Sparse Datasets Research Articles

Full-wavefield regularization to enhance signal-to-noise ratio in sparse low-fold land data for better reservoir attribute extraction

Sparse land seismic data, when acquired in areas with sand and detrital materials overlying faster velocity strata, are often marred by intense near-surface noise moving at slow speeds. This noise persists, even with the fine source and receiver spacing of high-channel-count 3D surveys, leading to aliasing issues. Traditional velocity-based filtering, whether in the frequency-wavenumber (f-k) or radon domains, is ineffective at removing this noise during data processing. Addressing the aliasing of slow near-surface noise through proper regularization before denoising can significantly enhance data quality. We introduce a novel approach called full-wavefield regularization and present its application for the first time on a sparse 3D low-fold offshore seismic data set. This technique aims to regularize both the seismic signals and coherent noise wave trains to a spacing where aliasing is not an issue. Consequently, the reflection and surface-wave components can be easily distinguished, and the noise can be eliminated. The results depict a marked improvement in the signal-to-noise ratio. This makes the data set usable and improves the computation of high-quality seismic attributes such as coherence and curvature, which supports better interpretation of the seismic data.

Knowledge assisted machine learning to clarify pore influence on fatigue life of forging/additive hybrid manufactured Ti-17 alloy

Forging/additive hybrid manufactured Ti alloy parts suffer from relatively low fatigue life due to the existence of metallurgical defects in the transition zone, which also brings difficulty to fatigue life modeling. In this work, the synergistic effect of pore size and location on the rotating-bending fatigue life of hybrid manufactured Ti-5Al-2Sn-2Zr-4Mo-4Cr (Ti-17) samples was systematically investigated with the combination of machine learning approaches and physical knowledge. A machine learning framework with a back propagation neural network and generative adversarial network (GAN) was constructed and employed on sparse and limited datasets. A general and interpretable model was obtained with a high level of 90% confidence. In general, the fatigue life of hybrid manufactured Ti-17 alloys decreases with pore size and increases with its distance to surface. Specifically, critical sizes were obtained for near-surface and in-depth pores that have negligible influence on fatigue life of hybrid manufactured samples with respect to pore-free samples. The present work thus provides a systematic platform for the evaluation of the fatigue performance of hybrid manufactured titanium alloys.

Benchmarking neural radiance fields for autonomous robots: An overview

Neural Radiance Field (NeRF) has emerged as a powerful paradigm for scene representation, offering high-fidelity renderings and reconstructions from a set of sparse and unstructured sensor data. In the context of autonomous robotics, where perception and understanding of the environment are pivotal, NeRF holds immense promise for improving performance. However, few survey has discussed such a potential. To fill this gap, we have collected over 200 papers since the publication of original NeRF in 2020 and present a thorough analysis of how NeRF can be used to enhance the capabilities of autonomous robots. We especially focus on the perception, localization and navigation, and decision-making modules of autonomous robots and delve into tasks crucial for autonomous operation, including 3-dimensional reconstruction, segmentation, pose estimation, simultaneous localization and mapping, navigation and planning, and interaction. Our survey meticulously benchmarks existing NeRF-based methods, comparing their reported performance, and providing insights into their strengths and limitations. Moreover, we target the existing challenges of applying NeRF in autonomous robots, including real-time processing, sparse input views, and explore promising avenues for future research and development in this domain. We especially discuss potential of integrating advanced deep learning techniques like 3-dimensional Gaussian splatting, large language models, and generative artificial intelligence. This survey serves as a roadmap for researchers seeking to leverage NeRF to empower autonomous robots, paving the way for innovative solutions that can navigate and interact seamlessly in complex environments.

On the Performance of a Data-Driven Backward Compatible Physics-Informed Neural Network for Prediction of Flow Past a Cylinder

Abstract This paper discusses a physics-informed surrogate model aimed at reconstructing the flow field from sparse datasets under a limited computational budget. A benchmark problem of 2D unsteady laminar flow past a cylinder is chosen to evaluate the performance of the surrogate model. Earlier studies were focused on forward problems with well-defined data. The present study attempts to develop models capable of reconstructing the flow-field data from sparse datasets mirroring real-world scenarios. We demonstrated the performance of data-driven models in reconstructing the flow field and compared the effectiveness of various training methodologies. The proposed surrogate model successfully reconstructed the flow field while also extracting pressure as a latent variable. The proposed surrogate model significantly outperformed data-driven models in accuracy, even under a limited computational budget. Furthermore, transfer learning of parameters of a pretrained model for different Reynolds numbers has reduced training time.

Physics-based and data-driven modelling and simulation of Solid Oxide Fuel Cells

This paper presents a comprehensive approach to multiscale and multiphysics modelling of Solid Oxide Fuel Cells (SOFCs) by combining physics-based simulations with data-driven techniques. The modelling approach is tailored to specific end-use scenarios, ensuring that parameter selection aligns with operational requirements for accurate and efficient SOFC design. The study begins by constructing Representative Volume Elements (RVEs) from reconstructed microstructures, applying first-order homogenisation to upscale material properties, which are then incorporated into a macroscopic SOFC model. A major contribution is the structured model definition based on physical process entities, using a graphical representation of model topology. This approach simplifies complex system interactions by representing capacities (such as reservoirs, distributed systems, and interfaces) and transport processes (e.g., diffusion, convection, thermal diffusion), thereby enhancing clarity and improving the accuracy of SOFC performance simulations.A machine learning framework complements the physics-based modelling by training Artificial Neural Networks (ANNs) on simulation-generated datasets, delivering fast and reliable performance predictions. The study compares two optimisation techniques — Levenberg–Marquardt (LM) and Adam optimiser — demonstrating that LM is more effective for sparse datasets and smaller networks, whereas Adam performs better with large datasets and higher learning capacities. This hybrid modelling approach not only boosts predictive accuracy for SOFC performance but also lowers computational costs. By integrating physics-based simulations, machine learning, and a knowledge-driven simulation platform, this work advances SOFC design and optimisation, contributing to more efficient and cost-effective clean energy solutions.Additionally, the paper introduces a knowledge-driven simulation platform to enhance data management and integrate multiscale, multiphysics models. The platform leverages structured data models and ontological mappings to improve semantic interoperability, allowing for dataset reuse and validation across different simulation stages. This ensures a robust, reusable, and well-organised workflow, facilitating large-scale simulations and improving overall modelling accuracy.

Sampling-efficient design optimization for categorical configurations and application to turbine blade cooling structures

Optimizing structural designs, especially for complex systems like turbine blade cooling structures, requires efficient strategies for handling categorical configurations alongside computationally expensive simulations. This article presents a Bayesian optimization strategy tailored for integrated tasks involving categorical configurations and high-dimensional continuous design variables. A Gaussian process with Con-Cat kernel is proposed in order to merge response datasets from diverse configurations effectively, capturing inter-configuration and intra-configuration correlations seamlessly. Additionally, a supervised dimension–reduction scheme is developed based on subspace activation, utilizing a half-Cauchy distribution. Remarkably, the Con-Cat kernel represents a generalization of standard kernels, achieving equivalence in scenarios solely involving continuous variables. The subspace activation scheme enhances surrogate modelling performance without introducing extra model parameters, which is particularly beneficial for sparse datasets. Numerical evaluations, including three mathematical functions, a supported beam problem, and turbine blade cooling structure design optimization, demonstrate the superiority of the proposed Bayesian optimization strategy, exhibiting up to an 85% improvement over five alternative approaches, especially in scenarios with sparse data.

Dealing with adverse drug reactions in the context of polypharmacy using regression models

Polypharmacy in older adults increases the risk of adverse drug reactions (ADRs), but studying this relationship is complex. In real-world data, the high number of medications, coupled with rare drug combinations, results in high-dimensional datasets that are difficult to analyze using conventional statistical methods. This study applies horseshoe and lasso regression for analyzing rare events in polypharmacy contexts, focusing on severe ADRs such as falls and bleedings. These regression models are executed on a multi-center dataset compiling 7175 cases from the ADRED project to detect potential ADR-associated drugs among 100 most common drugs in emergency department admissions. Positive predictors are classified by using 50% and 90% credibility intervals. This study demonstrates that regression models with horseshoe or lasso priors are effective for analyzing ADRs, providing a comprehensive consideration of multiple factors in large, sparse datasets and improving signal detection in polypharmacy, addressing a significant challenge in pharmacovigilance. Both priors yielded consistent and clinically meaningful results. The horseshoe regression resulted in fewer potential positive predictors overall, which could make it suitable as a diagnostic tool. While these regressions generate valuable information, there are still challenges in setting appropriate thresholds for determining and interpreting the positive results.

Multiple Data Imputation Methods Advance Risk Analysis and Treatability of Co-occurring Inorganic Chemicals in Groundwater.

Accurately assessing and managing risks associated with inorganic pollutants in groundwater is imperative. Historic water quality databases are often sparse due to rationale or financial budgets for sample collection and analysis, posing challenges in evaluating exposure or water treatment effectiveness. We utilized and compared two advanced multiple data imputation techniques, AMELIA and MICE algorithms, to fill gaps in sparse groundwater quality data sets. AMELIA outperformed MICE in handling missing values, as MICE tended to overestimate certain values, resulting in more outliers. Field data sets revealed that 75% to 80% of samples exhibited no co-occurring regulated pollutants surpassing MCL values, whereas imputed values showed only 15% to 55% of the samples posed no health risks. Imputed data unveiled a significant increase, ranging from 2 to 5 times, in the number of sampling locations predicted to potentially exceed health-based limits and identified samples where 2 to 6 co-occurring chemicals may occur and surpass health-based levels. Linking imputed data to sampling locations can pinpoint potential hotspots of elevated chemical levels and guide optimal resource allocation for additional field sampling and chemical analysis. With this approach, further analysis of complete data sets allows state agencies authorized to conduct groundwater monitoring, often with limited financial resources, to prioritize sampling locations and chemicals to be tested. Given existing data and time constraints, it is crucial to identify the most strategic use of the available resources to address data gaps effectively. This work establishes a framework to enhance the beneficial impact of funding groundwater data collection by reducing uncertainty in prioritizing future sampling locations and chemical analyses.

Optimizing wind power forecasting with RNN-LSTM models through grid search cross-validation

Wind energy is a crucial renewable resource that supports sustainable development and reduces carbon emissions. However, accurate wind power forecasting is challenging due to the inherent variability in wind patterns. This paper addresses these challenges by developing and evaluating some machine learning (ML) and deep learning (DL) models to enhance wind power forecasting accuracy. Traditional ML models, including Random Forest, k-nearest Neighbors, Ridge Regression, LASSO, Support Vector Regression, and Elastic Net, are compared with advanced DL models, such as Recurrent Neural Networks (RNN), Long Short-Term Memory (LSTM), Stacked LSTM, Graph Convolutional Networks (GCN), Temporal Convolutional Networks (TCN), and the Informer network, which is well-suited for long-sequence forecasting and large, sparse datasets. Recognizing the complexities of wind power forecasting, such as the need for high-resolution meteorological data and the limitations of ML models like overfitting and computational complexity, a novel hybrid approach is proposed. This approach uses hybrid RNN-LSTM models optimized through GS-CV. The models were trained and validated on a SCADA dataset from a Turkish wind farm, comprising 50,530 instances. Data preprocessing included cleaning, encoding, and normalization, with 70 % of the dataset allocated for training and 30 % for validation. Model performance was evaluated using key metrics such as R², MSE, MAE, RMSE, and MedAE. The proposed hybrid RNN-LSTM Models achieved outstanding results, with the RNN-LSTM model attaining an R² of 99.99 %, significantly outperforming other models. These results demonstrate the effectiveness of the hybrid approach and the Informer network in improving wind power forecasting accuracy, contributing to grid stability, and facilitating the broader adoption of sustainable energy solutions. The proposed model also achieved superior comparable performance when compared to state-of-the-art methods.

Comparative analysis of matrix factorization and graph convolutional networks in student

Abstract. For the educational worker, predicting students grades and having a deep understanding of students levels is quite important to improve their teaching methods. Fortunately, there have been several research to predict students grades in applying different models, such as Matrix Factorization (MF) and Graph Convolutional Networks (GCNs). This essay is talking about comparing two different models, MF and GCNs, which are going to exhibit the difference between them. By comparing their performance in predictive accuracy, interpretability, and computational efficiency, people can identify their strengths and areas for improvement. In this essay, the advantages and disadvantages of the two models will be listed and their performance will be compared. Therefore, in this context, this essay will introduce two models first, then show their performance in different experiences from past research and compare their results. As a result, MF shows a better performance in handling large-scale sparse datasets and providing meaningful interpretations, whereas GCNs are good at capturing complex dependencies and integrating multiple data sources.

Quantum computing enhanced knowledge tracing: Personalized KT research for mitigating data sparsity

With the development of artificial intelligence in education, knowledge tracing (KT) has become a current research hotspot and is the key to the success of personalized instruction. However, data sparsity remains a significant challenge in the KT domain. To address this challenge, this paper applies quantum computing (QC) technology to KT for the first time. It proposes two personalized KT models incorporating quantum mechanics (QM): quantum convolutional enhanced knowledge tracing (QCE-KT) and quantum variational enhanced knowledge tracing (QVE-KT). Through quantum superposition and entanglement properties, QCE-KT and QVE-KT effectively alleviate the data sparsity problem in the KT domain through quantum convolutional layers and variational quantum circuits, respectively, and significantly improve the quality of the representation and prediction accuracy of students’ knowledge states. Experiments on three datasets show that our models outperform ten benchmark models. On the most sparse dataset, QCE-KT and QVE-KT improve their performance by 16.44% and 14.78%, respectively, compared to DKT. Although QC is still in the developmental stage, this study reveals the great potential of QM in personalized KT, which provides new perspectives for solving personalized instruction problems and opens up new directions for applying QC in education.

Statistical Mapping of PFOA and PFOS in Groundwater throughout the Contiguous United States.

Per-and polyfluoroalkyl substances (PFAS) are synthetic chemicals that are increasingly being detected in groundwater. The negative health consequences associated with human exposure to PFAS make it essential to quantify the distribution of PFAS in groundwater systems. Mapping PFAS distributions is particularly challenging because a national patchwork of testing and reporting requirements has resulted in sparse and spatially biased data. In this analysis, an inhomogeneous Poisson process (IPP) modeling approach is adopted from ecological statistics to continuously map PFAS distributions in groundwater across the contiguous United States. The model is trained on a unique data set of 8910 PFAS groundwater measurements, using combined concentrations of two PFAS analytes. The IPP model predictions are compared with results from random forest models to highlight the robustness of this statistical modeling approach on sparse data sets. This analysis provides a new approach to not only map PFAS contamination in groundwater but also prioritize future sampling efforts.

Graph neural processes for molecules: an evaluation on docking scores and strategies to improve generalization

Neural processes (NPs) are models for meta-learning which output uncertainty estimates. So far, most studies of NPs have focused on low-dimensional datasets of highly-correlated tasks. While these homogeneous datasets are useful for benchmarking, they may not be representative of realistic transfer learning. In particular, applications in scientific research may prove especially challenging due to the potential novelty of meta-testing tasks. Molecular property prediction is one such research area that is characterized by sparse datasets of many functions on a shared molecular space. In this paper, we study the application of graph NPs to molecular property prediction with DOCKSTRING, a diverse dataset of docking scores. Graph NPs show competitive performance in few-shot learning tasks relative to supervised learning baselines common in chemoinformatics, as well as alternative techniques for transfer learning and meta-learning. In order to increase meta-generalization to divergent test functions, we propose fine-tuning strategies that adapt the parameters of NPs. We find that adaptation can substantially increase NPs' regression performance while maintaining good calibration of uncertainty estimates. Finally, we present a Bayesian optimization experiment which showcases the potential advantages of NPs over Gaussian processes in iterative screening. Overall, our results suggest that NPs on molecular graphs hold great potential for molecular property prediction in the low-data setting.Scientific contributionNeural processes are a family of meta-learning algorithms which deal with data scarcity by transferring information across tasks and making probabilistic predictions. We evaluate their performance on regression and optimization molecular tasks using docking scores, finding them to outperform classical single-task and transfer-learning models. We examine the issue of generalization to divergent test tasks, which is a general concern of meta-learning algorithms in science, and propose strategies to alleviate it.

Diverse Humanoid Robot Pose Estimation from Images Using Only Sparse Datasets

We present a novel dataset for humanoid robot pose estimation from images, addressing the critical need for accurate pose estimation to enhance human–robot interaction in extended reality (XR) applications. Despite the importance of this task, large-scale pose datasets for diverse humanoid robots remain scarce. To overcome this limitation, we collected sparse pose datasets for commercially available humanoid robots and augmented them through various synthetic data generation techniques, including AI-assisted image synthesis, foreground removal, and 3D character simulations. Our dataset is the first to provide full-body pose annotations for a wide range of humanoid robots exhibiting diverse motions, including side and back movements, in real-world scenarios. Furthermore, we introduce a new benchmark method for real-time full-body 2D keypoint estimation from a single image. Extensive experiments demonstrate that our extended dataset-based pose estimation approach achieves over 33.9% improvement in accuracy compared to using only sparse datasets. Additionally, our method demonstrates the real-time capability of 42 frames per second (FPS) and maintains full-body pose estimation consistency in side and back motions across 11 differently shaped humanoid robots, utilizing approximately 350 training images per robot.

Firth-Type Penalized Methods of the Modified Poisson and Least-Squares Regression Analyses for Binary Outcomes.

The modified Poisson and least-squares regression analyses for binary outcomes have been widely used as effective multivariable analysis methods to provide risk ratio and risk difference estimates in clinical and epidemiological studies. However, there is no certain evidence that assessed their operating characteristics under small and sparse data settings and no effective methods have been proposed for these regression analyses to address this issue. In this article, we show that the modified Poisson regression provides seriously biased estimates under small and sparse data settings. In addition, the modified least-squares regression provides unbiased estimates under these settings. We further show that the ordinary robust variance estimators for both of the methods have certain biases under situations that involve small or moderate sample sizes. To address these issues, we propose the Firth-type penalized methods for the modified Poisson and least-squares regressions. The adjustment methods lead to a more accurate and stable risk ratio estimator under small and sparse data settings, although the risk difference estimator is not invariant. In addition, to improve the inferences of the effect measures, we provide an improved robust variance estimator for these regression analyses. We conducted extensive simulation studies to assess the performances of the proposed methods under real-world conditions and found that the accuracies of the point and interval estimations were markedly improved by the proposed methods. We illustrate the effectiveness of these methods by applying them to a clinical study of epilepsy.

Modified Genetic Algorithm for Efficient High-Utility Itemset Mining

In pattern mining, high-utility itemset mining (HUIM) is useful for discovering high-utility patterns. The study of HUIM using heuristic techniques reflects issues in producing better offspring. It is ineffective in terms of search space organization, population diversity, and utility calculation, which impact runtime and accuracy. It is observed that very few researchers have experimented with genetic algorithm (GA) and are still facing the same issues as mentioned before. To overcome these problems, a novel approach is proposed for HUIM using modified GA and optimized local search (HUIM-MGALS) with six potential contributions. First is linking the utility with the Bitmap dataset to reduce utility access time, leading to effective search space organization. Second, HUIM-MGALS employs a fitness scaling strategy to avoid redundancy. Third, a high-utility itemset (HUI) revision strategy is employed to explore significant HUIs. Modified population diversity maintenance strategy and iterative crossover help to preserve significant HUIs and improve search capability as fourth and fifth contributions. Sixth, the use of multiple mutations refines the wasted individuals to boost accuracy. Extensive experimentation showed that HUIM-MGALS significantly outperforms the presented algorithms, up to 8.6 times faster. It also demonstrates superior HUI discovery capabilities for both sparse and dense datasets. This is supported by the modified population diversity maintenance strategy, which is proved to be the most impactful modification for HUI discovery in HUIM-MGALS.

Domain Decomposition for Data-Driven Reduced Modeling of Large-Scale Systems

This paper focuses on the construction of accurate and predictive data-driven reduced models of large-scale numerical simulations with complex dynamics and sparse training datasets. In these settings, standard, single-domain approaches may be too inaccurate or may overfit and hence generalize poorly. Moreover, processing large-scale datasets typically requires significant memory and computing resources, which can render single-domain approaches computationally prohibitive. To address these challenges, we introduce a domain-decomposition formulation into the construction of a data-driven reduced model. In doing so, the basis functions used in the reduced model approximation become localized in space, which can increase the accuracy of the domain-decomposed approximation of the complex dynamics. The decomposition furthermore reduces the memory and computing requirements to process the underlying large-scale training dataset. We demonstrate the effectiveness and scalability of our approach in a large-scale three-dimensional unsteady rotating-detonation rocket engine simulation scenario with more than 75 million degrees of freedom and a sparse training dataset. Our results show that compared to the single-domain approach, the domain-decomposed version reduces both the training and prediction errors for pressure by up to 13% and up to 5% for other key quantities, such as temperature, and fuel, and oxidizer mass fractions. Lastly, our approach decreases the memory requirements for processing by almost a factor of four, which in turn reduces the computing requirements as well.

From FFT to sparse FFT: Innovations in efficient signal processing for large sparse data

This paper explores the advancements from the traditional Fast Fourier Transform (FFT) to the Sparse Fast Fourier Transform (sFFT) and their implications for efficient signal processing of large, sparse datasets. FFT has long been a fundamental component in digital signal processing, significantly lowering the runtime of the Discrete Fourier Transform. However, the ingress of big data has necessitated much more efficient algorithms. In contrast, the sFFT exploits the sparsity in the signals themselves to reduce computational demand, and it becomes very efficient. This paper will discuss the theoretical backing of these two developments, FFT and sFFT, and the algorithmic development in both. In addition, it will also discuss the practical applications of both with emphasis on how the latter outperforms the former in large, sparse data. Comparative analysis shows that sFFT has far greater efficiency and noise tolerance, which is of value for network traffic analysis, astrophysical data analysis, and real-time medical imaging. The purpose of this paper is to provide clarity regarding these transformations and their relationship to being paradigms in modern signal analysis.

The 4D Camera: An 87 kHz Direct Electron Detector for Scanning/Transmission Electron Microscopy.

We describe the development, operation, and application of the 4D Camera-a 576 by 576 pixel active pixel sensor for scanning/transmission electron microscopy which operates at 87,000 Hz. The detector generates data at ∼480 Gbit/s which is captured by dedicated receiver computers with a parallelized software infrastructure that has been implemented to process the resulting 10-700 Gigabyte-sized raw datasets. The back illuminated detector provides the ability to detect single electron events at accelerating voltages from 30 to 300 kV. Through electron counting, the resulting sparse data sets are reduced in size by 10--300× compared to the raw data, and open-source sparsity-based processing algorithms offer rapid data analysis. The high frame rate allows for large and complex scanning diffraction experiments to be accomplished with typical scanning transmission electron microscopy scanning parameters.

Towards similar alignment and unique uniformity in collaborative filtering

Representation learning, with its desired properties, including Alignment and Uniformity, has recently emerged as an effective approach in collaborative filtering (CF) for recommender systems. Alignment measures the distance between positive pairs, and uniformity describes the distribution of all samples on the unit hypersphere. Despite the effectiveness of existing research, the challenges of insufficient alignment and uniformity bias persist in studies on the desired properties of recommender systems: (1) Sparse interaction information leads to an insufficient alignment representation. (2) Calculating the uniformity loss based on duplicate samples introduces bias, which affects the overall representation uniformity.Building on aforementioned challenges, we propose a Similar Alignment and Unique Uniformity model called SUAU. SUAU mitigates insufficient alignment by introducing additional item-similar item pairs for model training and employing a uniqueness strategy to prevent uniformity bias. More specifically, we propose a similar items generation method that identifies the most similar items based on the interaction behavior of the original items’ related users to form item-similar item pairs. The experimental results obtained on three highly sparse datasets demonstrate that the propose model achieves superior alignment and uniformity compared with state-of-the-art models, notably surpassing the best CF methods in terms of recommendation performance. We have open-sourced the source code on a publicly accessible website: https://github.com/ZzYUuuu/SUAU.