Environmental Pollution, Год журнала: 2024, Номер 356, С. 124395 - 124395
Опубликована: Июнь 18, 2024
Язык: Английский
Environmental Pollution, Год журнала: 2024, Номер 356, С. 124395 - 124395
Опубликована: Июнь 18, 2024
Язык: Английский
Expert Systems with Applications, Год журнала: 2025, Номер unknown, С. 127363 - 127363
Опубликована: Март 1, 2025
Язык: Английский
Процитировано
0Frontiers in Environmental Science, Год журнала: 2025, Номер 13
Опубликована: Март 28, 2025
Machine learning (ML) models have proven to be an efficient technique for better understanding and quantification of surface water quality, especially in agricultural watersheds where considerable anthropogenic activities occur. However, there is a lack systematic investigations that can examine the application different ML regression settings predict quality using group input variables, including hydrological (e.g., flow), meteorological precipitation), field crop cover) conditions. In this study, multiple models, support vector machine (SVM) trees (RT), were employed on 2-year dataset collected from sand plain sub-watershed southwestern Ontario, Canada (i.e., Lower Whitemans Creek) nitrate chloride concentrations at nine sampling sites within sub-watershed. The prediction capabilities these determined evaluation metrics coefficient determination (R 2 ) root-mean squared error (RMSE). general, Gaussian Process Regression (GPR) model was optimal algorithm 0.99 0.98 respectively training testing). According results feature importance analysis, it found conditions (specifically location site (main channel or tributary site) most crucial variables accurate predictions output variables. This study underscores implemented effectively quantify properties easily measurable parameters. These assist decision makers advancing successful actions steps towards protecting available resources.
Язык: Английский
Процитировано
0Marine Pollution Bulletin, Год журнала: 2025, Номер 216, С. 117977 - 117977
Опубликована: Апрель 18, 2025
Язык: Английский
Процитировано
0The Scientific World JOURNAL, Год журнала: 2025, Номер 2025(1)
Опубликована: Янв. 1, 2025
Background: Foreign direct investment (FDI) is a steadfast contributor to capital flows and plays an indispensable role in driving economic advancement emerging as pivotal avenue for financing growth Bangladesh. Therefore, this study identifies the factors that influence FDI inflows Moreover, authors explored more appropriate model predicting by comparing efficacy of other models’ predictions. Methods: This based on secondary data over period 1973 2021 collected from publicly accessible website World Bank. A generalized additive (GAM) was implemented describing proper splines. The model’s performance assessed using modified R ‐squared, Bayesian information criterion (BIC), Akaike (AIC). Results: Findings depict significant nonlinear relationship between Bangladesh’s key indicators, including GDP, trade openness, external debt, gross formation, national income (GNI) government rates exchange, total reserves, natural resource rent. It also observed GAM ( 2 = 0.987, I C 608.03, B 658.28) outperforms multiple linear regressions polynomial regression FDI, emphasizing superiority capturing complex relationships improving predictive accuracy. Conclusion: along with covariates considered study. believed study’s findings would assist taking efficient initiatives management proactive indicator optimization empower resilience foster sustainable growth. analysis revealed its related risk follow pattern. recommends reliable method suggest can guide policymakers developing strategies increase inflows, stimulate growth, ensure development
Язык: Английский
Процитировано
0Environmental Pollution, Год журнала: 2024, Номер 356, С. 124395 - 124395
Опубликована: Июнь 18, 2024
Язык: Английский
Процитировано
3