Machine Learning-Assisted Synthesis of Two-Dimensional Materials

Computational Micromechanics and Machine Learning-Informed Design of Composite Carbon Fiber-Based Structural Battery for Multifunctional Performance Prediction

Integrating load-bearing and energy storage capabilities within a single material system, known as multifunctional structural batteries, holds immense promise for advancing structural energy storage technologies. These systems offer significant weight reduction and enhanced safety, but their commercialization is hindered by challenges due to vast unexplored design spaces and costly trial-and-error processes. In this work, we employ an experimentally validated computational framework to accelerate the design of carbon fiber (CF)-based structural batteries impregnated with solid polymer electrolyte (SPE). To analyze the mechanical behavior, a finite element analysis (FEA) model powered by computational micromechanics was used to investigate the CF/SPE interface and damage mechanisms to predict the macro-effective material properties. To preform accurate forecasts on energy storage, a data-driven machine learning approach based on artificial neural networks (ANN) was optimized via a Bayesian optimization algorithm to predict the structural battery's future capacity. Furthermore, we validate the optimized ANN model in a rapid capacity degradation condition, showcasing the suitability of such algorithms for studying coupled multifunctional structures under mechanical and electrochemical loads, providing promising insights for optimizing the development of multifunctional composites.

Machine Learning-Assisted Prediction and Control of Bandgap for Organic-Inorganic Metal Halide Perovskites

Perovskite materials have wide application prospects in many fields due to their tunable and designable band gap characteristics. Machine learning has obvious advantages in quickly and effectively discovering new materials. However, noise interference within data sets frequently hinders the ability of traditional predictive and evaluative techniques to satisfy practical requirements. This study introduces an outlier removal strategy to examine the influence of varying degrees of outlier exclusion on the generalization performance of the learning model followed by the determination of the optimal configuration. The results indicated that the gradient boosting regression tree (GBRT) algorithm yielded a mean absolute error (MAE) of 0.0287, a mean squared error (MSE) of 0.0014, a root mean squared error (RMSE) of 0.0377, and an R-squared (R2) value of 0.979, demonstrating superior performance with a minimal prediction error compared to alternative algorithms. Moreover, the Shapley Additive Explanation (SHAP) method was utilized to elucidate the impact of various chemical compositions on the desired band gap, revealing that the ratio of I exerts the most significant influence, with the Pb, Br, and Sn ratios exerting a subsequent effect. We further investigated the effect of different chemical composition ratios on the band gap, and the experimental results show that individual elements maintain stability within particular proportionate bounds, thereby offering critical data to underpin band gap control strategies. This study provides new valuable insights for realizing accurate prediction and effective control of band gaps.

Using Machine Learning to Design a FeMOF Bidirectional Regulator for Electrochemiluminescence Sensing of Tau Protein

The single-luminophore-based ratiometric electrochemiluminescence (ECL) sensor coupling bidirectional regulator has become a research hotspot in the detection field because of its simplicity and accuracy. However, the limited bidirectional regulator hinders its further development. In this study, by leveraging the robust predictive capabilities of machine learning, we prepared an Fe-based metal-organic framework (FeMOF) as a bidirectional regulator for modulating the dual-emission ECL signals of a single luminophore for the first time. The proof of concept was demonstrated by applying FeMOF to the classical luminophore Ru(bpy)32+, and the results showed its ability to enhance the cathode ECL signal (Ecathode) and inhibit the anode ECL signal (Eanode). As an example, a ratiometric ECL sensor for Tau protein (Tau) detection utilizing the FeMOF/Ru(bpy)32+ system was developed. The incorporation of a bidirectional regulator in the ECL system effectively mitigated erratic fluctuations or minor discrepancies between the two signals and showed a stronger correlation and stability of Ecathode/Eanode than before regulation. As a result, the ECL sensor showed good analytical performance with a detection limit as low as 3.38 fg mL-1 (S/N = 3). Moreover, it was not only comparable in test results to the commercially available ELISA kit but also could well distinguish between normal and Alzheimer's disease (AD) patients (80% specificity and 90% sensitivity). Thus, the proposed strategy is promising to be extended to other ECL luminophores or MOFs, providing a new path for ratiometric ECL sensors.

The application of machine learning in 3D/4D printed stimuli-responsive hydrogels

The integration of machine learning (ML) in materials fabrication has seen significant advancements in recent scientific innovations, particularly in the realm of 3D/4D printing. ML algorithms are crucial in optimizing the selection, design, functionalization, and high-throughput manufacturing of materials. Meanwhile, 3D/4D printing with responsive material components has increased the vast design flexibility for printed hydrogel composite materials with stimuli responsiveness. This review focuses on the significant developments in using ML in 3D/4D printing to create hydrogel composites that respond to stimuli. It discusses the molecular designs, theoretical calculations, and simulations underpinning these materials and explores the prospects of such technologies and materials. This innovative technological advancement will offer new design and fabrication opportunities in biosensors, mechatronics, flexible electronics, wearable devices, and intelligent biomedical devices. It also provides advantages such as rapid prototyping, cost-effectiveness, and minimal material wastage.

Machine Learning Strategy for Optimizing Multiple Electrical Characteristics in Dual-Layer Oxide Thin Film Transistors

A machine learning (ML) strategy is suggested to optimize dual-layer oxide thin film transistor (TFTs) performance. In this study, Bayesian optimization (BO), an algorithm recognized for its efficiency in optimizing material design, is applied to guide the design of a channel layer composed of IZO and IGZO. The sputtering fabrication process, which has attracted attention as an oxide semiconductor channel layer deposition method, is fine-tuned using ML to enhance multiple electrical characteristics of transistors: field-effect mobility, threshold voltage, and subthreshold swing. Using BO, the sputtering conditions─plasma power, pressure, and gas ratio, which intricately influence device performance─were modified using 19 data sets of 84 scenarios. It reveals that the modulated process conditions improve field-effect mobility up to 46.7 cm2V-1s-1, achieving more than double the performance of conventional IGZO TFTs. Furthermore, it was observed that threshold voltage is optimized to zero voltage, and the subthreshold swing is considerably improved, contributing to reduced power consumption. This study demonstrates that leveraging ML to optimize TFTs design not only accelerates the design process but also improves device performance dramatically. Overall, this ML strategy manages complex correlations among process parameters, properties, and performance and sets a precedent for the expeditious optimization of semiconductor devices.

Machine Learning-Assisted Exploration of Intrinsically Spin-Ordered Two-Dimensional (2D) Nanomagnets

The existence of spontaneous spin-ordering in two-dimensional (2D) nanomagnets holds significant importance due to their several unique and promising properties that distinguish them from conventional 2D materials. In recent times, machine learning (ML) has emerged as a powerful tool for effectively exploring and identifying the optimal 2D materials for specific applications or properties within a limited span of time. Here, we have introduced ML-accelerated approaches to specifically estimate the properties, such as the HSE bandgap and magnetoanisotropic energy (MAE) of 2D magnetic materials. Supervised ML algorithms were employed to derive the descriptors that are capable of predicting the properties of intrinsic 2D magnetic materials. Furthermore, the feature selection score is also calculated to reduce the feature space complexity and improve the model accuracy. The input features were obtained from the C2DB database, and models were constructed using linear regression, Lasso, decision tree, random forest, XG Boost, and support vector machine algorithms. The random forest model predicted the HSE band gaps with an unprecedented low root-mean-square error (RMSE) of 0.22 eV, while the linear regression gives the best fit with RMSEs of 0.25 and 0.22 meV for the MAE(x) and MAE(y), respectively. Therefore, the integration of interpretable analytical models with density functional theory offers a swift and reliable approach for uncovering the properties of intrinsic 2D magnetic materials. This collaborative methodology not only ensures speed in analysis but also enriches the material space.

Preparation of Thermochromic Vanadium Dioxide Films Assisted by Machine Learning

In recent years, smart windows have attracted widespread attention due to their ability to respond to external stimuli such as light, heat, and electricity, thereby intelligently adjusting the ultraviolet, visible, and near-infrared light in solar radiation. VO2(M) undergoes a reversible phase transition from an insulating phase (monoclinic, M) to a metallic phase (rutile, R) at a critical temperature of 68 °C, resulting in a significant difference in near-infrared transmittance, which is particularly suitable for use in energy-saving smart windows. However, due to the multiple valence states of vanadium ions and the multiphase characteristics of VO2, there are still challenges in preparing pure-phase VO2(M). Machine learning (ML) can learn and generate models capable of predicting unknown data from vast datasets, thereby avoiding the wastage of experimental resources and reducing time costs associated with material preparation optimization. Hence, in this paper, four ML algorithms, namely multi-layer perceptron (MLP), random forest (RF), support vector machine (SVM), and extreme gradient boosting (XGB), were employed to explore the parameters for the successful preparation of VO2(M) films via magnetron sputtering. A comprehensive performance evaluation was conducted on these four models. The results indicated that XGB was the top-performing model, achieving a prediction accuracy of up to 88.52%. A feature importance analysis using the SHAP method revealed that substrate temperature had an essential impact on the preparation of VO2(M). Furthermore, characteristic parameters such as sputtering power, substrate temperature, and substrate type were optimized to obtain pure-phase VO2(M) films. Finally, it was experimentally verified that VO2(M) films can be successfully prepared using optimized parameters. These findings suggest that ML-assisted material preparation is highly feasible, substantially reducing resource wastage resulting from experimental trial and error, thereby promoting research on material preparation optimization.

Two-dimensional material assisted-growth strategy: new insights and opportunities

The exploration and synthesis of novel materials are integral to scientific and technological progress. Since the prediction and synthesis of two-dimensional (2D) materials, it is expected to play an important role in the application of industrialization and the information age, resulting from its excellent physical and chemical properties. Currently, researchers have effectively utilized a range of material synthesis techniques, including mechanical exfoliation, redox reactions, chemical vapor deposition, and chemical vapor transport, to fabricate two-dimensional materials. However, despite their rapid development, the widespread industrial application of 2D materials faces challenges due to demanding synthesis requirements and high costs. To address these challenges, assisted growth techniques such as salt-assisted, gas-assisted, organic-assisted, and template-assisted growth have emerged as promising approaches. Herein, this study gives a summary of important developments in recent years in the assisted growth synthesis of 2D materials. Additionally, it highlights the current difficulties and possible benefits of the assisted-growth approach for 2D materials. It also highlights novel avenues of development and presents opportunities for new lines of investigation.

Designing semiconductor materials and devices in the post-Moore era by tackling computational challenges with data-driven strategies

In the post-Moore's law era, the progress of electronics relies on discovering superior semiconductor materials and optimizing device fabrication. Computational methods, augmented by emerging data-driven strategies, offer a promising alternative to the traditional trial-and-error approach. In this Perspective, we highlight data-driven computational frameworks for enhancing semiconductor discovery and device development by elaborating on their advances in exploring the materials design space, predicting semiconductor properties and optimizing device fabrication, with a concluding discussion on the challenges and opportunities in these areas.

When Machine Learning Meets 2D Materials: A Review

The availability of an ever-expanding portfolio of 2D materials with rich internal degrees of freedom (spin, excitonic, valley, sublattice, and layer pseudospin) together with the unique ability to tailor heterostructures made layer by layer in a precisely chosen stacking sequence and relative crystallographic alignments, offers an unprecedented platform for realizing materials by design. However, the breadth of multi-dimensional parameter space and massive data sets involved is emblematic of complex, resource-intensive experimentation, which not only challenges the current state of the art but also renders exhaustive sampling untenable. To this end, machine learning, a very powerful data-driven approach and subset of artificial intelligence, is a potential game-changer, enabling a cheaper - yet more efficient - alternative to traditional computational strategies. It is also a new paradigm for autonomous experimentation for accelerated discovery and machine-assisted design of functional 2D materials and heterostructures. Here, the study reviews the recent progress and challenges of such endeavors, and highlight various emerging opportunities in this frontier research area.

Machine Learning-Assisted Large-Area Preparation of MoS2 Materials

Molybdenum disulfide (MoS2) is a layered transition metal-sulfur compound semiconductor that shows promising prospects for applications in optoelectronics and integrated circuits because of its low preparation cost, good stability and excellent physicochemical, biological and mechanical properties. MoS2 with high quality, large size and outstanding performance can be prepared via chemical vapor deposition (CVD). However, its preparation process is complex, and the area of MoS2 obtained is difficult to control. Machine learning (ML), as a powerful tool, has been widely applied in materials science. Based on this, in this paper, a ML Gaussian regression model was constructed to explore the growth mechanism of MoS2 material prepared with the CVD method. The parameters of the regression model were evaluated by combining the four indicators of goodness of fit (r2), mean squared error (MSE), Pearson correlation coefficient (p) and p-value (p_val) of Pearson's correlation coefficient. After comprehensive comparison, it was found that the performance of the model was optimal when the number of iterations was 15. Additionally, feature importance analysis was conducted on the growth parameters using the established model. The results showed that the carrier gas flow rate (Fr), molybdenum sulfur ratio (R) and reaction temperature (T) had a crucial impact on the CVD growth of MoS2 materials. The optimal model was used to predict the size of molybdenum disulfide synthesis under 185,900 experimental conditions in the simulation dataset so as to select the optimal range for the synthesis of large-size molybdenum disulfide. Furthermore, the model prediction results were verified through literature and experimental results. It was found that the relative error between the prediction results and the literature and experimental results was small. These findings provide an effective solution to the preparation of MoS2 materials with a reduction in the time and cost of trial and error.