Opportunities and challenges of text mining in aterials research

Research publications are the major repository of scientific knowledge. However, their unstructured and highly heterogenous format creates a significant obstacle to large-scale analysis of the information contained within. Recent progress in natural language processing (NLP) has provided a variety of tools for high-quality information extraction from unstructured text. These tools are primarily trained on non-technical text and struggle to produce accurate results when applied to scientific text, involving specific technical terminology. During the last years, significant efforts in information retrieval have been made for biomedical and biochemical publications. For materials science, text mining (TM) methodology is still at the dawn of its development. In this review, we survey the recent progress in creating and applying TM and NLP approaches to materials science field. This review is directed at the broad class of researchers aiming to learn the fundamentals of TM as applied to the materials science publications.

Applying machine learning to balance performance and stability of high energy density materials

The long-standing performance-stability contradiction issue of high energy density materials (HEDMs) is of extremely complex and multi-parameter nature. Herein, machine learning was employed to handle 28 feature descriptors and 5 properties of detonation and stability of 153 HEDMs, wherein all 21,648 data used were obtained through high-throughput crystal-level quantum mechanics calculations on supercomputers. Among five models, namely, extreme gradient boosting regression tree (XGBoost), adaptive boosting, random forest, multi-layer perceptron, and kernel ridge regression, were respectively trained and evaluated by stratified sampling and 5-fold cross-validation method. Among them, XGBoost model produced the best scoring metrics in predicting the detonation velocity, detonation pressure, heat of explosion, decomposition temperature, and lattice energy of HEDMs, and XGBoost predictions agreed best with the 1,383 experimental data collected from massive literatures. Feature importance analysis was conducted to obtain data-driven insight into the causality of the performance-stability contradiction and delivered the optimal range of key features for more efficient rational design of advanced HEDMs.

Screening metal-organic frameworks for adsorption-driven osmotic heat engines via grand canonical Monte Carlo simulations and machine learning

Adsorption-driven osmotic heat engines offer an alternative way for harvesting low-grade waste heat below 80°C. In this study, we performed a high-throughput computational screening based on grand canonical Monte Carlo simulations to identify the high-performance metal-organic frameworks (MOFs) from 1322 computationally ready experimental MOF structures for adsorption-driven osmotic heat engines with LiCl-methanol as the working fluid. Structure-property relationship analysis reveals that MOFs exhibiting high energy efficiency possess large working capacity, pore size and surface area, and moderate adsorption enthalpy comparable to the evaporation enthalpy. Furthermore, machine learning is employed to accelerate the computational screening for satisfied MOFs via the structure properties. The optimal structure properties of the MOFs are further identified via the ensemble-based regression model by optimizing the energy efficiency via the genetic algorithm, which shed light on rationally designing and fabricating MOFs for desired heat-to-electricity conversion.

Chiral Magnonics: Reprogrammable Nanoscale Spin Wave Networks Based on Chiral Domain Walls

Spin waves offer promising perspectives as information carriers for future computational architectures beyond conventional complementary metal-oxide-semiconductor (CMOS) technology, owing to their benefits for device minimizations and low-ohmic losses. Although plenty of magnonic devices have been proposed previously, scalable nanoscale networks based on spin waves are still missing. Here, we demonstrate a reprogrammable two-dimensional spin wave network by combining the chiral exchange spin waves and chiral domain walls. The spin-wave network can be extended to two dimensions and offers unprecedented control of exchange spin waves. Each cell in the network can excite, transmit, and detect spin waves independently in the chiral domain wall, and spin-wave logics are also demonstrated. Our results open up perspectives for integrating spin waves into future logic and computing circuits and networks.