Transfer Learning of Full Molecular Weight Distributions via High-Throughput Computer-Controlled Polymerization.

The skew and shape of the molecular weight distribution (MWD) of polymers have a significant impact on polymer physical properties. Standard summary metrics statistically derived from the MWD only provide an incomplete picture of the polymer MWD. Machine learning (ML) methods coupled with high-throughput experimentation (HTE) could potentially allow for the prediction of the entire polymer MWD without information loss. In our work, we demonstrate a computer-controlled HTE platform that is able to run up to 8 unique variable conditions in parallel for the free radical polymerization of styrene. The segmented-flow HTE system was equipped with an inline Raman spectrometer and offline size exclusion chromatography (SEC) to obtain time-dependent conversion and MWD, respectively. Using ML forward models, we first predict monomer conversion, intrinsically learning varying polymerization kinetics that change for each experimental condition. In addition, we predict entire MWDs including the skew and shape as well as SHAP analysis to interpret the dependence on reagent concentrations and reaction time. We then used a transfer learning approach to use the data from our high-throughput flow reactor to predict batch polymerization MWDs with only three additional data points. Overall, we demonstrate that the combination of HTE and ML provides a high level of predictive accuracy in determining polymerization outcomes. Transfer learning can allow exploration outside existing parameter spaces efficiently, providing polymer chemists with the ability to target the synthesis of polymers with desired properties.

Injectable Hybrid-Crosslinked Hydrogels as Fatigue-Resistant and Shape-Stable Skin Depots.

Injectable hydrogels have gained considerable attention, but they are typically mechanically weak and subject to repeated physiological stresses in the body. Herein, we prepared polyurethane diacrylate (EPC-DA) hydrogels, which are injectable and can be photocrosslinked into fatigue-resistant implants. The mechanical properties can be tuned by changing photocrosslinking conditions, and the hybrid-crosslinked EPC-DA hydrogels exhibited high stability and sustained release properties. In contrast to common injectable hydrogels, EPC-DA hydrogels exhibited excellent antifatigue properties with >90% recovery during cyclic compression tests and showed shape stability after application of force and immersion in an aqueous buffer for 35 days. The EPC-DA hydrogel formed a shape-stable hydrogel depot in an ex vivo porcine skin model, with establishment of a temporary soft gel before in situ fixing by UV crosslinking. Hybrid crosslinking using injectable polymeric micelles or nanoparticles may be a general strategy for producing hydrogel implants resistant to physiological stresses.

Design and Development of a Low Cost, Non-Contact Infrared Thermometer with Range Compensation.

Fever is a common symptom of many infections, e.g., in the ongoing COVID-19 pandemic, keeping monitoring devices such as thermometers in constant demand. Recent technological advancements have made infrared (IR) thermometers the choice for contactless screening of multiple individuals. Yet, even so, the measurement accuracy of such thermometers is affected by many factors including the distance from the volunteers' forehead, impurities (such as sweat), and the location measured on the volunteers' forehead. To overcome these factors, we describe the assembly of an Arduino-based digital IR thermometer with distance correction using the MLX90614 IR thermometer and HC-SR04 ultrasonic sensors. Coupled with some analysis of these factors, we also found ways to programme compensation methods for the final assembled digital IR thermometer to provide more accurate readings and measurements.