Truth Discovery in Material Science Databases

In condensed matter physics and materials science, predicting material properties necessitates understanding intricate many-body interactions. Conventional methods such as density functional theory and molecular dynamics often resort to simplifying approximations and are computationally expensive. Meanwhile, recent machine learning methods use handcrafted descriptors for material representation, which sometimes neglect vital crystallographic information and are often limited to single property prediction or a sub-class of crystal structures. In this study, we pioneer an unsupervised strategy, drawing inspiration from natural language processing to harness the underutilized potential of Crystallographic Information Files (CIFs). We conceptualize atoms and atomic positions within a crystallographic information file similarly to words in textual content. Using a Word2Vec-inspired technique, we produce atomic embeddings that capture intricate atomic relationships. Our model, CIFSemantics, trained on the extensive material project dataset, adeptly predicts 15 distinct material properties from the CIFs. Its performance rivals that of specialized models, marking a significant step forward in material property predictions.

Multi-output ensemble deep learning: A framework for simultaneous prediction of multiple electrode material properties

GCPNet: An interpretable Generic Crystal Pattern graph neural Network for predicting material properties.

k nearest neighbor (kNN) search is an important problem in a vast number of applications, including clustering, pattern recognition, image retrieval and recommendation systems. It finds k elements from a data source D that are closest to a given query point q in a metric space. In this paper, we extend kNN query to retrieve closest elements from multiple data sources. This new type of query is named k nearest group (kNG) query, which finds k groups of elements that are closest to q with each group containing one object from each data source. kNG query is useful in many location based services. To efficiently process kNG queries, we propose a baseline algorithm using R-tree as well as an improved version using Hilbert R-tree. We also study a variant of kNG query, named kNG Join, which is analagous to kNN Join. Given a set of query points Q, kNG Join returns k nearest groups for each point in Q. Such a query is useful in publish/subscribe systems to find matching items for a collection of subscribers. A comprehensive performance study was conducted on both synthetic and real datasets and the experimental results show that Hilbert R-tree achieves significantly better performance than R-tree in answering both kNG query and kNG Join.

A method has been developed for building fully atomistic models of chemically crosslinked PVA. It combines a dynamic crosslinking approach followed by a high‐temperature annealing procedure. The crosslinking procedure allows to control both crosslinking density and the amount of free crosslinking sites. It also takes into account some network defects, such as dangling tails and wasted loops, which have been experimentally observed on chemically crosslinked polymer networks. This procedure is applied to PVA which is chemically crosslinked with two different linear polyols. Several material properties such as glass transition temperature, Young's, shear and bulk modulus were predicted from the equilibrated structures and found to agree well with available experimental data.magnified image

Pb-Sn solders are known to coarsen and deform heterogeneously under shear thermomechanical cycling. Solder joint failure often occurs within these coarsened shear bands. The connection between microstructure and materials properties is well documented, which leads to the conclusion that an improved understanding of the interaction between stress and microstructural evolution will better enable the prediction of materials properties over time. In this paper, we simulate microstructural evolution of Pb-Sn solders using a novel two-phase version the Potts model, a kinetic Monte Carlo model that is coupled to a finite element mechanics model. Using this model, possible mechanisms for heterogeneous coarsening are explored.

High-quality internal experimental materials data are often “small data.” Using external datasets, e.g., data from the literature and other groups, to expand the “small data” to relatively “big data” is particularly important for improving the prediction accuracy of machine learning models. However, the most critical issue is how to use a small amount of internal reliable data to filter external data extracted from multiple sources and obtain optimal datasets with a distribution similar to that of internal data. This is called the multi-source materials data problem. This question was addressed by designing an active learning-based data screening (ALDS) model that is suitable for small material samples. This study used negative expansion materials as subjects. The results show that ALDS can be used to screen the external multi-source dataset and far exceeds traditional outlier filtering methods. The average mean absolute percentage error (MAPE) of the predictive key target property of the negative thermal expansion coefficient (NTEC) was reduced from 4.301 to 0.056. Furthermore, reverse design experiments were conducted on anti-perovskite manganese nitride (AMN), a type of negative thermal expansion material, to prove that the ALDS model can guide the reverse design on a small AMN dataset using the MAPE between ALDS prediction and the ground truth of samples’ three property indicators. This achieves high confidence levels with values of 0.203,0.126, and 0.115. This verifies that the ALDS proposed method improves the effect of ”materials small internal data” in guiding material design and property prediction.

The success of machine learning (ML) in materials property prediction depends heavily on how the materials are represented for learning. Two dominant families of material descriptors exist, one that encodes crystal structure in the representation and the other that only uses stoichiometric information with the hope of discovering new materials. Graph neural networks (GNNs) in particular have excelled in predicting material properties within chemical accuracy. However, current GNNs are limited to only one of the above two avenues owing to the little overlap between respective material representations. Here, a new concept of formula graph which unifies stoichiometry‐only and structure‐based material descriptors is introduced. A self‐attention integrated GNN that assimilates a formula graph is further developed and it is found that the proposed architecture produces material embeddings transferable between the two domains. The proposed model can outperform some previously reported structure‐agnostic models and their structure‐based counterparts while exhibiting better sample efficiency and faster convergence. Finally, the model is applied in a challenging exemplar to predict the complex dielectric function of materials and nominate new substances that potentially exhibit epsilon‐near‐zero phenomena.

Recent machine learning guided material research - A review

Abstract: Material research is an ever-growing field with the invention of new materials almost every day. It is not feasible for everybody working in the field to test each and every material on the Universal Testing Machine (UTM). This poses a limitation that has been sought to be tackled for quite some time now. One approach to tackle this is to use machine learning to predict the properties of the materials, thus eliminating the need of extensive time requirement and cost of performing experiments on the UTM. In this paper, the authors have trained and tested a machine learning based model that can predict material properties on the basis of composition and given temperature.

Internal stress in polycrystalline materials is an intrinsic attribute of the microstructure that affects a broad range of material properties. It is usually acquired through experiment in conjunction with continuum mechanics modelling, but its determination at nanometre and submicron scales is extremely difficult. Here, we report a bottom-up approach using atomistic calculation. We obtain the internal stress in polycrystalline copper with nanosized grains by first computing the stress associated with each atom and then sorting the stress into those associated with different self-equilibrating length scales, i.e. sample scale and grain cell, which gives type I, II and III residual stresses, respectively. The result shows highly non-uniform internal stress distribution; the internal stress depends sensitively on grain size and the grain shape anisotropy. Statistical distributions of the internal stresses, along with the means and variance, are calculated as a function of the mean grain size and temperature. The implementation of this work in assisting the interpretation of experimental results and predicting material properties is discussed.

In order to study the microstructure characteristics of an axially braided Carbon/Carbon (C/C) composite, a comprehensive observation and study of the mesoscopic and microstructure characteristics of an axially braided C/C composite is conducted. Scanning electron microscopy and Micro-CT were used to obtain the microstructure characteristics and distribution rules of the axially braided C/C composite material. The physical model of the material and the geometric model of the representative unit were established. At the same time, the characteristics of this kind of material are also obtained. The microstructure characteristics show that the axially braided C/C composite is a polymer with cracks and pores of different sizes, which is a three-dimensional and four-directions carbon fiber braided body as the reinforcing phase and pitch carbon as the reinforcing matrix. The microcosmic data obtained in this chapter is the basis for carrying out material property prediction and qualitative comparison of macro performance.

The IEEE 802.16 standard, which includes specification for the medium access control (MAC) and physical (PHY) layers, was designed to handle the requirements of different contemporary applications with diverse QoS requirements. IEEE 802.16 standard is equipped with signaling and bandwidth allocation algorithms that can accommodate many connections with a variety of QoS requirements at one subscriber station (SS). The connections may be varied in their bandwidth and latency requirements, so several researchers proposed an IEEE 802.16 schedulers with different objectives to provide for wireless resource allocations over a different range of traffic models. In this paper, we conduct a comprehensive performance study of scheduling algorithms in Point to multipoint mode of WiMAX. We first make a classification of WiMAX scheduling algorithms, then simulate a representative number of algorithms in each class taking into account the characteristics of the IEEE 802.16 standard. We evaluate the algorithms with respect to their abilities to support multiple classes of service, providing quality of service (QoS) guarantees, fairness amongst service classes and bandwidth utilization. To the best of our knowledge, no such comprehensive performance study has been reported in the literature. Simulation results indicate that none of the current algorithms is capable of effectively supporting all WiMAX classes of service. We demonstrate that an efficient, fair and robust scheduler for WiMAX is still an open research area. We conclude our study by making recommendations that can be used by WiMax protocol designers.

The structure and electronic properties of nitrides have garnered significant research interest. To improve prediction efficiency and generalization ability, this study proposes an large language model (LLM) fine-tuning method trained by data with description of nitride crystal structure, obtaining textual data directly through automated workflow, bypassing the need for complex feature engineering. The outcomes demonstrate a notable enhancement in the prediction of material properties. With the GPT-3.5-turbo model fine-tuned, the R 2 value went up from 0.6890 to 0.9868 and from 0.5119 to 0.9824. The fine-tuned GPT-3.5-turbo model outperforms GPT-3.5 and GPT-4.0 in terms of average prediction accuracy, with a 73.43 % and 67.13 % increase, respectively. Additionally, the generalizability of the model is checked by applying it to unknown nitrides. The average accuracy of the fine-tuned GPT-3.5-turbo model are 90.50 % and 80.40 % , compared with the results of the first principles calculation. These outcomes are on par with what shallow ML models achieve. The results of this work demonstrate that fine-tuned LLMs can serve as effective and generalizable tools for predicting the band gap ( E g ) and formation energy ( Δ H f ) of III-VIIIB and III-IVA nitrides, thereby simplifying the prediction process and saving time.

The prediction of elastic material properties via an adjoint formulation in this talk an efficient computational formulation to determine the acoustic properties of an elastic material, given its response to a time-harmonic excitation, is presented. Such problems arise in biomedical imaging using techniques such as Magnetic Resonance Elastography. The problem is posed as an inverse problem and its solution is computed using a mathematical programming algorithm (from mathematical programming). The functional to be minimized is the norm of the difference of the ‘‘measured’’ and a ‘‘trial’’ velocity field. At every iteration the trial velocity field is determined by solving the Helmholtz equation. The derivatives of the functional with respect to material properties, which form the input to the optimization algorithm, are computed by solving an adjoint problem. Using this formulation, the cost of computing derivatives is independent of the number of parameters used to represent the material properties, and thus the overall problem is rendered computationally tractable. A description of this methodology and an illustrative example to indicate its effectiveness will be presented.