer learning”. The proposed framework improves the accuracy and efficiency of surrogate-based optimization. A surrogate model is an approximation to a costly black-box function that can be used for more efficient search of optimal points. When design specifications change, the objective function changes too. Therefore, there is a need for a new surrogate model. However, the concept of transfer learning can be applied to refit the new surrogate more efficiently. In other words insights from previous experiences can be applied to learning and optimizing the new function. We use the proposed method in a particular problem pertaining to the design of “thin film multilayer solar cells”, where the goal is to maximize the external quantum efficiency of photoelectric conversion. The results show that the accuracy of the surrogate model is improved by 2–3 times using the transfer learning approach, using only half as many training data points as the original model. In addition, by transferring the design knowledge from one particular set of materials to another similar set of materials in the thin film structure, the surrogate-based optimization is improved, and is it obtained with far less computational time.

Evaluation of an artificial intelligent hydrocephalus diagnosis model based on transfer learning

“…The performance of transfer learning model depends to a large extent on that of the pre-training model. [ 10 , 11 ] The performance of the transfer learning model will improve, if much more advanced learning techniques and involve more medical image datasets is used in pre-trained models. In addition, the rapid development of convolutional neural networks outside medical imaging will also provide better performance and training models for transfer learning.…”

Instantaneous Property Prediction and Inverse Design of Plasmonic Nanostructures Using Machine Learning: Current Applications and Future Directions

“…Alternatively, the problem of insufficient training data can be addressed by using transfer learning techniques which connect the main task network to a successful, pre-trained network able to process low-level features [120]. Although the application of transfer learning is yet to be further developed for plasmonics, it has been performed to increase the training quality of small-dataset-based networks in nanophotonics [121], designing dielectric metasurfaces [122], and thin-film solar cells [123].…”

iQSPR in XenonPy: A Bayesian Molecular Design Algorithm

“…The sampling efficiency of iQSPR-X is highly influenced by the reliability of the evaluator that predicts the material properties for any given chemical structure. [18,[34][35][36][37][38][39][40][41] In this study, we applied a specific type of transfer learning using pre-trained neural networks. XenonPy currently provides 140,000 pretrained neural networks for the prediction of physical, chemical, electronic, thermodynamic, and mechanical properties of small organic molecules, polymers, and inorganic crystalline materials, with models for 15, 18, and 12 properties of these material types, respectively.…”