Multi-resolution Model Research Articles

Implementation of manifold coverage for 3D rock fracture network modeling and its application in rock permeability prediction

Fracture network modeling is an important prerequisite for studies on rock mechanical behaviors and permeability properties. At present, fracture patterns in most discrete fracture network (DFN) models are expressed by Euclidean geometries, which leads to distortion in describing complex fractured rocks. In order to solve this problem, a block texture synthesis method is proposed in this paper to generate multi-resolution two-dimensional (2D) DFN models for fractured coal. The results show that the generated multi-resolution 2D DFN models largely retain the fracture texture structure in the original exemplar. In addition, the concept of manifold coverage is adopted to optimize the 2D fracture image, and the three-dimensional (3D) texture-based DFN models are generated by the solid texture synthesis method from the optimized image. The results indicate that the 3D texture-based DFN models have good fidelity of natural fractures in fracture sets, orientation, density, roughness, fluctuation, aperture and connectivity from the perspective of geometric appearance. Comparison between the 3D DFN model with texture coverage and random coverage shows good consistency in fracture proportion, geometric pattern, and permeability properties. Therefore, the 3D DFN models based on random coverage provide a new idea for modeling fractured rocks and lattice models in numerical simulation of rock mechanical behaviors and permeability properties by various methods, such as RFPA2D/3D, FLAC2D/3D, and Lattice Boltzmann Method (LBM).

Optimal operating regime of an electric vehicle aggregator considering reserve provision

The number of electric vehicles (EVs) is growing rapidly due to environmental concerns and political supports. To better coordinate the charging behaviors of large numbers of EVs, the EV aggregator is an important intermediate between the electricity market and the EVs. This work proposes a two-stage optimal operational regime for an EV aggregator who participates in multiple markets under multiple uncertainties. In the day-ahead stage, a joint offering model is proposed to help the aggregator concurrently participate in both the energy and reserve markets under market price uncertainties. The concept of reserve capacity ratio is introduced in the joint offering model to allow different decisions for aggregators with various risk preferences. In the real-time stage, a rolling horizon control-based multi-resolution scheduling model is proposed to minimize the energy deviation cost under reserve deployment uncertainty. The uncertainties are modeled using representative scenarios and the stochastic optimization approach is applied to acquire the optimal solutions. The numerical results suggest that the proposed operational regime can significantly improve the profitability of the studied EV aggregator. The impact of reserve capacity ratios is also analyzed.

MDCADNet: Multi dilated & context aggregated dense network for non-textual components classification in digital documents

Non-Textual images like charts and tables are unlike natural images in various aspects, including high inter-class similarities, low intra-class similarities, substantial textual component proportions, and lower resolutions. This paper proposes a novel Multi-Dilated Context Aggregation based Dense Network (MDCADNet) addressing the multi-resolution and larger receptive field modeling need for the non-textual component classification task. MDCADNet includes a densely connected convolutional network for the feature map computation as front-end with a multi-dilated Backend Context Module (BCM). The proposed BCM generates multi-scale features and provides a systematic context aggregation of both low and high-level feature maps through its densely connected layers. Additionally, the controlled multi-dilation scheme offers a more extensive scale range for better prediction performance. A thorough quantitative evaluation has been performed on seven benchmark datasets for demonstrating the generalization capability of MDCADNet. Experimental results show MDCADNet performs consistently better than the state-of-the-art models across all datasets.

Multiresolution residual deep neural network for improving pelvic CBCT image quality.

Cone-beam computed tomography (CBCT) is frequently used for accurate image-guided radiation therapy. However, the poor CBCT image quality prevents its further clinical use. Thus, it is important to improve the HU accuracy and structure preservation of CBCT images. In this study, we proposed a novel method to generate synthetic CT (sCT) images from CBCT images. A multiresolution residual deep neural network (RDNN) was adopted for image regression from CBCT images to planning CT (pCT) images. At the coarse level, RDNN was first trained with a large amount of lower resolution images, which can make the network focus on coarse information and prevent overfitting problems. More fine information was obtained gradually by fine-tuning the coarse model using fewer number of higher resolution images. Our model was optimized by using aligned pCT and CBCT image pairs of a particular body region of 153 prostate cancer patients treated in our hospital (120 for training and 33 for testing). Five-fold cross-validation was used to tune the hyperparameters and the testing data were used to evaluate the performance of the final models. The mean absolute error (MAE) between CBCT and pCT on the testing data was 352.56 HU, while the MAE between the sCT and pCT images was 52.18 HU for our proposed multiresolution RDNN model, which reduced the MAE by 85.20% (p<0.01). In addition, the average structural similarity index measure between the sCT and CBCT was 19.64% (p=0.01) higher than that of pCT and CBCT. The sCT images generated using our proposed multiresolution RDNN have higher HU accuracy and structural fidelity, which may promote the further applications of CBCT images in the clinic for structure segmentation, dose calculation, and adaptive radiotherapy planning.

3D convolutional auto-encoder based multi-scale feature extraction for point cloud registration

Searching corresponding features between two consecutive point cloud sequences is a key step in frame-to-frame matching. Utilizing multi-resolution strategy and voxel model which reserves the original shape of input data, we propose a fully unsupervised Convolutional Auto-Encoder (CAE) based feature matching methodology that extracts features from multi-resolution voxel model. Different resolutions can capture different information: hight resolution better reflects local details, and low resolution can describe coarse appearance in a relative wide range. CAE is further adopted to encode the voxel patch of a specific resolution to a low dimension one. The final feature descriptor is concatenated by the encoded features of different resolutions and is used to determine the initial corresponding features in terms of Euclidean distance. Refined matches are obtained through RANSAC. Experiments based on KITTI dataset show that our features outperform state-of-the-art by almost 20–30% in average matching inlier ratio.

An Exploratory Evaluation of Multiscale Data Analysis for Landform Element Detection on High-Resolution DEM

The representation of landform element varies over multiple scales, or multiresolution digital elevation model (DEM) and its derivatives. When more details of land surfaces are available to be characterized based on the existing high spatial resolution elevation products, the influence of scale variation might become more significant. This poses a demand for determining a scale-independent approach being competent to support multiscale landform element detection on high-resolution DEMs. Although the practicability of the state-of-the-art scale-independent approaches have been reported on moderate-resolution DEMs, how these approaches perform based on the multiscale data including high and moderate spatial-resolution DEMs is still unexplored. This letter evaluates the performance of four scale-independent techniques including filtering, spatial pyramid, multiscale segmentation, and spatial-contextual approach in landform element detection on different spatial resolution DEMs. The experimental results show that spatial–contextual approach is more effective to support multiscale landform element detection than others.

Construction of an urban multi variable geospatial information integration model based on distributed artificial intelligence

In order to improve the ability of urban multi-spatial information integration, a multi-spatial information integration model based on artificial intelligence is proposed. The empirical analysis model of urban multivariate geospatial information integration is established, and the statistical characteristics are analysed according to the information distribution. The multi-resolution clustering model of urban multi-spatial information is established by using the multi-regression parameter method. The methods of fuzzy feature extraction and associated feature mining were used to extract information features, and the constraint parameters of urban multivariate geospatial information integration were analysed by GIS parameter estimation and statistical analysis. The parameter optimisation model of urban multivariate geospatial information integration is established and the artificial intelligence learning algorithm is used to integrate urban multivariate geospatial information. The simulation results show that this method has a good adaptability to the integration of urban multi-spatial information, and is helpful to the spatial distribution planning of geographic information, and improves the ability of accurate mining and scheduling of urban multi-spatial information.

The Hard Lessons and Shifting Modeling Trends of COVID-19 Dynamics: Multiresolution Modeling Approach.

The COVID-19 pandemic has placed epidemiologists, modelers, and policy makers at the forefront of the global discussion of how to control the spread of coronavirus. The main challenges confronting modelling approaches include real-time projections of changes in the numbers of cases, hospitalizations, and fatalities, the consequences of public health policy, the understanding of how best to implement varied non-pharmaceutical interventions and potential vaccination strategies, now that vaccines are available for distribution. Here, we: (i) review carefully selected literature on COVID-19 modeling to identify challenges associated with developing appropriate models along with collecting the fine-tuned data, (ii) use the identified challenges to suggest prospective modeling frameworks through which adaptive interventions such as vaccine strategies and the uses of diagnostic tests can be evaluated, and (iii) provide a novel Multiresolution Modeling Framework which constructs a multi-objective optimization problem by considering relevant stakeholders’ participatory perspective to carry out epidemic nowcasting and future prediction. Consolidating our understanding of model approaches to COVID-19 will assist policy makers in designing interventions that are not only maximally effective but also economically beneficial.

Predicting endometrial cancer subtypes and molecular features from histopathology images using multi-resolution deep learning models

SummaryThe determination of endometrial carcinoma histological subtypes, molecular subtypes, and mutation status is critical for the diagnostic process, and directly affects patients’ prognosis and treatment. Sequencing, albeit slower and more expensive, can provide additional information on molecular subtypes and mutations that can be used to better select treatments. Here, we implement a customized multi-resolution deep convolutional neural network, Panoptes, that predicts not only the histological subtypes but also the molecular subtypes and 18 common gene mutations based on digitized H&E-stained pathological images. The model achieves high accuracy and generalizes well on independent datasets. Our results suggest that Panoptes, with further refinement, has the potential for clinical application to help pathologists determine molecular subtypes and mutations of endometrial carcinoma without sequencing.

Multiresolution Modeling of High-Latitude Ionospheric Electric Field Variability and Impact on Joule Heating Using SuperDARN Data.

The most dynamic electromagnetic coupling between the magnetosphere and ionosphere occurs in the polar upper atmosphere. It is critical to quantify the electromagnetic energy and momentum input associated with this coupling as its impacts on the ionosphere and thermosphere system are global and major, often leading to considerable disturbances in near‐Earth space environments. The current general circulation models of the upper atmosphere exhibit systematic biases that can be attributed to an inadequate representation of the Joule heating rate resulting from unaccounted stochastic fluctuations of electric fields associated with the magnetosphere‐ionosphere coupling. These biases exist regardless of geomagnetic activity levels. To overcome this limitation, a new multiresolution random field modeling approach is developed, and the efficacy of the approach is demonstrated using Super Dual Auroral Radar Network (SuperDARN) data carefully curated for the study during a largely quiet 4‐hour period on February 29, 2012. Regional small‐scale electrostatic fields sampled at different resolutions from a probabilistic distribution of electric field variability conditioned on actual SuperDARN LOS observations exhibit considerably more localized fine‐scale features in comparison to global large‐scale fields modeled using the SuperDARN Assimilative Mapping procedure. The overall hemispherically integrated Joule heating rate is increased by a factor of about 1.5 due to the effect of random regional small‐scale electric fields, which is close to the lower end of arbitrarily adjusted Joule heating multiplicative factor of 1.5 and 2.5 typically used in upper atmosphere general circulation models. The study represents an important step toward a data‐driven ensemble modeling of magnetosphere‐ionosphere‐atmosphere coupling processes.

Fusion of 3D lung CT and serum biomarkers for diagnosis of multiple pathological types on pulmonary nodules

Background and Objective: Current researches on pulmonary nodules mainly focused on the binary-classification of benign and malignant pulmonary nodules. However, in clinical applications, it is not enough to judge whether pulmonary nodules are benign or malignant. In this paper, we proposed a fusion model based on the Lung Information Dataset Containing 3D CT Images and Serum Biomarkers (LIDCCISB) we constructed to accurately diagnose the types of pulmonary nodules in squamous cell carcinoma, adenocarcinoma, inflammation and other benign diseases. Methods: Using single modal information of lung 3D CT images and single modal information of Lung Tumor Biomarkers (LTBs) in LIDCCISB, a Multi-resolution 3D Multi-classification deep learning model (Mr-Mc) and a Multi-Layer Perceptron machine learning model (MLP) were constructed for diagnosing multiple pathological types of pulmonary nodules, respectively. To comprehensively use the double modal information of CT images and LTBs, we used transfer learning to fuse Mr-Mc and MLP, and constructed a multimodal information fusion model that could classify multiple pathological types of benign and malignant pulmonary nodules. Results: Experiments showed that the constructed Mr-Mc model can achieve an average accuracy of 0.805 and MLP model can achieve an average accuracy of 0.887. The fusion model was verified on a dataset containing 64 samples, and achieved an average accuracy of 0.906. Conclusions: This is the first study to simultaneously use CT images and LTBs to diagnose multiple pathological types of benign and malignant pulmonary nodules, and experiments showed that our research was more advanced and more suitable for practical clinical applications.

Multi-resolution B-splines data compression improves MIR spectroscopy-based Health diagnostic efficiency

MIR spectroscopy is becoming an increasingly important tool potentially useful for diagnosis purposes especially by studying body fluids. Indeed, diseases induce changes in the composition of fluids modifying the MIR spectra. However, such changes can be difficult to capture if the structure of the data is not considered. Our objective was to improve MIR spectra analysis by using approximation of the spectra by B-splines at different specific resolutions and to combine these spectra representations with a machine learning model to predict hepatic steatosis from serum study. The different resolutions make it possible to identify changes in shape over bands of various widths. The multiresolution model helps to improve the hepatic steatosis prediction compared to conventional approaches where the absorbances are considered as unstructured variables. In addition, B-splines provide both localized and compressed information that can be translated into biochemical terms more easily than with other classical approximation methods (wavelets, Fourier transforms).

SPiRaL: a multiresolution global tomography model of seismic wave speeds and radial anisotropy variations in the crust and mantle

SUMMARYSPiRaL is a joint global-scale model of wave speeds (P and S) and anisotropy (vertical transverse isotropy, VTI) variations in the crust and mantle. The model is comprised of &amp;gt;2.1 million nodes with five parameters at each node that capture velocity variations for P- and S-waves travelling at arbitrary directions in transversely isotropic media with a vertical symmetry axis (VTI). The crust (including ice, water, sediments and crystalline layers) is directly incorporated into the model. The default node spacing is approximately 2° in the lower mantle and 1° in the crust and upper mantle. The grid is refined with ∼0.25° minimum node spacing in highly sampled regions of the crust and upper mantle throughout North America and Eurasia. The data considered in the construction of SPiRaL includes millions of body wave traveltimes (crustal, regional and teleseismic phases with multiples) and surface wave (Rayleigh and Love) dispersion. A multiresolution inversion approach is employed to capture long-wavelength heterogeneities commonly depicted in global-scale tomography images as well as more localized details that are typically resolved in more focused regional-scale studies. Our previous work has demonstrated that such global-scale models with regional-scale detail can accurately predict both teleseismic and regional body wave traveltimes, which is necessary for more accurate location of small seismic events that may have limited signal at teleseismic distances. SPiRaL was constructed to predict traveltimes for event location and long-period waveform dispersion for seismic source inversion applications in regions without sufficiently tuned models. SPiRaL may also serve as a starting model for full-waveform inversion (FWI) with the goal of fitting waves with periods 10–50 s over multiple broad regions (thousands of kilometres) and potentially the globe. To gain insight to this possibility, we simulated waveforms for a small set of events using SPiRaL and independent waveform-based models for comparison. For the events tested, the performance of the traveltime-based SPiRaL model is shown to be generally on par with regional 3-D waveform-based models in three regions (western United States, Middle East, Korean Peninsula) suggesting SPiRaL may serve as a starting model for FWI over broad regions.

Matrix Autoregressive Spatio-Temporal Models

Matrix-variate time series are now common in economic, medical, environmental, and atmospheric sciences, typically associated with large matrix dimensions. We introduce a structured autoregressive (AR) model to characterize temporal dynamics in a matrix-variate time series by formulating the AR matrices in a bilinear form. This bilinear parameter structure reduces the model dimension and highlights dynamic interaction among columns and rows in the AR matrices, making the model highly explainable. We further incorporate spatial information and explore sparsity in the AR coefficients by introducing spatial neighborhoods. In addition, we consider a nonstationary multi-resolution spatial covariance model for innovation errors. The resulting spatio-temporal AR model is flexible in capturing heterogeneous spatial and temporal features while maintaining a parsimonious parameterization. The model parameters are estimated by maximum likelihood (ML) with a fast algorithm developed for computation. We conduct a simulation study and present an application to a wind-speed dataset to demonstrate the merits of our methodology. Supplementary files for this article are available online.

An Impact Study of GNSS RO Data on the Prediction of Typhoon Nepartak (2016) Using a Multiresolution Global Model with 3D-Hybrid Data Assimilation

AbstractConventional soundings are rather limited over the western North Pacific and can be largely compensated by GNSS radio occultation (RO) data. We utilize the GSI hybrid assimilation system to assimilate RO data and the multiresolution global model (MPAS) to investigate the RO data impact on prediction of Typhoon Nepartak that passed over southern Taiwan in 2016. In this study, the performances of assimilation with local RO refractivity and bending angle operators are compared for the assimilation analysis and typhoon forecast. Assimilations with both RO data have shown similar and comparable temperature and moisture increments after cycling assimilation and largely reduce the RMSEs of the forecast without RO data assimilation at later times. The forecast results at 60–15-km resolution show that RO data assimilation largely improves the typhoon track prediction compared to that without RO data assimilation, and assimilation with bending angle has better performances than assimilation with refractivity, in particular for wind forecast. The improvement in the forecasted track is mainly due to the improved simulation for the translation of the typhoon. Diagnostics of wavenumber-1 potential vorticity (PV) tendency budget indicates that the northwestward typhoon translation dominated by PV horizontal advection is slowed down by the southward tendency induced by the stronger differential diabatic heating south of the typhoon center for bending-angle assimilation. Simulations with the enhanced resolution of 3 km in the region of the storm track show further improvements in both typhoon track and intensity prediction with RO data assimilation. Positive RO impacts on track prediction are also illustrated for two other typhoons using the MPAS-GSI system.

Analysis of Visualization Technology of 3D Spatial Geographic Information System

Traditional urban planning is generally expressed in a two-dimensional geographic information system, but its performance is limited to the plane direction. It cannot give people more natural feelings and visionary experiences. The rapid development of three-dimensional geographic information systems brings people geographic information. The three-dimensional intuitive experience, but the traditional three-dimensional geographic information system has the disadvantages that the spatial properties are incompatible, the image rendering speed is slow, and the visualization effect is poor. In this paper, the traditional domain-oriented processing method is improved in spatial data processing and modeling. An optimized object-oriented optimization algorithm is proposed. The three-dimensional geographic information is optimized based on a dynamic multiresolution model and multilevel detail processing technology. The rendering of the system enhances the visualization. Based on the optimization algorithm of data processing and visualization technology proposed in this paper, the spatial data processing platform GISdata of 3D GIS is designed in this paper. At the same time, the 3D GIS is visualized based on OpenGL visualization software. It is shown that the optimization algorithm proposed in this paper has excellent preexperimental effects.

Individual-Specific Areal-Level Parcellations Improve Functional Connectivity Prediction of Behavior.

Resting-state functional magnetic resonance imaging (rs-fMRI) allows estimation of individual-specific cortical parcellations. We have previously developed a multi-session hierarchical Bayesian model (MS-HBM) for estimating high-quality individual-specific network-level parcellations. Here, we extend the model to estimate individual-specific areal-level parcellations. While network-level parcellations comprise spatially distributed networks spanning the cortex, the consensus is that areal-level parcels should be spatially localized, that is, should not span multiple lobes. There is disagreement about whether areal-level parcels should be strictly contiguous or comprise multiple noncontiguous components; therefore, we considered three areal-level MS-HBM variants spanning these range of possibilities. Individual-specific MS-HBM parcellations estimated using 10min of data generalized better than other approaches using 150min of data to out-of-sample rs-fMRI and task-fMRI from the same individuals. Resting-state functional connectivity derived from MS-HBM parcellations also achieved the best behavioral prediction performance. Among the three MS-HBM variants, the strictly contiguous MS-HBM exhibited the best resting-state homogeneity and most uniform within-parcel task activation. In terms of behavioral prediction, the gradient-infused MS-HBM was numerically the best, but differences among MS-HBM variants were not statistically significant. Overall, these results suggest that areal-level MS-HBMs can capture behaviorally meaningful individual-specific parcellation features beyond group-level parcellations. Multi-resolution trained models and parcellations are publicly available (https://github.com/ThomasYeoLab/CBIG/tree/master/stable_projects/brain_parcellation/Kong2022_ArealMSHBM).

A multi-resolution model for histopathology image classification and localization with multiple instance learning

Large numbers of histopathological images have been digitized into high resolution whole slide images, opening opportunities in developing computational image analysis tools to reduce pathologists' workload and potentially improve inter- and intra-observer agreement. Most previous work on whole slide image analysis has focused on classification or segmentation of small pre-selected regions-of-interest, which requires fine-grained annotation and is non-trivial to extend for large-scale whole slide analysis. In this paper, we proposed a multi-resolution multiple instance learning model that leverages saliency maps to detect suspicious regions for fine-grained grade prediction. Instead of relying on expensive region- or pixel-level annotations, our model can be trained end-to-end with only slide-level labels. The model is developed on a large-scale prostate biopsy dataset containing 20,229 slides from 830 patients. The model achieved 92.7% accuracy, 81.8% Cohen's Kappa for benign, low grade (i.e. Grade group 1) and high grade (i.e. Grade group ≥ 2) prediction, an area under the receiver operating characteristic curve (AUROC) of 98.2% and an average precision (AP) of 97.4% for differentiating malignant and benign slides. The model obtained an AUROC of 99.4% and an AP of 99.8% for cancer detection on an external dataset.

Multicanonical analyses of bluff airfoil drags in subcritical flows

We apply the multicanonical procedure in conjunction with an improved multi-resolution lattice Boltzmann model to evaluate the probability distribution function of the drag resulting from small but rarely occurring statistical deformations of a bluff airfoil NACA (National Advisory Committee for Aeronautics) 0050 and on a more streamlined NACA0030 airfoil with a larger aspect ratio. This analysis enables the effect of surface roughness on drags in a subcritical fluid flow to be examined in detail and demonstrates that the magnitude of the pressure drag, which is the primary component of the bluff airfoil drag, correlates with the width of the Fourier spectrum of the perturbation on the airfoil, while surface smoothness correlates with the frictional drag reduction in the subcritical fluid flow. Moreover, the multicanonical analysis differentiates between bluff and streamlined bodies without separately evaluating frictional and pressure drags.

Convolutional autoencoder based model HistoCAE for segmentation of viable tumor regions in liver whole-slide images

Liver cancer is one of the leading causes of cancer deaths in Asia and Africa. It is caused by the Hepatocellular carcinoma (HCC) in almost 90% of all cases. HCC is a malignant tumor and the most common histological type of the primary liver cancers. The detection and evaluation of viable tumor regions in HCC present an important clinical significance since it is a key step to assess response of chemoradiotherapy and tumor cell proportion in genetic tests. Recent advances in computer vision, digital pathology and microscopy imaging enable automatic histopathology image analysis for cancer diagnosis. In this paper, we present a multi-resolution deep learning model HistoCAE for viable tumor segmentation in whole-slide liver histopathology images. We propose convolutional autoencoder (CAE) based framework with a customized reconstruction loss function for image reconstruction, followed by a classification module to classify each image patch as tumor versus non-tumor. The resulting patch-based prediction results are spatially combined to generate the final segmentation result for each WSI. Additionally, the spatially organized encoded feature map derived from small image patches is used to compress the gigapixel whole-slide images. Our proposed model presents superior performance to other benchmark models with extensive experiments, suggesting its efficacy for viable tumor area segmentation with liver whole-slide images.