Average Coefficient Of Determination Research Articles

The enhancement scheme for the predictive ability of QSAR: A case of mutagenicity

Mutagenicity is one of the most dangerous properties from the point of view of medicine and ecology. Experimental determination of mutagenicity remains a costly process, which makes it attractive to identify new hazardous compounds based on available experimental data through in silico methods or quantitative structure-activity relationships (QSAR). A system for constructing groups of random models is proposed for comparing various molecular features extracted from SMILES and graphs. For mutagenicity (mutagenicity values were expressed by the logarithm of the number of revertants per nanomole assayed by Salmonella typhimurium TA98-S9 microsomal preparation) models, the Morgan connectivity values are more informative than the comparison of quality for different rings in molecules. The resulting models were tested with the previously proposed model self-consistency system. The average determination coefficient for the validation set is 0.8737 ± 0.0312.

Study on Land Subsidence Simulation Based on a Back-Propagation Neural Network Combined with the Sparrow Search Algorithm

Rapid simulation of land subsidence can provide an effective means of facilitating its management and control. This paper innovatively introduced a back-propagation (BP) neural network subsidence simulation model which was optimized by the sparrow search algorithm (SSA), hereinafter referred to as the SSA-BP model, to simulate land subsidence in Tongzhou District, Beijing. First, based on the time series interferometric synthetic aperture radar (InSAR) monitoring, different technologies such as spatial analysis, Google Earth Engine (GEE), and machine learning were utilized together with a variety of multi-source spatial data, including groundwater level, compressible layer thickness, Visible Infrared Imager Radiometer Suite (VIIRS) nighttime light images, and the OpenStreetMap (OSM) road distribution. Furthermore, we determined the optimal grid scale for land subsidence research and worked out a multifactor-driven SSA-BP land subsidence simulation model for which sensitivity analysis was performed with great care. Main conclusions: (1) From November 2010 to January 2020, the average annual surface displacement rate in Beijing’s subcentre, Tongzhou, ranged from −133.9 to +3.9 mm/year. (2) Our SSA-BP land subsidence simulation model allows for a relatively high overall accuracy. The average root mean square error (RMSE) is 5.00 mm/year, the average mean absolute error (MAE) is 3.80 mm/year, and the average coefficient of determination (R2) is 0.83. (3) Sensitivity analysis shows that the SSA-BP model driven by multiple factors has a far better simulation performance than the model driven by any single weighting factor, and displays the highest sensitivity to the groundwater level factor among all the weighting factors. In terms of subdividing the study area, our SSA-BP land subsidence model runs with multifunctional zones displayed a higher accuracy than that without. This paper made use of a machine learning model to simulate land subsidence in Beijing’s Tongzhou District and explored the sensitivity of different factors to land subsidence, which is helpful for its scientific prevention.

Enhanced Hydrological Simulations in Paddy-Dominated Watersheds Using the Hourly SWAT-MODFLOW-PADDY Modeling Approach

Accurate hydrological simulations are crucial for managing water resources and promoting sustainable agriculture in submerged paddy agricultural watersheds. The SWAT-MODFLOW, which couples the Soil and Water Assessment Tool (SWAT) and the Modular Groundwater Flow (MODFLOW) model, is a widely used tool for hydrologic simulations that consider surface water and groundwater (SW-GW) interactions. However, it falls short of effectively simulating the hydrological processes of submerged rice paddy field areas. To address this, we developed the hourly SWAT-MODFLOW-PADDY model, which enables integrated surface and groundwater simulations and effectively represents the hydrological responses of submerged paddy fields to high-resolution rainfall data. Our findings demonstrated that the hourly SWAT-MODFLOW-PADDY model could dynamically simulate soil moisture and runoff patterns in submerged paddy fields. Notably, the developed model showed enhanced performance throughout the entire period for hourly flow in the watershed, with an average coefficient of determination (R2) of 0.75, Nash and Sutcliffe efficiency (NSE) of 0.76, and percent bias (PBIAS) of 13.22 compared to the original model (R2 = 0.62, NSE = 0.70, PBIAS = 48.21). The model’s performance in predicting water quality was improved, and it highlighted the significant impact of complex hydrological mechanisms within submerged paddy fields on the spatial distribution of groundwater recharge and stream water volumes exchanged through SW-GW interactions. Given these promising results, the SWAT-MODFLOW-PADDY model could be a valuable resource for managing submerged paddy-dominated agricultural watersheds across various climates and regions.

Reconstructing 3D ocean subsurface salinity (OSS) from T–S mapping via a data-driven deep learning model

Despite the increasing volume of oceanographic data, the available ocean salinity data remains patently insufficient which limits studying ocean dynamics, climate change and the calculation of salinity-related ocean elements. Considering that traditional salinity reconstruction methods often suffer from various factors such as additional constraints, priori physical assumptions and large of specific regression coefficients, a generative adversarial networks (GANs) based deep learning (DL) framework is proposed to directly construct a near real-time, high-resolution daily three-dimensional ocean subsurface salinity (3D OSS) dataset from a data-driven perspective in this study. Four models with different structural combinations are designed in the China’s marginal seas. Experimental results demonstrate that the models can successfully reconstruct the high-precision and high-resolution 3D OSS on a daily scale in 12 depth levels (from 2 m to 200 m). The asymmetric inception-3DGAN model with all enhanced structures has the highest accuracy, the average root-mean-squared error (RMSE) is 0.135psu, the average coefficient of determination (R2) is 0.5641 and the percent bias is 0.436%. Comparing with model without enhanced structures, the average RMSE is decreased by 22.41% when adding all the enhancement structures. Besides, temporal and spatial error analysis are also conducted to evaluate the models’ performance from different aspects. Finally, the model results are used to analyze common ocean elements, such as water mass properties, dynamic fields and geostrophic velocity fields, demonstrating that the 3D OSS dataset construction approach proposed in this study not only provides some new insights into ocean observations, but also has high application values.

Prediction of the bed expansion of a liquid fluidized bed bioreactor applied to wastewater treatment and biogas production

The high potential of water treatment and biogas production systems using liquid fluidization is still underexplored. The design of this equipment is usually done using the simple Richardson-Zaki equation for bed expansion predictions, which is powerful but overlooks the interactions between fluid and particles. In this work, an alternative method based on a force balance on the bed and drag correlations to estimate the bed porosity was proposed. The accuracy of the methods was assessed by comparing bed porosity estimations with experiments carried out in a wide range of regimes (Reynolds numbers between 498 and 18664), using 7 different particles with various diameters (2.66 to 6.37 mm) and densities (1022 to 3585 kg/m3). On average, the fitting between the Richardson-Zaki equation and the experimental results was improved by 60% when the wall effects were considered. The alternative approach using the drag correlations showed promising results, presenting a coefficient of determination higher than 80% for all particles, and better precision in 4 out of the 7 particles compared to Richardson-Zaki. The results show that, in general, both the Richardson-Zaki equation and the drag correlation approach can be used to predict the liquid fluidized bed expansion. However, the proposed approach using drag correlations showed more reliable results, especially when the Rong drag model was applied, with an average coefficient of determination of 0.92. Comparisons with other results in the literature confirm the extent and the scalability of the method. The use of the proposed method to estimate the liquid fluidized bed expansion allows for easier and safer applicability of the technology in areas such as wastewater treatment and biogas production.

Automated analysis for multiplet identification from ultra-high resolution 2D- 1H, 13C-HSQC NMR spectra.

Background: Metabolism is essential for cell survival and proliferation. A deep understanding of the metabolic network and its regulatory processes is often vital to understand and overcome disease. Stable isotope tracing of metabolism using nuclear magnetic resonance (NMR) and mass spectrometry (MS) is a powerful tool to derive mechanistic information of metabolic network activity. However, to retrieve meaningful information, automated tools are urgently needed to analyse these complex spectra and eliminate the bias introduced by manual analysis. Here, we present a data-driven algorithm to automatically annotate and analyse NMR signal multiplets in 2D- 1H, 13C-HSQC NMR spectra arising from 13C - 13C scalar couplings. The algorithm minimises the need for user input to guide the analysis of 2D- 1H, 13C-HSQC NMR spectra by performing automated peak picking and multiplet analysis. This enables non-NMR specialists to use this technology. The algorithm has been integrated into the existing MetaboLab software package. Methods: To evaluate the algorithm performance two criteria are tested: is the peak correctly annotated and secondly how confident is the algorithm with its analysis. For the latter a coefficient of determination is introduced. Three datasets were used for testing. The first was to test reproducibility with three biological replicates, the second tested the robustness of the algorithm for different amounts of scaling of the apparent J-coupling constants and the third focused on different sampling amounts. Results: The algorithm annotated overall >90% of NMR signals correctly with average coefficient of determination ρ of 94.06 ± 5.08%, 95.47 ± 7.20% and 80.47 ± 20.98% respectively. Conclusions: Our results indicate that the proposed algorithm accurately identifies and analyses NMR signal multiplets in ultra-high resolution 2D- 1H, 13C-HSQC NMR spectra. It is robust to signal splitting enhancement and up to 25% of non-uniform sampling.

Inversion of Soil Moisture on Farmland Areas Based on SSA-CNN Using Multi-Source Remote Sensing Data

Soil moisture is a crucial factor in the field of meteorology, hydrology, and agricultural sciences. In agricultural production, surface soil moisture (SSM) is crucial for crop yield estimation and drought monitoring. For SSM inversion, a synthetic aperture radar (SAR) offers a trustworthy data source. However, for agricultural fields, the use of SAR data alone to invert SSM is susceptible to the influence of vegetation cover. In this paper, based on Sentinel-1 microwave remote sensing data and Sentinel-2 optical remote sensing data, a convolution neural network optimized by sparrow search algorithm (SSA-CNN) was suggested to invert farmland SSM. The feature parameters were first extracted from pre-processed remote sensing data. Then, the correlation analysis between the extracted feature parameters and field measured SSM data was carried out, and the optimal combination of feature parameters for SSM inversion was selected as the input data of the subsequent models. To enhance the performance of the CNN, the hyper-parameters of CNN were optimized using SSA, and the SSA-CNN model was built for SSM inversion based on the obtained optimal hyper-parameter combination. Three typical machine learning approaches, including generalized regression neural network, random forest, and CNN, were used for comparison to show the efficacy of the suggested method. With an average coefficient of determination of 0.80, an average root mean square error of 2.17 vol.%, and an average mean absolute error of 1.68 vol.%, the findings demonstrated that the SSA-CNN model with the optimal feature combination had a better accuracy among the 4 models. In the end, the SSM of the study region was inverted throughout four phenological periods using the SSA-CNN model. The inversion results indicated that the suggested method performed well in local situations.

An Independent Validation of SoilGrids Accuracy for Soil Texture Components in Croatia

While SoilGrids is an important source of soil property data for a wide range of environmental studies worldwide, there is currently an extreme lack of studies evaluating its accuracy against independent ground truth soil sampling data. This study aimed to provide a comprehensive insight into the accuracy of SoilGrids layers for three physical soil properties representing soil texture components (clay, silt, and sand soil contents) using ground truth data in the heterogeneous landscape of Croatia. These ground truth data consisted of 686 soil samples collected within the national project at a 0–30 cm soil depth, representing the most recent official national data available. The main specificity of this study was that SoilGrids was created based on zero soil samples in the study area, according to the ISRIC WoSIS Soil Profile Database, which is very sparse for the wider surroundings of the study area. The accuracy assessment metrics indicated an overall low accuracy of the SoilGrids data compared with the ground truth data in Croatia, with the average coefficient of determination (R2) ranging from 0.039 for silt and sand to 0.267 for clay, while the normalized root-mean-square error (NRMSE) ranged from 0.362 to 2.553. Despite the great value of SoilGrids in a vast range of environmental studies, this study proved that the accuracy of its products is highly dependent on the presence of ground truth data in the study area.

Machine learning assisted prediction of creep data of India specific reduced activation ferritic martensitic steel

The present study demonstrates the application of machine learning approach for predicting the creep deformation, rupture strain and rupture life of India specific reduced activation ferritic martensitic (INRAFM) steel. In this direction, various regression models were employed and found that the tree-based ensemble method (Extra trees regression (ETR)) offers better prediction of creep behaviour with the root mean square error (RMSE), average cross-validation score and coefficient of determination (R2) values of 0.00203, 0.979 and 0.996 respectively as compared to other models and which was used for further analysis of creep data. Initially, the creep data of INRAFM steel obtained from creep experiments for different stresses (σ) (200, 220, 240 and 260 MPa) at a test temperature (T) of 823 K was used to train the model for predicting strain values (ε) as output, namely ε = f (σ, T, t) approach, where t is time in hours (h). Subsequently, to assess the predictive capabilities of the model, the predicted data for the test condition of 250 MPa and 823 K was compared with experimental data. A good match was found between the predicted and experimental results with a correlation coefficient (Rcc) of 0.994. Later, the model was applied for predicting the creep curves at intermediate stress levels for the same temperature. Additionally, an effort has been made to predict the rupture time of the steel by providing strain as input variable, namely t = f (σ, T, ε) approach. The predicted rupture time values corresponding to different rupture strains are close to the experimental data. A comparison between both the predictive approaches (based on ε = f (σ, T, t) and t = f (σ, T, ε)) was carried out and presented. The results obtained in the present work reveal the potential of ETR approach for prediction of creep data.

The system of self-consistent models for pesticide toxicity to Daphnia magna

Quantitative structure-property/activity relationships (QSPRs/QSARs) are a tool of modern theoretical and computational chemistry. The self-consistent model system is both a method to build up a group of QSPR/QSAR models and an approach to checking the reliability of these models. Here, a group of models of pesticide toxicity toward Daphnia magna for different distributions into training and test sub-sets is compared. This comparison is the basis for formulating the system of self-consistent models. The so-called index of the ideality of correlation (IIC) has been used to improve the above models’ predictive potential of pesticide toxicity. The predictive potential of the suggested models should be classified as high since the average value of the determination coefficient for the validation sets is 0.841, and the dispersion is 0.033 (on all five models). The best model (number 4) has an average determination coefficient of 0.89 for the external validation sets (related to all five splits).

Characterization methods for natural fractures distribution in shale and tight reservoirs

Aperture distribution and spatial arrangement are fundamental characteristics of natural fractures. Since it is impossible to directly measure the aperture of all existing fractures, a power law (fractal model) has been commonly used to describe fracture apertures, which has also been extended to estimate fracture spacing and macrofractures density. Although a power law (fractal model) has commonly been used to describe fracture apertures, data points in small and large fracture size ranges tend to deviate from this distribution. In this study, a Variable Shape Distribution (VSD) method was derived from a fractal theory to model fracture size distribution. The VSD method was compared with seven other commonly used models. Eleven fracture datasets collected from five countries on four continents were regressed using these methods. The scale-free methods of the VSD and power law models showed more advantages than the scale-dependent methods. The VSD method was found to best fit all variable aperture size distribution patterns, with an average coefficient of determination of 0.99. The average fractal dimension for all samples calculated by the VSD method (1.36) was slightly higher than that of the power law (1.06). This study is unique in showing that the VSD method can solve a boundary characterization problem that has been widely neglected in previous studies. With the assumption of an even fracture distribution, the VSD method was further applied to estimate average fracture spacing, predict a threshold fracture length that controls the linkage of fractures, and predict fractures outside of the measurement range. This study not only proposes an advanced fractal method to model aperture size distributions in shale and tight rocks but also helps to better understand the importance of fractal dimensions and boundary characterizations.

Modelling of ultrasonic assisted osmotic dehydration of cape gooseberry using adaptive neuro-fuzzy inference system (ANFIS)

In the present investigation, the cape gooseberry (Physalis peruviana L.) was preserved by the application of osmotic dehydration (sugar solution) with ultrasonication. The experiments were planned based on central composite circumscribed design with four independent variables and four dependent variables, which yielded 30 experimental runs. The four independent variables used were ultrasonication power (XP) with a range of 100–500 W, immersion time (XT) in the range of 30–55 min, solvent concentration (XC) of 45–65 % and solid to solvent ratio (XS) with range 1:6–1:14 w/w. The effect of these process parameters on the responses weight loss (YW), solid gain (YS), change in color (YC) and water activity (YA) of ultrasound assisted osmotic dehydration (UOD) cape gooseberry was studied by using response surface methodology (RSM) and adaptive neuro-fuzzy inference system (ANFIS). The second order polynomial equation successfully modeled the data with an average coefficient of determination (R2) was found to be 0.964 for RSM. While for the ANFIS modeling, Gaussian type membership function (MF) and linear type MF was used for the input and output, respectively. The ANFIS model formed after 500 epochs and trained by hybrid model was found to have average R2 value of 0.998. On comparing the R2 value the ANFIS model found to be superior over RSM in predicting the responses of the UOD cape gooseberry process. So, the ANFIS was integrated with a genetic algorithm (GA) for optimization with the aim of maximum YW and minimum YS, YC and YA. Depending on the higher fitness value of 3.4, the integrated ANFIS-GA picked the ideal combination of independent variables and was found to be XP of 282.434 W, XT of 50.280 min, XC of 55.836 % and XS of 9.250 w/w. The predicted and experimental values of response at optimum condition predicted by integrated ANN-GA were in close agreement, which was evident by the relative deviation less than 7%.

Enhancing Soil Mapping with Hyperspectral Subsurface Images generated from soil lab Vis-SWIR spectra tested in southern Brazil

The Remote Sensing (RS) products involving the visible, near-infrared and short-wave infrared (Vis–NIR-SWIR, simply Vis-SWIR) wavelengths are applicable for spatial prediction of soil properties, usually in the process called Digital Soil Mapping (DSM). The multispectral optical orbital sensors lack spectral resolution, while the Proximal Soil Sensing (PSS) offers many application possibilities. The limited spectral resolution and soil cover are the main challenging aspects for DSM. The objective of the study was to combine the soil lab Vis-SWIR spectra within DSM technique to create new hyperspectral images to use as covariates in a novel method of soil mapping. The advantages of the method were demonstrated throughout the spatial prediction of the Total Carbon (TC) content on soils of the upper part of Itatiaia National Park (INP), (Rio de Janeiro and Minas Gerais States, southeastern Brazil). The covariates applied were multispectral orbital bands from Sentinel 2, relief with its terrain derivations, geology and geomorphology. Using uppermost soil horizon lab Vis-SWIR spectra information from 72 points in the upper part of INP, 130 hyperspectral images were generated, in other words, Hyperspectral Subsurface Image. The validation methods were 8-fold cross-validation (CV) and External Validation (EV) running alongside within Random Forest algorithm, where randomness was locked. The DSM reaches an average CV coefficient of determination (R2) of 0.39 and Root Mean Square Error (RMSE) of 4.6, while creating a new model with a set of hyperspectral images gave a CV R2 of 0.60 and RMSE of 4.06. The EV also presented an advantage for the second approach. The results support the method as the first strong integration between PSS and DSM, named by the authors as Hyperspectral Soil Mapping (HSM), which proved to be more efficient for mapping TC due to the pure soil lab Vis-SWIR spectra signal (free of atmospheric influence and vegetation cover). The method can be applied in dense or sparsely vegetated areas, for agricultural or conservation purposes, for various soil properties, with each and every wavelength.

EMPLOYEE PERFORMANCE VIEWED FROM ORGANIZATIONAL CULTURE, WORK ENVIRONMENT, AND TRAINING (Study at Sahid Hotel) SURAKARTA

This study looked into how training, work environment, and organizational culture affected employee performance at Hotel Sahid Jaya Solo. The classical assumption test, hypothesis testing, coefficient of determination, and multiple linear regression tests are among the data analysis methods used in this quantitative study. 80 employees made up the study's sample. 40 permanent employees of the Hotel Sahid Jaya Solo make up the sample. Purposive sampling was the method of selection employed in this study since there were various requirements for selection, one of which was that only permanent employees with a minimum of one year of employment were included in the samples. The results of this study show that organizational culture has positive and significant effects on employees' work lives, as do labor unions and work environments, while training has negative and insignificant effects on employees' work lives. The average coefficient of determination for each variable has a contribution of 81.9%, and the average coefficient of determination for each additional variable in this study is 18.1%.
 
 Keywords: Organizational Culture, Work Environment, Training, Employee Performance

Artificial Neural Network Model for Membrane Desalination: A Predictive and Optimization Study

Desalination is a sustainable method to solve global water scarcity. A Response Surface Methodology (RSM) approach is widely applied to optimize the desalination performance, but further investigations with additional inputs are restricted. An Artificial neuron network (ANN) method is proposed to reconstruct the parameters and demonstrate multivariate analysis. Graphene oxide (GO) content, Polyhedral Oligomeric Silsesquioxane (POSS) content, operating pressure, and salinity were combined as input parameters for a four-dimensional regression analysis to predict the three responses: contact angle, salt rejection, and permeation flux. Average coefficient of determination (R2) values ranged between 0.918 and 0.959. A mathematical equation was derived to find global max and min values. Three objective functions and three-dimensional diagrams were applied to optimize effective cost conditions. It served as the database for the membranologists to decide the amount of GO to be used to fabricate membranes by considering the effects of operating conditions such as salinity and pressure to achieve the desired salt rejection, permeation flux, contact angle, and cost. The finding suggested that a membrane with 0.0063 wt% of GO, operated at 14.2 atm for a 5501 ppm salt solution, is the preferred optimal condition to achieve high salt rejection and permeation flux simultaneously.

Kinetics of Electrically Enhanced Boron Removal From Silicon Using CaO-SiO2 and CaO-SiO2-Al2O3 Slag

An approach in analyzing the kinetics of reacting metallurgical system enhanced by applied electrical potential difference has been proposed. The approach accounted the electrochemical mechanism by combining Fick’s first law and Nernst–Planck equation, building upon the approach by Kim et al. and extending it to simultaneously solve the key kinetics parameters of boron diffusivity in slag (D(B)) and potential difference ({Delta phi }_{s}) across the slag phase. The approach was utilized to examine the kinetics of enhanced boron removal from silicon with CaO-SiO2 and CaO-SiO2-Al2O3 slags, in the context of silicon recycling and refining. The model was used to describe the mobility of boron in the molten silicon and slag phases, i.e., boron mass transfer coefficient in liquid silicon (km), in the slag (ks), and the diffusivity of boron in slag phase (D(B)). The results demonstrated that the new kinetics model fit well with the experimental data with an average coefficient of determination (R2 value) of 0.91. The ks and D(B) were calculated to be in the range of 0.9 to 1.3 × 10–6 and 1.1 to 29.2 × 10–9 m2 s−1, respectively. The application of external voltage was observed to reduce B final concentration in the silicon phase by 18 pct from approximately 120 to 100 ppmw in all samples. The addition of Al2O3 in the slag phase consistently reduced the mobility of boron in the slag phase by approximately 50 pct.

Forecasting the Degradation of Vitamin C Concentration in Commonly Consumed Vegetable Cabbage (Brassica oleracea) dipped in Different Pre-treatment Solutions

Vitamin C is considered an essential vitamin that is commonly found in most fruits and vegetables. It is susceptible to easy degradation, especially during pre-treatment and storage. This study aimed at forecasting the degradation of vitamin C in commonly consumed vegetable (cabbage) dipped in different pre-treatment solutions at different time intervals. The samples after dipping at different time intervals were prepared for analysis. Evaluation of the ascorbic acid content of the vegetable was determined using High-Performance Liquid Chromatography (HPLC). This consists of an isocratic elution procedure with ultraviolet-visible detection at 245 nm. The half-lives and rate constants were calculated using the integrated law method. Forecasts were determined using time series analysis. Degradation of vitamin C in this study followed a first-order kinetic model, and the average coefficient of determination (R2-value) was greater than 0.9413. The rate constants of vitamin C degradation for the vegetable dipped in different pretreatment solutions (sodium chloride, sodium benzoate, sodium metabisulfite and vinegar) at different time intervals were 0.0804, 0.1049, 0.0706 and 0.0553 minutes-1; half-lives were 8.2322, 7.3896, 10.9675, and 12.1086 minutes, respectively. The vegetable dipped in different pretreatments for 90 minutes exhibited ln(C) forecast of -2.2057, -4.6307, -1.1746, and 0.0789, respectively. The coefficient of correlation for sodium chloride, sodium benzoate, sodium metabisulfite, and vinegar are 0.084, 0.093, 0.063 and 0.059 respectively. The kinetic models were formulated using predicted initial contents, processing time, and measured contents. The vegetable dipped in vinegar pretreatment solution using ln(C) =ln(C0) - 0.0553t gave the best model. From the results, the most appropriate pretreatment solution for enhancing the shelf life of cabbage is synthetic vinegar (prepared from acetic acid) because it has a lower rate constant, lower coefficient of correlation, and the longest half-life.

Sediment load estimation using a novel regionalization sediment-response similarity method for ungauged catchments

The development and application of reliable hydrological models are challenging in ungauged or poorly gauged catchments. Although several regionalization methods have been developed for predicting hydrological variables in ungauged catchments, a large uncertainty usually exists in the prediction because previous methods typically depended on several static catchment attributes or long-term mean climatic descriptors, thereby neglecting the spatiotemporal variability of the climate. In this study, we propose a new regionalization method called sediment-response similarity (SRS) using the soil and water assessment tool model and self-organizing maps to estimate sediment load in ungauged catchments, considering spatiotemporal variability and the sediment load relation to rainfall characteristics of individual catchments. The performance of SRS was evaluated by comparing it against the conventional regionalization method (i.e., physical similarity) and calibration model results, in four gauged catchments of the lower Mekong River basin. The SRS method showed improved performance over the conventional approach in estimating sediment loads, with an average Nash-Sutcliffe efficiency (NSE) and coefficient of determination (R2) of 0.75 and 0.76, respectively, which were close to the respective values of NSE and R2 = 0.77, of the calibration model. Additionally, the SRS approach showed an error reduction of up to 7 %, compared with that of the physical similarity method, indicating the potential of the proposed regionalization method in estimating catchment-wide sediment load in ungauged catchments. The findings indicate that the SRS method ideally determines the similarity of sediment loads between gauged and ungauged catchments. The SRS approach effectively tackled the main challenge of selecting catchment attributes in the conventional regionalization method and minimizing the uncertainty of sediment prediction in ungauged catchments. This novel SRS method is a promising method for estimating, not only sediment load, but also other hydrological variables and rainfall-driven phenomena in the ungauged catchments globally.

All-in-one proxy to replace 4D seismic forward modeling with machine learning algorithms

Time-lapse seismic data provides valuable information to assist reservoir monitoring, model-based reservoir management, and development activities. 4D seismic information can be used quantitatively to estimate saturation-pressure changes or update reservoir simulation models through a data assimilation process, which traditionally requires a 4D seismic forward model that includes two steps: (1) petro-elastic model to relate rock and fluid properties to elastic attributes and (2) seismic model to depict wave propagation in the reservoir. The traditional forward model brings some complications in quantitative applications, such as time-lapse seismic history matching. Its multidisciplinary nature is a significant bottleneck to update simulation models, once observed 4D seismic data is used with production data in the assimilation process. Furthermore, it is time-consuming, especially in three-dimensional simulation models within data assimilation with several iterations. Here, the traditional forward model needs to be run hundreds or even thousands of times. Aside from being time-consuming, it requires substantial computer memory for complex geology, where more sophisticated seismic models are needed. In 4D seismic quantitative applications, the timely use of the information and its full benefits fade away due to the computational cost and time of the 4D seismic forward model. This research proposes a proxy (we call it, S4D-Proxy) to replace the traditional approach. The S4D-Proxy leverages machine learning models to detect hidden patterns and learn relations between input features (e.g., porosity and saturation-pressure changes) and the target (time-lapse difference of seismic amplitude). Training data are prepared and fed to the machine learning algorithms to relate the inputs and the desired output. The performances of the machine learning models are evaluated based on a numerical measure (coefficient of determination) and visual comparison of the results with the traditional forward model. Our results show that the average coefficient of determination for the test dataset is in an acceptable range. Moreover, the visual comparison of the proxy predictions with those from the traditional approach shows high similarity. Most hardening and softening 4D signals are reproduced with the proxy models. The main advantage of our approach is that it lowers the computational cost and time. The application of the proxy in data assimilation process could offer a significant speed advantage with faster 4D seismic forward modeling for data assimilation iterations. Unlike the traditional forward model, which is one step (petro-elastic model) then another (seismic model), our approach performs the forward modeling at once (all-in-one proxy model). It also offers an alternative 4D seismic forward model for time-lapse seismic feasibility study. All these advantages make the S4D-Proxy valuable and practical in permanent reservoir monitoring (PRM), where the reduced turnaround time in the forward model indicates the timely use of the 4D seismic information.

In Silico Simulation of Impacts of Metal Nano-Oxides on Cell Viability in THP-1 Cells Based on the Correlation Weights of the Fragments of Molecular Structures and Codes of Experimental Conditions Represented by Means of Quasi-SMILES.

A simulation of the effect of metal nano-oxides at various concentrations (25, 50, 100, and 200 milligrams per millilitre) on cell viability in THP-1 cells (%) based on data on the molecular structure of the oxide and its concentration is proposed. We used a simplified molecular input-line entry system (SMILES) to represent the molecular structure. So-called quasi-SMILES extends usual SMILES with special codes for experimental conditions (concentration). The approach based on building up models using quasi-SMILES is self-consistent, i.e., the predictive potential of the model group obtained by random splits into training and validation sets is stable. The Monte Carlo method was used as a basis for building up the above groups of models. The CORAL software was applied to building the Monte Carlo calculations. The average determination coefficient for the five different validation sets was R2 = 0.806 ± 0.061.