اشترك بالحزمة الذهبية واحصل على وصول غير محدود شمرا أكاديميا
تسجيل مستخدم جديدExperimental discovery of structure-property relationships in ferroelectric materials via active learning
511
0
0.0
(
0
)
اسأل ChatGPT حول البحث
ﻻ يوجد ملخص باللغة العربية
Emergent functionalities of structural and topological defects in ferroelectric materials underpin an extremely broad spectrum of applications ranging from domain wall electronics to high dielectric and electromechanical responses. Many of these have been discovered and quantified via local scanning probe microscopy methods. However, the search for these functionalities has until now been based by either trial and error or using auxiliary information such as topography or domain wall structure to identify potential objects of interest based on the intuition of operator or preexisting hypotheses, with subsequent manual exploration. Here, we report the development and implementation of a machine learning framework that actively discovers relationships between local domain structure and polarization switching characteristics in ferroelectric materials encoded in the hysteresis loop. The latter and descriptors such as nucleation bias, coercive bias, hysteresis loop area, or more complex functionals of hysteresis loop shape and corresponding uncertainties are used to guide the discovery via automated piezoresponse force microscopy (PFM) and spectroscopy experiments. As such, this approach combines the power of machine learning methods to learn the correlative relationships between high dimensional data, and human-based physics insights encoded in the acquisition function. For ferroelectric, this automated workflow demonstrates that the discovery path and sampling points of on-field and off-field hysteresis loops are largely different, indicating the on-field and off-field hysteresis loops are dominated by different mechanisms. The proposed approach is universal and can be applied to a broad range of modern imaging and spectroscopy methods ranging from other scanning probe microscopy modalities to electron microscopy and chemical imaging.
قيم البحث
اقرأ أيضاً
ABX3 perovskites have attracted intensive research interest in recent years due to their versatile composition and superior optoelectronic properties. Their counterparts, antiperovskites (X3BA), can be viewed as electronically inverted perovskite der
ivatives, but they have not been extensively studied for solar applications. Therefore, understanding their composition-property relationships is crucial for future photovoltaic application. Here, taking six antiperovskite nitrides X3NA (X2+ = Mg, Ca, Sr; A3- = P, As, Sb, Bi) as an example, we investigate the effect of X- and A-sites on the electronic, dielectric, and mechanical properties from the viewpoint of the first-principles calculations. Our calculation results show that the X-site dominates the conduction band, and the A-site has a non-negligible contribution to the band edge. These findings are completely different from traditional halide perovskites. Interestingly, when changing X- or A-site elements, a linear relationship between the tolerance factor and physical quantities, such as electronic parameters, dielectric constants, and Youngs modulus, is observed. By designing the Mg3NAs1-xBix alloys, we further verify this power of the linear relationship, which provides a predictive guidance for experimental preparation of antiperovskite alloys. Finally, we make a comprehensive comparison between the antiperovskite nitrides and conventional halide perovskites for pointing out the future device applications.
Active learning - the field of machine learning (ML) dedicated to optimal experiment design, has played a part in science as far back as the 18th century when Laplace used it to guide his discovery of celestial mechanics [1]. In this work we focus a
closed-loop, active learning-driven autonomous system on another major challenge, the discovery of advanced materials against the exceedingly complex synthesis-processes-structure-property landscape. We demonstrate autonomous research methodology (i.e. autonomous hypothesis definition and evaluation) that can place complex, advanced materials in reach, allowing scientists to fail smarter, learn faster, and spend less resources in their studies, while simultaneously improving trust in scientific results and machine learning tools. Additionally, this robot science enables science-over-the-network, reducing the economic impact of scientists being physically separated from their labs. We used the real-time closed-loop, autonomous system for materials exploration and optimization (CAMEO) at the synchrotron beamline to accelerate the fundamentally interconnected tasks of rapid phase mapping and property optimization, with each cycle taking seconds to minutes, resulting in the discovery of a novel epitaxial nanocomposite phase-change memory material.
Machine learning (ML) of quantum mechanical properties shows promise for accelerating chemical discovery. For transition metal chemistry where accurate calculations are computationally costly and available training data sets are small, the molecular
representation becomes a critical ingredient in ML model predictive accuracy. We introduce a series of revised autocorrelation functions (RACs) that encode relationships between the heuristic atomic properties (e.g., size, connectivity, and electronegativity) on a molecular graph. We alter the starting point, scope, and nature of the quantities evaluated in standard ACs to make these RACs amenable to inorganic chemistry. On an organic molecule set, we first demonstrate superior standard AC performance to other presently-available topological descriptors for ML model training, with mean unsigned errors (MUEs) for atomization energies on set-aside test molecules as low as 6 kcal/mol. For inorganic chemistry, our RACs yield 1 kcal/mol ML MUEs on set-aside test molecules in spin-state splitting in comparison to 15-20x higher errors from feature sets that encode whole-molecule structural information. Systematic feature selection methods including univariate filtering, recursive feature elimination, and direct optimization (e.g., random forest and LASSO) are compared. Random-forest- or LASSO-selected subsets 4-5x smaller than RAC-155 produce sub- to 1-kcal/mol spin-splitting MUEs, with good transferability to metal-ligand bond length prediction (0.004-5 {AA} MUE) and redox potential on a smaller data set (0.2-0.3 eV MUE). Evaluation of feature selection results across property sets reveals the relative importance of local, electronic descriptors (e.g., electronegativity, atomic number) in spin-splitting and distal, steric effects in redox potential and bond lengths.
Machine Learning (ML) has the potential to accelerate discovery of new materials and shed light on useful properties of existing materials. A key difficulty when applying ML in Materials Science is that experimental datasets of material properties te
nd to be small. In this work we show how material descriptors can be learned from the structures present in large scale datasets of material simulations; and how these descriptors can be used to improve the prediction of an experimental property, the energy of formation of a solid. The material descriptors are learned by training a Graph Neural Network to regress simulated formation energies from a materials atomistic structure. Using these learned features for experimental property predictions outperforms existing methods that are based solely on chemical composition. Moreover, we find that the advantage of our approach increases as the generalization requirements of the task are made more stringent, for example when limiting the amount of training data or when generalizing to unseen chemical spaces.
Regression machine learning is widely applied to predict various materials. However, insufficient materials data usually leads to a poor performance. Here, we develop a new voting data-driven method that could generally improve the performance of reg
ression learning model for accurately predicting properties of materials. We apply it to investigate a large family (2135) of two-dimensional hexagonal binary compounds focusing on ferroelectric properties and find that the performance of the model for electric polarization is indeed greatly improved, where 38 stable ferroelectrics with out-of-plane polarization including 31 metals and 7 semiconductors are screened out. By an unsupervised learning, actionable information such as how the number and orbital radius of valence electrons, ionic polarizability, and electronegativity of constituent atoms affect polarization was extracted. Our voting data-driven method not only reduces the size of materials data for constructing a reliable learning model but also enables to make precise predictions for targeted functional materials.
سجل دخول لتتمكن من نشر تعليقات
التعليقات
جاري جلب التعليقات
سجل دخول لتتمكن من متابعة معايير البحث التي قمت باختيارها
