Publication date: 10th April 2024
Overcoming the challenge of limited data availability within materials science is crucial for the broad-based applicability of machine learning within materials science, specifically the well-established deep learning paradigms that have been successful in image and natural language processing. One pathway to overcome this limited data availability is to use the framework of transfer learning, where a pre-trained machine learning model (on a larger dataset) can be fine-tuned on a target (typically smaller) dataset. Our study explores the utility of transfer learning as a systematic solution to address the lack of large datasets in materials science. We focus on developing a framework that leverages a Graph Neural Networks (GNN) to transfer learn material properties. To achieve this, we used seven diverse curated datasets from MatBench, encompassing sizes ranging from 941 to 132,752 data points. These datasets cover a spectrum of material properties, ranging from band gaps, to formation energies, and piezoelectric moduli. We employed three distinct pre-training strategies primarily to capture the impact of dataset size. Subsequently, we fine-tuned each pre-trained model on the remaining six datasets, once again employing three fine-tuning strategies to determine best performance. Importantly, we find that GNNs with greater flexibility during fine-tuning exhibited higher performance (in terms of r2scores), even surpassing models constructed from scratch using the respective datasets. Furthermore, we also examine the utility of our pre-training and fine-tuning strategies on properties that had minimal physical correlation with the seven pre-training datasets considered. In summary, we demonstrate transfer learning as a pivotal strategy by facilitating a comprehensive understanding of material properties, bridging data gaps, and enhancing material property prediction.
nanoGe is a prestigious brand of successful science conferences that are developed along the year in different areas of the world since 2009. Our worldwide conferences cover cutting-edge materials topics like perovskite solar cells, photovoltaics, optoelectronics, solar fuel conversion, surface science, catalysis and two-dimensional materials, among many others.
Previously nanoGe Spring Meeting (NSM) and nanoGe Fall Meeting (NFM), MATSUS is a multiple symposia conference focused on a broad set of topics of advanced materials preparation, their fundamental properties, and their applications, in fields such as renewable energy, photovoltaics, lighting, semiconductor quantum dots, 2-D materials synthesis, charge carriers dynamics, microscopy and spectroscopy semiconductors fundamentals, etc.
International Conference on Hybrid and Organic Photovoltaics
International Conference on Hybrid and Organic Photovoltaics (HOPV) is celebrated yearly in May. The main topics are the development, function and modeling of materials and devices for hybrid and organic solar cells. The field is now dominated by perovskite solar cells but also other hybrid technologies, as organic solar cells, quantum dot solar cells, and dye-sensitized solar cells and their integration into devices for photoelectrochemical solar fuel production.
Asia-Pacific International Conference on Perovskite, Organic Photovoltaics and Optoelectronics
The main topics of the Asia-Pacific International Conference on Perovskite, Organic Photovoltaics and Optoelectronics (IPEROP) are discussed every year in Asia-Pacific for gathering the recent advances in the fields of material preparation, modeling and fabrication of perovskite and hybrid and organic materials. Photovoltaic devices are analyzed from fundamental physics and materials properties to a broad set of applications. The conference also covers the developments of perovskite optoelectronics, including light-emitting diodes, lasers, optical devices, nanophotonics, nonlinear optical properties, colloidal nanostructures, photophysics and light-matter coupling.
The International Conference on Perovskite Thin Film Photovoltaics Perovskite Photonics and Optoelectronics (NIPHO) is the best place to hear the latest developments in perovskite solar cells as well as on recent advances in the fields of perovskite light-emitting diodes, lasers, optical devices, nanophotonics, nonlinear optical properties, colloidal nanostructures, photophysics and light-matter coupling.