Deep learning algorithm-enabled sediment characterization techniques to determination of water saturation for tight gas carbonate reservoirs in Bohai Bay Basin, China.

Understanding water saturation levels in tight gas carbonate reservoirs is vital for optimizing hydrocarbon production and mitigating challenges such as reduced permeability due to water saturation (Sw) and pore throat blockages, given its critical role in managing capillary pressure in water drive mechanisms reservoirs. Traditional sediment characterization methods such as core analysis, are often costly, invasive, and lack comprehensive spatial information. In recent years, several classical machine learning models have been developed to address these shortcomings. Traditional machine learning methods utilized in reservoir characterization encounter various challenges, including the ability to capture intricate relationships, potential overfitting, and handling extensive, multi-dimensional datasets. Moreover, these methods often face difficulties in dealing with temporal dependencies and subtle patterns within geological formations, particularly evident in heterogeneous carbonate reservoirs. Consequently, despite technological advancements, enhancing the reliability, interpretability, and applicability of predictive models remains imperative for effectively characterizing tight gas carbonate reservoirs. This study employs a novel data-driven strategy to prediction of water saturation in tight gas reservoir powered by three recurrent neural network type deep/shallow learning algorithms-Gated Recurrent Unit (GRU), Recurrent Neural Networks (RNN), Long Short-Term Memory (LSTM), Support Vector Machine (SVM), K-nearest neighbor (KNN) and Decision tree (DT)-customized to accurately forecast sequential sedimentary structure data. These models, optimized using Adam's optimizer algorithm, demonstrated impressive performance in predicting water saturation levels using conventional petrophysical data. Particularly, the GRU model stood out, achieving remarkable accuracy (an R-squared value of 0.9973) with minimal errors (RMSE of 0.0198) compared to LSTM, RNN, SVM, KNN and, DT algorithms, thus showcasing its proficiency in processing extensive datasets and effectively identifying patterns. By achieving unprecedented accuracy levels, this study not only enhances the understanding of sediment properties and fluid saturation dynamics but also offers practical implications for reservoir management and hydrocarbon exploration in complex geological settings. These insights pave the way for more reliable and efficient decision-making processes, thereby advancing the forefront of reservoir engineering and petroleum geoscience.

Microplastics: A potential proxy for tracing extreme flood events in estuarine environments.

The transport of microplastics (MPs) is susceptible to being influenced by catchment hydrology; however, there is a notable lack of research on their retention and responses to flood events in estuarine sedimentary records. Herein, we collected two cores in the Yangtze Estuary to explore their microplastic pollution, influencing factors and linkage to flood events. MP abundance exhibited a decreasing trend from the top to the bottom in both cores. Both plastic production and sediment mean grain size showed a significant positive correlation with MP abundance. The sedimentary record displayed a marked surge in MP abundance during the extreme flood period, suggesting a direct influence of flooding on MP deposition. The resuspension of upstream MPs and erosion of land-based MPs by heavy rain might be responsible for this increase. Furthermore, our study identified significant periodicities in MP abundance, closely aligned with the hydrological patterns of the Yangtze River. This study highlights the role of floods in fluvial MP distribution and proposes MPs as a proxy of extreme floods from the 20th century in estuarine environments.

A Vegetable Leaf Disease Identification Model Based on Image-Text Cross-Modal Feature Fusion.

In view of the differences in appearance and the complex backgrounds of crop diseases, automatic identification of field diseases is an extremely challenging topic in smart agriculture. To address this challenge, a popular approach is to design a Deep Convolutional Neural Network (DCNN) model that extracts visual disease features in the images and then identifies the diseases based on the extracted features. This approach performs well under simple background conditions, but has low accuracy and poor robustness under complex backgrounds. In this paper, an end-to-end disease identification model composed of a disease-spot region detector and a disease classifier (YOLOv5s + BiCMT) was proposed. Specifically, the YOLOv5s network was used to detect the disease-spot regions so as to provide a regional attention mechanism to facilitate the disease identification task of the classifier. For the classifier, a Bidirectional Cross-Modal Transformer (BiCMT) model combining the image and text modal information was constructed, which utilizes the correlation and complementarity between the features of the two modalities to achieve the fusion and recognition of disease features. Meanwhile, the problem of inconsistent lengths among different modal data sequences was solved. Eventually, the YOLOv5s + BiCMT model achieved the optimal results on a small dataset. Its Accuracy, Precision, Sensitivity, and Specificity reached 99.23, 97.37, 97.54, and 99.54%, respectively. This paper proves that the bidirectional cross-modal feature fusion by combining disease images and texts is an effective method to identify vegetable diseases in field environments.

Efficacy and safety of a 260-cm Amplatz Super Stiff guidewire during transradial percutaneous coronary intervention.

BACKGROUND: Although transradial percutaneous coronary intervention (TR-PCI) is widely used in clinical practice, guidewire-related complications are an important cause of transradial approach failure. We investigated the prognostic value of the 260-cm Amplatz Super Stiff guidewire for reducing the complication rate during TR-PCI. METHODS: Five hundred patients with positive Allen's test results were divided into 3 groups according to the type of angiography guidewire: group A, 150-cm Emerald guidewire standard J-tip (n = 160); group B, 150-cm Radifocus guidewire M (n = 176); and group C, exchangeable 260-cm Amplatz Super Stiff guidewire after placement of a 150-cm Radifocus guidewire M (n = 164). RESULTS: Group C had the highest success rate (P = .008) and the lowest incidence of operative complications such as radial artery spasms and hematomas (P = .030 and P = .036, respectively). In addition, the groups differed significantly in terms of fluoroscopy and catheter placement times (P = .02. and P < .001, respectively); group C had the shortest times for these occurrences. CONCLUSIONS: The exchangeable 260-cm Amplatz Super Stiff guidewire markedly decreased the incidence of guidewire-related complications, reduced fluoroscopy times, and increased the procedural success rate. Therefore, this tool can be considered a safe, effective, and feasible exchangeable guidewire for TR-PCI.

Comparison of Magnetic Microbubbles and Dual-modified Microbubbles Targeted to P-selectin for Imaging of Acute Endothelial Inflammation in the Abdominal Aorta.

PURPOSE: Ultrasound molecular imaging (UMI) has potential to evaluate an inflammatory profile of endothelium. However, it is less successful in large arteries. This study compared magnetic microbubbles (MBs) selectively targeted to endothelial P-selectin and dual-targeting MBs in vitro and in vivo. PROCEDURES: MBs were modified with P-selectin antibody (MBPM) or isotype control antibody (MBCM) via a magnetic streptavidin bridge, and MBs were conjugated to P-selectin antibody (MBP) or both P-selectin antibody and PAA-sialyl Lewisx (MBD) via regular streptavidin linker. Adherence of MBs was determined by using a parallel plate flow chamber at variable shear stress (0.5-24 dyn/cm2). Adhesive and magnetic behaviors of MBs were analyzed at 4.0 dyn/cm2 or at a flow rate of 50 mm/s. Attachment of MBs to P-selectin was determined with contrast-enhanced ultrasound (CEU) imaging of murine abdominal aorta inflammation. The expression of P-selectin was assessed by immunohistochemistry. RESULTS: The adhesive efficacy of MBD was greater than MBP and MBCM, but lower than MBPM under all shear stress conditions (P < 0.05). The behaviors of fast-binding and rolling slow down were noted in MBD and MBPM; meanwhile, magnetic shifting of MBs centerline was presented in MBPM. Contrast video intensity (VI) from adhered MBPM to P-selectin of the inflammatory aorta was significantly higher than those from MBD and MBP (P < 0.05). CONCLUSIONS: MBPM may be a better molecular probe than MBD for detection of P-selectin on aorta with CEU, likely due to the shifting of axial distribution. Thus, it may improve the detection of the inflammatory profile on large arteries by UMI.

Effects of beta-blockers on heart failure with preserved ejection fraction: a meta-analysis.

BACKGROUND: Effects of beta-blockers on the prognosis of the heart failure patients with preserved ejection fraction (HFpEF) remain controversial. The aim of this meta-analysis was to determine the impact of beta-blockers on mortality and hospitalization in the patients with HFpEF. METHODS: A search of MEDLINE, EMBASE, and the Cochrane Library databases from 2005 to June 2013 was conducted. Clinical studies reporting outcomes of mortality and/or hospitalization for patients with HFpEF (EF ≥ 40%), being assigned to beta-blockers treatment and non-beta-blockers control group were included. RESULTS: A total of 12 clinical studies (2 randomized controlled trials and 10 observational studies) involving 21,206 HFpEF patients were included for this meta-analysis. The pooled analysis demonstrated that beta-blocker exposure was associated with a 9% reduction in relative risk for all-cause mortality in patients with HFpEF (95% CI: 0.87 - 0.95; P < 0.001). Whereas, the all-cause hospitalization, HF hospitalization and composite outcomes (mortality and hospitalization) were not affected by this treatment (P=0.26, P=0.97, and P=0.88 respectively). CONCLUSIONS: The beta-blockers treatment for the patients with HFpEF was associated with a lower risk of all-cause mortality, but not with a lower risk of hospitalization. These finding were mainly obtained from observational studies, and further investigations are needed to make an assertion.

[Therapeutic effect of recombinant human brain natriuretic peptide for treatment of decompensated heart failure: comparison with nitroglycerin].

OBJECTIVE: To compare the therapeutic effect of recombinant human brain natriuretic peptide (rhBNP) and nitroglycerin on acute decompensated heart failure (ADHF). METHODS: Fifty ADHF patients were randomly divided into rhBNP group and nitroglycerin group. In all the patients, dyspnea and global clinical status were assessed before and at 30 min, 6 h and 24 h after drug administration, and the volume of fluid intake and urine along with hemodynamic parameters was recorded 24 h after drug administration. In the nitroglycerin group, the patients received an initial nitroglycerin dose of 5 microg/min, with subsequent dose increment of 5 microg/min every 3 to 5 min; the dose was adjusted individually according to the hemodynamics of the patients. The patients in rhBNP group were given rhBNP at the initial dose of 1.5 microg/kg by with an intravenous bolus injection followed by infusion at the rate of 0.0075 microg.kg(-1).min(-1) for 72 h. RESULTS: At 30 min and 6 h after drug administration, the patients in the rhBNP group showed significant greater improvement of dyspnea (P=0.042 and 0.019) and global clinical status (P=0.018 and 0.044) than those in the nitroglycerin group, but 24 h after drug administration, no significant difference was noted between the two groups (P=0.192 and 0.179). Twenty-four hours after drug administration, the mean urine volume was significantly greater in rhBNP group than in nitroglycerin group (1513.8-/+242.9 vs 1341.2-/+239.7 ml, P=0.015), and the ejection fraction increased and pulmonary arterial pressure and systolic blood pressure decreased at greater amplitude in the former group (P=0.001,0.000 and 0.002, respectively). At 72 h, the numbers of premature ventricular contraction and couplets premature beats and onset of paroxysmal ventricular tachycardia were significantly reduced in rhBNP group as compared with the nitroglycerin group (P=0, 0.001 and 0.002, respectively). CONCLUSION: RhBNP promotes urine excretion, decreases pulmonary arterial pressure and increases left ventricular ejection fraction to improve dyspnea and global clinical status and reduce the onset of ventricular arrhythmia in ADHF patients.

[Influence of atrioventricular delay of dual chamber pacemaker on cardiac function: evaluation by tissue Doppler echocardiography].

OBJECTIVE: To investigate the optimal atrioventricular delay (AVD) in using dual-chamber pacemaker. METHODS: Thirty patients with atrioventricular conduction block, aged 62 +/- 12, implanted for were implanted with DDD pacemakers. Program controller was used to program the AVD. Two-dimensional echocardiography was used to measure the hemodynamic parameters: cardiac output (CO), cardiac output index (CI), stroke volume (SV), left ventricular ejection fraction (LVEF), left ventricular end-systolic diameter (LVESd), left ventricular end-diastolic diameter (LVEDd), peak systolic velocity (Vs), and peak systolic time of the basic segment at inter-ventricular septum and left ventricular under the pattern of tissue velocity imaging at different values of AVD. For each patient, the AVD was prolonged to 250 ms stepwise by 30 ms starting from 100 ms. RESULTS: Cardiac function changed with different AVD. When the AVD was 160 ms, the maximal values were reached for CO (5.5 L/min+/-1.1 L/min, P<0.05), CI (3.5 Lxmin(-1)xm(-2)+/-0.8 Lxmin(-1)xm(-2), P<0.05), SV (78 ml+/-13 ml, P<0.05), LVEF (67%+/-7%, P<0.05), LVEDd (121 mm+/-29 mm, P<0.05), and Vs. LVESd reached its minimal value (37 mm+/-16 mm, P<0.05) and the Vs values of different ventricular walls reached the minimal too (all P<0.05). CONCLUSION: When the optimal AVD is selected the cardiac function can be significantly improved. Tissue Doppler echocardiography is useful in evaluating cardiac function and determining the optimal AVD.