APL Machine Learning最新文献

Predicting wind farm wake losses with deep convolutional hierarchical encoder–decoder neural networks 利用深度卷积分层编码器-解码器神经网络预测风电场尾流损失

APL Machine Learning Pub Date : 2024-02-15 DOI: 10.1063/5.0168973

David A. Romero, Saeede Hasanpoor, Enrico G. A. Antonini, C. H. Amon

{"title":"Predicting wind farm wake losses with deep convolutional hierarchical encoder–decoder neural networks","authors":"David A. Romero, Saeede Hasanpoor, Enrico G. A. Antonini, C. H. Amon","doi":"10.1063/5.0168973","DOIUrl":"https://doi.org/10.1063/5.0168973","url":null,"abstract":"Wind turbine wakes are the most significant factor affecting wind farm performance, decreasing energy production and increasing fatigue loads in downstream turbines. Wind farm turbine layouts are designed to minimize wake interactions using a suite of predictive models, including analytical wake models and computational fluid dynamics simulations (CFD). CFD simulations of wind farms are time-consuming and computationally expensive, which hinder their use in optimization studies that require hundreds of simulations to converge to an optimal turbine layout. In this work, we propose DeepWFLO, a deep convolutional hierarchical encoder–decoder neural network architecture, as an image-to-image surrogate model for predicting the wind velocity field for Wind Farm Layout Optimization (WFLO). We generate a dataset composed of image representations of the turbine layout and undisturbed flow field in the wind farm, as well as images of the corresponding wind velocity field, including wake effects generated with both analytical models and CFD simulations. The proposed DeepWFLO architecture is then trained and optimized through supervised learning with an application-tailored loss function that considers prediction errors in both wind velocity and energy production. Results on a commonly used test case show median velocity errors of 1.0%–8.0% for DeepWFLO networks trained with analytical and CFD data, respectively. We also propose a model-fusion strategy that uses analytical wake models to generate an additional input channel for the network, resulting in median velocity errors below 1.8%. Spearman rank correlations between predictions and data, which evidence the suitability of DeepWFLO for optimization purposes, range between 92.3% and 99.9%.","PeriodicalId":229559,"journal":{"name":"APL Machine Learning","volume":"20 25","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-02-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139962638","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Learning the stable and metastable phase diagram to accelerate the discovery of metastable phases of boron 学习稳定和逸散相图，加速发现硼的逸散相

APL Machine Learning Pub Date : 2024-01-08 DOI: 10.1063/5.0175994

Karthik Balasubramanian, Suvo Banik, Sukriti Manna, S. Srinivasan, SubramanianK.R.S. Sankaranarayanan

{"title":"Learning the stable and metastable phase diagram to accelerate the discovery of metastable phases of boron","authors":"Karthik Balasubramanian, Suvo Banik, Sukriti Manna, S. Srinivasan, SubramanianK.R.S. Sankaranarayanan","doi":"10.1063/5.0175994","DOIUrl":"https://doi.org/10.1063/5.0175994","url":null,"abstract":"Boron, an element of captivating chemical intricacy, has been surrounded by controversies ever since its discovery in 1808. The complexities of boron stem from its unique position between metals and insulators in the Periodic Table. Recent computational studies have shed light on some of the stable boron allotropes. However, the demand for multifunctionality necessitates the need to go beyond the stable phases into the realm of metastability and explore the potentially vast but elusive metastable phases of boron. Traditional search for stable phases of materials has focused on identifying materials with the lowest enthalpy. Here, we introduce a workflow that uses reinforcement learning coupled with decision trees, such as Monte Carlo tree search, to search for stable and metastable boron phases, with enthalpy as the objective. We discover new boron metastable phases and construct a phase diagram that locates their phase space (T, P) at different levels of metastability (ΔG) from the ground state and provides useful information on the domains of relative stability of the various stable and metastable boron phases.","PeriodicalId":229559,"journal":{"name":"APL Machine Learning","volume":"2 10","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-01-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139447019","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Unsupervised machine learning to analyze corneal tissue surfaces 无监督机器学习分析角膜组织表面

APL Machine Learning Pub Date : 2023-11-14 DOI: 10.1063/5.0159502

Carolin A. Rickert, Fabio Henkel, Oliver Lieleg

引用次数: 0

Scanning probe microscopy in the age of machine learning

APL Machine Learning Pub Date : 2023-11-10 DOI: 10.1063/5.0160568

Md Ashiqur Rahman Laskar, Umberto Celano

引用次数: 0

A tutorial on the Bayesian statistical approach to inverse problems 关于反问题贝叶斯统计方法的教程

APL Machine Learning Pub Date : 2023-11-06 DOI: 10.1063/5.0154773

Faaiq G. Waqar, Swati Patel, Cory M. Simon

{"title":"A tutorial on the Bayesian statistical approach to inverse problems","authors":"Faaiq G. Waqar, Swati Patel, Cory M. Simon","doi":"10.1063/5.0154773","DOIUrl":"https://doi.org/10.1063/5.0154773","url":null,"abstract":"Inverse problems are ubiquitous in science and engineering. Two categories of inverse problems concerning a physical system are (1) estimate parameters in a model of the system from observed input–output pairs and (2) given a model of the system, reconstruct the input to it that caused some observed output. Applied inverse problems are challenging because a solution may (i) not exist, (ii) not be unique, or (iii) be sensitive to measurement noise contaminating the data. Bayesian statistical inversion (BSI) is an approach to tackle ill-posed and/or ill-conditioned inverse problems. Advantageously, BSI provides a “solution” that (i) quantifies uncertainty by assigning a probability to each possible value of the unknown parameter/input and (ii) incorporates prior information and beliefs about the parameter/input. Herein, we provide a tutorial of BSI for inverse problems by way of illustrative examples dealing with heat transfer from ambient air to a cold lime fruit. First, we use BSI to infer a parameter in a dynamic model of the lime temperature from measurements of the lime temperature over time. Second, we use BSI to reconstruct the initial condition of the lime from a measurement of its temperature later in time. We demonstrate the incorporation of prior information, visualize the posterior distributions of the parameter/initial condition, and show posterior samples of lime temperature trajectories from the model. Our Tutorial aims to reach a wide range of scientists and engineers.","PeriodicalId":229559,"journal":{"name":"APL Machine Learning","volume":"7 8","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135679590","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Bayesian optimization approach to quantify the effect of input parameter uncertainty on predictions of numerical physics simulations 贝叶斯优化方法量化输入参数不确定性对数值物理模拟预测的影响

APL Machine Learning Pub Date : 2023-11-01 DOI: 10.1063/5.0151747

Samuel G. McCallum, James E. Lerpinière, Kjeld O. Jensen, Pascal Friederich, Alison B. Walker

{"title":"Bayesian optimization approach to quantify the effect of input parameter uncertainty on predictions of numerical physics simulations","authors":"Samuel G. McCallum, James E. Lerpinière, Kjeld O. Jensen, Pascal Friederich, Alison B. Walker","doi":"10.1063/5.0151747","DOIUrl":"https://doi.org/10.1063/5.0151747","url":null,"abstract":"An understanding of how input parameter uncertainty in the numerical simulation of physical models leads to simulation output uncertainty is a challenging task. Common methods for quantifying output uncertainty, such as performing a grid or random search over the model input space, are computationally intractable for a large number of input parameters represented by a high-dimensional input space. It is, therefore, generally unclear as to whether a numerical simulation can reproduce a particular outcome (e.g., a set of experimental results) with a plausible set of model input parameters. Here, we present a method for efficiently searching the input space using Bayesian optimization to minimize the difference between the simulation output and a set of experimental results. Our method allows explicit evaluation of the probability that the simulation can reproduce the measured experimental results in the region of input space defined by the uncertainty in each input parameter. We apply this method to the simulation of charge-carrier dynamics in the perovskite semiconductor methyl-ammonium lead iodide (MAPbI3), which has attracted attention as a light harvesting material in solar cells. From our analysis, we conclude that the formation of large polarons, quasiparticles created by the coupling of excess electrons or holes with ionic vibrations, cannot explain the experimentally observed temperature dependence of electron mobility.","PeriodicalId":229559,"journal":{"name":"APL Machine Learning","volume":"71 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135270611","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Asymmetric CycleGANs for inverse design of photonic metastructures 光子元结构逆设计的不对称循环gan

APL Machine Learning Pub Date : 2023-10-30 DOI: 10.1063/5.0159264

Jeygopi Panisilvam, Elnaz Hajizadeh, Hansani Weeratunge, James Bailey, Sejeong Kim

{"title":"Asymmetric CycleGANs for inverse design of photonic metastructures","authors":"Jeygopi Panisilvam, Elnaz Hajizadeh, Hansani Weeratunge, James Bailey, Sejeong Kim","doi":"10.1063/5.0159264","DOIUrl":"https://doi.org/10.1063/5.0159264","url":null,"abstract":"Using deep learning to develop nanophotonic structures has been an active field of research in recent years to reduce the time intensive iterative solutions found in finite-difference time-domain simulations. Existing work has primarily used a specific type of generative network: conditional deep convolutional generative adversarial networks. However, these networks have issues with producing clear optical structures in image files; for example, a large number of images show speckled noise, which often results in non-manufacturable structures. Here, we report the first use of cycle-consistent generative adversarial networks to design nanophotonic structures. This approach significantly reduces the amount of speckled noise present in generated geometric structures and allows shapes to have clear edges. We demonstrate that for a given input reflectance spectra, the system generates designs in the form of images, and a complementary network generates reflectance spectra if an image containing a shape is provided as an input. The results show a higher Frechet Inception Distance score than previous approaches, which indicates that the generated structures are of higher quality and are able to learn nonlinear relationships between both datasets. This method of designing nanophotonics provides alternative avenues for development that are more noise robust while still adhering to desired optical properties.","PeriodicalId":229559,"journal":{"name":"APL Machine Learning","volume":"542 ","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-10-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"136104071","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Analysis of Brownian motion trajectories of non-spherical nanoparticles using deep learning 基于深度学习的非球形纳米颗粒布朗运动轨迹分析

APL Machine Learning Pub Date : 2023-10-24 DOI: 10.1063/5.0160979

Hiroaki Fukuda, Hiromi Kuramochi, Yasushi Shibuta, Takanori Ichiki

{"title":"Analysis of Brownian motion trajectories of non-spherical nanoparticles using deep learning","authors":"Hiroaki Fukuda, Hiromi Kuramochi, Yasushi Shibuta, Takanori Ichiki","doi":"10.1063/5.0160979","DOIUrl":"https://doi.org/10.1063/5.0160979","url":null,"abstract":"As nanoparticles are being put to practical use as useful materials in the medical, pharmaceutical, and industrial fields, the importance of technologies that can evaluate not only nanoparticle populations of homogeneous size and density but also those of rich diversity is increasing. Nano-tracking analysis (NTA) has been commercialized and widely used as a method to measure individual nanoparticles in liquids and evaluate their size distribution by analyzing Brownian motion. We have combined deep learning (DL) for NTA to extract more property information and explored a methodology to achieve an evaluation for individual particles to understand their diversity. Practical NTA always assumes spherical shape when quantifying particle size using the Stokes–Einstein equation, but it is not possible to verify whether the measured particles are truly spherical. We developed a DL model that predicts the shape of nanoparticles using time series trajectory data of BM obtained from NTA measurements to address this problem. As a result, we were able to discriminate with ∼80% accuracy between spherical and rod-shaped gold nanoparticles of different shapes, which are evaluated to have nearly equal particle size without any discrimination by conventional NTA. Furthermore, we demonstrated that the mixing ratio of spherical and rod-shaped nanoparticles can be quantitatively estimated from measured data of mixed samples of nanoparticles. This result suggests that it is possible to evaluate particle shape by applying DL analysis to NTA measurements, which was previously considered impossible, and opens the way to further value-added NTA.","PeriodicalId":229559,"journal":{"name":"APL Machine Learning","volume":"46 3","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-10-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135266411","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Discovery of structure–property relations for molecules via hypothesis-driven active learning over the chemical space 通过化学空间的假设驱动的主动学习发现分子的结构-性质关系

APL Machine Learning Pub Date : 2023-10-20 DOI: 10.1063/5.0157644

Ayana Ghosh, Sergei V. Kalinin, Maxim A. Ziatdinov

{"title":"Discovery of structure–property relations for molecules via hypothesis-driven active learning over the chemical space","authors":"Ayana Ghosh, Sergei V. Kalinin, Maxim A. Ziatdinov","doi":"10.1063/5.0157644","DOIUrl":"https://doi.org/10.1063/5.0157644","url":null,"abstract":"The discovery of the molecular candidates for application in drug targets, biomolecular systems, catalysts, photovoltaics, organic electronics, and batteries necessitates the development of machine learning algorithms capable of rapid exploration of chemical spaces targeting the desired functionalities. Here, we introduce a novel approach for active learning over the chemical spaces based on hypothesis learning. We construct the hypotheses on the possible relationships between structures and functionalities of interest based on a small subset of data followed by introducing them as (probabilistic) mean functions for the Gaussian process. This approach combines the elements from the symbolic regression methods, such as SISSO and active learning, into a single framework. The primary focus of constructing this framework is to approximate physical laws in an active learning regime toward a more robust predictive performance, as traditional evaluation on hold-out sets in machine learning does not account for out-of-distribution effects which may lead to a complete failure on unseen chemical space. Here, we demonstrate it for the QM9 dataset, but it can be applied more broadly to datasets from both domains of molecular and solid-state materials sciences.","PeriodicalId":229559,"journal":{"name":"APL Machine Learning","volume":"182 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-10-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135617520","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 1

Optimization of a quantum cascade laser cavity for single-spatial-mode operation via machine learning 基于机器学习的单空间模式操作量子级联激光腔的优化

APL Machine Learning Pub Date : 2023-10-20 DOI: 10.1063/5.0158204

S. A. Jacobs, J. D. Kirch, Y. Hu, S. Suri, B. Knipfer, Z. Yu, D. Botez, R. Marsland, L. J. Mawst

引用次数: 0