Accelerating amorphous polymer electrolyte screening by learning to reduce errors in molecular dynamics simulated properties

ChiGNN: Interpretable Algorithm Framework of Molecular Chiral Knowledge-Embedding and Stereosensitive Property Prediction

Molecular chirality-related tasks have remained a notable challenge in materials machine learning (ML) due to the subtle spatial discrepancy between enantiomers. Designing appropriate steric molecular descriptions and embedding chiral knowledge are of great significance for improving the accuracy and interpretability of ML models. In this work, we propose a state-of-the-art deep learning framework, Chiral Graph Neural Network, which can effectively incorporate chiral physicochemical knowledge via Trinity Graph and stereosensitive Message Aggregation encoding. Combined with the quantile regression technique, the accuracy of the chiral chromatographic retention time prediction model outperformed the existing records. Accounting for the inherent merits of this framework, we have customized the Trinity Mask and Contribution Splitting techniques to enable a multilevel interpretation of the model's decision mechanism at atomic, functional group, and molecular hierarchy levels. This interpretation has both scientific and practical implications for the understanding of chiral chromatographic separation and the selection of chromatographic stationary phases. Moreover, the proposed chiral knowledge embedding and interpretable deep learning framework, together with the stereomolecular representation, chiral knowledge embedding method, and multilevel interpretation technique within it, also provide an extensible template and precedent for future chirality-related or stereosensitive ML tasks.

Data-driven design of electrolyte additives supporting high-performance 5 V LiNi0.5Mn1.5O4 positive electrodes

LiNi0.5Mn1.5O4 (LNMO) is a high-capacity spinel-structured material with an average lithiation/de-lithiation potential at ca. 4.6-4.7 V vs Li+/Li, far exceeding the stability limits of electrolytes. An efficient way to enable LNMO in lithium-ion batteries is to reformulate an electrolyte composition that stabilizes both graphitic (Gr) negative electrode with solid-electrolyte-interphase and LNMO with cathode-electrolyte-interphase. In this study, we select and test a diverse collection of 28 single and dual additives for the Gr||LNMO battery system. Subsequently, we train machine learning models on this dataset and employ the trained models to suggest 6 binary compositions out of 125, based on predicted final area-specific-impedance, impedance rise, and final specific-capacity. Such machine learning-generated new additives outperform the initial dataset. This finding not only underscores the efficacy of machine learning in identifying materials in a highly complicated application space but also showcases an accelerated material discovery workflow that directly integrates data-driven methods with battery testing experiments.

Noise-Aware Active Learning to Develop High-Temperature Shape Memory Alloys with Large Latent Heat

Shape memory alloys (SMAs) with large latent heat absorbed/released during phase transformation at elevated temperatures benefit their potential application on thermal energy storage (TES) in high temperature environment like power plants, etc. The desired alloys can be designed quickly by searching the vast component space of doped NiTi-based SMAs via data-driven method, while be challenging with the noisy experimental data. A noise-aware active learning strategy is proposed to accelerate the design of SMAs with large latent heat at elevated phase transformation temperatures based on noisy data. The optimal noise level is estimated by minimizing the model error with incorporation of a range of noise levels as noise hyper-parameters into the noise-aware Kriging model. The employment of this strategy leads to the discovery of the alloy with latent heat of -36.08 J g-1, 9.2% larger than the best value (-33.04 J g-1) in the original training dataset within another four experiments. Additionally, the alloy represents high austenite finish temperature (481.71°C) and relatively small hysteresis. This promotes the latent heat TES application of SMAs in high temperature circumstance. It is expected that the noise-aware approach can be convenient for the accelerated materials design via the data-driven method with noisy data.

Accelerating Polymer Discovery with Uncertainty-Guided PGCNN: Explainable AI for Predicting Properties and Mechanistic Insights

Deep learning holds great potential for expediting the discovery of new polymers from the vast chemical space. However, accurately predicting polymer properties for practical applications based on their monomer composition has long been a challenge. The main obstacles include insufficient data, ineffective representation encoding, and lack of explainability. To address these issues, we propose an interpretable model called the Polymer Graph Convolutional Neural Network (PGCNN) that can accurately predict various polymer properties. This model is trained using the RadonPy data set and validated using experimental data samples. By integrating evidential deep learning with the model, we can quantify the uncertainty of predictions and enable sample-efficient training through uncertainty-guided active learning. Additionally, we demonstrate that the global attention of the graph embedding can aid in discovering underlying physical principles by identifying important functional groups within polymers and associating them with specific material attributes. Lastly, we explore the high-throughput screening capability of our model by rapidly identifying thousands of promising candidates with low and high thermal conductivity from a pool of one million hypothetical polymers. In summary, our research not only advances our mechanistic understanding of polymers using explainable AI but also paves the way for data-driven trustworthy discovery of polymer materials.

Polymer design for solid-state batteries and wearable electronics

Solid-state batteries are increasingly centre-stage for delivering more energy-dense, safer batteries to follow current lithium-ion rechargeable technologies. At the same time, wearable electronics powered by flexible batteries have experienced rapid technological growth. This perspective discusses the role that polymer design plays in their use as solid polymer electrolytes (SPEs) and as binders, coatings and interlayers to address issues in solid-state batteries with inorganic solid electrolytes (ISEs). We also consider the value of tunable polymer flexibility, added capacity, skin compatibility and end-of-use degradability of polymeric materials in wearable technologies such as smartwatches and health monitoring devices. While many years have been spent on SPE development for batteries, delivering competitive performances to liquid and ISEs requires a deeper understanding of the fundamentals of ion transport in solid polymers. Advanced polymer design, including controlled (de)polymerisation strategies, precision dynamic chemistry and digital learning tools, might help identify these missing fundamental gaps towards faster, more selective ion transport. Regardless of the intended use as an electrolyte, composite electrode binder or bulk component in flexible electrodes, many parallels can be drawn between the various intrinsic polymer properties. These include mechanical performances, namely elasticity and flexibility; electrochemical stability, particularly against higher-voltage electrode materials; durable adhesive/cohesive properties; ionic and/or electronic conductivity; and ultimately, processability and fabrication into the battery. With this, we assess the latest developments, providing our views on the prospects of polymers in batteries and wearables, the challenges they might address, and emerging polymer chemistries that are still relatively under-utilised in this area.

Machine Learning on Microstructure-Property Relationship of Lithium-Ion Conducting Oxide Solid Electrolytes

Understanding the structure-property relationship of lithium-ion conducting solid oxide electrolytes is essential to accelerate their development and commercialization. However, the structural complexity of nonideal materials increases the difficulty of study. Here, we develop an algorithmic framework to understand the effect of microstructure on the properties by linking the microscopic morphology images to their ionic conductivities. We adopt garnet and perovskite polycrystalline oxides as examples and quantify the microscopic morphologies via extracting determined physical parameters from the images. It directly visualizes the effect of physical parameters on their corresponding ionic conductivities. As a result, we can determine the microstructural features of a Li-ion conductor with high ionic conductivity, which can guide the synthesis of highly conductive solid electrolytes. Our work provides a novel approach to understanding the microstructure-property relationship for solid-state ionic materials, showing the potential to extend to other structural/functional ceramics with various physical properties in other fields.

Multimodal Transformer for Property Prediction in Polymers

In this work, we designed a multimodal transformer that combines both the Simplified Molecular Input Line Entry System (SMILES) and molecular graph representations to enhance the prediction of polymer properties. Three models with different embeddings (SMILES, SMILES + monomer, and SMILES + dimer) were employed to assess the performance of incorporating multimodal features into transformer architectures. Fine-tuning results across five properties (i.e., density, glass-transition temperature (Tg), melting temperature (Tm), volume resistivity, and conductivity) demonstrated that the multimodal transformer with both the SMILES and the dimer configuration as inputs outperformed the transformer using only SMILES across all five properties. Furthermore, our model facilitates in-depth analysis by examining attention scores, providing deeper insights into the relationship between the deep learning model and the polymer attributes. We believe that our work, shedding light on the potential of multimodal transformers in predicting polymer properties, paves a new direction for understanding and refining polymer properties.

Synergistic theoretical and experimental study on the ion dynamics of bis(trifluoromethanesulfonyl)imide-based alkali metal salts for solid polymer electrolytes

Model validation of a well-known class of solid polymer electrolyte (SPE) is utilized to predict the ionic structure and ion dynamics of alternative alkali metal ions, leading to advancements in Na-, K-, and Cs-based SPEs for solid-state alkali metal batteries. A comprehensive study based on molecular dynamics (MD) is conducted to simulate ion coordination and the ion transport properties of poly(ethylene oxide) (PEO) with lithium bis(trifluoromethanesulfonyl)imide (LiTFSI) salt across various LiTFSI concentrations. Through validation of the MD simulation results with experimental techniques, we gain a deeper understanding of the ionic structure and dynamics in the PEO/LiTFSI system. This computational approach is then extended to predict ion coordination and transport properties of alternative alkali metal ions. The ionic structure in PEO/LiTFSI is significantly influenced by the LiTFSI concentration, resulting in different lithium-ion transport mechanisms for highly concentrated or diluted systems. Substituting lithium with sodium, potassium, and cesium reveals a weaker cation-PEO coordination for the larger cesium-ion. However, sodium-ion based SPEs exhibit the highest cation transport number, indicating the crucial interplay between salt dissociation and cation-PEO coordination for achieving optimal performance in alkali metal SPEs.

Chemistry-Informed Machine Learning for Polymer Electrolyte Discovery

Solid polymer electrolytes (SPEs) have the potential to improve lithium-ion batteries by enhancing safety and enabling higher energy densities. However, SPEs suffer from significantly lower ionic conductivity than liquid and solid ceramic electrolytes, limiting their adoption in functional batteries. To facilitate more rapid discovery of high ionic conductivity SPEs, we developed a chemistry-informed machine learning model that accurately predicts ionic conductivity of SPEs. The model was trained on SPE ionic conductivity data from hundreds of experimental publications. Our chemistry-informed model encodes the Arrhenius equation, which describes temperature activated processes, into the readout layer of a state-of-the-art message passing neural network and has significantly improved accuracy over models that do not encode temperature dependence. Chemically informed readout layers are compatible with deep learning for other property prediction tasks and are especially useful where limited training data are available. Using the trained model, ionic conductivity values were predicted for several thousand candidate SPE formulations, allowing us to identify promising candidate SPEs. We also generated predictions for several different anions in poly(ethylene oxide) and poly(trimethylene carbonate), demonstrating the utility of our model in identifying descriptors for SPE ionic conductivity.

Rational Design of Solid Polymer Electrolyte Based on Ionic Liquid Monomer for Supercapacitor Applications via Molecular Dynamics Study

The safety concern arising from flammable liquid electrolytes used in batteries and supercapacitors drives technological advances in solid polymer electrolytes (SPEs) in which flammable organic solvents are absent. However, there is always a trade-off between the ionic conductivity and mechanical properties of SPEs due to the lack of interaction between the ionic liquid and polymer resin. The inadequate understanding of SPEs also limits their future exploitation and applications. Herein, we provide a complete approach to develop a new SPE, consisting of a cation (monomer), anion and hardener from ions-monomers using molecular dynamics (MD) simulations. The results show that the strong solid-liquid interactions between the SPE and graphene electrode lead to a very small gap of ∼5.5 Å between the components of SPE and electrode, resulting in a structured solid-to-liquid interface, which can potentially improve energy storage performance. The results also indicated the critical role of the mobility of free-standing anions in the SPE network to achieve high ionic conductivity for applications requiring fast charge/discharge. In addition, the formations of hardener-depleted regions and cation-anion-poor/rich regions near the uncharged/charged electrode surfaces were observed at the molecular level, providing insights for rationally designing the SPEs to overcome the boundaries for further breakthroughs in energy storage technology.