Knowledge-guided machine learning enables sensor-based high-performance material characterization that drives accelerated materials discovery and manufacturing. Traditional materials discovery workflows are driven by low-throughput characterization processes that involve several manual sample preparation steps and require relatively large amounts of material. While automated material dispensing processes now provide the ability to automate the synthesis of materials, the characterization of material composition, structure, and properties remains challenging due to the lack of reliable high-throughput characterization methods. Commercial benchtop characterization instruments are gold standards for characterizing the composition, structure, and properties of materials but lack synergy with state-of-the-art accelerated materials discovery workflows, which are based on miniaturized transducers for material testing (e.g., sensors), automation, and low-volume test formats. Due to the time- and resource-intensive nature of experimentation and the limited budget imposed on autonomous experimentation workflows in practical applications, the data generated from accelerated material discovery workflows are usually sparse and imbalanced, challenging the construction and training of machine learning models. In this dissertation, we create knowledge-guided machine learning models to support sensor-based high-performance autonomous material characterization. Several different types of knowledge-guided machine learning models were established for high-performance sensor-based characterization of material composition and phase. Specifically, three new methodologies are proposed and developed: 1. A new rapid and autonomous high-performance characterization method for accelerated engineering of soft functional materials is proposed to overcome the challenge of low-throughput characterization and manual data analysis. The proposed method is compatible with state-of-the-art material synthesis platforms combining automated sensing and sensor physics-guided machine learning that reduces the characterization cycle time and improves the material phase classification accuracy. Utilizing domain knowledge of measurement processes that generate data (e.g., sensor physics) and thermodynamics that govern material phase for feature engineering improved model and process performance. 2. To help mitigate the challenge of low measurement confidence associated with material composition measurement using biosensors, a novel knowledge-guided machine learning approach that integrates domain knowledge in sensor chemistry and physics is proposed. The proposed method implements data augmentation techniques to address sparsity and imbalance of biosensor data and identified new features in biosensor time-series data that are predictive of target analyte concentration and probability of false positive and negative responses. 3. A novel deep learning model with knowledge-guided cost function supervision is proposed to improve biosensor performance, specifically to improve the classification of false responses and reduce biosensor time delay. This new methodology combines regression- and classification-based data analyses, significantly improving biosensor accuracy and speed. The method fuses theory that governs dynamic sensor response (i.e., data generation) with machine learning models to guide regression and classification tasks, providing improved model interpretability and explainability. With the advancement of knowledge-guided machine learning and sensing technologies, the performance of experimental tools and processes for accelerated materials discovery and manufacturing applications can continue to be improved, particularly with respect to speed and reliability, which are critical performance attributes for future industrial adoption. / Doctor of Philosophy / The process of discovering and engineering new molecules and materials is based on a sequential process of making and testing, referred to as synthesis and characterization, respectively, which is often repeated until a design objective or budget is met. While the area of material synthesis has advanced, given the development of 3D printing processes, the characterization process presents a bottleneck due to limited throughput. A combination of sensing, automation, and machine learning offers the potential to advance the performance of characterization tools and processes. This dissertation aims to improve the performance of experimental tools and processes for accelerated discovery and quality-assurance manufacturing of biomolecules and soft materials. This dissertation combines knowledge-guided machine learning with automated sensing to accelerate the characterization of soft material mechanical properties and phase and material composition. The proposed methods are validated in several applications.

No description available.

Metallhalogenid-Perowskite (MHP) haben sich als hervorragende Materialklasse im Bereich der Optoelektronik erwiesen, obwohl die Degradation der häufig verwendeten organischen Komponenten ihre Langzeitstabilität begrenzt. Um schnell stabile Alternativen zu finden, ist eine Parallelisierung des Prozesses der Materialentwicklung durch kombinatorische Synthese und Hochdurchsatzanalyse erforderlich. In dieser Arbeit wird dies durch die Entwicklung, Implementierung und Validierung zweier komplementärer Methoden für die kombinatorische Synthese realisiert. Zum einen wurde die lösungsmittelbasierte Methode des kombinatorischen Tintenstrahldrucks weiterentwickelt, indem ein neuer Algorithmus für eine verbesserte Tintenmischung bereitgestellt und validiert wurde. Zum anderen wurde die Synthese von CsyPb1-y(BrxI1-x)2-y-Doppelgradientenschichten durch Co-Verdampfung erreicht. Kombinatorische Bibliotheken, die durch diese beiden Methoden hergestellt wurden, wurden für die Hochdurchsatzuntersuchung der strukturellen und optischen Eigenschaften der anorganischen CsyPb1-y(BrxI1-x)2-y-MHP verwendet. Dies ermöglichte die schnelle Erstellung vollständiger Phasendiagramme für Dünnfilme des CsPb(BrxI1-x)3-Mischkristalls, die zeigen, dass die Zugabe von Br die halbleitende Perowskitphase stabilisiert und niedrigere Verarbeitungstemperaturen ermöglicht. Darüber hinaus wurden CsyPb1-y(BrxI1-x)2-y-Bibliotheken mit automatisierten, kontaktlosen optischen Raster-Messungen untersucht, die eine schnelle Sichtung von über 3400 Zusammensetzungen ermöglichten. Dies ermöglichte die Bewertung des photovoltaischen Potenzials von CsyPb1-y(BrxI1-x)2-y über einen sehr breiten Bereich von Zusammensetzungen. Das höchste Wirkungsgradpotenzial wurde für stöchiometrische Zusammensetzungen gefunden, wobei ein Überschuss an Pb oder Cs zu erhöhten Verlusten durch nichtstrahlende Rekombination führt. Diese Ergebnisse liefern wichtige Erkenntnisse für die weitere Entwicklung von anorganischen MHP-Bauelementen. / To keep up with the increasing need for specialized materials, a parallelization of the materials discovery process is needed through combinatorial synthesis and high-throughput analysis. The acceleration of materials discovery is especially of interest in the area of optoelectronics where metal halide perovskites (MHPs) have proven to be an excellent material class and have achieved impressive performance in photovoltaic devices among other applications. However, the degradation of the frequently employed organic components contributes to limiting the long-term stability of MHP devices. In this work, accelerated materials discovery is addressed through the development, implementation, and validation of two complementary methods for combinatorial synthesis. Firstly, the solution-based method of combinatorial inkjet printing was further developed by providing and validating a new algorithm for improved ink mixing. Secondly, the vapor-based synthesis of double-gradient CsyPb1-y(BrxI1-x)2-y was achieved by co-evaporation. Combinatorial libraries created by both methods were used for the high-throughput investigation of the structural and optical properties of the inorganic CsyPb1-y(BrxI1-x)2-y MHPs. This enabled the fast construction of complete phase diagrams for thin-films of the CsPb(BrxI1-x)3 solid solution which show that the addition of Br stabilizes the semiconducting perovskite phase and allows for lower processing temperatures. Additionally, CsyPb1-y(BrxI1-x)2-y libraries were investigated by automized, contact-less, optical mapping measurements, enabling the rapid screening of over 3400 compositions. This enabled the assessment of the photovoltaic potential of CsyPb1-y(BrxI1-x)2-y over a very broad compositional range. The maximum efficiency potential was found for stoichiometric compositions, with excess of Pb or Cs causing increased losses by non-radiative recombination. These results provide vital knowledge for further development of inorganic MHP devices.