Crystal structure prediction is a long-standing challenge in condensed matter and chemical science. Here we report a machine-learning approach for crystal structure prediction, in which a graph network (GN) is employed to establish a correlation model between the crystal structure and formation enthalpies at the given database, and an optimization algorithm (OA) is used to accelerate the search for crystal structure with lowest formation enthalpy. The framework of the utilized approach (a database + a GN model + an optimization algorithm) is flexible. We implemented two benchmark databases, i.e., the open quantum materials database (OQMD) and Matbench (MatB), and three OAs, i.e., random searching (RAS), particle-swarm optimization (PSO) and Bayesian optimization (BO), that can predict crystal structures at a given number of atoms in a periodic cell. The comparative studies show that the GN model trained on MatB combined with BO, i.e., GN(MatB)-BO, exhibit the best performance for predicting crystal structures of 29 typical compounds with a computational cost three orders of magnitude less than that required for conventional approaches screening structures through density functional theory calculation. The flexible framework in combination with a materials database, a graph network, and an optimization algorithm may open new avenues for data-driven crystal structural predictions.

devices, flexible substrates play a key role to fabricate high-performance electronics. In the past decade, various flexible substrates have been greatly developed. For instance, Chongwu and co-workers fabricated silver nanowire films on flexible polyethylene terephthalate (PET) substrates with good mechanical flexibility and demonstrated the application in a touch panel. [7] Johansson and co-workers reported a polyethylene naphthalate (PEN) substrate coated by Ag nanowire network for an extremely lightweight and ultraflexible colloidal quantum dots solar cell. [8] Jeong and co-workers fabricated copper conductors on polyimide and polyethersulfone substrates, exhibiting the potential accessibility for flexible electronics. [9] The abovementioned flexible substrates exhibit excellent stretchable ability and high-flexible performance. Because of their excellent mechanical and chemical stability, it takes extremely long time for them to degrade or decompose in the nature, leading to environmental pollution. Therefore, more and more attention is paid to looking for flexi ble, biocompatible, and environmentally friendly biomass substrates for wearable devices. [6,[10][11][12][13] Flexible biomass substrates based on nanofibrillated cellulose have been explored and are expected to be used in wearable electronics due to their excellent mechanical properties, renewability, and raw material abundance. Ma and co-workers successfully fabricated gallium arsenide microwave devices on flexible wood-derived cellulose nanofibril paper. [14] Ju and co-workers reported flexible, transparent phototransistors on biodegradable wood-derived cellulose nanofibrillated fiber substrates toward environment friendly electronics. [15] Hu and co-workers fabricated flexible organic field-effect transistors on tailorable softwood-derived nanopapers. [16] These successful studies suggest the feasibility to fabricate environment friendly cellulose-based substrates for flexible electronics, and further accelerate development of the flexible wearable devices.Currently flexible perovskite solar cells (PSCs) have gained wide attention by their excellent performance and potential application in wearable energy devices. [13,[17][18][19] As is well known, high performance flexible perovskite devices are still based on nonbiocompatible and nondegradable plastic substrates such as PET, PEN, and polydimethylsiloxane. Yu and co-workers first reported flexible perovskite solar cells fabricated on Wearable devices are mainly based on plastic substrates, such as polyethylene terephthalate and polyethylene naphthalate, which causes environmental pollution after use due to the long decomposition periods. This work reports on the fabrication of a biodegradable and biocompatible transparent conductive electrode derived from bamboo for flexible perovskite solar cells. The conductive bioelectrode exhibits extremely flexible and light-weight properties. After bending 3000 times at a 4 mm curvature radius or even undergoing a crumpling test, it still shows excellent e...

No abstract

Traditional materials discovery is in ‘trial-and-error’ mode, leading to the issues of low-efficiency, high-cost, and unsustainability in materials design. Meanwhile, numerous experimental and computational trials accumulate enormous quantities of data with multi-dimensionality and complexity, which might bury critical ‘structure–properties’ rules yet unfortunately not well explored. Machine learning (ML), as a burgeoning approach in materials science, may dig out the hidden structure–properties relationship from materials bigdata, therefore, has recently garnered much attention in materials science. In this review, we try to shortly summarize recent research progress in this field, following the ML paradigm: (i) data acquisition → (ii) feature engineering → (iii) algorithm → (iv) ML model → (v) model evaluation → (vi) application. In section of application, we summarize recent work by following the ‘material science tetrahedron’: (i) structure and composition → (ii) property → (iii) synthesis → (iv) characterization, in order to reveal the quantitative structure–property relationship and provide inverse design countermeasures. In addition, the concurrent challenges encompassing data quality and quantity, model interpretability and generalizability, have also been discussed. This review intends to provide a preliminary overview of ML from basic algorithms to applications.