Fine-grained Texture Research Articles

FNContra: Frequency-domain Negative Sample Mining in Contrastive Learning for limited-data image generation

Substantial training data is necessary to train an effective generative adversarial network(GANs), without which the discriminator is easily overfitting, causing the sub-optimal models. To solve these problems, this work explores the Frequency-domain Negative Sample Mining in Contrastive learning (FNContra) to improve data efficiency, which requires the discriminator to differentiate the definite relationships between the negative samples and real images. Concretely, this work first constructs multiple-level negative samples in the frequency domain and then proposes Discriminated Wavelet-instance Contrastive Learning (DWCL) and Generated Wavelet-prototype Contrastive Learning (GWCL). The former helps the discriminator learn the fine-grained texture features, and the latter impels the generated feature distribution to be close to real. Considering the learning difficulty of multi-level negative samples, this work proposes a dynamic weight driven by self-information, which ensures the resultant force is positive from the multi-level negative samples during the training. Finally, this work performs experiments on eleven datasets with different domains and resolutions. The quantitative and qualitative results demonstrate the superiority and effectiveness of the FNContra trained on limited data, and it indicates that FNContra can synthesize high-quality images. Notably, FNContra achieves the best FID scores on 10 out of 11 datasets, with improvements of 17.90 and 29.24 on Moongate and Shells, respectively, compared to the baseline. The code can be found at https://github.com/YQX1996/FNContra.

Detection of Subarachnoid Hemorrhage Using CNN with Dynamic Factor and Wandering Strategy-Based Feature Selection.

Objectives: Subarachnoid Hemorrhage (SAH) is a serious neurological emergency case with a higher mortality rate. An automatic SAH detection is needed to expedite and improve identification, aiding timely and efficient treatment pathways. The existence of noisy and dissimilar anatomical structures in NCCT images, limited availability of labeled SAH data, and ineffective training causes the issues of irrelevant features, overfitting, and vanishing gradient issues that make SAH detection a challenging task. Methods: In this work, the water waves dynamic factor and wandering strategy-based Sand Cat Swarm Optimization, namely DWSCSO, are proposed to ensure optimum feature selection while a Parametric Rectified Linear Unit with a Stacked Convolutional Neural Network, referred to as PRSCNN, is developed for classifying grades of SAH. The DWSCSO and PRSCNN surpass current practices in SAH detection by improving feature selection and classification accuracy. DWSCSO is proposed to ensure optimum feature selection, avoiding local optima issues with higher exploration capacity and avoiding the issue of overfitting in classification. Firstly, in this work, a modified region-growing method was employed on the patient Non-Contrast Computed Tomography (NCCT) images to segment the regions affected by SAH. From the segmented regions, the wide range of patterns and irregularities, fine-grained textures and details, and complex and abstract features were extracted from pre-trained models like GoogleNet, Visual Geometry Group (VGG)-16, and ResNet50. Next, the PRSCNN was developed for classifying grades of SAH which helped to avoid the vanishing gradient issue. Results: The DWSCSO-PRSCNN obtained a maximum accuracy of 99.48%, which is significant compared with other models. The DWSCSO-PRSCNN provides an improved accuracy of 99.62% in CT dataset compared with the DL-ICH and GoogLeNet + (GLCM and LBP), ResNet-50 + (GLCM and LBP), and AlexNet + (GLCM and LBP), which confirms that DWSCSO-PRSCNN effectively reduces false positives and false negatives. Conclusions: the complexity of DWSCSO-PRSCNN was acceptable in this research, for while simpler approaches appeared preferable, they failed to address problems like overfitting and vanishing gradients. Accordingly, the DWSCSO for optimized feature selection and PRSCNN for robust classification were essential for handling these challenges and enhancing the detection in different clinical settings.

Give me a hint: an explicit prior based image denoising

The performance of an image denoising method highly depends on its ability to produce smoothed homogeneous regions and preserve fine-grained texture details in the restored image. Existing denoising methods rely on implicit learning of Convolutional Neural Networks (CNNs) to restore an image. We show that the implicitly learned representations are limited in capacity, resulting in a sub-optimal pixel estimation of homogeneous regions and loss in texture details. In this work, we argue that explicitly introducing low and high frequency information enhances the representational capacity of denoising CNNs. To this end, we propose XPrior that provides the network with two explicit priors, i.e., a Gaussian smoothed image and an Edge map. This simple yet effective integration of priors with the noisy image enhances the model’s ability to restore images with high perceived quality. The proposed approach can easily be plugged into the existing denoising methods. Comprehensive experimental results show the superiority of the proposed approach that achieves a remarkable performance gain of 1.23 dB and 1.49 dB average PSNR on BSD68 dataset over DRUNet (Zhang in IEEE Trans Pattern Anal Mach Intell 10.1109/TPAMI.2021.3088914, 2021) and DnCNN (Zhang in IEEE Trans Image Process 26:3142–3155, 2017), respectively.

When guided diffusion model meets zero-shot image super-resolution

Existing deep learning-based single-image super-resolution (SR) methods typically rely on vast quantities of paired data. As an essential solution, zero-shot SR methods require only a single image to handle image-specific degradation. However, these methods still struggle to recover fine-grained details due to the lack of supervised information. In this work, we propose a novel guided Diffusion model for Zero-shot image SR (ZeroDiff) to explicitly direct image quality enhancement. Specifically, we elaborate two key guidance strategies: (1) high-frequency guidance and (2) content-consistent guidance. The former concentrates on boosting fine-grained textures by embedding high-frequency information into the cross-attention mechanism of the noise estimator. The latter avoids the sampling deviating from the original image in terms of structure and low-frequency content. Specifically, the noisy images at each diffusion step are injected into the corresponding sampling step, encouraging the sampled image to be consistent with that of the corresponding diffusion step. Moreover, we design a progressive zoom-in paradigm by gradually enlarging the image size and enriching the image details to boost the sampling efficiency of diffusion models, while enabling high-quality image reconstruction. Extensive experiments reveal that our method achieves comparable results with other state-of-the-art methods in quantitative and qualitative evaluations on both face and natural images from synthetic and real-world datasets.

Miocene magmatism in Northern Tunisia and its geodynamic implications

The Nefza igneous rocks in Northern Tunisia belong to the Miocene magmatic belt extending from Northern Tunisia to Morocco and consist mainly of Serravallian–Tortonian granodiorite and rhyodacite (~ 14–8 Ma) and Messinian basalts (~ 8–6 Ma). Differences in geochemical composition between units have been interpreted to be the result of geodynamic processes in the upper mantle below the Western Mediterranean area, but their implications for Northern Tunisia are unclear due to limited data. In this contribution, we present an updated geodynamic model for Northern Tunisia based on new petrographic and whole-rock geochemical results from the Nefza magmatic suite from outcrop and OB45 drill core samples. Petrographic observations show that rhyodacites display a microlithic texture with quartz, plagioclase, K-feldspar, biotite, and glass, whilst granodiorite contains plagioclase, quartz and exhibits fine-grained texture with a 2–3 mm crystal size. The Nefza magmatic rocks are overprinted by multiple weathering and alteration processes with loss of ignition (LOI) ranging between 0.88 and more than 5 wt%. The linear relationships between mobile elements (Ca, Na, P, K, Mg, Si), large-ion lithophile elements (LILE), and LOI suggest element mobilisation during alteration. Major and trace element compositions show the Nefza magmatic rocks plot in the rhyolite, dacite, and trachydacite fields for felsic rocks and plot in the basalt and trachybasalt fields for mafic rocks. Granodiorite and rhyodacite rocks exhibit negative Eu anomalies and a LILE enrichment (Rb, Ba, Pb) relative to high-field-strength elements (HFSE: Nb, Ta, Hf, Zr, REE). Mafic rocks enriched in LILE show geochemical characteristics between calc-alkaline and alkaline trends. Comparison with nearby regions suggests that the generation of calc-alkaline magmas resulted from the partial melting of the lithospheric mantle due to slab break-off or tearing in Eastern Algeria. The upward flow of asthenospheric material through the widening tear in the sinking slab leads to partial melting of the mantle and shallowing of the lithosphere–asthenosphere boundary, ultimately leading to the formation of alkaline magma. The Nefza geochemical variations underscore Mediterranean upper mantle heterogeneity, offering crucial insights into Mediterranean geodynamics. More studies are needed to constrain mantle dynamics and the region’s complex geological history.

Image inpainting by bidirectional information flow on texture and structure

Image inpainting aims to recover damaged regions of a corrupted image and maintain the integrity of the structure and texture within the filled regions. Previous popular approaches have restored images with both vivid textures and structures by introducing structure priors. However, the structure prior-based approaches meet the following main challenges: (1) the fine-grained textures suffer from adverse inpainting effects because they do not fully consider the interaction between structures and textures, (2) the features of the multi-scale objects in structural and textural information cannot be extracted correctly due to the limited receptive fields in convolution operation. In this paper, we propose a texture and structure bidirectional generation network (TSBGNet) to address the above issues. We first reconstruct the texture and structure of corrupted images; then, we design a texture-enhanced-FCMSPCNN (TE-FCMSPCNN) to optimize the generated textures. We also conjoin a bidirectional information flow (BIF) module and a detail enhancement (DE) module to integrate texture and structure features globally. Additionally, we derive a multi-scale attentional feature fusion (MAFF) module to fuse multi-scale features. Experimental results demonstrate that TSBGNet effectively reconstructs realistic contents and significantly outperforms other state-of-the-art approaches on three popular datasets. Moreover, the proposed approach yields promising results on the Dunhuang Mogao Grottoes Mural dataset.

Chemical-memory of biotite crystals preserves the temperature and pressure conditions of the mixing process between trachytic and rhyolitic magmas in the Glória Sul stock, Sergipano orogenic System, Northeast Brazil

Biotite is an important constituent in the microgranular syenitic enclaves of the Glória Sul stock, located in the central region of the Sergipano Orogenic System, Northeast Brazil. These enclaves are centimeter-sized, rounded, and ellipsoidal, finer-grained than the surrounding granites. They are composed of microcline, orthoclase, albite-oligoclase, diopside, quartz, hornblende, titanite, apatite, zircon, epidote, magnetite, ilmenite, thorite, and pyrite. The textures present in the enclaves indicate mixing between magmas and rapid cooling of the trachyte magma that formed the microgranular enclaves (fine-grained texture, acicular apatite and zircon, blade-shaped biotite). The studied biotite exhibits a magmatic texture and is chemically classified as Fe- and Mg-biotite, particularly those with TiO2 > 2.3%. The chemical evolution of biotite is controlled by two substitutions (VI R2+ + 2 VI Al3+ ═ VI □ + 2 VI Si4+ and VI R2+ + VI Ti ═ 2 VIAl3+) reflecting a decrease in titanium and an increase in aluminum. The chemical data of biotite crystals indicate that they crystallized from I type magma, with calc-alkaline affinity, suggesting that the rocks of Gloria Sul stock were formed by the interaction between mantle- and crustal-derived magmas. Thermobarometry of magmatic biotite (enclaves and granites) provided crystallization temperatures between 900 and 800 °C and a depth of 36 to 13 km. The interaction between trachytic (enclave) and rhyolitic (granite) magmas in Glória Sul stock at occurred at about 26 km depth and at a temperature about 800 °C.

Prior-guided adaptive generative adversarial network method for various types of borehole image inpainting

During geophysical exploration, inpainting defective logging images caused by mismatches between logging tools and borehole sizes can affect fracture and hole identification, petrographic analysis, and stratigraphic studies. However, existing methods do not describe sufficient stratigraphic continuity. In addition, they ignore the completeness of characterization in terms of fractures, gravel structures, and fine-grained textures in the logging images. To address these issues, we develop a deep-learning method for inpainting stratigraphic features. First, to enhance the continuity of image inpainting, we build a generative adversarial network and train it on numerous natural images to extract relevant features that guide the recovery of continuity characteristics. Second, to ensure that complete structural and textural features are found in geologic formations, we introduce a feature-extraction-fusion module with a cooccurrence mechanism consisting of channel attention (CA) and self-attention (SA). CA improves texture effects by adaptively adjusting control parameters based on highly correlated prior features from electrical logging images. SA captures long-range contextual associations across preinpainted gaps to improve completeness in fractures and gravel structure representation. Our method has been tested on various borehole images demonstrating its reliability and robustness.

Mafic microgranular enclaves and magmatic fabrics in the Ediacaran granitoids of Saghro, Eastern Anti-Atlas: Insights into magma emplacement and tectonic evolution

The Saghro inlier in the Anti-Atlas belt of Morocco comprises several granitoids dating from 600 to 550 million years ago (Ma), which are overlain by a volcano-sedimentary series. In particular, the granodioritic plutons exhibit widespread enclaves, which is a tool for emplacements mode and magma interaction processus during the Ediacaran evolution of the Anti-Atlas belt. This paper presents a detailed field mapping, petrographic analysis, and deformation quantification of the mafic microgranular enclaves (MMEs) and their host granitoids to characterize the emplacement mode of the plutons and the origin of MMEs.Macroscopically, the MMEs are rounded to ellipsoidal shapes and characterized by sharp, crenulated contacts, fine-grained textures, and some of them include fragments of host rock and feldspar xenocrysts. Petrographically, the MMEs exhibit a range of compositions from gabbroic to quartz diorite, and they are characterized by the presence of acicular apatite, quartz-feldspar ocelli, poikilitic and zoned plagioclases, which are the result of mixing/mingling of mafic and felsic magmas during the genesis of MMEs. The magmatic structures and enclave's organization in Saghro granitoids indicate two styles of emplacement. The c. 600 Ma Iknioun granodiorite exhibits an S-sigmoidal structure, representative of a syntectonic emplacement model within a transpressive dextral movement along E-W shear zones. While, in the 580-560 Ma Oussilkane, Tagmout, Igoudrane, and Bou Teglimt plutons, the organization of magmatic flow and orientations of enclaves suggest that the magma was emplaced as a post-tectonic dome. The variation in emplacement mode and the decrease in deformation intensity from the c. a. 600 Ma in the Iknioun pluton to the 580-560 Ma for the others plutons indicate a progressive shift in deformation regime from transpressive during the middle Ediacaran to a transtensive regime in the late Ediacaran, highlighting the progressive transition from Pan-African/Cadomian orogeny to Cambrian rifting.

C3TB-YOLOv5: integrated YOLOv5 with transformer for object detection in high-resolution remote sensing images

ABSTRACT In the realm of object detection from high-resolution remote sensing images (HRRSIs), the existing YOLOv5 methods encounter several challenges, including dense object arrangements, small object sizes, and complex backgrounds. To tackle these challenges, we propose a novel approach called C3TB-YOLOv5, which combines traditional YOLOv5 with the Transformer model to detect objects in HRRSIs. Unlike conventional YOLOv5 methods that primarily focus on capturing local information from remote sensing scenes, our C3TB-YOLOv5 method incorporates global information through the introduction of a new C3TB module. This module, based on the Transformer multi-head attention mechanism (AM), consists of two branches that extract local and global information from feature maps. By integrating these branches and establishing long-range relationships, our method successfully detects densely arranged small objects in HRRSIs. Furthermore, to improve the accuracy of tiny object detection, a novel detection head has been developed to effectively utilize the unused C3 module, thereby preventing the loss of fine-grained textures and positional features. In addition, we integrate an enhanced SimAM, namely Sim-GMP, into the model to adjust the focus across varying regions, effectively distinguishing the features of interested objects from complex backgrounds. Finally, to address the problem of sample imbalance in remote sensing object detection, the most recent Wise-IoU v3 loss function is employed to improve the accuracy of anchor box predictions for objects. To maintain a high object detection speed, the most critical C3 modules are substituted with the proposed C3TB module for the purpose of striking a good balance between object detection accuracy and model lightweight. Extensive experiments conducted on two remote sensing datasets of NWPU VHR-10 and VisDrone 2019 demonstrates that our method achieves superior object detection performance than state-of-the-art methods.

Mineralogical and chemical characterization of an oolitic iron ore, and sustainable phosphorus removal

An oolitic iron ore from Gara Djebilet, Algeria was characterized by X-ray diffraction, scanning electron microscopy, and energy dispersive spectrosopy and the phosphorus distribution between various phases studied. Two ore types were identified - a haematite-dominated, oolitic type and a more massive, magnetite-dominated type. The haematite-dominated ore had a higher phosphorus content, up to 0.6% in the iron oxide minerals, than the magnetite-dominated type (0.3% P). Owing to the very fine-grained texture of the gangue minerals, reducing the phosphorus content to levels suitable for steelmaking (below 0.05% P) by conventiobal means would entail an energy-intensive process with a high carbon footprint. Preliminary leaching test work using a sulphurous geothermal water as lixiviant, assisted by solar thermal acceleration, gave very promising results, removing 0.13% of the residual P (or 21.7% removal of total P) from the high-phosphorus oolitic ore.

Effect of Low Viscosity Contrast between Quartz and Plagioclase on Creep Behavior of the Mid-Crustal Shear Zone

Ultramylonites are among the most extreme fault rocks that commonly occur in the mid-crustal brittle–plastic transition and are mainly characterized by intensely sheared fine-grained microstructures and well-mixed mineral phases. Although the deformation mechanism of ultramylonites is key to understanding the rheological behavior of the mid-crustal shear zone, their microstructural development is still controversial owing to their intensely fine-grained textures. To investigate the possible crustal deformation mechanisms, we studied 13 mylonites obtained from the Kashio shear zone along the Median Tectonic Line that is the largest strike-slip fault in Japan. In particular, we investigated various mixed quartz–plagioclase layers developed within tonalitic mylonite, which are representative of the common mean grain size and crystal fabric of quartz among the studied samples. A high-quality phase-orientation map obtained by electron backscattered diffraction showed not only a wide range of quartz–plagioclase mixing (10%–80% in quartz modal composition) but also revealed a correlation between grain size reduction and crystal fabric weakening in quartz, indicating a change in the deformation mechanism from dislocation creep to grain-size-sensitive creep in the mixed quartz-plagioclase layers. In contrast, plagioclase showed an almost consistent fine grain size and weak to random crystal fabrics regardless of modal composition, indicating that grain size-sensitive creep is dominant. Combined with laboratory-determined flow laws, our results show that the Kashio shear zone could have developed under deformation mechanisms in which the viscosities of quartz and plagioclase are nearly comparable, effectively within 1017–1019 Pa·s, thereby possibly enabling extensive shearing along the Median Tectonic Line.

Atomic-scale environment of niobium in ore minerals as revealed by XANES and EXAFS at the Nb K-edge

Abstract. The mineralogy of niobium (Nb) is characterized by multicomponent oxides such as AB2O6, A2B2O7, ABO4, and ABO3 in which Nb is incorporated in the B site. Such complex crystal-chemistry prevents their unambiguous identification in ore deposits such as hydrothermal rocks and laterites which exhibit complex and fine-grained textures. The understanding of the processes controlling Nb ore deposit formation in various geological settings is therefore limited, although Nb is a critical element. In this study, we use X-ray absorption spectroscopy (XAS) at the Nb K-edge to investigate the local atomic-scale structure around Nb in a large set of natural and synthetic minerals of geological and technological importance. Our X-ray absorption near-edge structure (XANES) data at the Nb K-edge show three major features of variable position and intensity and then can be related to the local distortion and coordination number of the Nb site. Shell-by-shell fits of the extended X-ray absorption fine structure (EXAFS) data reveal that the NbO6 octahedra are distorted in a variety of pyrochlore species. At least two distinct first shells of O atoms are present while reported crystallographic data yield regular octahedra in the same minerals. Next-nearest Nb–Nb distances in pyrochlore and Nb-bearing perovskite mirror a corner-sharing NbO6 network, whereas the two Nb–Nb distances in columbite are typical of edge- and corner-sharing NbO6 octahedra. Such a resolution on the Nb site geometry and the intersite relationships between the next-nearest NbO6 octahedra is made possible by collecting EXAFS data under optimal conditions at 20 K and up to 16 Å−1. The local structure around substituted Nb5+ in Fe3+, Ti4+, and Ce4+ oxides suffers major changes relative to the unsubstituted structures. The substitution of Nb5+ for Ti4+ in anatase leads to the increase in the interatomic distances between Nb and its first and second Ti4+ neighbors. The substitution of Nb5+ for Ce4+ in cerianite reduces the coordination number of the cation from eight to four, and the Nb–O bonds are shortened compared to Ce–O ones. In hematite, Nb5+ occupies a regular site, whereas the Fe3+ site is strongly distorted suggesting major site relaxation due to charge mismatch. The sensitivity of XANES and EXAFS spectroscopies at the Nb K-edge to the local site geometry and next-nearest neighbors demonstrated in this study would help decipher Nb speciation and investigate mineralogical reactions of Nb minerals in deposit-related contexts such as hydrothermal and lateritic deposits.

Serpentinization and potential Ni‐Cr mineralization of the Andong ultramafic block in South Korea

AbstractSmall‐ to medium‐sized serpentinized ultramafic blocks have been found in several locations in South Korea. Ultramafic‐hosted serpentinization, described as a major hydrothermal process that affects the lithospheric mantle, is known to play a key role in mass fluxes enhanced by multiple fluid–rock interactions that ultimately lead to the formation of hydrothermal mineralization and natural hydrogen production. In this study, we attempted to interpret the hydrothermal alteration and associated Ni‐Cr mineralization of the Andong serpentinized ultramafic block (ASUB). Based on the mineralogical and geochemical studies, the serpentinites and serpentinized ultramafic rocks of the ASUB are interpreted to be derived from mantle peridotite. It shows the dunite, lherzolite, and wehrlite compositions which are mainly composed of olivine and pyroxene. Hydrothermal alteration transformed the ultramafic rock into serpentinitic rock, resulting in changes in rock textures from the parent rock (plutonic texture) to moderately altered rock (pseudomorphic porphyritic texture) and strongly altered rock (pseudomorphic fine grained texture) with mineralogical changes. Serpentinization and Ni‐Cr mineralization do not show any relationship. Considering the reported crystallization age of the parental rock (222 Ma) and measured age (214–187 Ma) of the granites intruded into the ASUB, the source magma responsible for the final hydrothermal event including serpentinization is inferred to be the Late Triassic to Early Jurassic granitic pluton. The ASUB might have formed due to the ascent of a mantle plume along the extensional regime (i.e., rift) in the supra‐subduction zone (SSZ), rather than in ophiolite‐related mid‐oceanic ridges or abyssal environments, which are identified in many places. Ni‐Cr mineralization, with the close association of pentlandite, pyrrhotite, and Cr‐spinel, likely resulted from co‐precipitation and dissemination during the crystallization of the parent peridotitic magma derived from the mantle.

Perception-Aware Texture Similarity Prediction.

Texture similarity plays important roles in texture analysis and material recognition. However, perceptually-consistent fine-grained texture similarity prediction is still challenging. The discrepancy between the texture similarity data obtained using algorithms and human visual perception has been demonstrated. This dilemma is normally attributed to the texture representation and similarity metric utilised by the algorithms, which are inconsistent with human perception. To address this challenge, we introduce a Perception-Aware Texture Similarity Prediction Network (PATSP-Net). This network comprises a Bilinear Lateral Attention Transformer network (BiLAViT) and a novel loss function, namely, RSLoss. The BiLAViT contains a Siamese Feature Extraction Subnetwork (SFEN) and a Metric Learning Subnetwork (MLN), designed on top of the mechanisms of human perception. On the other hand, the RSLoss measures both the ranking and the scaling differences. To our knowledge, either the BiLAViT or the RSLoss has not been explored for texture similarity tasks. The PATSP-Net performs better than, or at least comparably to, its counterparts on three data sets for different fine-grained texture similarity prediction tasks. We believe that this promising result should be due to the joint utilization of the BiLAViT and RSLoss, which is able to learn the perception-aware texture representation and similarity metric.

Advancing generalizations of multi-scale GAN via adversarial perturbation augmentations

The multi-scale generative adversarial networks (MS-GANs) typically introduce a series of GANs to process hierarchical image patches from a single image, which suites image manipulation scenarios where it takes one image as input to produce manipulated results. However, during MS-GAN training, leveraging only a single image in hierarchical patches brings data insufficiency for model generalization, which limits MS-GAN to produce fine-grained texture details. To address this problem, we theoretically formulate MS-GAN generalization from the PAC-Bayes bound perspective in this work. Under this formulation, we obtain a non-vacuous upper bound of the generalization error, and propose an adversarial perturbation augmentation method named AP-Aug. Given an input image, our AP-Aug produces adversarial perturbations to augment the original image. The augmented training images benefit MS-GAN to approach the generalization upper bound. To this end, we advance the generalizations of MS-GAN to improve image generation performance. In the experiments, our AP-Aug benefits MS-GAN to achieve high quality image generation under several image manipulation scenarios including paint2image, image style transfer, and image super-resolution. The improvement shows that our AP-Aug advances the MS-GAN generalizations for high quality image generations, which perform favorably against state-of-the-art approaches.

Influence of remediation by electrokinetic on the chemical and geotechnical properties of clayey soil contaminated by copper sulfate

The enhanced electrokinetic (EK) technique is an innovative approach and increasingly used in remediation of the fine-grained texture soils contaminated with different types of contaminant. In this study, the EK is enhanced by adding an intermediate compartment and using purging solutions at the electrode’s compartments. The natural clayey soil samples were obtained from Al-Ahadab oil field and artificially contaminated with two ratios of copper sulfate (66666.67 and 26666.67 mg/kg). The feasibility of using EK technique was evaluated by the efficiency of extracting copper from soil and the magnitude of recovery in the geotechnical properties of soil. The duration of remediation was continued for about 240-250 hours depending either on the continuity of electroosmosis flow or reach a constant rate of electrical current. The removal efficiency of copper from contaminated soil samples was ranged from 98.4% to 99.6%. The EK remediation technique proved a marginal impact on the specific gravity and Atterberg’s limits, but it has a significant effect on the shear strength parameters and compressibility of soil. Furthermore, the EK technique can be considered an efficient method for removing the low and high concentrations of copper sulfate from clayey soil of low permeability.

Comparative Grain Size Analysis of Modern Flood Sediments Based on Graphic and Moment Methods in the Lower Yellow River (Huang He), China

Grain size analysis of flood sediments is a key method for understanding the sedimentary environments of rivers worldwide; however, there is limited knowledge of how to effectively reflect the sedimentary environment of lower Yellow River (Huang He) flood events using grain size parameters. In this study, two widely used grain size analysis methods, the graphic method (GM) and moment method (MM), were compared, and their applicability to flood sediment analysis in the lower Yellow River was evaluated. Modern flood sediments (n = 143) in the lower Yellow River featured a fine-grained texture and were classified as silty sand (4.95 ≤ Φ ≤ 5.03) characterized by an inadequate sorting ability. The grain size distribution patterns obtained using the GM and MM revealed positive and extremely positive deviations with sharp and flat peaks, respectively. A strong correlation (0.6966 ≤ R2 ≤ 0.9961) was observed between the mean grain size and the sorting coefficient obtained using the GM and MM. Thus, both methods were deemed suitable and could be used interchangeably. Our results indicate that the MM should be applied to assess skewness because it provided comprehensive information regarding flood sediments in the lower Yellow River, whereas the GM is recommended for kurtosis analysis, as it highlighted the primary sedimentary dynamics during flood events. Methods must be selected based on the sedimentary environment when analyzing grain size parameters.

A Decoupled Semantic–Detail Learning Network for Remote Sensing Object Detection in Complex Backgrounds

Detecting multi-scale objects in complex backgrounds is a crucial challenge in remote sensing. The main challenge is that the localization and identification of objects in complex backgrounds can be inaccurate. To address this issue, a decoupled semantic–detail learning network (DSDL-Net) was proposed. Our proposed approach comprises two components. Firstly, we introduce a multi-receptive field feature fusion and detail mining (MRF-DM) module, which learns higher semantic-level representations by fusing multi-scale receptive fields. Subsequently, it uses multi-scale pooling to preserve detail texture information at different scales. Secondly, we present an adaptive cross-level semantic–detail fusion (CSDF) network that leverages a feature pyramid with fusion between detailed features extracted from the backbone network and high-level semantic features obtained from the topmost layer of the pyramid. The fusion is accomplished through two rounds of parallel global–local contextual feature extraction, with shared learning for global context information between the two rounds. Furthermore, to effectively enhance fine-grained texture features conducive to object localization and features conducive to object semantic recognition, we adopt and improve two enhancement modules with attention mechanisms, making them simpler and more lightweight. Our experimental results demonstrate that our approach outperforms 12 benchmark models on three publicly available remote sensing datasets (DIOR, HRRSD, and RSOD) regarding average precision (AP) at small, medium, and large scales. On the DIOR dataset, our model achieved a 2.19% improvement in mAP@0.5 compared to the baseline model, with a parameter reduction of 14.07%.

Aggregated Contextual Transformations for High-Resolution Image Inpainting.

Image inpainting that completes large free-form missing regions in images is a promising yet challenging task. State-of-the-art approaches have achieved significant progress by taking advantage of generative adversarial networks (GAN). However, these approaches can suffer from generating distorted structures and blurry textures in high-resolution images (e.g., 512×512). The challenges mainly drive from (1) image content reasoning from distant contexts, and (2) fine-grained texture synthesis for a large missing region. To overcome these two challenges, we propose an enhanced GAN-based model, named Aggregated COntextual-Transformation GAN (AOT-GAN), for high-resolution image inpainting. Specifically, to enhance context reasoning, we construct the generator of AOT-GAN by stacking multiple layers of a proposed AOT block. The AOT blocks aggregate contextual transformations from various receptive fields, allowing to capture both informative distant image contexts and rich patterns of interest for context reasoning. For improving texture synthesis, we enhance the discriminator of AOT-GAN by training it with a tailored mask-prediction task. Such a training objective forces the discriminator to distinguish the detailed appearances of real and synthesized patches, and in turn facilitates the generator to synthesize clear textures. Extensive comparisons on Places2, the most challenging benchmark with 1.8 million high-resolution images of 365 complex scenes, show that our model outperforms the state-of-the-art. A user study including more than 30 subjects further validates the superiority of AOT-GAN. We further evaluate the proposed AOT-GAN in practical applications, e.g., logo removal, face editing, and object removal. Results show that our model achieves promising completions in the real world. We release codes and models in https://github.com/researchmm/AOT-GAN-for-Inpainting.