Computational prediction of crystal materials properties can help to do large-scale insiliconscreening. Recent studies of material informatics have focused on expert design of multidimensionalinterpretable material descriptors/features. However, successes of deep learning suchas Convolutional Neural Networks (CNN) in image recognition and speech recognition havedemonstrated their automated feature extraction capability to effectively capture the characteristicsof the data and achieve superior prediction performance. Here, we propose CNN-OFM-Magpie, aCNN model with OFM (Orbital-field Matrix) and Magpie descriptors to predict the formationenergy of 4030 crystal material by exploiting the complementarity of two-dimensional OFM featuresand Magpie features. Experiments showed that our method achieves better performance thanconventional regression algorithms such as support vector machines and Random Forest. It is alsobetter than CNN models using only the OFM features, the Magpie features, or the basic one-hotencodings. This demonstrates the advantages of CNN and feature fusion for materials propertyprediction. Finally, we visualized the two-dimensional OFM descriptors and analyzed the featuresextracted by the CNN to obtain greater understanding of the CNN-OFM model.
more »
« less
XGBoost model for electrocaloric temperature change prediction in ceramics
An eXtreme Gradient Boosting (XGBoost) machine learning model is built to predict the electrocaloric (EC) temperature change of a ceramic based on its composition (encoded by Magpie elemental properties), dielectric constant, Curie temperature, and characterization conditions. A dataset of 97 EC ceramics is assembled from the experimental literature. By sampling data from clusters in the feature space, the model can achieve a coefficient of determination of 0.77 and a root mean square error of 0.38 K for the test data. Feature analysis shows that the model captures known physics for effective EC materials. The Magpie features help the model to distinguish between materials, with the elemental electronegativities and ionic charges identified as key features. The model is applied to 66 ferroelectrics whose EC performance has not been characterized. Lead-free candidates with a predicted EC temperature change above 2 K at room temperature and 100 kV/cm are identified.
more » « less- PAR ID:
- 10368282
- Publisher / Repository:
- Nature Publishing Group
- Date Published:
- Journal Name:
- npj Computational Materials
- Volume:
- 8
- Issue:
- 1
- ISSN:
- 2057-3960
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
more » « less
2D layered metal-organic frameworks (MOFs) are a new class of multifunctional materials that can provide electrical conductivity on top of the conventional structural characteristics of MOFs, offering potential applications in electronics and optics. Here, for the first time, we employ Machine Learning (ML) techniques to predict the thermodynamic stability and electronic properties of layered electrically conductive (EC) MOFs, bypassing expensive ab initio calculations for the design and discovery of new materials. Proper feature engineering is a very important factor in utilizing ML models for such purposes. Here, we show that a combination of elemental features, using generic statistical reduction methods and crystal structure information curated from the recently introduced EC-MOF database, leads to a reasonable prediction of the thermodynamic and electronic properties of EC MOFs. We utilize these features in training a diverse range of ML classifiers and regressors. Evaluating the performance of these different models, we show that an ensemble learning approach in the form of stacking ML models can lead to higher accuracy and more reliability on the predictive power of ML to be employed in future MOF research.
-
more » « less
The melting temperature is important for materials design because of its relationship with thermal stability, synthesis, and processing conditions. Current empirical and computational melting point estimation techniques are limited in scope, computational feasibility, or interpretability. We report the development of a machine learning methodology for predicting melting temperatures of binary ionic solid materials. We evaluated different machine-learning models trained on a dataset of the melting points of 476 non-metallic crystalline binary compounds using materials embeddings constructed from elemental properties and density-functional theory calculations as model inputs. A direct supervised-learning approach yields a mean absolute error of around 180 K but suffers from low interpretability. We find that the fidelity of predictions can further be improved by introducing an additional unsupervised-learning step that first classifies the materials before the melting-point regression. Not only does this two-step model exhibit improved accuracy, but the approach also provides a level of interpretability with insights into feature importance and different types of melting that depend on the specific atomic bonding inside a material. Motivated by this finding, we used a symbolic learning approach to find interpretable physical models for the melting temperature, which recovered the best-performing features from both prior models and provided additional interpretability.
-
more » « less
Abstract The availability of materials with high electrocaloric (EC) strengths is critical to enabling EC refrigeration in practical applications. Although large EC entropy changes, Δ
S EC, and temperature changes, ΔT EC, have been achieved in traditional thin‐film ceramics and polymer ferroelectrics, they require the application of very high electric fields and thus their EC strengths ΔS EC/ΔE and ΔT EC/ΔE are too low for practical applications. Here, a fundamental thermodynamic description is developed, and extraordinarily large EC strengths of a metal‐free perovskite ferroelectric [MDABCO](NH4)I3(MDABCO) are predicted. The predicted EC strengths: isothermal ΔS EC/ΔE and adiabatic ΔT EC/ΔE for MDABCO are 18 J m kg−1K−1MV−1and 8.06 K m MV−1, respectively, more than three times the largest reported values in BaTiO3single crystals. These predictions strongly suggest the metal‐free ferroelectric family of materials as the best candidates among existing materials for EC applications. The present work not only presents a general approach to developing thermodynamic potential energy functions for ferroelectric materials but also suggests a family of candidate materials with potentially extremely high EC performance. -
more » « less
Thermoelectric materials harvest waste heat and convert it into reusable electricity. Thermoelectrics are also widely used in inverse ways such as refrigerators and cooling electronics. However, most popular and known thermoelectric materials to date were proposed and found by intuition, mostly through experiments. Unfortunately, it is extremely time and resource consuming to synthesize and measure the thermoelectric properties through trial-and-error experiments. Here, we develop a convolutional neural network (CNN) classification model that utilizes the fused orbital field matrix and composition descriptors to screen a large pool of materials to discover new thermoelectric candidates with power factor higher than 10 μW/cm K2. The model used our own data generated by high-throughput density functional theory calculations coupled with ab initio scattering and transport package to obtain electronic transport properties without assuming constant relaxation time of electrons, which ensures more reliable electronic transport properties calculations than previous studies. The classification model was also compared to some traditional machine learning algorithms such as gradient boosting and random forest. We deployed the classification model on 3465 cubic dynamically stable structures with non-zero bandgap screened from Open Quantum Materials Database. We identified many high-performance thermoelectric materials with ZT > 1 or close to 1 across a wide temperature range from 300 to 700 K and for both n- and p-type doping with different doping concentrations. Moreover, our feature importance and maximal information coefficient analysis demonstrates two previously unreported material descriptors, namely, mean melting temperature and low average deviation of electronegativity, that are strongly correlated with power factor and thus provide a new route for quickly screening potential thermoelectrics with high success rate. Our deep CNN model with fused orbital field matrix and composition descriptors is very promising for screening high power factor thermoelectrics from large-scale hypothetical structures.
