检索结果-南通市图书馆

Discovering equations that govern experimental materials stability under environmental stress using scientific machine learning

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

npj Computational Materials 2022年第1期8卷 679-686页

作者： Richa Ramesh Naik Armi Tiihonen Janak Thapa Clio Batali Zhe Liu Shijing Sun tonio Buonassisi Massachusetts Institute of Technology 77 Massachusetts AvenueCambridgeMA02139USA

While machine learning(ML)in experimental research has demonstrated impressive predictive capabilities,extracting fungible knowledge representations from experimental data remains an elusive *** this manuscript,we use ML to infer the underlying differential equation(DE)from experimental data of degrading organic-inorganic methylammonium lead iodide(MAPI)perovskite thin films under environmental stressors(elevated temperature,humidity,and light).Using a sparse regression algorithm,we find that the underlying DE governing MAPI degradation across a broad temperature range of 35 to 85℃is described minimally by a second-order *** DE corresponds to the Verhulst logistic function,which describes reaction kinetics analogous to self-propagating *** examine the robustness of our conclusions to experimental variance and Gaussian noise and describe the experimental limits within which this methodology can be *** study highlights the promise and challenges associated with ML-aided scientific discovery by demonstrating its application in experimental chemical and materials systems.

关键词： stability analogous kinetics

Interpretable and Explainable Machine Learning for Materials Science and Chemistry

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Accounts of Materials Research 2022年第6期3卷 597-607页

作者： Felipe Oviedo Juan lavista Ferres tonio Buonassisi Keith T.Butler Massachusetts Institute of Technology CambridgeMassachusetts 02139United States Microsoft AI for Good Research lab RedmondWashington 98052United States SciML Scientific Computing DepartmentRutherford Appleton LaboratoryDidcot OX110DU.K. Department of Chemistry University of ReadingReading RG66ADU.K.

Machine learning has become a common and powerful tool in materials *** more data become available,with the use of high-performance computing and high-throughput experimentation,machine learning has proven potential to accelerate scientific research and technology *** the uptake of data-driven approaches for materials science is at an exciting,early stage,to realize the true potential of machine learning models for successful scientific discovery,they must have qualities beyond purely predictive *** predictions and inner workings of models should provide a certain degree of explainability by human experts,permitting the identification of potential model issues or limitations,building trust in model predictions,and unveiling unexpected correlations that may lead to scientific *** this work,we summarize applications of interpretability and explainability techniques for materials science and chemistry and discuss how these techniques can improve the outcome of scientific *** start by defining the fundamental concepts of interpretability and explainability in machine learning and making them less abstract by providing examples in the *** show how interpretability in scientific machine learning has additional constraints compared to general *** upon formal definitions in machine learning,we formulate the basic trade-offs among the explainability,completeness,and scientific validity of model explanations in scientific *** the context of these trade-offs,we discuss how interpretable models can be constructed,what insights they provide,and what drawbacks they *** present numerous examples of the application of interpretable machine learning in a variety of experimental and simulation studies,encompassing first-principles calculations,physicochemical characterization,materials development,and integration into complex *** discuss the varied impacts and uses of interpretabiltiy in these cases

关键词： explain purely insight

Machine learning enables polymer cloud-point engineering via inverse design

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

npj Computational Materials 2019年第1期5卷 523-528页

作者： Jatin N.Kumar Qianxiao Li Karen Y.T.Tang tonio Buonassisi Anibal L.Gonzalez-Oyarce Jun Ye Institute of Materials Research&Engineering 2 Fusionopolis Way#08-03Singapore 138634Singapore Institute of High-Performance Computing 1 Fusionopolis Way#16-16Singapore 138632Singapore Massachussets Institute of Technology CambridgeMA 02139USA

Inverse design is an outstanding challenge in disordered systems with multiple length scales such as polymers,particularly when designing polymers with desired phase *** we demonstrate high-accuracy tuning of poly(2-oxazoline)cloud point via machine *** a design space of four repeating units and a range of molecular masses,we achieve an accuracy of 4℃ root mean squared error(RMSE)in a temperature range of 24–90℃,employing gradient boosting with decision *** RMSE is>3x better than linear and polynomial *** perform inverse design via particle-swarm optimization,predicting and synthesizing 17 polymers with constrained design at 4 target cloud points from 37 to 80℃.Our approach challenges the status quo in polymer design with a machine learning algorithm,that is capable of fast and systematic discovery of new polymers.

关键词： inverse polymer enable

Two-step machine learning enables optimized nanoparticle synthesis

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

npj Computational Materials 2021年第1期7卷 498-507页

作者： Flore Mekki-Berrada Zekun Ren Tan Huang Wai Kuan Wong Fang Zheng Jiaxun Xie Isaac Parker Siyu Tian Senthilnath Jayavelu Zackaria Mahfoud Daniil Bash Kedar Hippalgaonkar Saif Khan tonio Buonassisi Qianxiao Li Xiaonan Wang Department of Chemical and Biomolecular Engineering National University of SingaporeSingaporeSingapore Singapore-MIT Alliance for Research and Technology SMART SingaporeSingapore Institute for Infocomm Research Agency for ScienceTechnology and Research(A*STAR)SingaporeSingapore Institute of Materials Research&Engineering SingaporeSingapore Department of Materials Science and Engineering Nanyang Technological UniversitySingaporeSingapore Massachusetts Institute of Technology CambridgeMAUSA Department of Mathematics National University of SingaporeSingaporeSingapore Institute of High Performance Computing SingaporeSingapore

In materials science,the discovery of recipes that yield nanomaterials with defined optical properties is costly and *** this study,we present a two-step framework for a machine learning-driven high-throughput microfluidic platform to rapidly produce silver nanoparticles with the desired absorbance *** a Gaussian process-based Bayesian optimization(BO)with a deep neural network(DNN),the algorithmic framework is able to converge towards the target spectrum after sampling 120 *** the dataset is large enough to train the DNN with sufficient accuracy in the region of the target spectrum,the DNN is used to predict the colour palette accessible with the reaction *** remaining interpretable by humans,the proposed framework efficiently optimizes the nanomaterial synthesis and can extract fundamental knowledge of the relationship between chemical composition and optical properties,such as the role of each reactant on the shape and amplitude of the absorbance spectrum.

关键词： spectrum synthesis. synthesis

Fast and interpretable classification of small X-ray diffraction datasets using data augmentation and deep neural networks

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

npj Computational Materials 2019年第1期5卷 624-632页

作者： Felipe Oviedo Zekun Ren Shijing Sun Charles Settens Zhe Liu Noor Titan Putri Hartono Savitha Ramasamy Brian L.DeCost Siyu I.P.Tian Giuseppe Romano Aaron Gilad Kusne tonio Buonassisi Massachusetts Institute of Technology CambridgeMA 02139USA Singapore-MIT Alliance for Research and Technology Singapore 138602Singapore Institute for Infocomm Research(I2R) Agency for ScienceTechnology and Research(A*STAR)Singapore 138632Singapore National Institute of Standards and Technology MS 8520GaithersburgMD 20899USA

X-ray diffraction(XRD)data acquisition and analysis is among the most time-consuming steps in the development cycle of novel thin-film *** propose a machine learning-enabled approach to predict crystallographic dimensionality and space group from a limited number of thin-film XRD *** overcome the scarce data problem intrinsic to novel materials development by coupling a supervised machine learning approach with a model-agnostic,physics-informed data augmentation strategy using simulated data from the Inorganic Crystal Structure Database(ICSD)and experimental *** a test case,115 thin-film metalhalides spanning three dimensionalities and seven space groups are synthesized and *** testing various algorithms,we develop and implement an all convolutional neural network,with cross-validated accuracies for dimensionality and space group classification of 93 and 89%,*** propose average class activation maps,computed from a global average pooling layer,to allow high model interpretability by human experimentalists,elucidating the root causes of ***,we systematically evaluate the maximum XRD pattern step size(data acquisition rate)before loss of predictive accuracy occurs,and determine it to be 0.16°2θ,which enables an XRD pattern to be obtained and classified in 5.5 min or less.

关键词： neural networks dimensionality

Benchmarking the performance of Bayesian optimization across multiple experimental materials science domains

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

npj Computational Materials 2021年第1期7卷 1742-1751页

作者： Qiaohao Liang Aldair E.Gongora Zekun Ren Armi Tiihonen Zhe Liu Shijing Sun James R.Deneault Daniil Bash Flore Mekki-Berrada Saif A.Khan Kedar Hippalgaonkar Benji Maruyama Keith A.Brown John Fisher III tonio Buonassisi Massachusetts Institute of Technology CambridgeMAUnited States Boston University BostonMAUnited States Singapore-MIT Alliance for Research and Technology SingaporeSingapore Air Force Research laboratory DaytonOhioUnited States Agency for Science Technology and Research(A*STAR)SingaporeSingapore National University of Singapore SingaporeSingapore Present address:Aalto University EspooFinland Present address:Northwestern Polytechincal University(NPU) Xi’anShaanxi P.R.China

Bayesian optimization(BO)has been leveraged for guiding autonomous and high-throughput experiments in materials ***,few have evaluated the efficiency of BO across a broad range of experimental materials *** this work,we quantify the performance of BO with a collection of surrogate model and acquisition function pairs across five diverse experimental materials *** defining acceleration and enhancement metrics for materials optimization objectives,we find that surrogate models such as Gaussian Process(GP)with anisotropic kernels and Random Forest(RF)have comparable performance in BO,and both outperform the commonly used GP with isotropic *** with anisotropic kernels has demonstrated the most robustness,yet RF is a close alternative and warrants more consideration because it is free from distribution assumptions,has smaller time complexity,and requires less effort in initial hyperparameter *** also raise awareness about the benefits of using GP with anisotropic kernels in future materials optimization campaigns.

关键词： optimization performance acceleration

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

从丹药到枪炮

Embedding physics domain knowledge into a Bayesian network enables layer-by-layer process innovation for photovoltaics

作者： (美)欧阳泰(tonio Andrade)

来源：南通市图书馆图书评论

学校读者我要写书评

暂无评论

npj Computational Materials 2020年第1期6卷 1592-1600页

作者： Zekun Ren Felipe Oviedo Maung Thway Siyu I.P.Tian Yue Wang Hansong Xue Jose Dario Perea Mariya layurova Thomas Heumueller Erik Birgersson Armin G.Aberle Christoph J.Brabec Rolf Stangl Qianxiao Li Shijing Sun Fen Lin Ian Marius Peters tonio Buonassisi Singapore-MIT Alliance for Research and Technology SMART Singapore 138602Singapore Solar Energy Research Institute of Singapore(SERIS) National University of SingaporeSingapore 117574Singapore Massachusetts Institute of Technology CambridgeMA 02139USA Institute of Materials for Electronics and Energy Technology(i-MEET) Friedrich-Alexander University Erlangen-Nürnberg91058 ErlangenGermany Helmholtz Institute HI-ErN Forschungszentrum JülichImmerwahrstrasse 291058 ErlangenGermany National University of Singapore Singapore 119077Singapore

Process optimization of photovoltaic devices is a time-intensive,trial-and-error endeavor,which lacks full transparency of the underlying physics and relies on user-imposed constraints that may or may not lead to a global ***,we demonstrate that embedding physics domain knowledge into a Bayesian network enables an optimization approach for gallium arsenide(GaAs)solar cells that identifies the root cause(s)of underperformance with layer-by-layer resolution and reveals alternative optimal process windows beyond traditional black-box *** Bayesian network approach links a key GaAs process variable(growth temperature)to material descriptors(bulk and interface properties,e.g.,bulk lifetime,doping,and surface recombination)and device performance parameters(e.g.,cell efficiency).For this purpose,we combine a Bayesian inference framework with a neural network surrogate device-physics model that is 100×faster than numerical *** the trained surrogate model and only a small number of experimental samples,our approach reduces significantly the time-consuming intervention and characterization required by the *** a demonstration of our method,in only five metal organic chemical vapor depositions,we identify a superior growth temperature profile for the window,bulk,and back surface field layer of a GaAs solar cell,without any secondary measurements,and demonstrate a 6.5%relative AM1.5G efficiency improvement above traditional grid search methods.

关键词： knowledge network enable

Author Correction:Embedding physics domain knowledge into a Bayesian network enables layer-by-layer process innovation for photovoltaics

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

npj Computational Materials 2020年第1期6卷 955-955页

作者： Zekun Ren Felipe Oviedo Maung Thway Siyu I.P.Tian Yue Wang Hansong Xue Jose Dario Perea Mariya layurova Thomas Heumueller Erik Birgersson Armin G.Aberle Christoph J.Brabec Rolf Stangl Qianxiao Li Shijing Sun Fen Lin Ian Marius Peters tonio Buonassisi Singapore-MIT Alliance for Research and Technology SMART Singapore Singapore Solar Energy Research Institute of Singapore (SERIS) National University of Singapore Singapore Singapore Massachusetts Institute of Technology Cambridge USA Institute of Materials for Electronics and Energy Technology (i-MEET) Friedrich-Alexander University Erlangen-Nürnberg Erlangen Germany Helmholtz Institute HI-ErN Forschungszentrum Jülich Erlangen Germany National University of Singapore Singapore Singapore

In the original version of the published Article,there was ambiguity in Eq.(1).To improve clarity,Eq.(1)has been corrected to the following.

关键词： enable corrected ambiguity