Borates and borosilicates are potential candidates for the design and development of glass formulations with important industrial and technological applications. A major challenge that retards the pace of development of borate/borosilicate based glasses using predictive modeling is the lack of reliable computational models to predict the structure‐property relationships in these glasses over a wide compositional space. A major hindrance in this pursuit has been the complexity of boron‐oxygen bonding due to which it has been difficult to develop adequate B–O interatomic potentials. In this article, we have evaluated the performance of three B–O interatomic potential models recently developed by Bauchy et al [
Empirical interatomic potentials require optimization of force field parameters to tune interatomic interactions to mimic ones obtained by quantum chemistry-based methods. The optimization of the parameters is complex and requires the development of new techniques. Here, we propose an INitial-DEsign Enhanced Deep learning-based OPTimization (INDEEDopt) framework to accelerate and improve the quality of the ReaxFF parameterization. The procedure starts with a Latin Hypercube Design (LHD) algorithm that is used to explore the parameter landscape extensively. The LHD passes the information about explored regions to a deep learning model, which finds the minimum discrepancy regions and eliminates unfeasible regions, and constructs a more comprehensive understanding of physically meaningful parameter space. We demonstrate the procedure here for the parameterization of a nickel–chromium binary force field and a tungsten–sulfide–carbon–oxygen–hydrogen quinary force field. We show that INDEEDopt produces improved accuracies in shorter development time compared to the conventional optimization method.
more » « less- Award ID(s):
- 1660477
- NSF-PAR ID:
- 10229579
- Publisher / Repository:
- Nature Publishing Group
- Date Published:
- Journal Name:
- npj Computational Materials
- Volume:
- 7
- Issue:
- 1
- ISSN:
- 2057-3960
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
more » « less
Abstract J .Non‐Cryst. Solids , 2018, 498, 294–304], Du et al [J. Am. Ceram. Soc. https://doi.org/10.1111/jace.16082 ] and Edèn et al [Phys. Chem. Chem. Phys. , 2018, 20, 8192–8209] aiming to reproduce the short‐to‐medium range structures of sodium borosilicate glasses in the system 25 Na2Ox B2O3(75 −x ) SiO2(x = 0‐75 mol%). To evaluate the different force fields, we have computed at the density functional theory level the NMR parameters of11B,23Na, and29Si of the models generated with the three potentials and the simulated MAS NMR spectra compared with the experimental counterparts. It was observed that the rigid ionic models proposed by Bauchy and Du can both reliably reproduce the partitioning between BO3and BO4species of the investigated glasses, along with the local environment around sodium in the glass structure. However, they do not accurately reproduce the second coordination sphere of silicon ions and the Si–O–T (T = Si, B) and B‐O‐T distribution angles in the investigated compositional space which strongly affect the NMR parameters and final spectral shape. On the other hand, the core‐shell parameterization model proposed by Edén underestimates the fraction of BO4species of the glass with composition 25Na2O 18.4B2O356.6SiO2but can accurately reproduce the shape of the11B and29Si MAS‐NMR spectra of the glasses investigations due to the narrower B–O–T and Si‐O‐T bond angle distributions. Finally, the effect of the number of boron atoms (also distinguishing the BO3and BO4units) in the second coordination sphere of the network former cations on the NMR parameters have been evaluated. -
The development of reliable, yet computationally efficient interatomic forcefields is key to facilitate the modeling of glasses. However, the parameterization of novel forcefields is challenging as the high number of parameters renders traditional optimization methods inefficient or subject to bias. Here, we present a new parameterization method based on machine learning, which combines ab initio molecular dynamics simulations and Bayesian optimization. By taking the example of glassy silica, we show that our method yields a new interatomic forcefield that offers an unprecedented agreement with ab initio simulations. This method offers a new route to efficiently parameterize new interatomic forcefields for disordered solids in a non-biased fashion.more » « less
-
more » « less
Abstract Background Optimization of DNA and protein sequences based on Machine Learning models is becoming a powerful tool for molecular design. Activation maximization offers a simple design strategy for differentiable models: one-hot coded sequences are first approximated by a continuous representation, which is then iteratively optimized with respect to the predictor oracle by gradient ascent. While elegant, the current version of the method suffers from vanishing gradients and may cause predictor pathologies leading to poor convergence.
Results Here, we introduce Fast SeqProp, an improved activation maximization method that combines straight-through approximation with normalization across the parameters of the input sequence distribution. Fast SeqProp overcomes bottlenecks in earlier methods arising from input parameters becoming skewed during optimization. Compared to prior methods, Fast SeqProp results in up to 100-fold faster convergence while also finding improved fitness optima for many applications. We demonstrate Fast SeqProp’s capabilities by designing DNA and protein sequences for six deep learning predictors, including a protein structure predictor.
Conclusions Fast SeqProp offers a reliable and efficient method for general-purpose sequence optimization through a differentiable fitness predictor. As demonstrated on a variety of deep learning models, the method is widely applicable, and can incorporate various regularization techniques to maintain confidence in the sequence designs. As a design tool, Fast SeqProp may aid in the development of novel molecules, drug therapies and vaccines.
-
more » « less
Abstract We present a phase-field (PF) model to simulate the microstructure evolution occurring in polycrystalline materials with a variation in the intra-granular dislocation density. The model accounts for two mechanisms that lead to the grain boundary migration: the driving force due to capillarity and that due to the stored energy arising from a spatially varying dislocation density. In addition to the order parameters that distinguish regions occupied by different grains, we introduce dislocation density fields that describe spatial variation of the dislocation density. We assume that the dislocation density decays as a function of the distance the grain boundary has migrated. To demonstrate and parameterize the model, we simulate microstructure evolution in two dimensions, for which the initial microstructure is based on real-time experimental data. Additionally, we applied the model to study the effect of a cyclic heat treatment (CHT) on the microstructure evolution. Specifically, we simulated stored-energy-driven grain growth during three thermal cycles, as well as grain growth without stored energy that serves as a baseline for comparison. We showed that the microstructure evolution proceeded much faster when the stored energy was considered. A non-self-similar evolution was observed in this case, while a nearly self-similar evolution was found when the microstructure evolution is driven solely by capillarity. These results suggest a possible mechanism for the initiation of abnormal grain growth during CHT. Finally, we demonstrate an integrated experimental-computational workflow that utilizes the experimental measurements to inform the PF model and its parameterization, which provides a foundation for the development of future simulation tools capable of quantitative prediction of microstructure evolution during non-isothermal heat treatment.
-
more » « less
Abstract Submarine groundwater discharge (SGD) is an important driver of coastal biogeochemical budgets worldwide. Radon (222Rn) has been widely used as a natural geochemical tracer to quantify SGD, but field measurements are time consuming and costly. Here, we use deep learning to predict coastal seawater radon in SGD‐impacted regions. We hypothesize that deep learning could resolve radon trends and enable preliminary insights with limited field observations of groundwater tracers. Two deep learning models were trained on global coastal seawater radon observations (
n = 39,238) with widely available inputs (e.g., salinity, temperature, water depth). The first model used a one‐dimensional convolutional neural network (1D‐CNN‐RNN) framework for site‐specific gap filling and producing short‐term future predictions. A second model applied a fully connected neural network (FCNN) framework to predict radon across geographically and hydrologically diverse settings. Both models can predict observed radon concentrations withr 2 > 0.76. Specifically, the FCNN model offers a compelling development because synthetic radon tracer data sets can be obtained using only basic water quality and meteorological parameters. This opens opportunities to attain radon data from regions with large data gaps, such as the Global South and other remote locations, allowing for insights that can be used to predict SGD and plan field experiments. Overall, we demonstrate how field‐based measurements combined with big‐data approaches such as deep learning can be utilized to assess radon and potentially SGD beyond local scales.
