High Coefficient Of Determination Research Articles

A practical equation for predicting saturated hydraulic conductivity of fine-grained soils

The saturated hydraulic conductivity (ks) of soils plays a crucial role in various agricultural and environmental engineering applications, particularly in relation to pollution prevention and water migration. Firstly, the traditional Kozeny-Carman (KC) equation, which are commonly used to estimate ks, has limitations in predicting ks for different types of fine-grained soils based on the analyses of permeability test data in the literature. Secondly, to tackle this issue, a modified KC equation was proposed by introducing an expression for the shape parameter and establishing a relationship between the tortuosity equation and the plastic limit. Additionally, the validation of the proposed equation was conducted using ks values of 25 fine-grained soils obtained from other sources. Finally, a comparison was made with the four commonly used ks models to evaluate its performance. The results indicate that the proposed equation demonstrates a relatively high coefficient of determination and a low root mean square error. This suggests that the proposed equation has the potential to accurately assess ks for fine-grained soils. The predictions for ks using the modified equation showed good agreement with the experimental data mentioned in the literature.

High-performing structural optimization of graphene quantum dots as glyphosate herbicide photoluminescent probes: real case studies and mechanism insights

The widespread usage of the herbicide glyphosate calls for urgent action, aiming at the development of new, simple, low-cost, and eco-friendly detection approaches. In the last decade, investigation of graphene quantum dots (GQDs) as potential optical probes for various pollutants rapidly grew, thanks to their easy-manipulative structure, remarkable photoluminescence (PL) in the visible part of the spectrum, good dispersibility, biocompatibility, and non-toxicity, as well. Herein, a fast, simple, and environmentally friendly method for GQDs structural modification is presented. GQDs raw powder was exposed to γ- rays at three different doses (100, 200, and 300 kGy) in air, without any solvent or reagents. Irradiation of dots under such affordable conditions led to the additional incorporation of oxygen-containing moieties in the GQD structure. For the first time, oxygen-rich GQDs irradiated at a 300 kGy dose were successfully applied as direct turn-off PL probe for glyphosate detection. The high coefficient of determination (R-squared (R2) = 0.99) and very low limit of detection (3.02 μmol L-1) reveal good linearity between the potential sensor and analyte, as well as sensitivity. Glyphosate was successfully detected in celery samples, with a recovery value of 107 ± 0.85%. To evaluate the biological safety of the proposed sensing probe, [3-(4,5-dimethylthiazol-2-yl)-2,5-diphenyltetrazolium bromide] (MTT) and the hemolysis assays were performed. Obtained results show that irradiated and non-irradiated GQDs did not cause the death of MRC-5 cells, and hemolysis of erythrocytes. The obtained results demonstrate that GQDs irradiated in an air medium can be potentially applied for glyphosate detection.

Influence of loading on the heat transfer rate and specific water consumption of detached loosed fresh palm fruits during vertical mini-batch sterilization

This study presents the effect of loading on the heat transfer rate and specific water consumption of detached loosed fresh palm fruits during sterilization. Sterilization is an integral process of palm oil extraction that consumes a lot of water. However, most industrial research in the past focused on fresh fruit bunch (FFB) sterilization dynamics. At the same time, the medium- and small-scale industries sterilize already detached loosed fresh palm fruits (LFPF) that have been removed from the spikelet as purchased from aggregators. Therefore, the process data generated from the sterilization of FFB might not be optimal for sterilizing LFPF. This study, therefore, investigates the transient response of variation in LFPF loading of the sterilization chamber to steam injection during steam sterilization of LFPF at 3 ± 0.5 bars using a vertical, single-peak LFPF sterilizer that combines the boiler and sterilizer in a single unit. The LFPF were loaded at mass intervals of 0.2 kg ranging from 0.2 kg to 2 kg. The vapour temperature dynamics, heat transfer rate, steam energy utilization efficiency and specific water consumption parameters were studied. The average vapour temperature varied from 100 °C to 130 °C for the LFPF mass range of 0.2 to 2 kg at steam injection temperature of 140 °C and pressure of 3 ± 0.5 bars. This temperature range matched the saturated vapour temperature of pure water at 1.0––2.8 bars absolute pressure but slightly lower than the saturated vapour temperature of 133.54 °C for pure steam at 3 bars. The percentage of steam energy utilization effectiveness is inversely related to the steam mass flow rate. While energy effectiveness increased with loading mass, the steam mass flow rate decreased with increased LFPF mass. The value of the heat transfer rate ranged between 1.7––55.4 W, while the specific heat transfer rate ranged between 8.5–––41.8 W/kg. The average specific water consumption ranged from 0.014 to 0.09 kg-water/kg-LFPF, with an average value of 0.031 kg-water/kg-LFPF. This value is lower than 0.112–––0.5 kg-water/kg-FFB, with an average value of 0.256 kg-water/kg-FFB for conventional FFB steam sterilization. This represents an 87.9 % reduction in water consumption in conventional FFB steam sterilization. An empirical model deduced for specific heat transfer rate and water consumption for steam sterilization of LFPF at 3 ± 0.5 bars and vapour temperature range of 100––130 °C showed a high coefficient of determination above 99 %.

Artificial Neural Network-Based Prediction of Physical and Mechanical Properties of Concrete Containing Glass Aggregates

This comprehensive study analyzes the use of crushed glass as both fine and coarse aggregate in concrete, as well as the prediction accuracy of Artificial Neural Networks (ANN). The primary objectives are to understand the interactions between concrete’s constituents and to assess the accuracy of ANN models in predicting concrete’s mechanical and physical properties. This is achieved using a two-decade experimental results dataset of concrete’s compressive and tensile strengths, slump, density, and the corresponding mix design proportions, including waste glass aggregate. A series of 70 concrete samples were carefully built and tested, with compressive strengths varying from 12 to 71 MPa and glass aggregate percentages ranging from 0-100%. These samples served as the basis for the creation of an input dataset and ANN targets. The ANN model underwent intensive training, validation, testing, and statistical regression analysis. The ANN models are exceptionally accurate, with a continuously low error margin of roughly 2%, highlighting their usefulness in matching experimental and predicted results. Validation techniques highlight the models' dependability, with consistently high coefficients of determination (R-values), including 0.99484, demonstrating their robustness in replicating complicated concrete properties. The data analysis shows a unique pattern, with optimum glass aggregate percentages in the range of 10–20%. Beyond this range, there is a noticeable decline in concrete properties. Finally, the study confirms the efficacy of ANN in predictive modeling while also validating the potential of crushed glass to replace natural aggregates in concrete. Doi: 10.28991/CEJ-2024-010-05-018 Full Text: PDF

Optimization of irrigation (ETc) and nitrogen levels under drip fertigation in okra (Abelmoschus esculentus L.) using response surface methodology (RSM)

A comprehensive field investigation was conducted to enhance the productivity, profitability, and water use efficiency (WUE) of summer okra through the optimization of irrigation and nitrogen fertilizer application. The study involved 3 irrigation levels – 0.75 Epan (pan evaporation) as I1, 1.00 Epan as I2, and 1.25 Epan as I3 – as the main plot factors, and 4 nitrogen concentrations – 75% recommended nitrogen dose (RDN) as N1, 100% RDN as N2, 125% RDN as N3, and 150% RDN as N4 – as the subplot variables. The results of the study revealed a significant influence of irrigation and nitrogen levels on various key parameters. Above-ground dry matter, yield, plant height, WUE, net returns, and benefit-to-cost ratio (B:C) exhibited an incremental trend with increasing irrigation and nitrogen levels, up to a certain threshold. Beyond this threshold, further increments in irrigation and nitrogen led to diminishing returns. The models developed for estimating crop yield, above-ground dry matter, plant height, WUE, net returns, and B:C demonstrated impressive accuracy, with high coefficients of determination (R2) and satisfactory precision. The optimized irrigation level (crop evapotranspiration, ETc) ranged from 418.39–441.23 mm. At the same time, the ideal nitrogen application rate was found to be in the range of 167.04–176.13 kg N/ha. These optimal conditions resulted in peak crop yield of 28 295 kg/ha, above-ground dry matter of 6 709.1 kg/ha, plant height of 66.3 cm, WUE of 5.26 kg/m3, B:C of 4.54, and net returns amounting to 441 133 INR/ha. In conclusion, the application of response surface methodology facilitated the identification of the impact of each factor on individual responses, as well as the determination of optimal conditions that simultaneously maximize multiple desirable outcomes. These findings hold significant promise for improving the cultivation of summer okra while optimizing resource use and economic returns.

Landscape and Socioeconomic Factors Determine Malaria Incidence in Tropical Forest Countries.

Deforestation, landscape dynamics, and socioeconomic factors within the tropical Americas, Africa, and Asia may have different impacts on malaria incidence. To evaluate how these drivers affect malaria incidence at the global and regional scale, we collected malaria incidence rates from 2000 to 2019 from 67 tropical countries, along with forest loss, land use change types, and socioeconomic elements. LASSO regression, linear mixed effect modeling, and k-fold cross validation were used to create and evaluate the models. Regionality plays a role in the significance of varying risk factors. The Tropical Americas model had the highest coefficient of determination (marginal R2 = 0.369), while the Africa model showed the highest predictive accuracy with only a 17.4% error rate. Strong associations between tree cover loss (β = -4037.73, p < 0.001) and percentage forest area (β = 5373.18, p = 0.012) in Africa, and percent of key biodiversity areas under protection (β = 496.71, p < 0.001; β = 1679.20, p < 0.001) in the tropical Americas and Asia with malaria incidence indicates that malaria risk should be considered during conservation policy development, and recommends that individual approaches to policy and investment be considered when implementing malaria interventions on different spatial scales.

Effect of pH, Carbonate and Clay Content on Magnesium Measurement Methods on Hungarian Soils

More exact information on soil nutrient management is crucial due to environmental protection, nature conservation, decreasing sources for mining, general precaution, etc. Soil magnesium (Mg) analytical methods of potassium chloride (KCl), Mehlich 3 (M3), water (WA) and cobalt hexamine (CoHex) extractions are compared with an elemental analysis and X-ray fluorescence (XRF) analysis. The ratio of the available to the total Mg content was calculated and compared on the whole dataset. The results showed that the linear regressions between all the pairs of Mg content measurement methods were significant. The linear relationship between the KCl and CoHex methods has the highest determination coefficient (R2 = 0.96), followed by WA–M3 (R2 = 0.68), M3–CoHex (R2 = 0.66) and M3–KCl (R2 = 0.60). The M3 solution demonstrated a greater capacity for extracting Mg from the soil. The second part is the analysis of the influence of CaCO3, pH, soil texture and clay content on the measurable magnesium content of soils. It was established that the extraction methods, the soil and the classification method of the soil properties affect the evaluation. These results may help through the nutrient replenishment and the melioration of soils. These results can help the examination of mineral nutrients, especially the Mg uptake.

A comprehensive analysis of low velocity impact response of [0/±45/90]s thin woven GFRP composites at room temperature

This study is motivated by the need to explore the low-velocity impact behavior of angle-ply thin woven GFRP composites with stacking sequence of [0/±45/90]s, especially the lack of literature concerning damage analysis correlation with a comprehensive range of measurements. The damage diameter, area, and perimeter length are characterized in this study by a novel AutoCAD image processing technique. The test results revealed that specimens subjected to impact energies in the range of 2–30 J are free from edge delamination compared to those tested at 40–50 J. Decreasing the contact duration at impact energy of 60 J is due to perforation accompanied with damage propagation toward the specimen edges and thus, the contact force is sharply dropped from its maximum value of about 4.48kN to 1.3kN. Consequently, both rebound speed and coefficient of restitution dropped to zero. The direct measurement of the energy threshold is increased in the following order: energy threshold at Fmax (2.3–14.9 J), first penetration (load drop) after peak load (23.9–25.6 J), penetration energy threshold (37.9 J), perforation energy threshold (31.1 J), and perforation and crack propagation energies (43.3 J). The perimeter length represents a novel damage parameter, exhibiting a strong correlation with impact energy, as evidenced by a high coefficient of determination of 0.97.

Enhancing photovoltaic energy forecasting: a progressive approach using wavelet packet decomposition

Abstract Accurate photovoltaic (PV) energy forecasting plays a crucial role in the efficient operation of PV power stations. This study presents a novel hybrid machine-learning (ML) model that combines Gaussian process regression with wavelet packet decomposition to forecast PV power half an hour ahead. The proposed technique was applied to the PV energy database of a station located in Algeria and its performance was compared to that of traditional forecasting models. Performance evaluations demonstrate the superiority of the proposed approach over conventional ML methods, including Gaussian process regression, extreme learning machines, artificial neural networks and support vector machines, across all seasons. The proposed model exhibits lower normalized root mean square error (nRMSE) (2.116%) and root mean square error (RMSE) (208.233 kW) values, along with a higher coefficient of determination (R2) of 99.881%. Furthermore, the exceptional performance of the model is maintained even when tested with various prediction horizons. However, as the forecast horizon extends from 1.5 to 5.5 hours, the prediction accuracy decreases, evident by the increase in the RMSE (710.839 kW) and nRMSE (7.276%), and a decrease in R2 (98.462%). Comparative analysis with recent studies reveals that our approach consistently delivers competitive or superior results. This study provides empirical evidence supporting the effectiveness of the proposed hybrid ML model, suggesting its potential as a reliable tool for enhancing PV power forecasting accuracy, thereby contributing to more efficient grid management.

Removal of ciprofloxacin and heavy metals from water by bentonite/activated carbon composite: Kinetic, isotherm, thermodynamic and breakthrough curve modeling studies

This study explores the potential of a new, cost-effective adsorbent for removing ciprofloxacin (CIP) and heavy metals (HMs) from wastewater. This adsorbent is a mesoporous activated carbon (AC) crafted from sugarcane bagasse modified with bentonite (SCBB). The prepared composite was characterized using FTIR, XRD, SEM, and BET techniques. Optimal adsorption conditions were determined, with initial concentrations set at 15 and 300 mg/L, adsorbent doses at 100 and 50 mg, temperatures at 25 and 45 °C, and pH levels at 6 for CIP and HMs, respectively, in batch experiments. Kinetics data confirmed that adsorption follows pseudo-first-order model, with intraparticle diffusion identified as the rate-determining step. Three-parameter models were superior in describing experimental data compared to two-parameter models, with the Sips isotherm model indicating multilayer adsorption beyond monolayer saturation. Hydrophobicity likely plays a key role in CIP adsorption, potentially complemented by hydrogen bonding, while HMs are adsorbed through ion exchange, complexation, and pore diffusion processes. Furthermore, SCBB exhibited excellent adsorption performance (≥90 %) even after ten regeneration cycles. The impact of various operating parameters, including bed depth, feed concentration, and flow rate, were optimized in fixed bed column. Breakthrough data fitting the Dose Response, Thomas, and Yoon-Nelson models yielded high coefficients of determination (R2 ≥ 0.98). The techno-economic analysis identified SCBB preparation ($0.31/kg) as the main cost factor, but still predicts profitability with a payback period of 0.88 years and a break-even point of 58.6 %. Overall, the developed SCBB composite demonstrates significant potential as an efficient, cost-effective, and sustainable adsorbent, with applicability for the treatment of industrial wastewater contaminated with CIP and HMs.

Hybrid emerging model predictive data-driven forecasting of three-phase electrical signals of photovoltaic systems using GBR-LSTM

In numerous industrial contexts, precise analysis and forecasting of electrical signals within three-phase systems are indispensable. As a result, this work presents DeepPhase, a hybrid framework that combines Long Short-Term Memory (LSTM) neural networks with gradient-boosted regression (GBR) to predict the current, voltage, and power of electrical signals. The performance of the model is evaluated in comparison to benchmark models, namely Bidirectional LSTM (BiLSTM), K-Nearest Neighbors (KNN), and LSTM, which utilize essential Key Performance Indicators (KPIs). As demonstrated by its highest Coefficient of Determination (R2) of 0.999, Mean Absolute Error (MAE) of 6.94 × 10−5, Mean Absolute Percentage Error (MAPE) of 0.07 %, and Root Mean Square Error (RMSE) of 0.000156, DeepPhase consistently exhibits predictive precision. For Three-Phase Current, MAE is 2.13 × 10−3, MAPE is 0.01 %, RMSE is 0.062432, and R2 is 0.960596; and for Three-Phase Voltage, MAE is 9.52E-03, MAPE is 0.03 %, RMSE is 0.014, and R2 is 0.999. The results of this study highlight the effectiveness of DeepPhase in analyzing the dynamics of complex Three-Phase electrical signals. This has significant implications for improving decision-making and control strategies in complex electrical systems.

Relationships of infrared thermography temperature with core temperature in goat.

Rectal temperature is widely used as an indicator of animal health. However, rectal temperature is conventionally measured by an invasive method, which may reduce animal welfare. So, this study aimed to determine the relationships between the deep-body (core) temperature and body surface temperatures in goats and develop a linear regression equation to establish the core temperature based on body surface temperatures. Body surface temperatures (head, eye, muzzle, horn, back, scrotum and groin) of goats were measured by infrared thermography (IRT). Ambient temperatures were measured by digital thermometer. Core temperatures were measured by a digital vet thermometer. Pearson correlation analysis was used to analyze the relationship between body surface temperatures, ambient temperature, and core temperature. Simple linear regression analysis was used to develop core temperature assessment equations. Correlation analysis showed that groin temperature was highly correlated with core temperature, and low correlated with ambient temperature. The body surface temperature of other region was low correlated with core temperature, and highly correlated with ambient temperature. Regression analysis showed that the determination coefficient of core temperature assessment equation based on groin temperature was the highest (P < 0.0001, R2 = 0.55), and those based on surface temperature of other regions were low (P < 0.01, R2 ≤ 0.16). We concluded that body surface temperatures obtained by IRT could be used for the assessment of goat core temperature. The core temperature assessment equations developed by the temperature of the body surface, which is less affected by ambient temperature, was found to have a higher determination coefficient than the equations developed using body surface temperature that is more affected by ambient temperature.

Transformer‐based framework for accurate segmentation of high‐resolution images in structural health monitoring

AbstractHigh‐resolution image segmentation is essential in structural health monitoring (SHM), enabling accurate detection and quantification of structural components and damages. However, conventional convolutional neural network‐based segmentation methods face limitations in real‐world deployment, particularly when handling high‐resolution images producing low‐resolution outputs. This study introduces a novel framework named Refined‐Segment Anything Model (R‐SAM) to overcome such challenges. R‐SAM leverages the state‐of‐the‐art zero‐shot SAM to generate unlabeled segmentation masks, subsequently employing the DEtection Transformer model to label the instances. The key feature and contribution of the R‐SAM is its refinement module, which improves the accuracy of masks generated by SAM without the need for extensive data annotations and fine‐tuning. The effectiveness of the proposed framework was assessed through qualitative and quantitative analyses across diverse case studies, including multiclass segmentation, simultaneous segmentation and tracking, and 3D reconstruction. The results demonstrate that R‐SAM outperforms state‐of‐the‐art convolution neural network‐based segmentation models with a mean intersection‐over‐union of 97% and a mean boundary accuracy of 87%. In addition, achieving high coefficients of determination in target‐free tracking case studies highlights its versatility in addressing various challenges in SHM.

An Accurate Approach for Predicting Soil Quality Based on Machine Learning in Drylands

Nowadays, machine learning (ML) is a useful technology due to its high accuracy in constructing non-linear models and algorithms that can adapt to the complexity and diversity of data. Thus, the current work aimed to predict the soil quality index (SQI) from extensive soil data, achieving high accuracy with the artificial neural networks (ANN) model. However, the efficiency of ANN depends on the accuracy of the data that is prepared for training. For this purpose, MATLAB programming language was used to enable the calculation, classification, and compilation of the results into databases within a few minutes. The proposed MATLAB program was highly efficient, accurate, and quick in calculating soil big data for training the machine compared with traditional methods. The database contains 306 vector sets, 80% of them are used for training and the remaining 20% are reserved for testing. The optimal model obtained comprises one hidden layer with 250 neurons and one output layer with a sigmoid function. The ANN achieved a high coefficient of determination (R2) values for SQI estimation, with around 0.97 and 0.98 for training and testing, respectively. The results indicate that 36.93% of the total soil samples belonged to the very high quality class (C1). In contrast, the high quality (C2), moderate quality (C3), low quality (C4), and very low quality (C5) classes accounted for 10.46%, 31.37%, 20.92%, and 0.33% of the samples, respectively. The high contents of CaCO3, pH, sodium saturation, salinity, and clay content were identified as limiting factors in certain areas. The results of this study indicated high accuracy of soil quality assessment using physical, chemical, and fertility soil features in regression analysis with ANN. This method, which is suitable for arid zones, enhances agricultural productivity and decision-making by identifying critical soil quality categories and constraints.

Pemodelan Data Time Series Menggunakan Pendekatan Regresi Polinomial Lokal Pada Data Harga Saham MDKA

&lt;p class="AbstractEnglish"&gt;Investment is an important way to manage finances for profit. One of the most popular investments in Indonesia is buying and selling shares. In addition to getting profits, they also have risks. Therefore, analyzing stock prices before buying and selling is an important key in stock investing. Investors should buy stocks at a low price and sell them at a high price. One of the methods used is parametric regression analysis, but it has assumptions that must be met. A more flexible alternative is local polynomial regression without any particular assumptions. PT Merdeka Copper Gold Tbk with MDKA stock code is a company engaged in the mining and industrialization of gold, silver, and other associated minerals. The study of modeling the lowest daily price of MDKA shares using local polynomial regression showed excellent results. The high coefficient of determination exceeding 67% on the in-sample data indicates strong model performance, and the Mean Absolute Percentage Error (MAPE) value on the out-of-sample data is less than 10%, ensuring excellent model accuracy.&lt;/p&gt;&lt;p class="AbstractEnglish"&gt;&lt;strong&gt;Keywords: &lt;/strong&gt;local polynomial regression; MDKA shares; time series&lt;/p&gt;

Estimating Cotton Yield in the Brazilian Cerrado Using Linear Regression Models from MODIS Vegetation Index Time Series

Satellite remote sensing data expedite crop yield estimation, offering valuable insights for farmers’ decision making. Recent forecasting methods, particularly those utilizing machine learning algorithms like Random Forest and Artificial Neural Networks, show promise. However, challenges such as validation performances, large volume of data, and the inherent complexity and inexplicability of these models hinder their widespread adoption. This paper presents a simpler approach, employing linear regression models fitted from vegetation indices (VIs) extracted from MODIS sensor data on the Terra and Aqua satellites. The aim is to forecast cotton yields in key areas of the Brazilian Cerrado. Using data from 281 commercial production plots, models were trained (167 plots) and tested (114 plots), relating seed cotton yield to nine commonly used VIs averaged over 15-day intervals. Among the evaluated VIs, Enhanced Vegetation Index (EVI) and Triangular Vegetation Index (TVI) exhibited the lowest root mean square errors (RMSE) and the highest determination coefficients (R2). Optimal periods for in-season yield prediction fell between 90 and 105 to 135 and 150 days after sowing (DAS), corresponding to key phenological phases such as boll development, open boll, and fiber maturation, with the lowest RMSE of about 750 kg ha−1 and R2 of 0.70. The best forecasts for early crop stages were provided by models at the peaks (maximum value of the VI time series) for EVI and TVI, which occurred around 80–90 DAS. The proposed approach makes the yield predictability more inferable along the crop time series just by providing sowing dates, contour maps, and their respective VIs.

Machine Learning-Assisted design of boron and nitrogen doped graphene nanosheets with tailored thermomechanical properties

Doping graphene with boron and/or nitrogen enhances its potential for various applications, such as electronics and energy devices. However, these modifications impact the material's properties, influencing its response to external forces, temperature, and heating. Investigating the connection between the structure of co-doped graphene nanosheets and their thermomechanical properties is crucial for accurate predictions and tailored nanosheet engineering. In the present study, molecular dynamics (MD) simulations were performed to compute the thermal and mechanical properties of 300 randomly generated boron/nitrogen co-doped graphene nanosheets with doping concentrations in the range of 0%-15%. Next, the obtained MD results were used to train, tune, and validate a wide spectrum of supervised machine learning models, including linear regression models, regression trees, support vector machines, Gaussian process regression models, kernel approximation models, ensembles of regression trees, and regression neural networks. Our aim is to find models that better estimate, without overfitting, the structure-properties relation of boron/nitrogen co-doped nanosheets. To this end, the models with the highest coefficient of determination (R2) and the lowest root mean square error (RMSE) were utilized. Finally, an appropriate implementation of guided random search algorithms, mainly Genetic Algorithms, was used to solve the inverse problem, i.e., find the nanosheet structure which exhibits the desired set of property values. To this end, thermal conductivity, Young’s modulus, failure stress, and failure strain were specified as target values. A detailed comparison between the employed models and their validation via MD simulations is also included. The achieved results provide sufficient evidence of the accuracy and viability of the applied procedure in both prediction of thermomechanical properties as well as identification of structures with desired properties. This study provides a roadmap that could help scientists and engineers develop nanosheets-based materials with tunable thermomechanical properties, ultimately leading to the creation of innovative and high-performance technologies.

Characterizing future changes in compound flood risk by capturing the dependence between rainfall and river flow: An application to the Yangtze River Basin, China

Compound floods induced by co-occurring multiple drivers may exacerbate the flood impacts and lead to larger flood damage. Exploring future changes in compound flood risk is imperative for flood management and disaster reduction. This study attempts to investigate future changes in compound flood risk across the Yangtze River Basin during 2030 ∼ 2100. Future river flow was projected using an improved hydrological model and pairwise series of extremes of rainfall and river flow were extracted from both observed and projected series. Subsequently, stochastic pairs of rainfall and river flow characterizing compound floods were proportionally sampled from their bivariate joint distributions. The damage from each compound flood was obtained from the flood damage function constructed by Random Forests (RF). Further, the expected annual damage (EAD) was calculated to investigate future changes in compound flood risk. Results show that: (1) Future annual maximums of rainfall and river flow are expected to increase by 14.51 % ∼ 66.13 % and 1.72 % ∼ 55.73 % in the mainstream and northern tributaries, while future annual peak discharge in the southern tributaries (except for the Dongting Lake Basin) is expected to decrease by 4.18 % ∼ 12.30 %. A similar spatial distribution of future changes is also found in the bivariate joint distribution of rainfall and river flow. (2) The high coefficient of determination (R2) of 0.84 indicates the satisfactory simulation and projection capacity of the constructed flood damage function. The positive stepped relationship between flood damage and rainfall or river flow reflects the superposition of multiple flood damage processes. (3) The Han River Basin, the Jialing River Basin, and the two-lakes (the Dongting and Poyang Lakes) area face great threat from compound floods in both historical and future periods. Future compound flood risk is expected to increase by 13.43 % ∼ 46.04 % in these regions except for the Poyang Lake Basin, while future risk is expected to increase by 2.03 % ∼ 46.04 % in the whole basin. The findings help improve the understanding of future flood risk variations in the Yangtze River Basin and provide essential information for damage reduction.

Advancing pediatric head CT dose prediction: correlating patient size metrics with AP and LAT dimensions in Moroccan population

This study aims to establish comprehensive relationships between patient size, focusing on effective diameter (Deff) and water-equivalent diameter (Dw), in conjunction with anterior-posterior (AP) and lateral (LAT) dimensions. The primary goal is to refine precise patient dose estimations in pediatric head computed tomography (CT) examinations. Our examination involved a dataset of 105 pediatric head CT images sourced from a Moroccan pediatric university hospital. These images, selected from the central scanning range, underwent quantification for LAT, AP, Deff, and Dw, with measurements carried out using RadiAnt Dicom Viewer for lateral and anteroposterior dimensions. Our analytical approach encompassed modeling Deff and Dw as functions of LAT, AP, and combined AP + LAT dimensions. Additionally, Dw was modeled as a function of Deff and calculated Size Specific Dose Estimates (SSDE) based on Dw was compared to SSDE computed from one single dimension. The outcomes revealed strong correlations among Deff, Dw, and fundamental geometric dimensions (LAT, AP, and AP + LAT), as indicated by consistently high coefficients of determination (R² > 0.8). SSDE calculated from Dw shows impressive correlation with SSDE computed from a single dimension (R² > 0.9). This study offers insights into the relationships between patient size and critical dimensions, identifying high correlations that can represent a significant advancement in predicting doses for pediatric head CT examinations. This introduces the potential for streamlining the determination of head diameter and dose by relying on a single dimension, thereby enhancing the efficiency of dose predictions by facilitating the monitoring of radiation exposure of this population in clinical routine.

Improvement in Forecasting Short-Term Tropical Cyclone Intensity Change and Their Rapid Intensification Using Deep Learning

Abstract Forecasting the intensity of a tropical cyclone (TC) remains challenging, particularly when it undergoes rapid changes in intensity. This study aims to develop a convolutional neural network (CNN) for 24-h forecasts of the TC intensity changes and their rapid intensifications over the western Pacific. The CNN model, the DeepTC, is trained using a unique loss function, an amplitude focal loss, to better capture large intensity changes, such as those during rapid intensification (RI) events. We showed that the DeepTC outperforms operational forecasts, with a lower mean absolute error (8.9%–10.2%) and a higher coefficient of determination (31.7%–35%). In addition, the DeepTC exhibits a substantially better skill at capturing RI events than operational forecasts. To understand the superior performance of the DeepTC in RI forecasts, we conduct an occlusion sensitivity analysis to quantify the relative importance of each predictor. Results revealed that scalar quantities such as latitude, previous intensity change, initial intensity, and vertical wind shear play critical roles in successful RI prediction. Additionally, the DeepTC utilizes the three-dimensional distribution of relative humidity to distinguish RI cases from non-RI cases, with higher dry–moist moisture gradients in the mid-to-low troposphere and steeper radial moisture gradients in the upper troposphere showed during RI events. These relationships between the identified key variables and intensity change were successfully simulated by the DeepTC, implying that the relationship is physically reasonable. Our study demonstrates that the DeepTC can be a powerful tool for improving RI understanding and enhancing the reliability of TC intensity forecasts.