Alok Choudhary

Mixture-of-Experts (MoE) architectures achieve scalable learning by routing inputs to specialized subnetworks through conditional computation. However, conventional MoE designs assume homogeneous expert capability and domain-agnostic routing-assumptions that are fundamentally misaligned with medical imaging, where anatomical structure and regional disease heterogeneity govern pathological patterns. We introduce Regional Expert Networks (REN), the first anatomically-informed MoE framework for medical image classification. REN encodes anatomical priors by training seven specialized experts, each dedicated to a distinct lung lobe or bilateral lung combination, enabling precise modeling of region-specific pathological variation. Multi-modal gating mechanisms dynamically integrate radiomics biomarkers with deep learning (DL) features extracted by convolutional (CNN), Transformer (ViT), and state-space (Mamba) architectures to weight expert contributions at inference. Applied to interstitial lung disease (ILD) classification on a 597-patient, 1,898-scan longitudinal cohort, REN achieves consistently superior performance: the radiomics-guided ensemble attains an average AUC of 0.8646 ± 0.0467, a +12.5% improvement over the SwinUNETR single-model base-line (AUC 0.7685, p = 0.031). Lower-lobe experts reach AUCs of 0.88-0.90, outperforming DL baselines (CNN: 0.76-0.79) and mirroring known patterns of basal ILD progression. Evaluated under rigorous patient-level cross-validation, REN demonstrates strong generalizability and clinical interpretability, establishing a scalable, anatomically-guided framework potentially extensible to other structured medical imaging tasks. Code is available on our GitHub https://github.com/NUBagciLab/MoE-REN.

High-level I/O libraries, such as PnetCDF and HDF5, are commonly used by large-scale scientific applications to perform I/O tasks in parallel. These I/O libraries store the metadata of data objects in files along with their raw data. To ensure metadata consistency during parallel data object creation, they require applications to call the metadata APIs collectively using consistent metadata. Such a requirement can result in an expensive consistency check, as its cost increases with the metadata volume and the number of processes. To address this limitation, we propose a new file header format, which uses partitioned metadata blocks to enable independent data object creation and reduce the objects required for consistency check. Our performance evaluation shows that this new design achieves a scalable performance, cutting data object creation times by up to 196 × when running on 4096 MPI processes to create 5,684,800 data objects in parallel.

Introduction: A new entrant to medical school is fresh from school and entering a different world of professional college. Students are often ill-prepared for the changes and challenges that lie ahead. The National Medical Commission (NMC) foundation course is purposively designed to include various relevant issues that are important to lay a solid foundation for budding professionals. All aspects necessary to cultivate the character of an academic medical graduate and prepare students for the expected challenges have been included in the course material. This study aimed to evaluate the educational impact of the foundation course on MBBS students. Methods: This study was conducted on 150 students in a medical college in Dehradun, Uttarakhand. The programme evaluation was done with structured feedback from the students, with the faculty engaged in the delivery, focusing on the educational impact on the students. Results: Modules where students responded positively that had an educational impact were the role of doctor in society, Indian Medical Graduate (IMG) roles and goals, Basic Life Support (BLS), first aid, universal precautions, and biomedical waste management. Most students agreed strongly that the module on the role of doctors in society and professionalism and ethics had the most educational impact and motivated them the most. Conclusion: The foundation course was perceived as a welcome addition to the MBBS program and has covered many important areas which have a definite educational impact on the students.

In this study, we present an artificial intelligence (AI)-driven framework for predicting the microstructural texture of polycrystalline materials after a specific deformation process. The microstructural texture is defined in terms of the orientation distribution function (ODF) which indicates the volume density of crystal orientations. Our approach leverages an encoder-decoder model with Long Short-Term Memory (LSTM) layers to model the relationship between processing conditions and material properties. As a case study, we apply our framework to copper, generating a dataset of 3125 unique processing parameter combinations and their corresponding ODF vectors. The resulting predictions enable the calculation of homogenized properties. Our AI-driven framework outperforms traditional material processing simulations, yielding faster results with limited error rates (< 0.3% for both the elastic matrix C and the compliance matrix S), making it a promising tool for the expedited design of microstructures with tailored properties.

Understanding the large deformation behavior of materials under external forces is crucial for reliable engineering applications. The mechanical properties of materials depend on their underlying microstructures, which change over time during deformation. Experimental observation of these processes is time-consuming and influenced by various conditions. Therefore, we developed MicroProcSim, a physics-based simulation tool to replicate the deformation process of cubic microstructures. MicroProcSim can predict the evolution of texture, represented by the orientation distribution function (ODF), over time under various loads and strain rates. This software package can be run on both Windows and Linux operating systems. Unlike conventional crystal plasticity finite element software, MicroProcSim offers a distinct advantage by rapidly generating deformed textures, as it bypasses incorporating grain morphology. Furthermore, comparisons with existing experimental and computational studies on texture evolution have demonstrated that this software seamlessly replicates real-world material processing conditions through a simple modification of a single input matrix. Editor’s Video Summary: The online version of this article (10.1007/s40192-025-00405-6) contains an Editor's Video Summary, which is available to authorized users.

High-level I/O libraries, such as HDF5 and PnetCDF, are commonly used by large-scale scientific applications to perform I/O tasks in parallel. These I/O libraries store the metadata such as data types and dimensionality along with the raw data in the same files. While these libraries are well-optimized for concurrent access to the raw data, they are designed neither to handle a large number of data objects efficiently nor to create different data objects independently by multiple processes, as they require applications to call data object creation APIs collectively with consistent metadata among all processes. Applications that process data gathered from remote sensors, such as particle collision experiments in high-energy physics, may generate data of different sizes from different sensors and desire to store them as separate data objects. For such applications, the I/O library's requirement on collective data object creation can become very expensive, as the cost of metadata consistency check increases with the metadata volume as well as the number of processes. To address this limitation, using PnetCDF as an experimental platform, we investigate solutions in this paper that abide the netCDF file format, as well as propose a new file header format that enables independent data object creation. The proposed file header consists of two sections, an index table and a list of metadata blocks. The index table contains the reference to the metadata blocks and each block stores metadata of objects that can be created collectively or independently. The new design achieves a scalable performance, cutting data object creation times by up to 582x when running on 4096 MPI processes to create 5,684,800 data objects in parallel. Additionally, the new method reduces the memory footprints, with each process requiring an amount of memory space inversely proportional to the number of processes.

Abstract Background Interstitial lung disease (ILD) affects &gt; 40% of patients with systemic sclerosis (SSc/scleroderma) and is the leading cause of disease-related mortality. Although therapies may slow progression, outcomes remain poor, partly because ILD is often detected after irreversible lung injury has occurred. Although chest computed tomography (CT) is a sensitive tool for ILD detection and is recommended at SSc diagnosis, it is oftentimes not performed and even less often performed serially. We sought to develop tools to predict ILD and mortality in patients with SSc using data routinely available in the electronic health record (EHR) to inform medical decision-making. Methods We analyzed longitudinal EHR data from two SSc cohorts: Northwestern University (1,169 participants; derivation cohort) and Yale University (376 participants; validation cohort). We identified clinical features from existing cohort-linked EHR queries composing a convenience sample of data from participants spanning decades rather than employing a single unified data collection effort. Three ILD experts independently reviewed CT reports and classified each as having or lacking ILD. To explore derivation cohort data structure, patients with &gt; =3 forced vital capacity (FVC) results available were identified and stratified according to prevalent or absent ILD. Using unsupervised trajectory-based clustering exploratory analyses, we determined standardized patterns across groups. ML models were then developed using clinical EHR data as predictor variables and prevalent ILD and all-cause mortality as outcome variables. Model performance was assessed using area under the receiver operating characteristic curve (AUC). Results Seventy-four clinical features with low missingness, including demographic, vital sign, laboratory, and pulmonary function test data, were utilized for analyses. Four robust PFT trajectory clusters were identified that were associated with ILD prevalence and mortality in exploratory analyses. A ML model for ILD detection achieved an AUC of 0.832 and retained performance in the Yale cohort (AUC 0.754). In addition to established predictors such as autoantibodies and pulmonary function, the model identified routine laboratory measurements, including red cell distribution width (RDW), white blood cell count, and serum chloride, as important contributors. One-year mortality prediction achieved AUCs of 0.904 in the North-western cohort and 0.910 in the Yale cohort. Among patients with SSc-ILD, one-year mortality was predicted with AUCs of 0.744 and 0.902 in the Northwestern and Yale cohorts, respectively. Unexpectedly, we found that subtle laboratory abnormalities (such as change in RDW) contributed to predicting mortality. Conclusions Our prediction models comprised of widely available EHR data are useful tools to identify SSc patients at high risk for prevalent ILD and all-cause mortality. Integration of these models into clinical practice could enable scalable risk stratification and inform individualized ILD screening and monitoring strategies for SSc patients.

Recent developments in materials science have made it possible to synthesize millions of individual nanoparticles on a chip. However, many steps in the characterization process still require extensive human input. To address this challenge, we present an automated image processing pipeline that optimizes high-throughput nanoparticle characterization using intelligent image segmentation and coordinate generation. The proposed method can rapidly analyze each image and return optimized acquisition coordinates suitable for multiple analytical STEM techniques, including 4D-STEM, EELS, and EDS. The pipeline employs computer vision and unsupervised learning to remove the image background, segment the particle into areas of interest, and generate acquisition coordinates. This approach eliminates the need for uniform grid sampling, focusing data collection on regions of interest. We validated our approach using a diverse dataset of over 900 high-resolution grayscale nanoparticle images, achieving a 96.0% success rate based on expert-validated criteria. Using established 4D-STEM acquisition times as a baseline, our method demonstrates a 25.0 to 29.1-fold reduction in total processing time. By automating this crucial preprocessing step and optimizing data acquisition, our pipeline significantly accelerates materials characterization workflows while reducing unnecessary data collection.

Abstract Rationale: Interstitial lung disease (ILD) is a common complication of systemic sclerosis (SSc) associated with significant morbidity and mortality. Professional society guidelines vary but some recommend screening all patients with SSc at diagnosis with computed tomography (CT). Early detection of ILD, however, remains challenging, as subtle CT features can be of unclear significance. Radiomics, which involves extracting quantitative features from information-rich medical imaging, can capture subtle textural and structural changes that are not easily observable to radiologists. We hypothesize that by leveraging radiomic features, machine learning models can aid clinicians in early ILD detection and risk stratification in SSc. Methods: We analyzed CT scans performed between 2015-2024 on patients with SSc enrolled in the Northwestern Scleroderma Registry. Radiomic feature extraction yielded 107 first-order features that detailed the lung's texture, shape, and intensity patterns. Principal component analysis (PCA) was utilized to reduce these features to 12 principal components, capturing the majority of variance in the data. Optuna, an optimization library, was employed to build models to detect ILD using radiomic features. These models included XGBoost, random forest, logistic regression, LightGBM, and gradient boosting. Receiver operator characteristic analysis was implemented to assess the accuracy of model predictions using an 64:16:20 train:validation:test split. Large Language Models (LLMs) were used to assist in plot generation with authors reviewing output. Results: 1221 CT scans were available for analysis from 434 patients with SSc (83% female, median age 58yr [IQR: 50, 66]). 808 CTs (66%) had evidence of ILD reported by a thoracic radiologist. PCA plots of distinct patterns of radiomic features from CT scans clustered patients with and without ILD (Figure 1A). Using ML algorithms via the Optuna framework, radiomic features successfully detected ILD in SSc patients. We used the highest validation area under the receiver operating characteristic curve (AUROC) to select the model and apply on an unseen test set and obtained an AUROC of 0.88 (Figure 1B). Conclusion: Distinct radiomic patterns were identified through ML algorithms that detect ILD in SSc patients with good discrimination. Our findings underscore the utility of radiomics in diagnosis in this high-risk population. Future research will integrate clinical data with radiomic features via deep learning models to improve predictive performance, thereby improving the care of patients with systemic sclerosis.

Abstract Background: Ventilator-associated pneumonia (VAP) is one of the deadliest hospital-acquired infections, with a mortality rate ranging from 25-70%. Currently, clinical models to predict VAP development are limited. Development of such a model would potentially allow physicians to intervene earlier with diagnostics and treatment, thereby improving patient outcomes. Methods: We examined VAP episodes from patients enrolled in the SCRIPT study, a cohort study of patients on mechanical ventilation who underwent a bronchoalveolar lavage for suspected pneumonia. A team of five attending physicians reviewed patient charts and adjudicated VAP episodes. We visualized patient-day features using hierarchical clustering with Ward's method. Clinical features such as vital signs, ventilator parameters, laboratory values, and medication data were used to develop several machine learning models trained to identify patients on a day to day basis for high risk of developing VAP within the next 7 days. LLMs were used to help coding, with all output reviewed by the team. We used five fold cross validation. For explainability, we used SHAP plots to examine which clinical features impacted model decision-making. Results: We examined ICU stay data from 688 patients, 268 of whom developed VAP. Median patient age was 62 (IQR 51-71), and 59% were male; 42% died. Our dataset had 1,296 ICU-days occurring within seven days before a VAP episode. For clean model training, we used patient days from patients who were adjudicated not to have pneumonia on enrollment into the study and who did not develop VAP during their stay to label the negative class (646 days). Visualization using hierarchical clustering showed correlation with length of hospitalization and ventilation (Figure 1A). The best-performing models using XGBoost had a mean AUROC of 0.774 with standard deviation of 0.026 (Figure 1B). Important features based on SHAP included PEEP, platelets, and day of hospitalization (Figure 1C). Conclusions: Machine learning models can predict VAP onset within the next 7 days with moderate performance. Future work will focus on revising feature selection and attempting alternative machine learning strategies such as deep learning models.

Abstract Rationale: Interstitial lung disease (ILD) affects 40-75% of patients with systemic sclerosis (SSc) and is the leading cause of death in this population. SSc-ILD is a heterogeneous disease with a variable clinical course. Current available therapies preserve lung function; however, benefits appear to be modest and are counterbalanced by toxicity. While biomarkers have been reported for progressive disease, their utility is limited. We hypothesize that machine learning (ML) could improve mortality prediction in patients with SSc and SSc-ILD by leveraging readily available electronic health record (EHR) data. Methods: We used data from participants with SSc recruited to the Northwestern University Scleroderma Registry from 1996-2024. EHR data—clinical, laboratory, and spirometric—were extracted, and features were selected. ILD diagnosis was assigned by adjudication of chest CT reports. Multiple ML algorithms were tested to build models to predict mortality (or lung transplant) using EHR features in the entire SSc cohort and a subgroup of those with SSc-ILD. A 70:10:20 patient-wise split for training:validation:testing was implemented. Optuna was employed for hyperparameter optimization on the validation set, and the best model was selected. Receiver operating characteristic (ROC) analysis was used to evaluate each model on the held-out test set. Feature importance was assessed through ablation analysis. Results: 1,170 participants with SSc were available for analysis, encompassing 9,191 person-years of observation. 193 (16%) participants died during the observation period. 709 (61%) had CT data available, and 454 (64%) of these had SSc-ILD for subgroup analysis. 109 (24%) participants with SSc-ILD died during the observation period. EHR features predicted mortality in SSc patients within one (AUC=0.91), three (AUC=0.89), and five years (AUC=0.82) (Figure 1A). Ablation analysis identified features highly predictive of one-year mortality in SSc that are routinely assessed but rarely utilized, including blood counts and chemistries (Figure 1B). Similarly, ML algorithms used EHR features to predict mortality in a subgroup of patients with SSc-ILD within one (AUC=0.71), three (AUC=0.73), and five years (AUC=0.80) (Figure 1C). Ablation analysis again identified predictive features for one-year mortality in those with SSc-ILD (Figure 1D). Conclusions: ML analysis of readily available EHR data predicts mortality in those with SSc and SSc-ILD with high sensitivity and specificity. Ablation analyses identified features predictive of one-year mortality that are routinely collected but rarely assessed to ascertain risk. These models could assist in clinical decision-making, particularly regarding treatment. Future research will integrate quantitative imaging features and employ deep learning models to further improve model performance.

Modern data mining methods have seen a widespread and growing application in the field of materials science for regression-based predictive modeling due to their effectiveness in extracting and utilizing the hidden information from the materials datasets. However, due to the costly and time-consuming nature of the methods involved in obtaining the experimental and computational data, the majority of the materials datasets are small in size. Moreover, limited hand-engineered representations available from the raw materials data make it harder to improve the accuracy of predictive models on such small and specialized training datasets. In this paper, we introduce a novel technique that combines transfer learning (TL) and representation learning (RL) using a pre-trained deep neural network to maximize accuracy without additional computational costs on inorganic material properties. The performance of the proposed method is compared against traditional machine learning (ML), and deep neural network models trained from scratch (SC) with elemental fraction (EF) as input, more informative physical attributes (PA) as input (for a stringent comparison), as well as conventional TL and RL techniques using deep neural networks. The results demonstrate that the proposed method can improve the accuracy as compared to SC models and conventional TL and RL techniques.

Polycrystalline materials are crucial in various industries, necessitating a comprehensive understanding of the processing-structure-property-performance (PSPP) relationships. Traditional experimental methods are laborious and slow, while computational approaches predominantly address forward problems, deriving structures and properties from processing conditions. Conversely, inferring processing parameters from desired microstructures and properties remains a crucial yet challenging inverse problem due to the complex and nonlinear mappings involved. In this work, we propose a deep learning-based framework exploring non-sequential and sequential models to address two key inverse problems: predicting processing parameters from microstructures and from properties. Focusing on microstructural texture defined by the orientation distribution function (ODF), we apply our framework to copper, generating a dataset of 31,588 unique processing strain rates (<tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$s$</tex><sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">-1</sup>) in [0, 1] with corresponding ODFs and homogenized properties through simulations. Our inverse prediction results on processing parameters demonstrate high accuracy, with average test RMSEs of 0.0152 from microstructures and 0.0295 from properties. These findings validate the framework's efficacy as a tool for polycrystalline materials process design, enabling the precise determination of processing methods to achieve desired microstructures and properties.

Deep Neural Networks, as a subset of AI, outper-form in understanding complex relationships. The key to this success lies in the network's ability to adapt to problem-specific nuances. During model training, the network dynamically optimizes its weights by updating them during backpropagation while trying to minimize the value of the loss function. Throughout this process, the shaping of model weights is crucially linked to how they were initialized. In this study, we introduce the auxiliary network model, called Sup-Walsh (Support Walsh), which reorganizes weights to enhance class boundaries. We tested our approach on three publicly available datasets using popular classification models. For instance, when using AlexNet [1] on the MNIST dataset [2], integrating Sup-Walsh led to a significant increase in accuracy after first epoch from 14.61% to 78.99%. Similarly, GoogleNet [3] on the FashionMNIST dataset [4] showed a notable 31.61% accuracy difference between configurations without and with Sup-Walsh after first epoch. Across nearly all experiments, our proposed method consistently outperformed existing approaches, demonstrating its potential to improve classification accuracy. Code availability: Code is available at Efficient-Weight-Initializer.

Generative models have been widely used in the field of computer vision due to their ability to produce unseen data points. Its application has proven to be useful in various scientific domains such as materials science for generating new microstructure images that require learning nonlinear and one-to-many property-microstructure relationships. However, existing simulation-based solutions for this application are inefficient and time-consuming. Moreover, nonlinearity from the lower to higher dimensions poses considerable challenges. In this work, we propose a novel Mixture Density Network (MDN) based Quan-tized Autoencoder Network designed to generate microstructure images from only a single data point by establishing one-to-many nonlinear relationships from property to microstructure. Once the autoencoder effectively compresses spatial information into the property domain, we use the combination of produced latent vectors and property values to create a supplementary dataset for MDN. Upon completion of the model training, generative structures are extracted and merged to create a framework that generates images based on target property values (i.e., absorption values in this study). The trained MDN demonstrates proficiency in generating latent vectors within distribution, while the proposed Vector Quantized Variational Autoencoder (VQ-VAE) efficiently maps the embedding table to the latent space, generating images from property values within the range of properties observed during training. We demonstrate that our proposed model consistently outperforms the baselines with respect to generating new microstructure images having target properties and overcoming the above-mentioned challenges.

Recent progress in deep learning has significantly impacted materials science, leading to accelerated material discovery and innovation. ElemNet, a deep neural network model that predicts formation energy from elemental compositions, exemplifies the application of deep learning techniques in this field. However, the "black-box" nature of deep learning models often raises concerns about their interpretability and reliability. In this study, we propose XElemNet to explore the interpretability of ElemNet by applying a series of explainable artificial intelligence (XAI) techniques, focusing on post-hoc analysis and model transparency. The experiments with artificial binary datasets reveal ElemNet's effectiveness in predicting convex hulls of element-pair systems across periodic table groups, indicating its capability to effectively discern elemental interactions in most cases. Additionally, feature importance analysis within ElemNet highlights alignment with chemical properties of elements such as reactivity and electronegativity. XElemNet provides insights into the strengths and limitations of ElemNet and offers a potential pathway for explaining other deep learning models in materials science.

Recent innovations have made it possible to produce millions of distinct nanoparticles on a chip. These vast volumes of data are impossible to analyze manually, necessitating the development of automated tools. In previous work, we created a binary classification machine learning model to select quality nanoparticle images for downstream analysis. In this work, we show that adding a custom image preprocessing step before model training can produce significantly higher-performing models in a fraction of the time and make the model more robust to different image noise levels and microscope acquisition settings. The proposed image processing pipeline effectively cleans raw nanoparticle images, enhances key features, and allows us to use much lower resolution images and simpler neural network model architectures, resulting in higher performance and significant cost savings. Experiments demonstrate superior performance relative to our baseline, including a 15% improvement in recall and more than a 10% increase in accuracy. Given the high cost of downstream analysis, it is critical to minimize false positives in our application, and our best-performing model obtains a precision of 97.3% and weighted F-score of 95.9% on an unseen test set. Additionally, model training time is reduced from 15.5 hours to 32 seconds. We expect that adopting this pipeline for AI-driven automated nanoparticle characterization will offer a considerable speedup in the laboratory, allowing researchers to rapidly and accurately analyze much greater volumes of data and accelerate materials discovery.

Introduction Reconstructing low-level particle tracks in neutrino physics can address some of the most fundamental questions about the universe. However, processing petabytes of raw data using deep learning techniques poses a challenging problem in the field of High Energy Physics (HEP). In the Exa.TrkX Project, an illustrative HEP application, preprocessed simulation data is fed into a state-of-art Graph Neural Network (GNN) model, accelerated by GPUs. However, limited GPU memory often leads to Out-of-Memory (OOM) exceptions during training, due to the large size of models and datasets. This problem is exacerbated when deploying models on High-Performance Computing (HPC) systems designed for large-scale applications. Methods We observe a high workload imbalance issue during GNN model training caused by the irregular sizes of input graph samples in HEP datasets, contributing to OOM exceptions. We aim to scale GNNs on HPC systems, by prioritizing workload balance in graph inputs while maintaining model accuracy. Our paper introduces diverse balancing strategies aimed at decreasing the maximum GPU memory footprint and avoiding the OOM exception, across various datasets. Results Our experiments showcase memory reduction of up to 32.14% compared to the baseline. We also demonstrate the proposed strategies can avoid OOM in application. Additionally, we create a distributed multi-GPU implementation using these samplers to demonstrate the scalability of these techniques on the HEP dataset. Discussion By assessing the performance of these strategies as data loading samplers across multiple datasets, we can gauge their effectiveness in both single-GPU and distributed environments. Our experiments, conducted on datasets of varying sizes and across multiple GPUs, broaden the applicability of our work to various GNN applications that handle input datasets with irregular graph sizes.

Abstract Background Criteria to identify patients who are ready to be liberated from mechanical ventilation are imprecise, often resulting in prolonged mechanical ventilation or reintubation, both of which are associated with adverse outcomes. Daily protocol-driven assessment of the need for mechanical ventilation leads to earlier extubation but requires dedicated personnel. We sought to determine whether machine learning applied to the electronic health record could predict successful extubation. Methods We examined 37 clinical features from patients from a single-center prospective cohort study of patients in our quaternary care medical ICU who required mechanical ventilation and underwent a bronchoalveolar lavage for known or suspected pneumonia. We also tested our models on an external test set from a community hospital ICU in our health care system. We curated electronic health record data aggregated from midnight to 8AM and labeled extubation status. We deployed three data encoding/imputation strategies and built XGBoost, LightGBM, logistic regression, LSTM, and RNN models to predict successful next-day extubation. We evaluated each model’s performance using Area Under the Receiver Operating Characteristic (AUROC), Area Under the Precision Recall Curve (AUPRC), Sensitivity (Recall), Specificity, PPV (Precision), Accuracy, and F1-Score. Results Our internal cohort included 696 patients and 9,828 ICU days, and our external cohort had 333 patients and 2,835 ICU days. The best model (LSTM) predicted successful extubation on a given ICU day with an AUROC 0.87 (95% CI 0.834-0.902) and the internal test set and 0.87 (95% CI 0.848-0.885) on the external test set. A Logistic Regression model performed similarly (AUROC 0.86 internal test, 0.83 external test). Across multiple model types, measures previously demonstrated to be important in determining readiness for extubation were found to be most informative, including plateau pressure and Richmond Agitation Sedation Scale (RASS) score. Our model often predicted patients to be stable for extubation in the days preceding their actual extubation, with 63.8% of predicted extubations occurring within three days of true extubation. We also tested the best model on cases of failed extubations (requiring reintubation within two days) not seen by the model during training. Our best model would have identified 35.4% (17/48) of these cases in the internal test set and 48.1% (13/27) cases in the external test set as unlikely to be successfully extubated. Conclusions Machine learning models can accurately predict the likelihood of extubation on a given ICU day from data available in the electronic health record. Predictions from these models are driven by clinical features that have been associated with successful extubation in clinical trials.

Traditionally, materials discovery has been driven more by evidence and intuition than by systematic design. However, the advent of "big data" and an exponential increase in computational power have reshaped the landscape. Today, we use simulations, artificial intelligence (AI), and machine learning (ML) to predict materials characteristics, which dramatically accelerates the discovery of novel materials. For instance, combinatorial megalibraries, where millions of distinct nanoparticles are created on a single chip, have spurred the need for automated characterization tools. This paper presents an ML model specifically developed to perform real-time binary classification of grayscale high-angle annular dark-field images of nanoparticles sourced from these megalibraries. Given the high costs associated with downstream processing errors, a primary requirement for our model was to minimize false positives while maintaining efficacy on unseen images. We elaborate on the computational challenges and our solutions, including managing memory constraints, optimizing training time, and utilizing Neural Architecture Search tools. The final model outperformed our expectations, achieving over 95% precision and a weighted F-score of more than 90% on our test data set. This paper discusses the development, challenges, and successful outcomes of this significant advancement in the application of AI and ML to materials discovery.

This study addresses the pressing issue of air pollution in four maj or Indian cities with a specific focus on PM2.5 and other pollutants. Considering the fact that the Air Quality Index(AQI) is an indicator of air pollution, we apply an efficient model of Machine Learning for the prediction of AQI. Our model employs the Synthetic Minority Oversampling Technique (SMOTE) in collaboration with different regression techniques. We employ four well-known techniques such Support Vector Machine, Catboost, Random Forest Regression, and XGBoost. A model with the greatest precision will be implemented for air quality prediction, providing valuable insights to environmentalists and governing bodies. The predictions have been documented in graphical formats for a better understanding of the steps to be taken for the improvement of accuracy. By acting on these predictions, proactive measures can be taken for the mitigation of air pollution, safeguarding public health, and reducing the adverse impact of pollutants on the urban population.

Modern data mining techniques using machine learning (ML) and deep learning (DL) algorithms have been shown to excel in the regression-based task of materials property prediction using various materials representations. In an attempt to improve the predictive performance of the deep neural network model, researchers have tried to add more layers as well as develop new architectural components to create sophisticated and deep neural network models that can aid in the training process and improve the predictive ability of the final model. However, usually, these modifications require a lot of computational resources, thereby further increasing the already large model training time, which is often not feasible, thereby limiting usage for most researchers. In this paper, we study and propose a deep neural network framework for regression-based problems comprising of fully connected layers that can work with any numerical vector-based materials representations as model input. We present a novel deep regression neural network, iBRNet, with branched skip connections and multiple schedulers, which can reduce the number of parameters used to construct the model, improve the accuracy, and decrease the training time of the predictive model. We perform the model training using composition-based numerical vectors representing the elemental fractions of the respective materials and compare their performance against other traditional ML and several known DL architectures. Using multiple datasets with varying data sizes for training and testing, We show that the proposed iBRNet models outperform the state-of-the-art ML and DL models for all data sizes. We also show that the branched structure and usage of multiple schedulers lead to fewer parameters and faster model training time with better convergence than other neural networks. Scientific contribution: The combination of multiple callback functions in deep neural networks minimizes training time and maximizes accuracy in a controlled computational environment with parametric constraints for the task of materials property prediction.

Abstract Modern data mining methods have demonstrated effectiveness in comprehending and predicting materials properties. An essential component in the process of materials discovery is to know which material(s) will possess desirable properties. For many materials properties, performing experiments and density functional theory computations are costly and time-consuming. Hence, it is challenging to build accurate predictive models for such properties using conventional data mining methods due to the small amount of available data. Here we present a framework for materials property prediction tasks using structure information that leverages graph neural network-based architecture along with deep-transfer-learning techniques to drastically improve the model’s predictive ability on diverse materials (3D/2D, inorganic/organic, computational/experimental) data. We evaluated the proposed framework in cross-property and cross-materials class scenarios using 115 datasets to find that transfer learning models outperform the models trained from scratch in 104 cases, i.e., ≈90%, with additional benefits in performance for extrapolation problems. We believe the proposed framework can be widely useful in accelerating materials discovery in materials science.

A process simulator provides valuable insights into the evolution of microstructures under various elementary processes, employing the Orientation Distribution Function (ODF) as a representation of the microstructure's texture. However, such simulations often involve complex physical computations, making them time-consuming. To address this, our study introduces an artificial intelligence (AI)-based framework to predict the microstructural texture of polycrystalline materials using a specified deformation process. As a case study, we apply our framework to copper. The dataset includes 3,125 unique processing parameter combinations and their corresponding ODF vectors generated using a process simulator. The resulting predictions enable the calculation of homogenized properties. As opposed to traditional material processing simulations, our AI-driven framework offers faster results with minimal error rates (less than 0.5%). This indicates that our approach is a promising tool for rapidly predicting processing-specific microstructures and properties, thereby offering significant improvements over conventional simulation techniques.

Large-scale parallel applications can face significant I/O performance bottlenecks, making efficient I/O crucial. This work presents a comparative study of several parallel I/O implementations in the Weather Research and Forecasting model, including PnetCDF blocking and non-blocking I/O options, netCDF4, HDF5 Log VOL, and ADIOS. For I/O methods creating files in a canonical data layout, PnetCDF's non-blocking option offers up to 2x improvement over its blocking option and up to 4.5x over HDF5 via netCDF4, demonstrating the effectiveness of the write request aggregation technique. The HDF5 Log VOL outperforms ADIOS with a 4x improvement in write performance when creating files in the log layout, although both require non-negligible time to convert the file back to canonical order for post-run analysis. From these results we extract some observations that can guide I/O strategies for modern parallel codes.

Abstract Contemporary materials science has seen an increasing application of various artificial intelligence techniques in an attempt to accelerate the materials discovery process using forward modeling for predictive analysis and inverse modeling for optimization and design. Over the last decade or so, the increasing availability of computational power and large materials datasets has led to a continuous evolution in the complexity of the techniques used to advance the frontier. In this Review, we provide a high-level overview of the evolution of artificial intelligence in contemporary materials science for the task of materials property prediction in forward modeling. Each stage of evolution is accompanied by an outline of some of the commonly used methodologies and applications. We conclude the work by providing potential future ideas for further development of artificial intelligence in materials science to facilitate the discovery, design, and deployment workflow. Graphical abstract

Prediction of the autogenous shrinkage referred to as the reduction of apparent volume of concrete under seal and isothermal conditions is of great significance in the service life analysis and design of durable concrete structures, especially with the increasing use of concrete with low water-to-cement ratios. However, due to the highly complex mechanism of autogenous shrinkage, it is hard to design accurate mechanistic models for it. Existing state-of-the-art models for autogenous shrinkage do not perform well for several reasons such as not being able to capture faster shrinkage change at early ages (swelling), coefficients used are derived using statistical optimization methods to fit certain databases only, and mechanism to identify the most influencing factors on autogenous shrinkage is not present. Moreover, it is also challenging to deploy a machine learning framework directly to perform predictive analysis due to the sparse and noisy nature of the available experimental dataset. In this paper, we study and propose a method to combine the physics-based knowledge and the predictive ability of deep regression neural networks to mitigate the shortcomings of the existing models. We introduce a novel data augmentation technique that utilizes physics based knowledge to improve the accuracy while maintaining the characteristics of autogenous shrinkage in its predictions simultaneously. Using state-of-the-art B4 model, a genetic algorithm, and a deep neural network trained using raw data for comparison, we show that the proposed methods help improve the accuracy of the model as compared to other methods. We also observe that the proposed method is able to successfully learn and predict the swelling component of the shrinkage strain curve as well, which cannot be predicted using the existing state-of-the-art models.

The development of high-speed detectors and associated data acquisition workflows in electron microscopes has enabled data generation at an unprecedented rate. It is not uncommon to generate terabytes of data per hour which can easily overwhelm computing infrastructure and downstream processing, thereby limiting the full utilization of the microscope hardware [1]. Implementing a selective approach to imaging to only acquire high-fidelity data from areas of interest is common in manual instrument operation, where bright- or dark-field STEM images are acquired first to identify regions of interest for collecting higher-dimensional spectroscopy or diffraction data. In the context of automated acquisitions workflows, this procedure becomes significantly more challenging, as it becomes necessary to quickly make decisions about regions of interest in the absence of a human operator. To that end, we have developed machine learning models working with low-fidelity dark-field STEM images of nanostructure arrays to perform a binary quality assessment to determine the highest priority areas to acquire high-fidelity data. Our models will be deployed in an automated electron microscopy system for the high-throughput analysis of nanomaterial megalibraries. Megalibraries contain arrays of 108 nanoparticles with spatially encoded size and composition gradients on a single chip, these libraries are uniquely suited for the discovery of new materials at high throughput [2]. Given the volume of materials in a megalibrary, we have designed our models to be highly effective at binary classification on unseen images while minimizing the single-inference times and the number of false positive results which would result in long latencies and high downstream processing cost. In this presentation, we will describe the computational challenges and solutions implemented in this design (e.g., memory constraints, training time, Neural Architecture Search (NAS) tools). We present the standard neural network evaluation metrics, training time, and single-inference time for the most accurate model; our best-performing model achieves a precision of >95%. We further report a weighted F-score of >90% on our test data set as a balancing metric of precision and recall for a given application. Given that false positives would incur a high downstream cost in the analysis pipeline, we chose to prioritize precision over recall by a factor of 9-to-1. This binary classification of low-fidelity data represents an important step towards fully automated electron microscopy workflows, as it introduces a methodology for autonomous decision-making in situ. The acceleration resulting from this automation effectively increases the experimental throughput, enabling the analysis of materials at an unprecedented rate [3]. Automated quality assessment on a nanoparticle megalibrary. (A) Schematic illustration of the screening process, acquiring images at nanoparticle locations. (B) Acquired high-angle annular dark-field (HAADF) images as seen by the model. Scale bars: 200 nm. (C) Illustration of the quality assessment pipeline, where each raw image is fed into the model, returning a binary classifier. If the image passes the test, the microscope can magnify and focus on that region to acquire high-fidelity datasets. Scale bars: 20 nm.

Abstract Materials design aims to identify the material features that provide optimal properties for various engineering applications, such as aerospace, automotive, and naval. One of the important but challenging problems for materials design is to discover multiple polycrystalline microstructures with optimal properties. This paper proposes an end-to-end artificial intelligence (AI)-driven microstructure optimization framework for elastic properties of materials. In this work, the microstructure is represented by the Orientation Distribution Function (ODF) that determines the volume densities of crystallographic orientations. The framework was evaluated on two crystal systems, cubic and hexagonal, for Titanium (Ti) in Joint Automated Repository for Various Integrated Simulations (JARVIS) database and is expected to be widely applicable for materials with multiple crystal systems. The proposed framework can discover multiple polycrystalline microstructures without compromising the optimal property values and saving significant computational time.

Artificial intelligence based predictive modeling has become increasingly sought-after in the field of materials science for training property prediction models due to their promising ability to extract and utilize data-driven information from materials data. However, current methods typically use limited hand-engineered fixed-length representations obtained from available composition-based information only, making model inputs a stumbling block when handling small and specialized training datasets. In this paper, we study and propose a method to perform representation learning (RL) that is both applicable and adaptive for generalized use across various domains. We introduce a RL technique that utilizes pre-activation based representations extracted from a model pre-trained using a deep neural network to maximize the accuracy. We perform model training for inorganic material properties using composition-based numerical vectors representing the elemental fractions (EF) of the materials by leveraging source models trained on large datasets to build target models on small datasets and then compare its performance against traditional machine learning (ML), deep neural network and RL-based graph neural network (GNN) models trained from scratch (SC) with EF as input, more informative physical attributes (PA) as input, as well as conventional TL/RL techniques. Using large <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$(\sim 345K)$</tex> datasets for source model training and small computational <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$(\sim 28K)$</tex> and experimental <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$(\sim 2K)$</tex> datasets for target model training and testing, we show that the proposed RL methods help significantly improve the accuracy of the model as compared to the SC models and conventional TL/RL techniques for all data sizes and properties by using only EF as input. We also perform a statistical significance analysis by calculating the p-value to find that the observed improvement in the accuracy of proposed RL model over SC, RL-based GNN, and conventional TL/RL models is indeed significant.

Stress-strain curves are important representations of a given material's mechanical properties, which depend primarily on the orientation of the individual crystals in the microstructure. Generating stress-strain curves from numerical methods such as the crystal plasticity finite element (CPFE) simulations is computationally intensive. As a result, it is difficult to generate complete stress-strain curves for all possible orientations of a material. In this work, we propose a bilinear stress-strain curve prediction framework for metallic alloys by integrating supervised and unsupervised deep learning methods via transfer learning principles. As a specific case-study, we focus on predicting stress-strain curves of Nickel (Ni)-based superalloys that have important applications in aerospace industry. Using a small training set of just 100 complete stress-strain curves (4,000 strain steps each) of different orientations generated by CPFE simulation code, we were able to build a model that could accurately predict stress-strain curves (<2 % error) using simple features that could be obtained by running the CPFE simulation for just a single strain step. The proposed model can thus predict the complete stress-strain curve for a given orientation of Ni-based superalloys in a fraction of a second, which amounts to a speedup of over 4000x as compared to the simulation.

Modern machine learning (ML) and deep learning (DL) techniques using high-dimensional data representations have helped accelerate the materials discovery process by efficiently detecting hidden patterns in existing datasets and linking input representations to output properties for a better understanding of the scientific phenomenon. While a deep neural network comprised of fully connected layers has been widely used for materials property prediction, simply creating a deeper model with a large number of layers often faces with vanishing gradient problem, causing a degradation in the performance, thereby limiting usage. In this paper, we study and propose architectural principles to address the question of improving the performance of model training and inference under fixed parametric constraints. Here, we present a general deep-learning framework based on branched residual learning (BRNet) with fully connected layers that can work with any numerical vector-based representation as input to build accurate models to predict materials properties. We perform model training for materials properties using numerical vectors representing different composition-based attributes of the respective materials and compare the performance of the proposed models against traditional ML and existing DL architectures. We find that the proposed models are significantly more accurate than the ML/DL models for all data sizes by using different composition-based attributes as input. Further, branched learning requires fewer parameters and results in faster model training due to better convergence during the training phase than existing neural networks, thereby efficiently building accurate models for predicting materials properties.

The objective of this project is to design, develop, and evaluate scalable software to enhance resilience, data checkpointing, program restart, and analysis. The proposed tasks are to 1) develop scalable machine learning techniques to learn temporal change patterns in a scalable and in-situ manner, and to minimize data movement and maximize learning locally closest to data; 2) design a concise data representation and indexing mechanism to capture the distribution of changes in data that can guarantee point-wise user-defined tolerable errors while reducing the data storage requirements by an order of magnitude or more; 3) develop data reduction techniques as library modules; 4) exploit local SSD for minimizing data movement in storage hierarchy; 5) develop anomaly detection algorithms that can predict corruptions based on learning of emerging patterns; 6) develop software libraries to be incorporated within widely used data formats and APIs; and 7) evaluate the proposed software using DOE scientific applications. The outcomes of the proposed work are to satisfy many synergistic data reduction and resilience requirements for large-scale data intensive applications executed on extreme-scale computing systems. The developed mechanism for error-bound data approximation is directly applicable to existing scientific applications. Through machine learning from historical events and change distribution, this work will enable anomaly detection for DOE computer facility.

Running scientific workflow applications on high-performance computing systems provides promising results in terms of accuracy and scalability. An example is the particle track reconstruction research in high-energy physics that consists of multiple machine-learning tasks. However, as the modern HPC system scales up, researchers spend more effort on coordinating the individual workflow tasks due to their increasing demands on computational power, large memory footprint, and data movement among various storage devices. These issues are further exacerbated when intermediate result data must be shared among different tasks and each is optimized to fulfill its own design goals, such as the shortest time or minimal memory footprint. In this paper, we investigate the data management challenges presented in scientific workflows. We observe that individual tasks, such as data generation, data curation, model training, and inference, often use data layouts only best for one's I/O performance but orthogonal to its successive tasks. We propose various solutions by employing alternative data structures and layouts in consideration of two tasks running consecutively in the workflow. Our experimental results show up to a 16.46x and 3.42x speedup for initialization time and I/O time respectively, compared to previous approaches.