Model R2 Research Articles

Predictive Modelling of Alkali-Slag Cemented Tailings Backfill Using a Novel Machine Learning Approach

This study utilizes machine learning (ML) techniques to predict the performance of slag-based cemented tailings backfill (CTB) activated by soda residue (SR) and calcium carbide slag (CS). An experimental database consisting of 240 test results is utilized to thoroughly evaluate the accuracy of seven ML techniques in predicting the properties of filling materials. These techniques include support vector machine (SVM), random forest (RF), backpropagation (BP), genetic algorithm optimization of BP (GABP), radial basis function (RBF) neural network, convolutional neural network (CNN), and long short-term memory (LSTM) network. The findings reveal that the RBF and SVM models demonstrate significant advantages, achieving a coefficient of determination (R2) of approximately 0.99, while the R2 for other models ranges from 0.86 to 0.98. Additionally, a dynamic growth model to predict strength is developed using ML techniques. The RBF model accurately predicts the time required for filling materials to reach a specified strength. In contrast, the BP, SVM, and CNN models show delays in predicting this curing age, and the RF, GABP, and LSTM models tend to overestimate the strength of the filling material when it approaches or fails to reach 2 MPa. Finally, the RBF model is employed to perform coupling analysis on filling materials with various mix ratios and curing ages. This analysis effectively predicts the changes in filling strength over different curing ages and raw material contents, offering valuable scientific support for the design of filling materials.

Leveraging graph neural networks and gate recurrent units for accurate and transparent prediction of baseball pitching speed

Long short-term memory (LSTM) networks are widely used in biomechanical data analysis but have the significant limitations in interpretability and decision transparency. Combining graph neural networks (GNN) with gate recurrent units (GRU) may offer a better solution. This study proposes and validates a hybrid GNN-GRU model for predicting baseball pitching speed and enhancing its interpretability using layer-wise relevance propagation (LRP). C3D data from 53 baseball athletes were downloaded from a public dataset. Kinematic features of 9 joints and pitching speed during the pitching process were calculated using Visual3D, resulting in a total of 208 valid pitches. The feature data were input into both LSTM and GNN-GRU hybrid models, with hyperparameters tuned using particle swarm optimization. LRP was employed to obtain the contribution rate changes of kinematic features to the prediction results throughout the pitching cycle. The prediction accuracy of the models was evaluated using mean absolute error (MAE), mean squared error (MSE), and R-squared (R2). The results showed that there were the significant statistical differences in the MAE and R2 metrics between the LSTM model and the GNN-GRU model in predicting pitching speed on the test set. The MAE (P = 0.000, Z = − 5.170, Cohen’s d = 1.514) and R2 (P = 0.000, Z = − 2.981, Cohen’s d = 2.314) of the LSTM model were significantly lower than those of the GNN-GRU model. Compared to LSTM, the GNN-GRU model achieved better prediction accuracy but was potentially more susceptible to the influence of data variability. Moreover, the GNN-GRU-based model demonstrated the better interpretability and decision transparency.

The Role of Cognitive Performance in Older Europeans’ General Health: Insights from Relative Importance Analysis

This study explores the role of cognitive performance in the general health of older Europeans aged 50 and over, focusing on gender differences, using data from 336,500 respondents in the sixth wave of the Survey of Health, Aging, and Retirement in Europe (SHARE). Cognitive functioning was assessed through self-rated reading and writing skills, orientation in time, numeracy, memory, verbal fluency, and word-list learning. General health status was estimated by constructing a composite index of physical and mental health-related measures, including chronic diseases, mobility limitations, depressive symptoms, self-perceived health, and the Global Activity Limitation Indicator. Participants were classified into good or poor health status, and logistic regression models assessed the predictive significance of cognitive variables on general health, supplemented by a relative importance analysis to estimate relative effect sizes. The results indicated that males had a 51.1% lower risk of reporting poor health than females, and older age was associated with a 4.0% increase in the odds of reporting worse health for both genders. Memory was the strongest predictor of health status (26% of the model R2), with a greater relative contribution than the other cognitive variables. No significant gender differences were found. While this study estimates the odds of reporting poorer health in relation to gender and various cognitive characteristics, adopting a lifespan approach could provide valuable insights into the longitudinal associations between cognitive functioning and health outcomes.

Two-stage cascade learning for accurate vegetation coverage estimation in Qilian County using Sentinel-2 satellite data

ABSTRACT Fractional Vegetation Cover (FVC) is an important parameter reflecting vegetation status, accurately grasping the change in vegetation cover can help in evaluating ecosystem quality and maintaining its functions. Based on Sentinel-2 multispectral remote sensing data, this paper firstly proves that the ensemble learning method XGBoost can improve the estimation accuracy (R2 = 0.9179, RMSE = 0.1399, MAE = 0.0609). The factors influencing the estimation of vegetation coverage were discussed in this process. The results show that the FVC estimation model is the best when considering VIRE1, VIRE2, VIRE3, SWIR1, SWIR2, NDVI, SAVI and EVI attributes. On this basis, the two-stage cascade learning for vegetation coverage estimation is put forward to construct the prediction model by combining clustering and ensemble learning. The strategy firstly uses an unsupervised learning algorithm to process the data initially and output the coarse-grained segmentation results, thus reducing the data processing complexity. Then, the supervised learning algorithm is used to fine-tune these rough results and output finer segmentation results. This method combines the advantages of unsupervised and supervised learning to improve classification accuracy, model reliability, and overall performance. Finally, the R2 of the cascade learning model composed of K-means and XGBoost reaches 0.9796, the RMSE drops to 0.0423, and the MAE is 0.0294. By comparing the estimation results of different cascade models, the superiority and applicability of the proposed method were verified.

Investigation on Thermal Conductivity of Soil Under Freeze–Thaw Action Based on Machine Learning Models

Thermal conductivity is a crucial factor for the soil, which is significantly affected by environmental conditions. Based on the variation in the thermal conductivity and the influencing factors of silty clay obtained by the freeze–thaw cycle test, this paper adopted four machine learning models optimized by particle swarm optimization (PSO), including the artificial neural network model (ANN), random forest model (RF), support vector machine model (SVM), and extreme gradient boosting model (XGBoost) to predict the thermal conductivity of the soil. Meanwhile, mean absolute error (MAE), root mean square error (RMSE), and correlation coefficient(R2) were used to evaluate the accuracy of the models. The accuracy of the machine learning model and empirical model were also compared. Then, the Monte Carlo simulation was used to analyze the stability of the models. The research results showed that the predicted performance of the machine learning models is significantly better than the empirical models. Among all the machine learning models, the R2 of the PSO-ANN model is above 0.95, while both RMSE and MAE values are below 0.02 (W·m⁻¹·K⁻¹). In addition, the stability order of the machine learning models is PSO-XGBoost, PSO-ANN, PSO-RF, and PSO-SVM. Therefore, comprehensively considering the accuracy and stability of the four machine learning models, the PSO-ANN model is recommended to predict soil’s thermal conductivity under freeze–thaw action.

An Adaptive Prediction Framework of Ship Fuel Consumption for Dynamic Maritime Energy Management

Accurate prediction of fuel consumption is critical for achieving efficient and low-carbon ship operations. However, the variability of the marine environment introduces significant challenges, as it leads to dynamic changes in monitoring data, complicating real-time and precise fuel consumption prediction. To address this issue, the authors proposed an incremental learning-based prediction framework to enhance adaptability to temporal dependencies in fuel consumption data. The framework dynamically adjusts a dual adaption mechanism for input features and target labels while incorporating rolling retraining to enable continuous model updates. The effectiveness of the proposed approach was validated using a real-world dataset from an LPG carrier, where it was benchmarked against conventional machine learning models, including Random Forest (RF), Linear Regression (LR), Support Vector Machine (SVM), and Multi-Layer Perceptron (MLP). Experimental results demonstrate that the proposed approach could significantly improve prediction accuracy in both offline and online scenarios. In offline mode, the proposed framework improves the R2 of various machine learning models by at least 21.97%. In online mode, the proposed method increases R2 by at least 17.97%. This work provides a new solution for real-time fuel consumption prediction in dynamic marine environments.

Stranger danger or good Samaritan? A cross-sectional study examining correlates of tolerance of risk in outdoor play among Canadian parents

BackgroundNegative parental perceptions of risk may restrict children’s opportunities for outdoor play. Excessively minimizing children’s exposure to risks in their environment may have a range of developmental consequences. The purpose of this cross-sectional study was to assess correlates of parental tolerance of risk among a large sample of Canadian parents.MethodsIn this cross-sectional study, a sample of 2,291 parents of 7–12 year olds completed online questionnaires assessing a range of potential individual (e.g., gender), social (e.g., neighbourhood cohesion), and environmental (e.g., walkability) correlates of parental tolerance of risk. Logistic regressions were created to examine associations between these factors and odds of being in the most risk averse quartile. The logistic regression was built in hierarchal steps relying on the Akaike information criterion (AIC) and pseudo R2 for model progression.ResultsThe final model had a pseudo R2 of 0.18. Five out of seventeen correlates were associated with risk aversion in parents. Concerns about stranger danger were associated with a higher odds of risk aversion (OR = 2.33, 95%CI[1.93, 2.82]). A higher number of children in the home was associated with lower odds of risk aversion in parents (OR = 0.80, 95%CI[0.69, 0.92], and parents of children born outside of Canada had higher odds of being risk adverse when compared to parents born in Canada (OR = 2.13, 95%CI[1.54, 2.94]). Finally, being very concerned with COVID-19 increased the odds of risk aversion (OR = 3.07, 95%CI[1.93, 5.04], while having a household income of > 100,000 lowered the odds of risk aversion (OR = 0.56, 95%CI[0.36, 0.87]).ConclusionsTailored interventions that reframe perceptions of risk for parents are needed. Such interventions could reframe concerns about stranger danger which persist despite occurrences of stranger abduction being extremely rare. Interventions could also be targeted to immigrant families and those with fewer children as they appear to be more averse to risk. A complementary focus on examining how cultural background influences risk perceptions is needed in future research.

Impact of botulinum toxin type A on ocular pain with neuropathic features.

Impact of botulinum toxin type A on ocular pain with neuropathic features.

Mine water inflow prediction model based on variational mode decomposition and gated recurrent units optimized by improved chimp optimization algorithm

Water damage accidents occur frequently in mines in China, and accurate prediction of incoming water has become an important guarantee for the safe and efficient mining of coal resources. To improve the accuracy of mine water prediction, this paper proposes the VMD-iCHOA-GRU mine water prediction model by selecting and improving it according to the previous research results in decomposition method, time series prediction model and optimization algorithm. After processing the raw data and setting the model parameters, MAE, RMSE, MAPE and R2 are selected as the evaluation indexes of prediction accuracy, and VMD-GRU model, iCHOA-GRU model, CHOA-GRU model and GRU model are selected as the comparison models to validate the advantages of the VMD-iCHOA-GRU model in the prediction of mine inrush water. The results show that the VMD-iCHOA-GRU model has the best prediction effect on the trend of water inflow, with the evaluation index values of 0.00862, 0.01059, 0.02189%, 0.87079, respectively, and with the smallest MAE, RMSE, MAPE, and the largest R2, and the highest prediction accuracy of the VMD-iCHOA-GRU model.

Towards cleaner air in urban areas: The dual influence of urban built environment factors and regional transport.

Towards cleaner air in urban areas: The dual influence of urban built environment factors and regional transport.

Uncertainty Analysis of Remote Sensing Estimation of Chinese Fir (Cunninghamia lanceolata) Aboveground Biomass in Southern China

Forest aboveground biomass (AGB) is not only the basis for forest carbon stock research, but also an important parameter for assessing the forest carbon cycle and ecological functions of forests. However, there are various uncertainties in the estimation process, limiting the accuracy of AGB estimation. Therefore, we extracted the spectral features, vegetation indices and texture factors from remote sensing images based on the field data and Landsat 8 OLI remote sensing images in Southern China to quantify the uncertainties. Then, we established three AGB estimation models, including K Nearest Neighbor Regression (KNN), Gradient Boosted Regression Tree (GBRT) and Random Forest (RF). Uncertainties at the plot scale and models were measured by using error equations to analyze the influences of uncertainties at different scales on AGB estimation. Results were as follows: (1) The R2 of the per-tree biomass model for Cunninghamia lanceolata was 0.970, while the uncertainty of the residual and parameters for per-tree biomass model was 4.62% and 4.81%, respectively; and the uncertainty transferred to the plot scale was 3.23%. (2) The estimation methods had the most significant effects on the remote sensing models. RF was more accurate than other two methods, and had the highest accuracy (R2 = 0.867, RMSE = 19.325 t/ha) and lowest uncertainty (5.93%), which outperformed both the KNN and GBRT models (KNN: R2 = 0.368, RMSE = 42.314 t/ha, uncertainty = 14.88%; GBRT: R2 = 0.636, RMSE = 32.056 t/ha, uncertainty = 6.3%). Compared to KNN and GBRT, the R2 of RF was enhanced by 0.499 and 0.231, while the uncertainty was decreased by 8.95% and 0.37%, respectively. The uncertainty associated with the scale of remote sensing models remains the primary source of uncertainty when compared to the plot scale. On the remote sensing scale, RF is the model with the best estimation effect. This study examines the impact of both plot-scale and remote sensing model-scale methodologies on the estimation of AGB for Cunninghamia lanceolata. The findings aim to offer valuable insights and considerations for enhancing the accuracy of AGB estimations.

Risk factors affecting polygenic score performance across diverse cohorts.

Apart from ancestry, personal or environmental covariates may contribute to differences in polygenic score (PGS) performance. We analyzed the effects of covariate stratification and interaction on body mass index (BMI) PGS (PGSBMI) across four cohorts of European (N = 491,111) and African (N = 21,612) ancestry. Stratifying on binary covariates and quintiles for continuous covariates, 18/62 covariates had significant and replicable R2 differences among strata. Covariates with the largest differences included age, sex, blood lipids, physical activity, and alcohol consumption, with R2 being nearly double between best- and worst-performing quintiles for certain covariates. Twenty-eight covariates had significant PGSBMI-covariate interaction effects, modifying PGSBMI effects by nearly 20% per standard deviation change. We observed overlap between covariates that had significant R2 differences among strata and interaction effects - across all covariates, their main effects on BMI were correlated with their maximum R2 differences and interaction effects (0.56 and 0.58, respectively), suggesting high-PGSBMI individuals have highest R2 and increase in PGS effect. Using quantile regression, we show the effect of PGSBMI increases as BMI itself increases, and that these differences in effects are directly related to differences in R2 when stratifying by different covariates. Given significant and replicable evidence for context-specific PGSBMI performance and effects, we investigated ways to increase model performance taking into account nonlinear effects. Machine learning models (neural networks) increased relative model R2 (mean 23%) across datasets. Finally, creating PGSBMI directly from GxAge genome-wide association studies effects increased relative R2 by 7.8%. These results demonstrate that certain covariates, especially those most associated with BMI, significantly affect both PGSBMI performance and effects across diverse cohorts and ancestries, and we provide avenues to improve model performance that consider these effects.

Risk factors affecting polygenic score performance across diverse cohorts

Apart from ancestry, personal or environmental covariates may contribute to differences in polygenic score (PGS) performance. We analyzed the effects of covariate stratification and interaction on body mass index (BMI) PGS (PGSBMI) across four cohorts of European (N = 491,111) and African (N = 21,612) ancestry. Stratifying on binary covariates and quintiles for continuous covariates, 18/62 covariates had significant and replicable R2 differences among strata. Covariates with the largest differences included age, sex, blood lipids, physical activity, and alcohol consumption, with R2 being nearly double between best- and worst-performing quintiles for certain covariates. Twenty-eight covariates had significant PGSBMI–covariate interaction effects, modifying PGSBMI effects by nearly 20% per standard deviation change. We observed overlap between covariates that had significant R2 differences among strata and interaction effects – across all covariates, their main effects on BMI were correlated with their maximum R2 differences and interaction effects (0.56 and 0.58, respectively), suggesting high-PGSBMI individuals have highest R2 and increase in PGS effect. Using quantile regression, we show the effect of PGSBMI increases as BMI itself increases, and that these differences in effects are directly related to differences in R2 when stratifying by different covariates. Given significant and replicable evidence for context-specific PGSBMI performance and effects, we investigated ways to increase model performance taking into account nonlinear effects. Machine learning models (neural networks) increased relative model R2 (mean 23%) across datasets. Finally, creating PGSBMI directly from GxAge genome-wide association studies effects increased relative R2 by 7.8%. These results demonstrate that certain covariates, especially those most associated with BMI, significantly affect both PGSBMI performance and effects across diverse cohorts and ancestries, and we provide avenues to improve model performance that consider these effects.

The association of origin and environmental conditions with performance in professional IRONMAN triathletes

We have (i) little knowledge about where the fastest professional IRONMAN triathletes originate from and where the fastest races take place and (ii) we have no knowledge of the optimal weather conditions for an IRONMAN triathlon. The aims of the present study were, therefore, (i) to investigate the origin and the fastest IRONMAN race courses for professional triathletes and (ii) to evaluate the best environmental conditions (i.e. water and air temperatures and type of race course) for the fastest IRONMAN race times in professional IRONMAN triathletes. Data of all professional female and male IRONMAN triathletes competing between 2002 and 2022 in all IRONMAN races held worldwide were collected. A total of 6,943 finishers´ records (4,162 from men and 2,781 from women) from 58 different countries participating in 54 different event locations between 2002 and 2022 were considered. Data was analyzed using descriptive statistics and machine learning (ML) regression models. The models considered gender, country of origin, event location, water, and air temperature as independent variables to predict the final race time. Three different ML models were built and evaluated, based on three algorithms, in order of growing complexity and predictive power: Decision Tree Regressor, Random Forest Regressor, and XG Boost Regressor. Most of the athletes originated from the USA (1786), followed by athletes from Germany (674), Canada (426), Australia (396), United Kingdom (342), France (325), and Switzerland (276). Most of the athletes competed in IRONMAN Hawaii (925), IRONMAN Florida (563), IRONMAN Austria (452), IRONMAN France (354), IRONMAN Wisconsin (330), IRONMAN Lanzarote (322) and IRONMAN Texas (313). The Decision Tree and the XG Boost models were the best performing models (r2 = 0.48) and rated the relative feature importances in the order gender, country of origin, water temperature, air temperature and event location. Men were on average ~ 0.8 h faster than women. Switzerland had the fastest and Japan and Slovakia the slowest athletes. IRONMAN Brazil Florianopolis, IRONMAN Barcelona, and IRONMAN Louisville hold the fastest races. Optimal water temperature was over 22 °C and optimal air temperature between 19 and 26 °C. Between 2002 and 2022, most professional IRONMAN triathletes originated from the USA, and most professional IRONMAN triathletes competed in IRONMAN Hawaii. The fastest athletes originated from Switzerland, the fastest race courses were IRONMAN Brazil Florianopolis, IRONMAN Barcelona, and IRONMAN Louisville. The fastest race times were achieved in water temperature warmer than 22 °C and air temperature between 19 and 26 °C.

High-prediction QSAR Modeling Study Based on the Efficacy of a Novel 6-hydroxybenzothiazole-2-carboxamide Targeted Monoamine Oxidase B in the Treatment of Neurodegenerative Diseases.

Neurodegenerative diseases are a group of disorders characterized by progressive neuronal degeneration and death, of which Alzheimer's disease and Parkinson's disease are the most common. These diseases are closely associated with increased expression of monoamine oxidase B (MAO-B), an important enzyme that regulates neurotransmitter concentration, and its overactivity leads to oxidative stress and neurotoxicity, accelerating the progression of neurodegenerative diseases. Therefore, the development of effective MAO-B inhibitors is important for the treatment of neurodegenerative diseases. This study aims to improve the prediction of the efficacy of novel 6-hydroxybenzothiazole- 2-carboxamide compounds in inhibiting MAO-B by improving the quantitative constitutive effect relationship (QSAR) modeling and to provide a theoretical basis for the discovery of novel neuroprotective drugs. The study first optimized the structures of 36 compounds using the heuristic method (HM) in CODESSA software to construct linear QSAR models. Subsequently, key descriptors were screened by using the gene expression programming (GEP) technique to generate nonlinear QSAR models and validate them. The R², F-value, and R²cv of the linear model were 0.5724, 10.3752, and 0.4557, respectively, whereas the nonlinear model constructed by the GEP algorithm showed higher prediction accuracies by achieving R² values of 0.89 and 0.82, and mean squared errors (MSE) of 0.0799 and 0.1215 for the training and test sets, respectively. In addition, molecular docking experiments confirmed that the novel compound 31 was tightly bound to the MAO-B active site with significant inhibitory activity. In this study, we successfully improved the prediction ability of the efficacy of novel 6-hydroxybenzothiazole-2-carboxamide compounds to inhibit MAO-B by improving the QSAR model. This not only provides new drug candidates for the treatment of neurodegenerative diseases, but also provides important theoretical guidance for subsequent drug design and development, which can help accelerate the process of new drug discovery and reduce the disease burden of patients.

Experimental Study on the Photothermal Properties of Thermochromic Glass

Reducing energy consumption in buildings is critical to reducing CO2 emissions and mitigating global warming. Studies have shown that heating and cooling loads account for more than 40% of building energy consumption, and thermochromic glass (TCG) with dynamically adjustable solar transmittance is an excellent way to reduce this load. Although a large number of studies have tested the spectral parameters of TCG in totally transparent and totally turbid states, the impact of dynamic changes in optical properties on the simulation accuracy of building energy consumption has been neglected. In this study, a method is proposed for a hydrogel-type TCG to dynamically test its spectral parameters based on spectrophotometry. The method uses a spectrophotometer and a PID heater to achieve the dynamic optical parameter testing of TCGs at different temperatures. In this paper, the transmission and reflection spectra of the two TCGs at 20~25 °C, 30~35 °C, 40 °C, 45 °C, 50 °C, and 55 °C were obtained, and the regression segmentation functions of visible transmittance and solar transmittance were established. The R2 of the function model is 0.99. In addition, the test results show that the thermochromic glass selected in this paper can selectively transmit different wavelengths of light, and its transmission mainly occurs in the visible and near-infrared wavelengths from 320 to 1420 nm, while the transmission rate of other wavelengths is very low. As the temperature increases, the visible, solar, and ultraviolet transmittances decrease at a similar rate. In addition, the higher the temperature acting on the thermochromic (TC) layer, the greater its haze.

Prediction of Proteolysis-Targeting Chimeras Retention Time Using XGBoost Model Incorporated with Chromatographic Conditions.

Proteolysis-targeting chimeras (PROTACs) are heterobifunctional molecules that target undruggable proteins, enhance selectivity and prevent target accumulation through catalytic activity. The unique structure of PROTACs presents challenges in structural identification and drug design. Liquid chromatography (LC), combined with mass spectrometry (MS), enhances compound annotation by providing essential retention time (RT) data, especially when MS alone is insufficient. However, predicting RT for PROTACs remains challenging. To address this, we compiled the PROTAC-RT data set from literature and evaluated the performance of four machine learning algorithms─extreme gradient boosting (XGBoost), random forest (RF), K-nearest neighbor (KNN) and support vector machines (SVM)─and a deep learning model, fully connected neural network (FCNN), using 24 molecular fingerprints and descriptors. Through screening combinations of molecular fingerprints, descriptors and chromatographic condition descriptors (CCs), we developed an optimized XGBoost model (XGBoost + moe206+Path + Charge + CCs) that achieved an R2 of 0.958 ± 0.027 and an RMSE of 0.934 ± 0.412. After hyperparameter tuning, the model's R2 improved to 0.963 ± 0.023, with an RMSE of 0.896 ± 0.374. The model showed strong predictive accuracy under new chromatographic separation conditions and was validated using six experimentally determined compounds. SHapley Additive exPlanations (SHAP) not only highlights the advantages of XGBoost but also emphasizes the importance of CCs and molecular features, such as bond variability, van der Waals surface area, and atomic charge states. The optimized XGBoost model combines moe206, path, charge descriptors, and CCs, providing a fast and precise method for predicting the RT of PROTACs compounds, thus facilitating their annotation.

Assessing the Impact of Information Sources on Public Engagement in Social Actions: A Study on the Russia-Ukraine Conflict

This study evaluates the impact of information sources on public engagement in social actions related to the Russia-Ukraine conflict. Data were collected through an online questionnaire distributed across Albania, achieving a response rate of 83.8% from 500 distributed questionnaires. The survey ensured anonymity and confidentiality of respondents, enhancing the reliability of the data collected. The analysis began with an assessment of the internal consistency of the questionnaire using Cronbach's alpha, which resulted in a value of 0.723, indicating reliable measures. Factor analysis identified five key components influencing opinions on the Russia-Ukraine conflict: information sources and perception of reality, views on external stances and support, concerns about peace and sovereignty, military intervention and neutrality, and influences on Albania’s stance. Multiple regression analysis demonstrated that these factors significantly predict social action participation related to the conflict, with an overall model R² of 0.727. The analysis revealed that well-informed individuals are more likely to engage in social actions, while concerns about Albania's stance have a negative influence. This research underscores the importance of reliable information and external support views in shaping public engagement in social actions. The findings provide a structured understanding of how various factors influence public perceptions and actions, offering valuable insights for policymakers and researchers in conflict and social behavior studies. This paper has some limitation as; inclusiveness of all groups in society equally and psychological biases can affect our observations. Received: 3 November 2024 / Accepted: 31 December 2024 / Published: 05 January 2025

Waste PET bottle-derived carbon for defluorination of fluoride-polluted water

ABSTRACT This study synthesises expanded graphite (EG) from graphitised carbon from waste polyethylene terephthalate (PET) bottles. The adsorbent material was characterised using FTIR, XRF, XRD, SEM, Raman Spectroscopy, and BET surface area analysis. The synthesised EG defluorinated wastewater, utilising response surface methodology (RSM) for experimental design and optimisation. XRD patterns confirmed the successful synthesis of graphite and EG, demonstrating structural modifications. Raman spectra indicated higher crystalline order in EG, with D and G band shifts and an increased ID/IG intensity ratio from 0.89–1.04. BET analysis revealed a specific surface area of 247.1 m²/g. . FTIR analysis showed abundant functional groups, particularly hydroxyl (-OH) and alkene (C = C). Batch adsorption experiments revealed that fluoride adsorption onto EG depended on pH, time, and initial fluoride concentration. Optimal conditions for fluoride removal, determined using RSM with central composite design (CCD), demonstrated a maximum fluoride removal rate of 97%. Isotherm data fitted both Langmuir and Freundlich model, and kinetics data aligned well with the pseudo-first-order model. ANOVA showed significant effects of contact time, pH, adsorbent dose, and initial fluoride concentration on removal efficiency. The model's R² value of 0.98 and lack of fit value of 0.1554 confirmed the quality of the second-order polynomial model. Optimal conditions for maximum fluoride removal efficiency of 97% were validated at 5 mg/L fluoride concentration, pH 4, adsorbent dose of 5 g/L, and a contact time of 30 min. Therefore, the present study demonstrated efficient fluoride-polluted water treatment using waste-derived EG.

Estimating forest aboveground carbon sink based on landsat time series and its response to climate change

Accurately estimating forest carbon sink and exploring their climate-driven mechanisms are critical to achieving carbon neutrality and sustainable development. Fewer studies have used machine learning-based dynamic models to estimate forest carbon sink. The climate-driven mechanisms in Shangri-La have yet to be explored. In this study, a genetic algorithm (GA) was used to optimize the parameters of random forest (RF) to establish dynamic models to estimate the carbon sink intensity (CSI) of Pinus densata in Shangri-La and analyze the combined effects of multi-climatic factors on CSI. We found that (1) GA can effectively improve the estimation accuracy of RF, the R2 can be improved by up to 34.8%, and the optimal GA-RF model R2 is 0.83. (2) The CSI of Pinus densata in Shangri-La was 0.45–0.72 t C·hm− 2 from 1987 to 2017. (3) Precipitation has the most significant effect on CSI. The combined weak drive of precipitation, temperature, and surface solar radiation on CSI was the most dominant drive for Pinus densata CSI. These results indicate that dynamic models can be used for large-scale long-term estimation of carbon sink in highland forest, providing a feasible method. Clarifying the driving mechanism will provide a scientific basis for forest resource management.