Machine Learning Models for Predicting Polymer Solubility in Solvents across Concentrations and Temperatures.

Artificial intelligence and machine learning have become essential tools in predicting material properties to aid in the accelerated design of new materials. Polymer solubility, critical for new formulations and solution processing, is one such property. However, current models are limited by inadequate experimental data sets that cannot capture the complexity and detail for many features contributing to polymer solubility.

Design of Recyclable Plastics with Machine Learning and Genetic Algorithm.

We present an artificial intelligence-guided approach to design durable and chemically recyclable ring-opening polymerization (ROP) class polymers. This approach employs a genetic algorithm (GA) that designs new monomers and then utilizes virtual forward synthesis (VFS) to generate almost a million ROP polymers. Machine learning models to predict thermal, thermodynamic, and mechanical properties─crucial for application-specific performance and recyclability─are used to guide the GA toward optimal polymers.

Fast and Efficient Fabrication of Functional Electronic Devices through Grayscale Digital Light Processing 3D Printing.

Fabricating polymeric composites with desirable characteristics for electronic applications is a complex and costly process. Digital light processing (DLP) 3D printing emerges as a promising technique for manufacturing intricate structures. In this study, polymeric samples are fabricated with a conductivity difference exceeding three orders of magnitude in various portions of a part by employing grayscale DLP (g-DLP) single-vat single-cure 3D printing deliberate resin design.

AI-assisted discovery of high-temperature dielectrics for energy storage.

Electrostatic capacitors play a crucial role as energy storage devices in modern electrical systems. Energy density, the figure of merit for electrostatic capacitors, is primarily determined by the choice of dielectric material. Most industry-grade polymer dielectrics are flexible polyolefins or rigid aromatics, possessing high energy density or high thermal stability, but not both.

Pendant Group Functionalization of Cyclic Olefin for High Temperature and High-Density Energy Storage.

High-temperature flexible polymer dielectrics are critical for high density energy storage and conversion. The need to simultaneously possess a high bandgap, dielectric constant and glass transition temperature forms a substantial design challenge for novel dielectric polymers. Here, by varying halogen substituents of an aromatic pendant hanging off a bicyclic mainchain polymer, a class of high-temperature olefins with adjustable thermal stability are obtained, all with uncompromised large bandgaps.

Polyphosphazene-Based Anion-Anchored Polymer Electrolytes For All-Solid-State Lithium Metal Batteries.

Safety concerns of traditional liquid electrolytes, especially when paired with lithium (Li) metal anodes, have stimulated research of solid polymer electrolytes (SPEs) to exploit the superior thermal and mechanical properties of polymers. Polyphosphazenes are primarily known for their use as flame retardant materials and have demonstrated high Li-ion conductivity owing to their highly flexible P = N backbone which promotes Li-ion conduction via inter- and intrachain hopping along the polymer backbone. While polyphosphazenes are largely unexplored as SPEs in the literature, a few existing examples showed promising ionic conductivity.

Machine-Guided Discovery of Acrylate Photopolymer Compositions.

Additive manufacturing (AM) can be advanced by the diverse characteristics offered by thermoplastic and thermoset polymers and the further benefits of copolymerization. However, the availability of suitable polymeric materials for AM is limited and may not always be ideal for specific applications. Additionally, the extensive number of potential monomers and their combinations make experimental determination of resin compositions extremely time-consuming and costly.

Informatics-Driven Design of Superhard B-C-O Compounds.

Materials containing B, C, and O, due to the advantages of forming strong covalent bonds, may lead to materials that are superhard, i.e., those with a Vicker's hardness larger than 40 GPa.

Chemical Circularity in 3D Printing with Biobased Δ-Valerolactone.

Digital Light Processing (DLP) is a vat photopolymerization-based 3D printing technology that fabricates parts typically made of chemically crosslinked polymers. The rapidly growing DLP market has an increasing demand for polymer raw materials, along with growing environmental concerns. Therefore, circular DLP printing with a closed-loop recyclable ink is of great importance for sustainability.

Probing Electronic Band Structures of Dielectric Polymers via Pre-Breakdown Conduction.

The electronic band structure, especially the defect states at the conduction band tail, dominates electron transport and electrical degradation of a dielectric material under an extremely high electric field. However, the electronic band structure in a dielectric is barely well studied due to experimental challenges in detecting the electrical conduction to an extremely high electric field, i.e.

Accelerated Scheme to Predict Ring-Opening Polymerization Enthalpy: Simulation-Experimental Data Fusion and Multitask Machine Learning.

Ring-opening enthalpy (Δ) is a fundamental thermodynamic quantity controlling the polymerization and depolymerization of an important class of recyclable polymers, namely, those created from ring-opening polymerization (ROP). Highly accurate first-principles-based computational methods to compute Δ are computationally too demanding to efficiently guide the design of depolymerizable polymers. In this work, we develop a generalizable machine-learning model that was trained on experimental measurements and reliably computed simulation results of Δ (the latter provides a pathway to systematically increase the chemical diversity of the data).

Low-temperature 3D printing of transparent silica glass microstructures.

Transparent silica glass is one of the most essential materials used in society and industry, owing to its exceptional optical, thermal, and chemical properties. However, glass is extremely difficult to shape, especially into complex and miniaturized structures. Recent advances in three-dimensional (3D) printing have allowed for the creation of glass structures, but these methods involve time-consuming and high-temperature processes.

Effect of Fluorine in Redesigning Energy-Storage Properties of High-Temperature Dielectric Polymers.

Exploration of novel polymer dielectrics exhibiting high electric-field stability and high energy density with high efficiency at elevated temperatures is urgently needed for ever-demanding energy-storage technologies. Conventional high-temperature polymers with conjugated backbone structures cannot fulfill this demand due to their deteriorated performance at elevated electric fields. Here, in search of new polymer structures, we have explored the effect of fluorine groups on the energy-storage properties of polyoxanorbornene imide polymers with simultaneous wide band gap and high glass transition temperature ().

Data-driven predictions of complex organic mixture permeation in polymer membranes.

Membrane-based organic solvent separations are rapidly emerging as a promising class of technologies for enhancing the energy efficiency of existing separation and purification systems. Polymeric membranes have shown promise in the fractionation or splitting of complex mixtures of organic molecules such as crude oil. Determining the separation performance of a polymer membrane when challenged with a complex mixture has thus far occurred in an ad hoc manner, and methods to predict the performance based on mixture composition and polymer chemistry are unavailable.

polyBERT: a chemical language model to enable fully machine-driven ultrafast polymer informatics.

Polymers are a vital part of everyday life. Their chemical universe is so large that it presents unprecedented opportunities as well as significant challenges to identify suitable application-specific candidates. We present a complete end-to-end machine-driven polymer informatics pipeline that can search this space for suitable candidates at unprecedented speed and accuracy.

Thin-Film Organic Heteroepitaxy.

Incorporating crystalline organic semiconductors into electronic devices requires understanding of heteroepitaxy given the ubiquity of heterojunctions in these devices. However, while rules for commensurate epitaxy of covalent or ionic inorganic material systems are known to be dictated by lattice matching constraints, rules for heteroepitaxy of molecular systems are still being written. Here, it is found that lattice matching alone is insufficient to achieve heteroepitaxy in molecular systems, owing to weak intermolecular forces that describe molecular crystals.

Chemically Recyclable Polymer System Based on Nucleophilic Aromatic Ring-Opening Polymerization.

The development of chemically recyclable polymers with desirable properties is a long-standing but challenging goal in polymer science. Central to this challenge is the need for reversible chemical reactions that can equilibrate at rapid rates and provide efficient polymerization and depolymerization cycles. Based on the dynamic chemistry of nucleophilic aromatic substitution (SAr), we report a chemically recyclable polythioether system derived from readily accessible benzothiocane () monomers.

One-Pot Synthesis of Depolymerizable δ-Lactone Based Vitrimers.

A depolymerizable vitrimer that allows both reprocessability and monomer recovery by a simple and scalable one-pot two-step synthesis of vitrimers from cyclic lactones is reported. Biobased δ-valerolactone with alkyl substituents (δ-lactone) has low ceiling temperature; thus, their ring-opening-polymerized aliphatic polyesters are capable of depolymerizing back to monomers. In this work, the amorphous poly(δ-lactone) is solidified into an elastomer (i.

A general-purpose material property data extraction pipeline from large polymer corpora using natural language processing.

The ever-increasing number of materials science articles makes it hard to infer chemistry-structure-property relations from literature. We used natural language processing methods to automatically extract material property data from the abstracts of polymer literature. As a component of our pipeline, we trained MaterialsBERT, a language model, using 2.

Polymer Informatics at Scale with Multitask Graph Neural Networks.

Artificial intelligence-based methods are becoming increasingly effective at screening libraries of polymers down to a selection that is manageable for experimental inquiry. The vast majority of presently adopted approaches for polymer screening rely on handcrafted chemostructural features extracted from polymer repeat units-a burdensome task as polymer libraries, which approximate the polymer chemical search space, progressively grow over time. Here, we demonstrate that directly "machine learning" important features from a polymer repeat unit is a cheap and viable alternative to extracting expensive features by hand.

Solvent selection for polymers enabled by generalized chemical fingerprinting and machine learning.

We present machine learning models trained on experimental data to predict room-temperature solubility for any polymer-solvent pair. The new models are a significant advancement over past data-driven work, in terms of protocol, validity, and versatility. A generalizable fingerprinting method is used for the polymers and solvents, making it possible, in principle, to handle any polymer-solvent combination.

Vapor-Phase Infiltration of Polymer of Intrinsic Microporosity 1 (PIM-1) with Trimethylaluminum (TMA) and Water: A Combined Computational and Experimental Study.

Vapor-phase infiltration, a postpolymerization modification process, has demonstrated the ability to create organic-inorganic hybrid membranes with excellent stability in organic solvents while maintaining critical membrane properties of high permeability and selectivity. However, the chemical reaction pathways that occur during VPI and their implications on the hybrid membrane stability are poorly understood. This paper combines quartz crystal microbalance gravimetry (QCM) and chemical characterization with first-principles simulations at the atomic scale to study each processing step in the infiltration of polymer of intrinsic microporosity 1 (PIM-1) with trimethylaluminum (TMA) and its co-reaction with water vapor.

Modulating Polymerization Thermodynamics of Thiolactones Through Substituent and Heteroatom Incorporation.

A central challenge in the development of next-generation sustainable materials is to design polymers that can easily revert back to their monomeric starting material through chemical recycling to monomer (CRM). An emerging monomer class that displays efficient CRM are thiolactones, which exhibit rapid rates of polymerization and depolymerization. This report details the polymerization thermodynamics for a series of thiolactone monomers through systematic changes to substitution patterns and sulfur heteroatom incorporation.