Physics-Informed Machine Learning for Anomaly Detection in Subsurface Sensor Data and Automated Reporting

ObjectivesTo develop and identify machine learning (ML) models using pretreatment 2-deoxy-2-[18F]fluoro-D-glucose ([18F]-FDG)-positron emission tomography (PET)-based radiomic features to differentiate benign from malignant parotid gland diseases (PGDs).Materials and methodsThis retrospective study included 62 patients with 63 PGDs who underwent pretreatment [18F]-FDG-PET/computed tomography (CT). The lesions were assigned to the training (n = 44) and testing (n = 19) cohorts. In total, 49 [18F]-FDG-PET-based radiomic features were utilized to differentiate benign from malignant PGDs using five different conventional ML algorithmic models (random forest, neural network, k-nearest neighbors, logistic regression, and support vector machine) and the deep learning (DL)-based ensemble ML model. In the training cohort, each conventional ML model was constructed using the five most important features selected by the recursive feature elimination method with the tenfold cross-validation and synthetic minority oversampling technique. The DL-based ensemble ML model was constructed using the five most important features of the bagging and multilayer stacking methods. The area under the receiver operating characteristic curves (AUCs) and accuracies were used to compare predictive performances.ResultsIn total, 24 benign and 39 malignant PGDs were identified. Metabolic tumor volume and four GLSZM features (GLSZM_ZSE, GLSZM_SZE, GLSZM_GLNU, and GLSZM_ZSNU) were the five most important radiomic features. All five features except GLSZM_SZE were significantly higher in malignant PGDs than in benign ones (each p < 0.05). The DL-based ensemble ML model had the best performing classifier in the training and testing cohorts (AUC = 1.000, accuracy = 1.000 vs AUC = 0.976, accuracy = 0.947).ConclusionsThe DL-based ensemble ML model using [18F]-FDG-PET-based radiomic features can be useful for differentiating benign from malignant PGDs.Second abstractThe DL-based ensemble ML model using [18F]-FDG-PET-based radiomic features can overcome the previously reported limitation of [18F]-FDG-PET/CT scan for differentiating benign from malignant PGDs. The DL-based ensemble ML approach using [18F]-FDG-PET-based radiomic features can provide useful information for managing PGD.

Batteries, recognized as effective energy storage solutions, are considered the main facilitators of the world-wide transition towards clean and renewable energy sources. Among different types of batteries, lithium-ion (Li-ion) variants offer higher energy densities and relatively longer life spans when compared to other types. Nonetheless, a primary concern with these batteries is their lifetime. Batteries undergo various degradation mechanisms under storage and use, significantly impacting their lifespan. To this end, it is crucial to predict the degradation and lifetime of Li-ion batteries under given conditions.Researchers use three main methodologies to perform battery health diagnostics and to predict the lifetime of batteries. One approach revolves around using mechanistic, first-principle electrochemical models, also known as physics-based models. If equipped with proper thermodynamic theories, such models can show promising capabilities; however, holistic degradation prediction with these models is still challenging due to the computational complexities and the multitude of parameters that need to be fine-tuned in this approach. The other common strategy is to use empirical models to predict battery degradation. These models generally entail fewer parameters to be identified and are computationally less intensive to solve. Nonetheless, empirical models can suffer from the accuracy point-of-view as they are constrained to predict degradation trends introduced by certain degradation modes. Another common technique in battery life prediction is to utilize purely data-driven methods, such as machine learning (ML) algorithms, which also have shown promising results in the literature on rapid health predictions. However, these methods require large volumes of experimental data for training and testing ML models to ensure accuracy. In addition, data-driven methods are likely to extrapolate poorly to conditions beyond their training data and are indifferent towards the underlying degradation mechanisms. Recently, physics-informed machine learning (PI-ML) methods have garnered significant attention. They integrate physics-based or empirical models (developed based on physics) with a data-driven approach and allow one to train ML models on a smaller set of experimental data.To the best of the authors’ knowledge, the performance comparison between first-principle and empirical models when integrated within PI-ML remains unclear. Therefore, in this work, we aim to compare these two models when applied to prognostics (capacity forecasting and remaining useful life prediction) of a set of Li-ion batteries. To perform this study, we generate aging data for 40 Li-ion coin cells cycled under randomized conditions. Each cell undergoes a three-step charging stage followed by a two-step discharge stage. After obtaining the aging data, we will develop two PI-ML models, one equipped with a physics-based model and another with a set of empirical models. Both PI-ML models in this work will follow the sequential integration approach, where the training data for the final PI-ML model come from both experimental and computational data, the latter of which are obtained from the physics-based or empirical models. The parameters for the physics-based and empirical models are identified from another set of experimental data. Finally, the PI-ML models will be tested with experimental data obtained at different cycling conditions. The data flow for the sequential architecture of PI-ML is shown in the attached figure. This comparative study will help identify the performance of physics-based and empirical models when integrated into PI-ML. The main performance metric considered in this work is each model’s ability to extrapolate beyond the experimental training data set, hence aiding the final PI-ML model in generalizing to conditions not covered by its experimental training data set. Figure 1

Understanding the spatial distribution of soil organic carbon (SOC) content over different climatic regions will enhance our knowledge of carbon gains and losses due to climatic change. However, little is known about the SOC content in the contrasting arid and sub-humid regions of Iran, whose complex SOC–landscape relationships pose a challenge to spatial analysis. Machine learning (ML) models with a digital soil mapping framework can solve such complex relationships. Current research focusses on ensemble ML models to increase the accuracy of prediction. The usual ensemble method is boosting or weighted averaging. This study proposes a novel ensemble technique: the stacking of multiple ML models through a meta-learning model. In addition, we tested the ensemble through rescanning the covariate space to maximize the prediction accuracy. We first applied six state-of-the-art ML models (i.e., Cubist, random forests (RF), extreme gradient boosting (XGBoost), classical artificial neural network models (ANN), neural network ensemble based on model averaging (AvNNet), and deep learning neural networks (DNN)) to predict and map the spatial distribution of SOC content at six soil depth intervals for both regions. In addition, the stacking of multiple ML models through a meta-learning model with/without rescanning the covariate space were tested and applied to maximize the prediction accuracy. Out of six ML models, the DNN resulted in the best modeling accuracies, followed by RF, XGBoost, AvNNet, ANN, and Cubist. Importantly, the stacking of models indicated a significant improvement in the prediction of SOC content, especially when combined with rescanning the covariate space. For instance, the RMSE values for SOC content prediction of the upper 0–5 cm of the soil profiles of the arid site and the sub-humid site by the proposed stacking approaches were 17% and 9% respectively, less than that obtained by the DNN models—the best individual model. This indicates that rescanning the original covariate space by a meta-learning model can extract more information and improve the SOC content prediction accuracy. Overall, our results suggest that the stacking of diverse sets of models could be used to more accurately estimate the spatial distribution of SOC content in different climatic regions.

P125. Development of a novel ensemble machine learning algorithm for prediction of complications and readmission after anterior cervical spinal fusion

Harmful Algal Blooms (HABs), driven by environmental pollution, pose significant threats to water quality, public health, and aquatic ecosystems. This study aims to enhance the prediction of HABs in Lake Erie, part of the Great Lakes system, by utilizing ensemble machine learning (ML) models coupled with explainable artificial intelligence (XAI) for interpretability. Using water quality data from 2013 to 2020, various physical, chemical, and biological parameters were analyzed to predict chlorophyll-a (Chl-a) concentrations, a proxy for algal blooms. The study employed multiple ensemble ML models, including Random Forest (RF), Deep Forest (DF), Gradient Boosting (GB), and XGBoost, and compared their performance against individual models such as Support Vector Machine (SVM), Decision Tree (DT), and Multi-Layer Perceptron (MLP). The findings reveal that ensemble models, particularly XGBoost and Deep Forest (DF), achieve superior predictive accuracy with R² values of 0.8517 and 0.8544, respectively. The application of SHapley Additive exPlanations (SHAP) provided insights into the relative importance of input features, identifying Particulate Organic Nitrogen (PON), Particulate Organic Carbon (POC), and Total Phosphorus (TP) as critical factors influencing Chl-a concentrations. This research demonstrates the effectiveness of integrating ensemble ML models with XAI to improve HAB prediction accuracy and interpretability. The results support the development of proactive water quality management strategies and highlight the potential of advanced ML techniques in environmental monitoring.

A study on road accident prediction and contributing factors using explainable machine learning models: analysis and performance

Geomechanical analysis is fundamental to well planning and field development, ensuring operational safety and efficiency in the entire life cycle of the well. Traditional methods for constructing one-dimensional mechanical earth models (1D MEM) are time-intensive, requiring weeks of manual data handling and expert interpretation, with accuracy heavily dependent on complete and high-quality datasets. This study presents an integrated, machine learning (ML)-driven approach that automates the entire geomechanical workflow—from data import, quality control to generation of 1D MEM properties and wellbore stability analysis, reducing analysis time by over 90% and improving model accuracy through intelligent ML algorithms, ultimately enabling cleaner, safer, and more profitable drilling operations. The process starts with quality control and the detection of outliers via interquartile range (IQR) and isolation forest (IF) algorithms on multiple wells. The ML model fills in missing log segments and predicts any missing logs in the key wells employing the random forest regression algorithm based on training from the available wells. Rock mechanical properties are calculated by applying lithology-based industry-used formulations, and lithology is predicted with prediction errors of less than 10% using both supervised and unsupervised ML techniques. Automated normal compaction trend (NCT) generation based on shale formation is used for precise pore pressure prediction for target wells, calibrated against modular formation dynamics tester (MDT) / repeat formation tester (RFT) / drill stem test (DST) data. The subsequent 1D MEM properties are calculated using industry-standard equations that offer mud window planning and wellbore stability analysis. This ML-based solution is a paradigm shift in geomechanical analysis, cutting weeks of traditional workflows down to hours while preserving high accuracy through systematic calibration against field and core data, ultimately optimizing drilling operations and reducing non-productive time (NPT) in a range of geological settings.

While the rapid development of vaccines during the COVID-19 pandemic helped save billions of lives, a significant percentage of the population reported adverse reactions after vaccination. Post-vaccination surveys were conducted to understand the possible side effects. Analyzing and understanding the side effects enables the relevant stakeholders to gain more understanding of the vaccine and allows the individual to make informed decisions about whether to receive the vaccine. This work aims to identify a robust approach that can be used to predict the possibility of potential adverse symptoms. A dataset comprising 840 participants with 15 Post-Vaccination Symptoms was considered for the study. Synthetic Minority Oversampling TEchnique (SMOTE) was used to handle the class imbalance of the dataset. A combination of SMOTE and ensemble machine learning models was used to predict the adverse reactions to COVID-19 vaccines. The ensemble Machine Learning (ML) models that are considered for this study are Random Forest, Extreme Gradient Boosting Machine (XGBoost), Light Gradient Boosting Machine, and AdaBoost. The metrics accuracy, precision, recall and Receiver Operating Characteristic-Area Under the Curve (ROC-AUC) were used to measure the performance of the models. The dataset was pre-processed to handle missing values and one-hot encoding was applied to convert categorical variables into the numerical format. Insights into the data distribution and relationships between variables were gained through exploratory data and correlation analysis, respectively. Class imbalance in the target variables was addressed using SMOTE, resulting in a significantly improved F1-score and ROC-AUC score. Among the ensemble ML models, XGBoost delivered the best performance metrics. A combined performance score was calculated by averaging the F1-score and accuracy to identify the best model. XGBoost obtained the highest performance score among the ensemble ML models, and its performance is further enhanced by performing the threshold adjustment using the maximum F1- score strategy. The findings suggest that the combination of SMOTE and ensemble learning models with threshold adjustment provides a more efficient prediction of adverse effects after COVID-19 vaccination, aiding in healthcare decision-making.

The Message Queuing Telemetry Transport (MQTT) protocol is widely adopted in IoT networks due to its lightweight and scalable design, making it ideal for resource-constrained devices. However, its minimal architecture lacks built-in encryption and robust identity authentication, leaving it vulnerable to a range of security threats. To address these vulnerabilities, this work proposes a hybrid framework that integrates machine learning (ML) and deep learning (DL) models to enhance intrusion and anomaly detection in MQTT based IoT networks. The framework leverages real world IoT traffic data from the MQTTEEB-D dataset with diverse preprocessing techniques to train the model. The framework is implemented and evaluated through a multi-metric approach, where each metric assesses a distinct aspect of the framework to identify lightweight processing models for resource-constrained environments. Results consistently showed that ML models outperformed their DL counterparts in terms of detection reliability, classification balance, and error minimization. While DL models demonstrated moderate effectiveness in capturing temporal patterns, they exhibited higher misclassification rates and reduced calibration. The findings underscore the effectiveness of lightweight ML models for scalable and dependable intrusion detection in MQTT based IoT networks.

Landslide disaster risk reduction necessitates the investigation of different geotechnical causal factors for slope failures. Machine learning (ML) techniques have been proposed to study causal factors across many application areas. However, the development of ensemble ML techniques for identifying the geotechnical causal factors for slope failures and their subsequent prediction has lacked in literature. The primary goal of this research is to develop and evaluate novel feature selection methods for identifying causal factors for slope failures and assess the potential of ensemble and individual ML techniques for slope failure prediction. Twenty-one geotechnical causal factors were obtained from 60 sites (both landslide and non-landslide) spread across a landslide-prone area in Mandi, India. Relevant causal factors were evaluated by developing a novel ensemble feature selection method that involved an average of different individual feature selection methods like correlation, information-gain, gain-ratio, OneR, and F-ratio. Furthermore, different ensemble ML techniques (Random Forest (RF), AdaBoost (AB), Bagging, Stacking, and Voting) and individual ML techniques (Bayesian network (BN), decision tree (DT), multilayer perceptron (MLP), and support vector machine (SVM)) were calibrated to 70% of the locations and tested on 30% of the sites. The ensemble feature selection method yielded six major contributing parameters to slope failures: relative compaction, porosity, saturated permeability, slope angle, angle of the internal friction, and in-situ moisture content. Furthermore, the ensemble RF and AB techniques performed the best compared to other ensemble and individual ML techniques on test data. The present study discusses the implications of different causal factors for slope failure prediction.

Performance investigation of osmotically assisted reverse osmosis using explainable machine learning models: A comparative study

The proliferation of Internet of Things (IoT) devices in personal and household environments has led to a significant increase in security vulnerabilities. These devices, due to their limited computational resources, often struggle to support conventional security solutions, making them prime targets for cyberattacks. This paper explores the potential of lightweight machine learning (ML) models to enhance the security of personal IoT devices. By leveraging the power of AI, lightweight models can offer real-time threat detection and anomaly identification without compromising the device's performance or requiring extensive computational resources. The paper investigates various ML techniques that are well-suited for IoT environments, such as decision trees, k-nearest neighbours (KNN), and support vector machines (SVM), focusing on their ability to detect intrusions, unauthorized access, and other malicious activities while maintaining efficiency. Additionally, the study highlights the trade-offs between model complexity, accuracy, and resource consumption, offering practical insights for deploying ML solutions in resource-constrained IoT systems. Key challenges, including data privacy, model generalization, and the adaptability of models to diverse IoT ecosystems, are addressed. Finally, the paper discusses future directions for the integration of more advanced lightweight models, such as federated learning and edge computing, which could further enhance security capabilities while ensuring minimal impact on IoT device performance. Through this review, the paper advocates for the adoption of lightweight ML models as a feasible and scalable solution to securing personal IoT devices in an increasingly connected world.

Significance of activation functions in developing an online classifier for semiconductor defect detection

The prevalence of streaming data across various sectors poses significant challenges for real-time anomaly detection due to its volume, velocity, and variability. Traditional data processing methods often need to be improved for such dynamic environments, necessitating robust, scalable, and efficient real-time analysis systems. This study compares two advanced machine learning approaches—LSTM autoencoders and Matrix Profile algorithms—to identify the most effective method for anomaly detection in streaming environments using the NYC taxi dataset. Existing literature on anomaly detection in streaming data highlights various methodologies, including statistical tests, window-based techniques, and machine learning models. Traditional methods like the Generalized ESD test have been adapted for streaming data but often require a full historical dataset to function effectively. In contrast, machine learning approaches, particularly those using LSTM networks, are noted for their ability to learn complex patterns and dependencies, offering promising results in real-time applications. In a comparative analysis, LSTM autoencoders significantly outperformed other methods, achieving an F1-score of 0.22 for anomaly detection, notably higher than other techniques. This model demonstrated superior capability in capturing temporal dependencies and complex data patterns, making it highly effective for the dynamic and varied data in the NYC taxi dataset. The LSTM autoencoder's advanced pattern recognition and anomaly detection capabilities confirm its suitability for complex, high-velocity streaming data environments. Future research should explore the integration of LSTM autoencoders with other machine-learning techniques to enhance further the accuracy, scalability, and efficiency of anomaly detection systems. This study advances our understanding of scalable machine-learning approaches and underscores the critical importance of selecting appropriate models based on the specific characteristics and challenges of the data involved.

Background A significant number of tongue squamous cell carcinoma (TSCC) patients are diagnosed at late stage. Objectives We primarily aimed to develop a machine learning (ML) model based on ensemble ML paradigm to stratify advanced-stage TSCC patients into the likelihood of overall survival (OS) for evidence-based treatment. We compared the survival outcome of patients who received either surgical treatment only (Sx) or surgery combined with postoperative radiotherapy (Sx + RT) or postoperative chemoradiotherapy (Sx + CRT). Material and Methods A total of 428 patients from Surveillance, Epidemiology, and End Results (SEER) database were reviewed. Kaplan-Meier and Cox proportional hazards models examine OS. In addition, a ML model was developed for OS likelihood stratification. Results Age, marital status, N stage, Sx, and Sx + CRT were considered significant. Patients with Sx + RT showed better OS than Sx + CRT or Sx alone. A similar result was obtained for T3N0 subgroup. For T3N1 subgroup, Sx + CRT appeared more favorable for 5-year OS. In T3N2 and T3N3 subgroups, the numbers of patients were small to make insightful conclusions. The OS predictive ML model showed an accuracy of 86.3% for OS likelihood prediction. Conclusions and Significance Patients stratified as having high likelihood of OS may be managed with Sx + RT. Further external validation studies are needed to confirm these results.