About

Ankit Agrawal is a Research Professor at Northwestern University, affiliated with the Department of Electrical and Computer Engineering. His research focuses on high performance data mining and its applications across various fields such as materials science, healthcare, social media, and bioinformatics. His work addresses the challenges posed by big data, including its size and complexity, by integrating high performance computing with data mining techniques to enable large-scale, data-guided discovery in multiple application domains. Agrawal's research aims to advance data-driven science and discovery, emphasizing the development of methods capable of handling high-dimensional, multi-scale, and spatio-temporal data.

Research topics

• Computer Science
• Machine Learning
• Artificial Intelligence
• Data Mining
• Algorithm
• Data science
• Physics
• Composite material
• Statistical physics
• Geometry
• Mathematics
• Nanotechnology
• Materials science

Selected publications

• Recent advances and applications of deep learning methods in materials science

  npj Computational Materials · 2022 · 1031 citations

  • Computer Science
  • Artificial Intelligence
  • Computer Science

  Abstract Deep learning (DL) is one of the fastest-growing topics in materials data science, with rapidly emerging applications spanning atomistic, image-based, spectral, and textual data modalities. DL allows analysis of unstructured data and automated identification of features. The recent development of large materials databases has fueled the application of DL methods in atomistic prediction in particular. In contrast, advances in image and spectral data have largely leveraged synthetic data enabled by high-quality forward models as well as by generative unsupervised DL methods. In this article, we present a high-level overview of deep learning methods followed by a detailed discussion of recent developments of deep learning in atomistic simulation, materials imaging, spectral analysis, and natural language processing. For each modality we discuss applications involving both theoretical and experimental data, typical modeling approaches with their strengths and limitations, and relevant publicly available software and datasets. We conclude the review with a discussion of recent cross-cutting work related to uncertainty quantification in this field and a brief perspective on limitations, challenges, and potential growth areas for DL methods in materials science.

  PublisherOA PDFDOI

• Cross-property deep transfer learning framework for enhanced predictive analytics on small materials data

  Nature Communications · 2021 · 154 citations

  Senior authorCorresponding
  • Computer Science
  • Computer Science
  • Artificial Intelligence

  Artificial intelligence (AI) and machine learning (ML) have been increasingly used in materials science to build predictive models and accelerate discovery. For selected properties, availability of large databases has also facilitated application of deep learning (DL) and transfer learning (TL). However, unavailability of large datasets for a majority of properties prohibits widespread application of DL/TL. We present a cross-property deep-transfer-learning framework that leverages models trained on large datasets to build models on small datasets of different properties. We test the proposed framework on 39 computational and two experimental datasets and find that the TL models with only elemental fractions as input outperform ML/DL models trained from scratch even when they are allowed to use physical attributes as input, for 27/39 (≈ 69%) computational and both the experimental datasets. We believe that the proposed framework can be widely useful to tackle the small data challenge in applying AI/ML in materials science.

  DOI

• Enabling deeper learning on big data for materials informatics applications

  Scientific Reports · 2021 · 62 citations

  Senior authorCorresponding
  • Computer Science
  • Artificial Intelligence
  • Computer Science

  The application of machine learning (ML) techniques in materials science has attracted significant attention in recent years, due to their impressive ability to efficiently extract data-driven linkages from various input materials representations to their output properties. While the application of traditional ML techniques has become quite ubiquitous, there have been limited applications of more advanced deep learning (DL) techniques, primarily because big materials datasets are relatively rare. Given the demonstrated potential and advantages of DL and the increasing availability of big materials datasets, it is attractive to go for deeper neural networks in a bid to boost model performance, but in reality, it leads to performance degradation due to the vanishing gradient problem. In this paper, we address the question of how to enable deeper learning for cases where big materials data is available. Here, we present a general deep learning framework based on Individual Residual learning (IRNet) composed of very deep neural networks that can work with any vector-based materials representation as input to build accurate property prediction models. We find that the proposed IRNet models can not only successfully alleviate the vanishing gradient problem and enable deeper learning, but also lead to significantly (up to 47%) better model accuracy as compared to plain deep neural networks and traditional ML techniques for a given input materials representation in the presence of big data.

  DOI

• Learning to Predict Crystal Plasticity at the Nanoscale: Deep Residual Networks and Size Effects in Uniaxial Compression Discrete Dislocation Simulations

  Scientific Reports · 2020 · 31 citations

  Senior authorCorresponding
  • Computer Science
  • Materials science
  • Statistical physics

  The density and configurational changes of crystal dislocations during plastic deformation influence the mechanical properties of materials. These influences have become clearest in nanoscale experiments, in terms of strength, hardness and work hardening size effects in small volumes. The mechanical characterization of a model crystal may be cast as an inverse problem of deducing the defect population characteristics (density, correlations) in small volumes from the mechanical behavior. In this work, we demonstrate how a deep residual network can be used to deduce the dislocation characteristics of a sample of interest using only its surface strain profiles at small deformations, and then statistically predict the mechanical response of size-affected samples at larger deformations. As a testbed of our approach, we utilize high-throughput discrete dislocation simulations for systems of widths that range from nano- to micro- meters. We show that the proposed deep learning model significantly outperforms a traditional machine learning model, as well as accurately produces statistical predictions of the size effects in samples of various widths. By visualizing the filters in convolutional layers and saliency maps, we find that the proposed model is able to learn the significant features of sample strain profiles.

  DOI

Recent grants

• Collaborative Research: AI-Driven Multi-Scale Design of Materials under Processing Constraints

  NSF · $379k · 2021–2025

Frequent coauthors

• Alok Choudhary

  Northwestern University

  179 shared

• Wei‐keng Liao

  Northwestern University

  117 shared

• Allan L. Klein

  Synta Pharmaceuticals (United States)

  48 shared

• Alok Choudhary

  Northwestern University

  33 shared

• Abdullah Yesilyaprak

  Ascension Providence Hospital

  28 shared

• Ashwin S. Kumar

  Georgetown University

  28 shared

• Beni Verma

  Case Western Reserve University

  27 shared

• Amit K. Dey

  27 shared

Education

• PhD, Computer Science

  Iowa State University

  2009

• B.Tech., Electronics and Computer Engineering

  Indian Institute of Technology Roorkee

  2006

Similar researchers at Northwestern University

• Mercouri G. Kanatzidish-205
• Chad Mirkinh-189
• Omar Farhah-184
• Tobin J. Marksh-176
• Joseph Hupph-171