Synthesis of nitrogen-doped amorphous carbon nanotubes from novel cobalt-based MOF precursors for improving potassium-ion storage capability.

Amorphous carbon materials with sophisticated morphologies, variable carbon layer structures, abundant defects, and tunable porosities are favorable as anodes for potassium-ion batteries (PIBs). Synthesizing amorphous carbon materials typically involves the pyrolysis of carbonaceous precursors. Nonetheless, there is still a lack of studies focused on achieving multifaceted structural optimizations of amorphous carbon through precursor formulation. Herein, nitrogen-doped amorphous carbon nanotubes (NACNTs) are derived from a novel composite precursor of cobalt-based metal-organic framework (CMOF) and graphitic carbon nitride (g-CN). The addition of g-CN in the precursor optimizes the structure of amorphous carbon such as morphology, interlayer spacing, nitrogen doping, and porosity. As a result, NACNTs demonstrate significantly improved electrochemical performance. The specific capacities of NACNTs after cycling at current densities of 100 mA/g and 1000 mA/g increased by 194 % and 230 %, reaching 346.6 mAh/g and 211.8 mAh/g, respectively. Furthermore, the NACNTs anode is matched with an organic cathode for full-cell evaluation. The full-cell attains a high specific capacity of 106 mAh/gcathode at a current density of 100 mA/g, retaining 90.5 % of the specific capacity of the cathode half-cell. This study provides a valuable reference for multifaceted structural optimization of amorphous carbon to improve potassium-ion storage capability.

Vacuum ammonia stripping from liquid digestate: Effects of pH, alkalinity, temperature, negative pressure and process optimization.

High ammonia-nitrogen digestate has become a key bottleneck limiting the anaerobic digestion of organic solid waste. Vacuum ammonia stripping can simultaneously remove and recover ammonia nitrogen, which has attracted a lot of attention in recent years. To investigate the parameter effects on the efficiency and mass transfer, five combination conditions (53 °C 15 kPa, 60 °C 20 kPa, 65 °C 25 kPa, 72 °C 35 kPa, and 81 °C 50 kPa) were conducted for ammonia stripping of sludge digestate. The results showed that 80% of ammonia nitrogen was stripped in 45 min for all experimental groups, but the ammonia transfer coefficient varied under different conditions, which increased with the rising of boiling point temperature, and reached the maximum value (39.0 mm/hr) at 81 °C 50 kPa. The ammonia nitrogen removal efficiency was more than 80% for 30 min vacuum stripping after adjusting the initial pH to above 9.5, and adjustment of the initial alkalinity also affects the pH value of liquid digestate. It was found that pH and alkalinity are the key factors influencing the ammonia nitrogen dissociation and removal efficiency, while temperature and vacuum mainly affect the ammonia nitrogen mass transfer and removal velocity. In terms of the mechanism of vacuum ammonia stripping, it underwent alkalinity destruction, pH enhancement, ammonia nitrogen dissociation, and free ammonia removal. In this study, two-stage experiments of alkalinity destruction and ammonia removal were also carried out, which showed that the two-stage configuration was beneficial for ammonia removal. It provides a theoretical basis and practical technology for the vacuum ammonia stripping from liquid digestate of organic solid waste.

Strategies for improving expression of recombinant human chorionic gonadotropin in Chinese Hamster Ovary (CHO) cells.

Optimizations of the gene expression cassette combined with the selection of an appropriate signal peptide are important factors that must be considered to enhance heterologous protein expression in Chinese Hamster Ovary (CHO) cells. In this study, we investigated the effectiveness of different signal peptides on the production of recombinant human chorionic gonadotropin (r-hCG) in CHO-K1 cells. Four optimized expression constructs containing four promising signal peptides were stably transfected into CHO-K1 cells. The generated CHO-K1 stable pool was then evaluated for r-hCG protein production. Interestingly, human serum albumin and human interleukin-2 signal peptides exhibited relatively greater extracellular secretion of the r-hCG with an average yield of (16.59 ± 0.02 µg/ml) and (14.80 ± 0.13 µg/ml) respectively compared to the native and murine IgGκ light chain signal peptides. The stably transfected CHO pool was further used as the cell substrate to develop an optimized upstream process followed by a downstream phase of the r-hCG. Finally, the biological activity of the purified r-hCG was assessed using in vitro bioassays. The combined data highlight that the choice of signal peptide can be imperative to ensure an optimal secretion of a recombinant protein in CHO cells. In addition, the stable pool technology was a viable approach for the production of biologically active r-hCG at a research scale with acceptable bioprocess performances and consistent product quality.

A Lightweight Method for Breast Cancer Detection Using Thermography Images with Optimized CNN Feature and Efficient Classification.

Breast cancer is a prominent cause of death among women worldwide. Infrared thermography, due to its cost-effectiveness and non-ionizing radiation, has emerged as a promising tool for early breast cancer diagnosis. This article presents a hybrid model approach for breast cancer detection using thermography images, designed to process and classify these images into healthy or cancerous categories, thus supporting disease diagnosis. Multiple pre-trained convolutional neural networks are employed for image feature extraction, and feature filter methods are proposed for feature selection, with diverse classifiers utilized for image classification. Evaluating the DRM-IR test set revealed that the combination of ResNet34, Chi-square ( χ 2 ) filter, and SVM classifier demonstrated superior performance, achieving the highest accuracy at 99.62 % . Furthermore, the highest accuracy improvement obtained was 18.3 % when using the SVM classifier and Chi-square filter compared to regular convolutional neural networks. The results confirmed that the proposed method, with its high accuracy and lightweight model, outperforms state-of-the-art breast cancer detection from thermography image methods, making it a good choice for computer-aided diagnosis.

Research status and prospect of flexible optimization design methodology of propeller CNC polishing machines.

Among the components of high-tech ships, the structural complexity of the propeller profile requires a high degree of flexibility in the CNC polishing machine. In addressing this requirement, the study formulates the flexible optimization problem pertaining to research on the propeller CNC polishing machine. A comprehensive analysis is undertaken to scrutinize the geometric features of the propeller and the phenomenon of polished contact. The propeller profile-polishing head dynamic contact mechanism is revealed, and the contact force characteristics of propeller polishing are obtained. It is suggested that the propeller configuration-process-polishing machine structure coupling mechanism be explored under the influence of polishing contact force. Subsequently, a dynamic model of the propeller CNC polishing process is formulated. Based on the above model, a simulation of the motion personification and structural flexibility of the propeller CNC polishing machine is proposed to obtain dynamic personification and flexibility rules. Integrating polishing contact force characteristics with dynamic personification and flexibility rules, the dynamic flexible collaborative optimization principle of the propeller CNC polishing machine is revealed. On this basis, multi-objective optimization modeling and solving are carried out, forming a new method for the flexible optimization design of propeller CNC polishing machines.

Preoperative very low-energy diets for obese patients undergoing intra-abdominal colorectal surgery: a retrospective cohort study (RetroPREPARE).

BACKGROUND: Very low-energy diets (VLEDs) prescribed prior to bariatric surgery have been associated with decreased operative time, technical difficulty, and postoperative morbidity. To date, limited data are available regarding the impact of VLEDs prior to colorectal surgery. We designed this study to determine whether preoperative VLEDs benefit patients with obesity undergoing colorectal surgery. METHODS: This is a single-center retrospective cohort study. Individuals undergoing elective colorectal surgery with a body mass index (BMI) of greater than 30 kg/m2 from 2015 to 2022 were included. The exposure of interest was VLEDs for 2-4 weeks immediately prior to surgery. The control group consisted of patients prior to January 2018 who did not receive preoperative VLED. The primary outcome was 30 day postoperative morbidity. Multivariable logistic regression modeling was used to determine associations with 30 day postoperative morbidity. RESULTS: Overall, 190 patients were included, 89 patients received VLEDs (median age: 66 years; median BMI: 35.9 kg/m2; 48.3% female) and 101 patients did not receive VLEDs (median age: 68 years; median BMI: 32.1 kg/m2; 44.6% female). One-hundred four (54.7%) patients experienced 30 day postoperative morbidity. Multivariable regression analysis identified three variables associated with postoperative morbidity: VLEDs [odds ratio (OR) 0.22, 95% confidence intervals (CI) 0.08-0.61, P < 0.01], Charlson comorbidity index (OR 1.25, 95% CI 1.03-1.52, P = 0.02), and rectal dissections (OR 2.71, 95% CI 1.30-5.65, P < 0.01). CONCLUSIONS: The use of a preoperative VLED was associated with a significant reduction in postoperative morbidity in patients with obesity prior to colorectal surgery. A high-quality randomized controlled trial is required to confirm these findings.

Advancements in Flexible Electronics Fabrication: Film Formation, Patterning, and Interface Optimization for Cutting-Edge Healthcare Monitoring Devices.

Flexible electronics can seamlessly adhere to human skin or internal tissues, enabling the collection of physiological data and real-time vital sign monitoring in home settings, which give it the potential to revolutionize chronic disease management and mitigate mortality rates associated with sudden illnesses, thereby transforming current medical practices. However, the development of flexible electronic devices still faces several challenges, including issues pertaining to material selection, limited functionality, and performance instability. Among these challenges, the choice of appropriate materials, as well as their methods for film formation and patterning, lays the groundwork for versatile device development. Establishing stable interfaces, both internally within the device and in human-machine interactions, is essential for ensuring efficient, accurate, and long-term monitoring in health electronics. This review aims to provide an overview of critical fabrication steps and interface optimization strategies in the realm of flexible health electronics. Specifically, we discuss common thin film processing methods, patterning techniques for functional layers, interface challenges, and potential adjustment strategies. The objective is to synthesize recent advancements and serve as a reference for the development of innovative flexible health monitoring devices.

A simple and intuitive model for long-range 3D potential distributions of in-operando TEM-samples: Comparison with electron holographic tomography.

Electron holography is a powerful tool to investigate the properties of micro- and nanostructured electronic devices. A meaningful interpretation of the holographic data, however, requires an understanding of the 3D potential distribution inside and outside the sample. Standard approaches to resolve these potential distributions involve projective tilt series and their tomographic reconstruction, in addition to extensive simulations. Here, a simple and intuitive model for the approximation of such long-range potential distributions surrounding a nanostructured coplanar capacitor is presented. The model uses only independent convolutions of an initial potential distribution with a Gaussian kernel, allowing the reconstruction of the entire potential distribution from only one measured projection. By this, a significant reduction of the required computational power as well as a drastically simplified measurement process is achieved, paving the way towards quantitative electron holographic investigation of electrically biased nanostructures.

Integrated water resource management in the Segura Hydrographic Basin: An artificial intelligence approach.

Managing resources effectively in uncertain demand, variable availability, and complex governance policies is a significant challenge. This paper presents a paradigmatic framework for addressing these issues in water management scenarios by integrating advanced physical modelling, remote sensing techniques, and Artificial Intelligence algorithms. The proposed approach accurately predicts water availability, estimates demand, and optimizes resource allocation on both short- and long-term basis, combining a comprehensive hydrological model, agronomic crop models for precise demand estimation, and Mixed-Integer Linear Programming for efficient resource distribution. In the study case of the Segura Hydrographic Basin, the approach successfully allocated approximately 642 million cubic meters (hm3) of water over six months, minimizing the deficit to 9.7% of the total estimated demand. The methodology demonstrated significant environmental benefits, reducing CO2 emissions while optimizing resource distribution. This robust solution supports informed decision-making processes, ensuring sustainable water management across diverse contexts. The generalizability of this approach allows its adaptation to other basins, contributing to improved governance and policy implementation on a broader scale. Ultimately, the methodology has been validated and integrated into the operational water management practices in the Segura Hydrographic Basin in Spain.

Mapping between measurement scales in meta-analysis, with application to measures of body mass index in children.

Quantitative evidence synthesis methods aim to combine data from multiple medical trials to infer relative effects of different interventions. A challenge arises when trials report continuous outcomes on different measurement scales. To include all evidence in one coherent analysis, we require methods to "map" the outcomes onto a single scale. This is particularly challenging when trials report aggregate rather than individual data. We are motivated by a meta-analysis of interventions to prevent obesity in children. Trials report aggregate measurements of body mass index (BMI) either expressed as raw values or standardized for age and sex. We develop three methods for mapping between aggregate BMI data using known or estimated relationships between measurements on different scales at the individual level. The first is an analytical method based on the mathematical definitions of z-scores and percentiles. The other two approaches involve sampling individual participant data on which to perform the conversions. One method is a straightforward sampling routine, while the other involves optimization with respect to the reported outcomes. In contrast to the analytical approach, these methods also have wider applicability for mapping between any pair of measurement scales with known or estimable individual-level relationships. We verify and contrast our methods using simulation studies and trials from our data set which report outcomes on multiple scales. We find that all methods recreate mean values with reasonable accuracy, but for standard deviations, optimization outperforms the other methods. However, the optimization method is more likely to underestimate standard deviations and is vulnerable to non-convergence.

Comprehensive Insights on MXene-Based TENGs: from Structures, Functions to Applications.

The rapid advancement of triboelectric nanogenerators (TENGs) has introduced a transformative approach to energy harvesting and self-powered sensing in recent years. Nonetheless, the untapped potential of TENGs in practical scenarios necessitates multiple strategies like material selections and structure designs to enhance their output performance. Given the various superior properties, MXenes, a kind of novel 2D materials, have demonstrated great promise in enhancing TENG functionality. Here, this review comprehensively delineates the advantages of incorporating MXenes into TENGs, majoring in six pivotal aspects. First, an overview of TENGs is provided, stating their theoretical foundations, working modes, material considerations, and prevailing challenges. Additionally, the structural characteristics, fabrication methodologies, and family of MXenes, charting their developmental trajectory are highlighted. The selection of MXenes as various functional layers (negative and positive triboelectric layer, electrode layer) while designing TENGs is briefed. Furthermore, the distinctive advantages of MXene-based TENGs and their applications are emphasized. Last, the existing challenges are highlighted, and the future developing directions of MXene-based TENGs are forecasted.

Integrated municipal solid waste management using ArcGIS tools: A case of akaki-kality sub-city, addis ababa, ethiopia.

This study aimed to optimize the solid waste collection and transportation system using ArcGIS Network Analyst and location-allocation tools. The generated solid waste was characterized by proximate analysis. The generation rate and composition were determined according to standard methods. The average solid waste generation rates for households, commercial sites, institutions, and recreational places were 0.48 kg/c/day, 15.03 kg/fac/day, 9.32 kg/fac/day, and 22.8 kg/fac/day, respectively. The estimated total generation rate of the sub-city is 207,004.03 kg/day and 712.13 m3/day as discarded base. Composition analysis revealed that food waste is the major component of municipal solid waste, with estimated weight and volume of 134,696.08 kg and 299.46 m3, respectively. Proximate analysis indicated that food and textile wastes have relatively high moisture content and fixed carbon. Candidate pre-collection bin allocations were optimized based on factors such as road network, distribution of solid waste generators, and existing temporary dumping sites, resulting in 1052 potential bin locations. Transfer station allocation was optimized by considering land use-land cover, slope, and geology. Twelve transfer routes and four transport routes were established to efficiently serve the bins and final waste destinations. In conclusion, the study demonstrates that ArcGIS Network Analyst and location-allocation tools can effectively optimize the municipal solid waste collection and transportation system, providing a robust framework for improving waste management efficiency. However, further research is recommended to validate these findings through field application.

Enhancement of carotenogenesis by Blakeslea trispora in a mixed culture with bacteria.

Among carotenoids, ꞵ-carotene has the highest biological activity and is found as an all-trans isomer in many biological systems. Blakeslea trispora is a microorganism that is of interest to industries for the commercial production of ꞵ-carotene. This study investigated the effect of different bacteria on carotenogenesis in B. trispora. The B. trispora bisexual mold was cultured in a production medium, and different bacterial cells were added to it after 24 h. Then, the culture conditions and the culture medium were optimized in the presence of the selected bacteria using the experimental design. The percentage of carotenoids obtained from the mixed culture was determined using high-performance liquid chromatography (HPLC). Results showed that Kocuria rhizophila had the greatest effect on increasing the production of carotenoids in B. trispora. The highest content of carotenoids obtained during optimization was 770 ± 7.5 mg/L, a 6.8-fold increase compared to the control. HPLC analysis of carotenoids indicated the presence of two main peaks, ꞵ-carotene and γ-carotene, in which the primary carotenoid was ꞵ-carotene followed by γ-carotene with a lower content. Therefore, due to the importance of ꞵ-carotene in industry, the use of biostimulants is one of the appropriate strategies to increase the production of this pigment in industry.

Quantifying the frequency modulation in electrograms during simulated atrial fibrillation in 2D domains.

Atrial fibrillation (AF) affects millions of people in the world, causing increased morbidity and mortality. Treatment involves antiarrhythmic drugs and catheter ablation, showing high success for paroxysmal AF but challenges for persistent AF. Experimental evidence suggests reentrant waves and rotors contribute to AF substrates. Ablation procedures rely on electroanatomical maps and electrogram (EGM) signals; however, current methods used in clinical practice lack consideration for time-frequency varying EGM components. The fractional Fourier transform (FrFT) can be adopted to capture time-varying frequency components, thereby enhancing the comprehension of arrhythmogenic substrates during AF for improved ablation strategies. To this end, a FrFT-based algorithm is developed to characterize non-stationary components in EGM signals from simulated AF episodes. The proposed algorithm comprises a pre-processing step to enhance the coarser features of the EGM waveform, a windowing process for dynamic assessment of the EGM, and a FrFT order optimization stage that seeks compact signal representations in fractional Fourier domains. The resulting order is related to the rate of frequency change in the signal, making it a useful indicator for frequency-modulated components. The FrFT-based algorithm is implemented on EGM signals from AF simulations in 2D domains representing a region of the atrial tissue. Consequently, the computed optimum FrFT orders are used to build maps that are spatially correlated to the underlying propagation dynamics of the simulated AF episode. The results evince that the extreme values in the optimum orders map pinpoint the localization of fibrillatory mechanisms, generating EGM activation waveforms with varying frequency content over time.

Evaluation of intensive remediation using simulation-optimization modeling based on long-term monitoring at a DNAPL contaminated site.

Simulation-optimization modeling is extensively used to identify optimal remediation designs. However, verifying these optimal solutions often remains unclear. In this study, we determine optimal groundwater remediation strategies using simulation-optimization modeling and assess the effectiveness of previous remediation efforts by validating optimized results through 14 years of long-term monitoring of trichloroethylene (TCE) contamination. The study site is the Road Administrative Office (RAO) in Wonju, Korea, where significant TCE contamination has occurred, and long-term in-situ remediation and monitoring have been conducted. We employ MODFLOW for simulating groundwater flow and MT3D for modeling dissolved TCE concentration distribution. The Non-dominated Sorting Genetic Algorithm-II (NSGA-II) is applied to derive optimal groundwater remediation designs. Initial simulation results effectively predicted long-term TCE contamination trends and the impact of short-term in-situ remediation. Our evaluation involved comparing these optimal designs with field test outcomes, leading to the integration of continuous intensive pump-and-treat with in-situ remediation strategies. By comparing various modeling scenarios against long-term TCE contamination trends, we confirmed the effectiveness of previous remediation efforts and demonstrated that the optimal remediation design substantially minimized TCE concentrations at the main source zone. This study highlights successful strategies in historical contamination and remediation trend assessments, proposing an optimal design for pump-and-treat with reduced pumping stress to manage remaining TCE contamination at the site effectively.

Surface Optimization of Noble-Metal-Free Conductive [Mn1/4Co1/2Ni1/4]O2 Nanosheets for Boosting Their Efficacy as Hybridization Matrices.

Conductive 2D nanosheets have evoked tremendous scientific efforts because of their high efficiency as hybridization matrices for improving diverse functionalities of nanostructured materials. To address the problems posed by previously reported conductive nanosheets like poorly-interacting graphene and cost-ineffective RuO2 nanosheets, economically feasible noble-metal-free conductive [MnxCo1-2xNix]O2 oxide nanosheets are synthesized with outstanding interfacial interaction capability. The surface-optimized [Mn1/4Co1/2Ni1/4]O2 nanosheets outperformed RuO2/graphene nanosheets as hybridization matrices in exploring high-performance visible-light-active (λ >420 nm) photocatalysts. The most efficient g-C3N4-[Mn1/4Co1/2Ni1/4]O2 nanohybrid exhibited unusually high photocatalytic activity (NH4 + formation rate: 1.2 mmol g-1 h-1), i.e., one of the highest N2 reduction efficiencies. The outstanding hybridization effect of the defective [Mn1/4Co1/2Ni1/4]O2 nanosheets is attributed to the optimization of surface bonding character and electronic structure, allowing for improved interfacial coordination bonding with g-C3N4 at the defect sites. Results from spectroscopic measurements and theoretical calculations reveal that hybridization helps optimize the bandgap energy, and improves charge separation, N2 adsorptivity, and surface reactivity. The universality of the [Mn1/4Co1/2Ni1/4]O2 nanosheet as versatile hybridization matrices is corroborated by the improvement in the electrocatalytic activity of hybridized Co-Fe-LDH as well as the photocatalytic hydrogen production ability of hybridized CdS.

A cascaded FAS-UNet+ framework with iterative optimization strategy for segmentation of organs at risk.

Segmentation of organs at risks (OARs) in the thorax plays a critical role in radiation therapy for lung and esophageal cancer. Although automatic segmentation of OARs has been extensively studied, it remains challenging due to the varying sizes and shapes of organs, as well as the low contrast between the target and background. This paper proposes a cascaded FAS-UNet+ framework, which integrates convolutional neural networks and nonlinear multi-grid theory to solve a modified Mumford-shah model for segmenting OARs. This framework is equipped with an enhanced iteration block, a coarse-to-fine multiscale architecture, an iterative optimization strategy, and a model ensemble technique. The enhanced iteration block aims to extract multiscale features, while the cascade module is used to refine coarse segmentation predictions. The iterative optimization strategy improves the network parameters to avoid unfavorable local minima. An efficient data augmentation method is also developed to train the network, which significantly improves its performance. During the prediction stage, a weighted ensemble technique combines predictions from multiple models to refine the final segmentation. The proposed cascaded FAS-UNet+ framework was evaluated on the SegTHOR dataset, and the results demonstrate significant improvements in Dice score and Hausdorff Distance (HD). The Dice scores were 95.22%, 95.68%, and HD values were 0.1024, and 0.1194 for the segmentations of the aorta and heart in the official unlabeled dataset, respectively. Our code and trained models are available at https://github.com/zhuhui100/C-FASUNet-plus .

Machine learning as a tool predicting short-term postoperative complications in Crohn's disease patients undergoing intestinal resection: What frontiers?

The recent study, "Predicting short-term major postoperative complications in intestinal resection for Crohn's disease: A machine learning-based study" investigated the predictive efficacy of a machine learning model for major postoperative complications within 30 days of surgery in Crohn's disease (CD) patients. Employing a random forest analysis and Shapley Additive Explanations, the study prioritizes factors such as preoperative nutritional status, operative time, and CD activity index. Despite the retrospective design's limitations, the model's robustness, with area under the curve values surpassing 0.8, highlights its clinical potential. The findings align with literature supporting preoperative nutritional therapy in inflammatory bowel diseases, emphasizing the importance of comprehensive assessment and optimization. While a significant advancement, further research is crucial for refining preoperative strategies in CD patients.

Tail Bounds on the Runtime of Categorical Compact Genetic Algorithm.

The majority of theoretical analyses of evolutionary algorithms in the discrete domain focus on binary optimization algorithms, even though black-box optimization on the categorical domain has a lot of practical applications. In this paper, we consider a probabilistic model-based algorithm using the family of categorical distributions as its underlying distribution and set the sample size as two. We term this specific algorithm the categorical compact genetic algorithm (ccGA). The ccGA can be considered as an extension of the compact genetic algorithm (cGA), which is an efficient binary optimization algorithm. We theoretically analyze the dependency of the number of possible categories K, the number of dimensions D, and the learning rate η on the runtime. We investigate the tail bound of the runtime on two typical linear functions on the categorical domain: categorical OneMax (COM) and KVAL. We derive that the runtimes on COM and KVAL are O(Dln(DK)/η) and Θ(DlnK/η) with high probability, respectively. Our analysis is a generalization for that of the cGA on the binary domain.

An efficient water quality index forecasting and categorization using optimized Deep Capsule Crystal Edge Graph neural network.

The world's freshwater supply, predominantly sourced from rivers, faces significant contamination from various economic activities, confirming that the quality of river water is critical for public health, environmental sustainability, and effective pollution control. This research addresses the urgent need for accurate and reliable water quality monitoring by introducing a novel method for estimating the water quality index (WQI). The proposed approach combines cutting-edge optimization techniques with Deep Capsule Crystal Edge Graph neural networks, marking a significant advancement in the field. The innovation lies in the integration of a Hybrid Crested Porcupine Genghis Khan Shark Optimization Algorithm for precise feature selection, ensuring that the most relevant indicators of water quality (WQ) are utilized. Furthermore, the use of the Greylag Goose Optimization Algorithm to fine-tune the neural network's weight parameters enhances the model's predictive accuracy. This dual optimization framework significantly improves WQI prediction, achieving a remarkable mean squared error (MSE) of 6.7 and an accuracy of 99%. By providing a robust and highly accurate method for WQ assessment, this research offers a powerful tool for environmental authorities to proactively manage river WQ, prevent pollution, and evaluate the success of restoration efforts. PRACTITIONER POINTS: Novel method combines optimization and Deep Capsule Crystal Edge Graph for WQI estimation. Preprocessing includes data cleanup and feature selection using advanced algorithms. Deep Capsule Crystal Edge Graph neural network predicts WQI with high accuracy. Greylag Goose Optimization fine-tunes network parameters for precise forecasts. Proposed method achieves low MSE of 6.7 and high accuracy of 99%.