Low-cost, high-efficiency metal halide perovskite solar cells (PSC) are a promising alternative to Si photovoltaics, but poor stability currently precludes commercialization. We present a framework for accelerated PSC design using machine learning (ML) to identify optimal compositions, fabrication parameters, and device operating conditions. We present four examples showcasing our ML roadmap using various types of neural networks, applied to diverse problems such as forecasting time-series photoluminescence (PL) from perovskite thin films, projecting PSC power output and degradation over time, and predicting figures of merit from simple, high-throughput experimental procedures. Our paradigm informs the rational development of perovskite devices, providing an accelerated pathway to commercialization.
Perovskite solar cells (PSC) are a promising low-cost energy source for niche markets, such as energy harvesting semitransparent windows, and colored or arbitrary shaped solar modules for portable power sources or building facades. Furthermore, the possibility to fabricate flexible solar modules allows the integration of the whole manufacturing process into a roll-to-roll facility with the potential of reducing dramatically the fabrication costs. In the quest for high efficiency flexible PSC, the absorbed sunlight can be maximized employing a light trapping technique, such as using a microstructured substrate capable to scatter or diffract the incoming light into multiple directions elongating the optical path in the absorber. This work presents a new strategy to pattern microstructures on polymers suitable as transparent substrates for flexible PSC with enhanced light trapping. This industrial compatible approach consists only on two processing steps. First, a cylindrical metallic stamp is structured using Direct Laser Interference Patterning (DLIP), and next, the stamp is used in a roll-to-roll hot embossing system to transfer the stamp pattern to polymeric foils. Optimizing the DLIP processing and hot embossing parameters, high-quality imprints were obtained with periodic features with a spatial period of 2.7 μm. PSC were deposited onto these structured substrates showing an increase in the light absorption and efficiency. Spectroscopic characterization using an integrating sphere suggests that the PSC efficiency increase is caused by an elongated optical path inside the perovskite due to scattering and diffraction in the visible spectrum.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.