Low Resolution Research Articles

Resolution Enhancement of Metabolomic J-Res NMR Spectra Using Deep Learning.

J-Resolved (J-Res) nuclear magnetic resonance (NMR) spectroscopy is pivotal in NMR-based metabolomics, but practitioners face a choice between time-consuming high-resolution (HR) experiments or shorter low-resolution (LR) experiments which exhibit significant peak overlap. Deep learning neural networks have been successfully used in many fields to enhance quality of natural images, especially with regard to resolution, and therefore offer the prospect of improving two-dimensional (2D) NMR data. Here, we introduce the J-RESRGAN, an adapted and modified generative adversarial network (GAN) for image super-resolution (SR), which we trained specifically for metabolomic J-Res spectra to enhance peak resolution. A novel symmetric loss function was introduced, exploiting the inherent vertical symmetry of J-Res NMR spectra. Model training used simulated high-resolution J-Res spectra of complex mixtures, with corresponding low-resolution spectra generated via blurring and down-sampling. Evaluation of peak pair resolvability on J-RESRGAN demonstrated remarkable improvement in resolution across a variety of samples. In simulated plasma data, 100% of peak pairs exhibited enhanced resolution in super-resolution spectra compared to their low-resolution counterparts. Similarly, enhanced resolution was observed in 80.8-100% of peak pairs in experimental plasma, 85.0-96.7% in urine, 94.4-98.9% in full fat milk, and 82.6-91.7% in orange juice. J-RESRGAN is not sample type, spectrometer or field strength dependent and improvements on previously acquired data can be seen in seconds on a standard desktop computer. We believe this demonstrates the promise of deep learning methods to enhance NMR metabolomic data, and in particular, the power of J-RESRGAN to elucidate overlapping peaks, advancing precision in a wide variety of NMR-based metabolomics studies. The model, J-RESRGAN, is openly accessible for download on GitHub at https://github.com/yanyan5420/J-RESRGAN.

An MS-TCN based spatiotemporal model with three-axis tactile for enhancing flexible printed circuit assembly

Purpose Current flexible printed circuit (FPC) assembly relies heavily on manual labor, limiting capacity and increasing costs. Small FPC size makes automation challenging as terminals can be visually occluded. The purpose of this study is to use 3D tactile sensing to mimic human manual mating skills for enabling sensing offset between FPC terminals (FPC-t) and FPC mating slots (FPC-s) under visual occlusion. Design/methodology/approach The proposed model has three stages: spatial encoding, offset estimation and action strategy. The spatial encoder maps sparse 3D tactile data into a compact 1D feature capturing valid spatial assembly information to enable temporal processing. To compensate for low sensor resolution, consecutive spatial features are input to a multistage temporal convolutional network which estimates alignment offsets. The robot then performs alignment or mating actions based on the estimated offsets. Findings Experiments are conducted on a Redmi Note 4 smartphone assembly platform. Compared to other models, the proposed approach achieves superior offset estimation. Within limited trials, it successfully assembles FPCs under visual occlusion using three-axis tactile sensing. Originality/value A spatial encoder is designed to encode three-axis tactile data into feature maps, overcoming multistage temporal convolution network’s (MS-TCN) inability to directly process such input. Modifying the output to estimate assembly offsets with related motion semantics overcame MS-TCN’s segmentation points output, unable to meet assembly monitoring needs. Training and testing the improved MS-TCN on an FPC data set demonstrated accurate monitoring of the full process. An assembly platform verified performance on automated FPC assembly.

Magnetic nanomaterials mediate precise magnetic therapy.

Magnetic nanoparticle (MNP)-mediated precision magnet therapy plays a crucial role in treating various diseases. This therapeutic strategy compensates for the limitations of low spatial resolution and low focusing of magnetic stimulation, and realizes the goal of wireless teletherapy with precise targeting of focal areas. This paper summarizes the preparation methods of magnetic nanomaterials, the properties of magnetic nanoparticles, the biological effects, and the measurement methods for detecting magnetism; discusses the research progress of precision magnetotherapy in the treatment of psychiatric disorders, neurological injuries, metabolic disorders, and bone-related disorders, and looks forward to the future development trend of precision magnet therapy.&#xD.

Data extension of high-resolution wind speed database by fusing meteorological observation and local objective analysis data with POD–LSE

Newly generated high-resolution meteorological reanalysis data have been published over the past few years on short records. Producing high-resolution data in long-term time scales is challenging due to high computational costs and complex weather models. In contrast, urban meteorological observations have been continuously recorded for decades, although at a low spatial resolution. This study proposes a data fusion method using Proper Orthogonal Decomposition (POD) and Linear Stochastic Estimation (LSE). It fuses meteorological observations and high spatial resolution local objective analysis (LA) data to reproduce a high-resolution and long-term fusion database for urban areas without observations. First, the accuracy of LA data was verified by comparison with meteorological observations. Subsequently, the accuracy of the generated fusion data was investigated by comparison with Doppler lidar observations. Finally, the performance of single- and multi-time LSE in data fusion is discussed. These results indicate that the proposed method generates high-resolution and long-term fusion wind speed data that are similar to the Doppler lidar observations. In addition, the fusion model built using hourly data can accurately generate a highly sampled database at 10-min intervals. The single-time LSE method is recommended to be applied over the multi-time delay method for data fusion.

DiffPlate: A Diffusion Model for Super-Resolution of License Plate Images

License plate recognition is a pivotal challenge in surveillance applications, predominantly due to the low resolution and diminutive size of license plates, which impairs recognition accuracy. The advent of AI-based super-resolution techniques offers a promising avenue to ameliorate the resolution of such images. Despite the deployment of various super-resolution methodologies, including Convolutional Neural Networks (CNNs) and Generative Adversarial Networks (GANs), the quest for satisfactory outcomes in license plate image enhancement persists. This paper introduces “DiffPlate”, a novel Diffusion Model specifically tailored for license plate super-resolution. Leveraging the unprecedented capabilities of Diffusion Models in image generation, DiffPlate is meticulously trained on a dataset comprising low-resolution and high-resolution pairs of Saudi license plates, curated for our surveillance application. Our empirical analysis substantiates that DiffPlate markedly eclipses state-of-the-art alternatives such as SwinIR and ESRGAN, evidencing a 26.47% and 37.32% enhancement in Peak Signal-to-Noise Ratio (PSNR) against these benchmarks, respectively. Furthermore, DiffPlate achieves superior performance in terms of Structural Similarity Index (SSIM), with a 4.88% and 16.21% improvement over SwinIR and ESRGAN, respectively. Human evaluative studies further corroborate that images refined by DiffPlate were preferred 92% more frequently compared to those processed by other algorithms. Through DiffPlate, we present a new solution to the license plate super-resolution challenge, demonstrating significant potential for adoption in real-world surveillance systems.

Fusion of multi-resolution data for estimating speed-density relationships

Estimating traffic flow models, such as speed-density relationships, using data from multiple sources with different temporal resolutions is a prevalent challenge encountered in real-world scenarios. The resolution incompatibility is often intuitively addressed by averaging the high-resolution (HR) data to synchronize with the low-resolution (LR) data. This paper shows that ignoring the variability of HR data within the LR interval during the averaging process could lead to systematic data point distortions, resulting in biased model estimations. The average absolute biases of models estimated from the average data increase with the lost variability of HR data within the LR intervals. Subsequently, it proves that for any given complete average data dataset, there must exist an optimal dataset that minimizes the average absolute bias in model estimations introduced by the averaging process. A novel procedure for determining the practical optimal dataset is proposed. To test the proposed method, real-world HR data from four sites in Hong Kong and Nanjing, China were collected to mimic situations with multi-resolution data. Results demonstrated that the proposed method can significantly reduce the average absolute biases of models estimated from the determined practical optimal dataset, as compared to models estimated from the complete average dataset.

Frequency-hopping along with resolution-turning for fast and enhanced reconstruction in ultrasound tomography

The distorted Born iterative (DBI) method is considered to obtain images with high-contrast and resolution. Besides satisfying the Born approximation condition, the frequency-hopping (FH) technique is necessary to gradually update the sound contrast from the first iteration and progress to the actual sound contrast of the imaged object in subsequent iterations. Inspired by the fact that the higher the frequency, the higher the resolution. Because low-frequency allows for low-resolution object imaging, hence for high-resolution imaging requirements, using low-frequency to possess a high-resolution image from the first iteration will be less efficient. For an effective reconstruction, the object’s resolution at low frequencies should be small. And similarly, with high frequencies, the object resolution should be larger. Therefore, in this paper, the FH, and the resolution-turning (RT) technique are proposed to obtain object images with high-contrast and -resolution. The convergence speed in the initial iterations is rapidly achieved by utilizing low frequency in the frequency-turning technique and low image resolution in the resolution-turning technique. It is crucial to ensure accurate object reconstruction for subsequent iterations. The desired spatial resolution is attained by employing high frequency and large image resolution. The resolution-turning distorted Born iterative (RT-DBI) and frequency-hopping distorted Born iterative (FH-DBI) solutions are thoroughly investigated to exploit their best performance. This makes sense because if it is not good to choose the number of iterations for the frequency f1 in FH-DBI and for the resolution of N1 × N1 in RT-DBI, then these solutions give even worse quality than traditional DBI. After that, the RT-FH-DBI integration was investigated in two sub-solutions. We found that the lower frequency f1 used both before and after the RT would get the best performance. Consequently, compared to the traditional DBI approaches, the normalized error and total runtime for the reconstruction process were dramatically decreased, at 83.6% and 18.6%, respectively. Besides fast and quality imaging, the proposed solution RT-FH-DBI is promised to produce high-contrast and high-resolution object images, aiming at object reconstruction at the biological tissue. The development of 3D imaging and experimental verification will be studied further.

Simple and low-cost microscopy setup for 3D particle field measurement using incoherent illumination and open-source hardware.

The quantification of 3D particle field is of interest for a vast range of fields. While in-line particle holography (PH) can provide high-resolution measurements of particles, it suffers from speckle noise. Plenoptic imaging (PI) is less susceptible to speckle noises, but it involves a trade-off between spatial and angular resolution, rendering images with low resolution. Here, we report a simple microscopy setup with the goals of getting the strengths of both techniques. It is built with off-the-shelf and cost-effective components including a photographic lens, a diaphragm, and a CCD camera. The cost of the microscopy setup is affordable to small labs and individual researchers. The pupil plane of the proposed setup can be mechanically accessible, allowing us to implement pupil plane modulation and increase the depth of field (DOF) without requiring any additional relay lenses. It also allows us to understand the working principle of pupil plane modulation clearly, benefiting microscopy education. It illuminates the sample (particles) using diffuse white light, and thus avoids the problem of speckle noise. It captures multiple perspective images via pupil plane modulation, without requiring trading off angular and spatial resolution. We validate the setup with 2D and 3D particle samples. RESEARCH HIGHLIGHTS: We report a simple and cost-effective microscopy setup with the goals of getting the strengths of plenoptic imaging and in-line particle holography. It is built with off-the-shelf and cost-effective components. The cost of the microscopy setup is affordable to small labs and individual researchers. The pupil plane of the proposed setup can be mechanically accessible, allowing us to implement pupil plane modulation and increase the DOF without requiring any additional relay lenses. It also allows us to understand the working principle of pupil plane modulation clearly, benefiting microscopy education. It illuminates the sample (particles) using diffuse white light, and thus avoids the problem of speckle noise. It captures multiple perspective images via pupil plane modulation, without requiring trading off angular and spatial resolution. We validate the setup with 2D and 3D particle samples.

Spatiotemporal alterations in the brain oscillations of Arctic explorers

BackgroundThe limited understanding of the physiology and psychology of polar expedition explorers has prompted concern over the potential cognitive impairments caused by exposure to extreme environmental conditions. Prior research has demonstrated that such stressors can negatively impact cognitive function, sleep quality, and behavioral outcomes. Nevertheless, the impact of the polar environment on neuronal activity remains largely unknown. MethodsIn this study, we aimed to investigate spatiotemporal alterations in brain oscillations of 13 individuals (age range: 22 - 48 years) who participated in an Arctic expedition. We utilized electroencephalography (EEG) to record cortical activity before and during the Arctic journey, and employed standardized low resolution brain electromagnetic tomography to localize changes in alpha, beta, theta, and gamma activity. ResultsOur results reveal a significant increase in the power of theta oscillations in specific regions of the Arctic, which differed significantly from pre-expedition measurements. Furthermore, microstate analysis demonstrated a significant reduction in the duration of microstates (MS) D and alterations in the local synchrony of the frontoparietal network. ConclusionOverall, these findings provide novel insights into the neural mechanisms underlying adaptation to extreme environments. These findings have implications for understanding the cognitive consequences of polar exploration and may inform strategies to mitigate potential neurological risks associated with such endeavors. Further research is warranted to elucidate the long-term effects of Arctic exposure on brain function.

P-279 Significant increased isolation of escherichia coli in Iranian women with endometriosis: a case control – study

Abstract Study question Considering the role of bacterial infection in causing endometriosis, we decided to compare the cultures of endometriosis-affected women a in this study Summary answer Considering the possible role of E. coli in the progression and/or recurrence of endometriosis and also infertility What is known already (5). Due to the finding of endotoxin of E. coli species in the peritoneal cavity and menstrual fluid of endometriosis patients, infection with this bacterium has recently been proposed as an effective factor in the occurrence and growth of endometriosis lesions. Study design, size, duration This prospective case-control study was carried out in the Women’s Department of Shiraz University of Medical Sciences in collaboration with the Bacteriology and Virology Department between 60 participants. Participants/materials, setting, methods 30 women with endometriosis in stages 3 and 4 of the disease, and 30 women without endometriosis who were candidates for surgery due to benign uterine diseases, underwent endometrial biopsy with Novak Kort in sterile conditions before starting their operation, and the results of their endometrial culture were analyzed and compared in terms of the presence of Enterobacter spp., Klebsiella spp., and E. coli species. Main results and the role of chance Based on the comparison between the two groups, only E. coli species had a significant association with the presence of endometriosis (P = 0.001). There was no significant relationship between the location of endometriosis in the pelvic cavity and culture results. Parity among the E. coli negative group was significantly higher compared to the E. coli positive group (P < 0.001). Limitations, reasons for caution Lack of sample trail for repeat testing and antibiotic susceptibility testing, low taxonomical resolution, and costly laboratory setup and maintenance are other limitations of this technology Wider implications of the findings we suggest that in women who have endometriosis and recurrent IVF failure and also in cases of endometriosis recurrence after surgical treatment, treatment of couples with appropriate antibiotics and repeated culture along with subsequent antibiotic susceptibility testing until their culture becomes negative could be beneficial. Trial registration number IR.SUMS.MED.REC.1400.097

A Cross-Resolution Surface Net Radiative Inversion Based on Transfer Learning Methods

Net radiation (Rn) is a key component of the Earth’s energy balance. With the rise of deep learning technology, remote sensing technology has made significant progress in the acquisition of large-scale surface parameters. However, the generally low spatial resolution of net radiation data and the relative scarcity of surface flux site data at home and abroad limit the potential of deep learning methods in constructing high spatial resolution net radiation models. To address this challenge, this study proposes an innovative approach of a multi-scale transfer learning framework, which assumes that composite models at different spatial scales are similar in structure and parameters, thus enabling the training of accurate high-resolution models using fewer samples. In this study, the Heihe River Basin was taken as the study area and the Rn products of the Global Land Surface Satellite (GLASS) were selected as the target for coarse model training. Based on the dense convolutional network (DenseNet) architecture, 25 deep learning models were constructed to learn the spatial and temporal distribution patterns of GLASS Rn products by combining multi-source data, and a 5 km coarse resolution net radiation model was trained. Subsequently, the parameters of the pre-trained coarse-resolution model were fine-tuned with a small amount of measured ground station data to achieve the transfer from the 5 km coarse-resolution model to the 1 km high-resolution model, and a daily high-resolution net radiation model with 1 km resolution for the Heihe River Basin was finally constructed. The results showed that the bias, R2, and RMSE of the high-resolution net radiation model obtained by transfer learning were 0.184 W/m2, 0.924, and 24.29 W/m2, respectively, which was better than those of the GLASS Rn products. The predicted values were highly correlated with the measured values at the stations and the fitted curves were closer to the measured values at the stations than those of the GLASS Rn products, which further demonstrated that the transfer learning method could capture the soil moisture and temporal variation of net radiation. Finally, the model was used to generate 1 km daily net radiation products for the Heihe River Basin in 2020. This study provides new perspectives and methods for future large-scale and long-time-series estimations of surface net radiation.

O-260 Identifying seminiferous tubules for sperm retrieval during microdissection testicular sperm extraction (M-TESE) using deep learning

Abstract Study question Is it possible to utilize artificial intelligence (AI) in the selection of seminiferous tubules for sperm retrieval during microdissection testicular sperm extraction (M-TESE)? Summary answer AI algorithm was able to segment seminiferous tubules deemed to be good candidates for sperm retrieval with IoU of 0.746 and F1 score of 72.5%. What is known already M-TESE is an advanced surgical procedure reserved for sperm retrieval in men with non-obstructive azoospermia (NOA). Meta-analysis have shown M-TESE might be superior in relation to sperm retrieval rates and postsurgical complications when compared to conventional techniques. Limitations of the technique are the relatively long learning curve for the surgeons and the longer intraoperative time required to identify the tubules with active spermatogenesis. Convolutional neural networks (CNNs) have been shown to successfully identify areas of interest in medical images such as CT and MRI scans. The possibility of utilizing trained CNNs in M-TESE procedures has so far not been studied. Study design, size, duration This is a cross sectional study analyzing image data gathered during M-TESE procedures including the first five men enrolled in a prospective study designed specifically to test the utilization of AI in the treatment of NOA. All participants signed written informed consent. Images were collected intraoperatively with low and high resolution cameras according to predefined protocol. Participants/materials, setting, methods CNN model with down and upsampling architecture was trained using patch-based technique with corresponding labelled truth image pairs based on combination of semi-automated hue saturation value thresholding and manual segmentation of seminiferous tubules. Tubules were allocated into two different classes by the operating surgeon according to the visual perception of their morphology as type 1 (i.e. larger, opaque, good candidates for micro dissection) and type 2 (i.e. sclerotic or atrophic; unlikely to harbor active spermatogenesis). Main results and the role of chance CNN models were trained on 1809 patches with corresponding ground truth segmented images. Two algorithms were tested: the first was trained solely to detect and semantically distinguish type 1 seminiferous tubules. The second was trained to semantically segment the major anatomical structures: tunica albuginea, testicular parenchyma, blood vessels; lobules and the two types of seminiferous tubules describe above. Validation was performed on 988 image patches not previously shown to the algorithm. After grid search for optimal learning rate and augmentation the first algorithm was able to segment type 1 tubules with F1 score of 72.5% and Jaccard Index (IoU) of 0.746. Training took 856 minutes on 48 core high performance computer (HPC) equipped with single graphics processing unit (GPU). Same computational environment was used in the training of the second algorithm. This model was able to segment anatomical structures such as parenchyma (IoU=0.732) and testicular lobules (IoU=0.683) but performed sub optimally on the clinically relevant type 1 tubules (IoU=0.432). The first trained algorithm was able to segment a single high resolution surgical image in 3.4 seconds on an HPC. However, the same procedure took 5.5 minutes on standard desktop computer with 8 core Intel processor without GPU. Limitations, reasons for caution The number of patients is relatively small and therefore more training data would be needed to achieve robust performance. Training data were labelled by single surgeon limiting the generalizability and possibly biasing the selection process. The need of HPC environment for real time segmentation can limit the clinical use. Wider implications of the findings This pilot study shows the potential of AI to help in choosing suitable tubules for micro dissection, shortening the learning curve for young andrological surgeons. The access to cluster based computation is getting easier by the day and can soon allow instant intraoperative AI segmentation, thus shortening the surgical procedure. Trial registration number NA

Attention Guide Axial Sharing Mixed Attention (AGASMA) Network for Cloud Segmentation and Cloud Shadow Segmentation

Segmenting clouds and their shadows is a critical challenge in remote sensing image processing. The shape, texture, lighting conditions, and background of clouds and their shadows impact the effectiveness of cloud detection. Currently, architectures that maintain high resolution throughout the entire information-extraction process are rapidly emerging. This parallel architecture, combining high and low resolutions, produces detailed high-resolution representations, enhancing segmentation prediction accuracy. This paper continues the parallel architecture of high and low resolution. When handling high- and low-resolution images, this paper employs a hybrid approach combining the Transformer and CNN models. This method facilitates interaction between the two models, enabling the extraction of both semantic and spatial details from the images. To address the challenge of inadequate fusion and significant information loss between high- and low-resolution images, this paper introduces a method based on ASMA (Axial Sharing Mixed Attention). This approach establishes pixel-level dependencies between high-resolution and low-resolution images, aiming to enhance the efficiency of image fusion. In addition, to enhance the effective focus on critical information in remote sensing images, the AGM (Attention Guide Module) is introduced, to integrate attention elements from original features into ASMA, to alleviate the problem of insufficient channel modeling of the self-attention mechanism. Our experimental results on the Cloud and Cloud Shadow dataset, the SPARCS dataset, and the CSWV dataset demonstrate the effectiveness of our method, surpassing the state-of-the-art techniques for cloud and cloud shadow segmentation.

Enhancing Spatial Resolution in Tandem Mass Spectrometry Ion/Ion Reaction Imaging Experiments through Image Fusion.

We have recently developed a charge inversion ion/ion reaction to selectively derivatize phosphatidylserine lipids via gas-phase Schiff base formation. This tandem mass spectrometry (MS/MS) workflow enables the separation and detection of isobaric lipids in imaging mass spectrometry, but the images acquired using this workflow are limited to relatively poor spatial resolutions due to the current time and limit of detection requirements for these ion/ion reaction imaging mass spectrometry experiments. This trade-off between chemical specificity and spatial resolution can be overcome by using computational image fusion, which combines complementary information from multiple images. Herein, we demonstrate a proof-of-concept workflow that fuses a low spatial resolution (i.e., 125 μm) ion/ion reaction product ion image with higher spatial resolution (i.e., 25 μm) ion images from a full scan experiment performed using the same tissue section, which results in a predicted ion/ion reaction product ion image with a 5-fold improvement in spatial resolution. Linear regression, random forest regression, and two-dimensional convolutional neural network (2-D CNN) predictive models were tested for this workflow. Linear regression and 2D CNN models proved optimal for predicted ion/ion images of PS 40:6 and SHexCer d38:1, respectively.

ReLAP-Net: Residual Learning and Attention Based Parallel Network for Hyperspectral and Multispectral Image Fusion

Remote sensing applications require high-resolution images to obtain precise information about the Earth???s surface. Multispectral images have high spatial resolution but low spectral resolution. Hyperspectral images have high spectral resolution but low spatial resolution. This study proposes a residual learning and attention-based parallel network based on residual network and channel attention. The network performs image fusion of a high spatial resolution multispectral image and a low spatial resolution hyperspectral image. The network training and fusion experiments are conducted on four public benchmark data sets to show the effectiveness of the proposed model. The fusion performance is compared with classical signal processing???based image fusion techniques. Four image metrics are used for the quantitative evaluation of the fused images. The proposed network improved fusion ability by reducing the root mean square error and relative dimensionless global error in synthesis and increased the peak signal-to-noise ratio when compared to other state-of-the-art models.

Cross-correlation-based convolutional neural network with velocity regularization for high-resolution velocimetry of particle images

Particle image velocimetry (PIV) stands as a pivotal experimental technique in fluid dynamics, enabling the visualization and analysis of fluid flows. Traditional methods for extracting velocity fields from particle images often rely on window-cross correlation PIV or, more recently, optical flow techniques rooted in intensity conservation principles. However, the former approach suffers from low resolution, whereas the latter is hampered by computational inefficiency and a high susceptibility to noise. Recent studies have demonstrated the effectiveness of convolutional neural networks (CNNs) in processing particle images to obtain high-resolution and high-accuracy velocity fields, though traditional CNN architectures are still not satisfying in accuracy. The present study introduces an enhanced network, En-FlowNetC, based on the cross correlation-based CNN FlowNetC, specifically designed to process PIV particle images and achieve high-accuracy, high-resolution velocity fields. It incorporates a velocity regularization and is trained and validated on canonical datasets. The results indicate that En-FlowNetC surpasses traditional CNN networks in accuracy and markedly outperforms the classic Horn–Schunck optical flow method in both complex and simple flow scenarios. Furthermore, this study confirms the beneficial impact of velocity regularization, when judiciously applied, on network accuracy. The proposed modifications compared to the original FlowNetC are also examined in the ablation experiments. Overall, En-FlowNetC provides an effective deep-learning solution for PIV analysis, paving the way for future endeavors aimed at achieving highly accurate and resolved velocimetry.

SeisResoDiff: Seismic resolution enhancement based on a diffusion model

High resolution of post-stack seismic data assists in better interpretation of subsurface structures as well as high accuracy of impedance inversion. Therefore, geophysicists consistently strive to acquire higher resolution seismic images in petroleum exploration. Although there have been successful applications of conventional signal processing and machine learning for post-stack seismic resolution enhancement, there is limited reference to the seismic applications of the recent emergence and rapid development of generative artificial intelligence. Hence, we propose to apply diffusion models, among the most popular generative models, to enhance seismic resolution. Specifically, we apply the classic diffusion model — denoising diffusion probabilistic model (DDPM), conditioned on the seismic data in low resolution, to reconstruct corresponding high-resolution images. Herein the entire scheme is referred to as SeisResoDiff. To provide a comprehensive and clear understanding of SeisResoDiff, we introduce the basic theories of diffusion models and detail the optimization objective’s derivation with the aid of diagrams and algorithms. For implementation, we first propose a practical workflow to acquire abundant training data based on the generated pseudo-wells. Subsequently, we apply the trained model to both synthetic and field datasets, evaluating the results in three aspects: the appearance of seismic sections and slices in the time domain, frequency spectra, and comparisons with the synthetic data using real well-logging data at the well locations. The results demonstrate not only effective seismic resolution enhancement, but also additional denoising by the diffusion model. Experimental comparisons indicate that training the model on noisy data, which are more realistic, outperforms training on clean data. The proposed scheme demonstrates superiority over some conventional methods in high-resolution reconstruction and denoising ability, yielding more competitive results compared to our previous research.

Impacts of Moisture Advection Scheme on Precipitation in the Steep Topography Region between the Tibetan Plateau and the Sichuan Basin

Abstract Water vapor transport is a crucial process in modeling and can contribute to errors in precipitation forecasts. To investigate the sensitivity of precipitation to the moisture advection scheme, this study introduced the two-step shape-preserving advection scheme (TSPAS), which has been proven to improve precipitation simulation over steep topography at lower resolutions, into the Southwest Center Weather Research and Forecast (WRF)-based Intelligent Numerical Grid Forecast System (SWC-WINGS) at a convection-permitting resolution. According to experiments conducted throughout the summer of 2021, the precipitation over the eastern slope of the Tibetan Plateau (TP) is highly sensitive to the moisture advection scheme. TSPAS successfully improved precipitation over the eastern slope of the TP, especially for torrential rainfall. The fractions skill score (FSS) is improved by 0.075 (27.78%) for daily precipitation with a threshold of 100 mm. Compared with the experiment with the original WRF advection scheme, the TSPAS reduced the overestimation of precipitation in the topographic region and excessive water vapor transport in a low-level atmosphere. To understand the precipitation improvement contributed by the advection scheme, additional experiments were conducted for a particular precipitation process from two approaches: switching advection schemes during the rainfall evolution and updating the variables related to moisture advection individually. Results demonstrate that the precipitation improvement is mainly contributed by the moisture advection scheme before the precipitation. Among the different variables, the combination of wind and water vapor was the most influential factor causing the precipitation improvement under the TSPAS.

Self-Supervised Deep Blind Video Super-Resolution.

Existing deep learning-based video super-resolution (SR) methods usually depend on the supervised learning approach, where the training data is usually generated by the blurring operation with known or predefined kernels (e.g., Bicubic kernel) followed by a decimation operation. However, this does not hold for real applications as the degradation process is complex and cannot be approximated by these idea cases well. Moreover, obtaining high-resolution (HR) videos and the corresponding low-resolution (LR) ones in real-world scenarios is difficult. To overcome these problems, we propose a self-supervised learning method to solve the blind video SR problem, which simultaneously estimates blur kernels and HR videos from the LR videos. As directly using LR videos as supervision usually leads to trivial solutions, we develop a simple and effective method to generate auxiliary paired data from original LR videos according to the image formation of video SR, so that the networks can be better constrained by the generated paired data for both blur kernel estimation and latent HR video restoration. In addition, we introduce an optical flow estimation module to exploit the information from adjacent frames for HR video restoration. Experiments show that our method performs favorably against state-of-the-art ones on benchmarks and real-world videos.

TSUDepth: Exploring temporal symmetry-based uncertainty for unsupervised monocular depth estimation

When faced with occlusions and non-rigid motions, machines often struggle with depth estimation, a task effortlessly performed by humans with just one eye. Continuous RGB images embody rich temporal features, such as symmetry and optical flow, which current deep-learning models fail to effectively leverage. In response to this limitation, we introduce an innovative framework known as Temporal Symmetry-based Uncertainty (TSU)-Depth, aimed at enhancing the accuracy of unsupervised monocular depth estimation. The Temporal Symmetry-based Occlusion Optimization (TSOO) component plays a pivotal role in robustly identifying occluded regions and comparable optimization across adjacent frames. Simultaneously, we propose Temporal Optical Flow Masking (TOFM) to effectively identify and exclude static pixels (such as out-of-range depths and non-rigid objects) between adjacent frames. Additionally, we introduce Cross-Resolution Distillation (CRED) to enhance depth estimation accuracy across various resolutions, especially in low input resolution scenarios. Furthermore, we designed a new depth estimation structure utilizing the DPT structure and incorporating a GRU module to enhance performance details. Through extensive experiments on benchmark datasets, including KITTI, Cityscapes, and Make3D, our TSUDepth framework has consistently demonstrated state-of-the-art performance. Code is available at https://github.com/BlueEg/TSUDepth/.