Search for: All records

Physical reservoir computing leverages the intrinsic history-dependence and nonlinearity of hardware to encode spatiotemporal signals directly at the sensor level, enabling low-latency processing of dynamic inputs. Encoding delity depends on the separability of multi-state outputs, yet in practice it is often hampered by empirically chosen, suboptimal operating conditions. Here, we apply Bayesian optimization to improve the encoding performance of solution-processed Al₂O₃/In₂O₃ thin- lm transistors. By exploring a ve-dimensional pulse-parameter input space and using the normalized degree of separation for output state distinguishability, we demonstrate high- delity 6-bit temporal encoding corresponding to 64 output states. We further show that a model based on simpler 4-bit data can effectively guide optimization for more complex 6-bit tasks, substantially reducing experimental effort. Using a six-frame moving-car image sequence as a benchmark, we nd that the optimized 6-bit pulse conditions signi cantly enhance encoding accuracy, with 4-bit derived parameters performing comparably in terms of pixel errors. Shapley Additive Explanations (SHAP) analysis further reveals that gate-pulse amplitude and drain voltage are the dominant contributors to output state separation. This work establishes a data-driven strategy for identifying optimal operating conditions in reservoir devices and outlines a framework that can be transferred to diverse material platforms and physical reservoir implementations. 

The nematode Caenorhabditis elegans biosynthesizes the ascarosides, a large, modular family of pheromones that are used in chemical communication. A number of carboxylesterase domain-containing (CEST) enzymes are responsible for decorating the glycolipid core of the ascarosides with a variety of modifications. However, these enzymes, which are homologous to human carboxylesterases and acetylcholinesterase, have not been characterized biochemically, and thus the mechanism whereby they attach different modifications to the ascarosides is unknown. Here, we report the expression, purification, and biochemical characterization of a soluble CEST enzyme for the first time. In this study, we focused on CEST-9.2, which is responsible for making (E)-2-methyl-2-butenoyl (MB)-modified ascarosides. We identified candidate substrates for the enzyme, and we successfully expressed a truncated version of CEST-9.2, which is lacking the transmembrane domain, in several expression systems, including Escherichia coli, Pichia pastoris, and Spodoptera frugiperda Sf9 cells. The purified CEST-9.2 from each of these systems was tested against candidate substrates, including ascarosides and either MB-coenzyme A (CoA), MB-choline, or MB-carnitine. No enzymatic activity was detected using these substrates, suggesting that either the transmembrane domain is necessary for activity or that the correct substrates have not yet been identified. We showed that the purified CEST-9.2 from Sf9 cells is well-folded and dimeric, offering a potential starting point for future structural and mechanistic studies. 

Photonic curing (PC) can facilitate high-speed perovskite solar cell (PSC) manufacturing because it uses high-intensity light pulses to crystallize perovskite films in milliseconds. However, optimizing PC conditions is challenging due to its many variables, and using power conversion efficiency (PCE) as the optimization metric is both time-consuming and labor-intensive. This work presents a machine learning (ML) approach to optimize PC conditions for fabricating methylammonium lead iodide (MAPbI3) films by quantitatively comparing their ultraviolet-visible (UV-vis) absorbance spectra to thermal annealed (TA) films using four similarity metrics. We perform Bayesian optimization coupled with Gaussian process regression (BO-GP) to minimize the similarity metrics. Refining PC conditions using active learning based on BO-GP models, we achieve a PC MAPbI3 film with an absorbance spectrum closely matching a TA reference film, which is further verified by its crystalline and morphological properties. Thus, we demonstrate that the UV-vis absorption spectrum can accurately proxy film quality. Additionally, we use an AI-based segmentation model for a more efficient grain size analysis. However, when we use the optimized PC condition to fabricate PSCs, we find that interaction between MAPbI3 and the hole transport layer (HTL) during PC critically degrades the PSC performance. By adding a buffer layer between the HTL and MAPbI3, the optimized PC PSCs produce a champion PCE of 11.8%, comparable to the TA reference of 11.7%. Using UV-vis similarity metrics instead of device PCE as the objective in our BO-GP method accelerates the optimization of PC processing conditions for MAPbI3 films. 

Batch Bayesian optimization is widely used for optimizing expensive experimental processes when several samples can be tested together to save time or cost. 

Indium tin oxide (ITO) coated Willow glass is an excellent substrate for roll-to-roll manufacturing of perovskite solar cells (PSCs) but can have large variability in its optical and electrical properties. Photonic curing uses intense light pulses instead of heat to process materials and has the potential to facilitate faster processing speeds in roll-to-roll manufacturing to upscale the production of PSCs. The substrate materials’ properties play an integral role in the photonic curing outcome. Here, we present the effect of ITO transmission on the photonic curing of NiO sol-gel precursors into metal oxide and consequently the PSC performance.