Comparison between the WFD approaches and newly developed water quality model for monitoring transitional and coastal water quality in Northern Ireland

The Science of The Total Environment, Journal Year: 2023, Volume and Issue: 901, P. 165960 - 165960

Published: Aug. 3, 2023

This study aims to evaluate existing approaches for monitoring and assessing water quality in waterbodies the North of Ireland using newly developed methodologies. The results reveal significant differences between new technique "one-out, all-out" approach rating quality. found status be "good," "fair," "marginal," whereas classified as "moderate," respectively. outperformed different waterbody types, with high R2 = 1, NSE 0.99, MEF 0 values. Furthermore, final assessment methodologies had lowest uncertainty (<1 %), efficiency measures (NSE MEF) indicate that are bias-free assess at any geographic scale. this proposed effective states transitional coastal Ireland. also highlighted limitations importance updating resource management systems better protection these waterbodies. findings have implications planning other similar regions.

Language: Английский

---

Metaheuristic approaches for prediction of water quality indices with relief algorithm-based feature selection

Ecological Informatics, Journal Year: 2023, Volume and Issue: 75, P. 102122 - 102122

Published: May 9, 2023

Language: Английский

---

A hybrid forecasting method for cooling load in large public buildings based on improved long short term memory

Journal of Building Engineering, Journal Year: 2023, Volume and Issue: 76, P. 107238 - 107238

Published: July 3, 2023

Language: Английский

---

Machine learning models to predict daily actual evapotranspiration of citrus orchards under regulated deficit irrigation

Ecological Informatics, Journal Year: 2023, Volume and Issue: 76, P. 102133 - 102133

Published: May 19, 2023

Precise estimations of actual evapotranspiration (ETa) are essential for various environmental issues, including those related to agricultural ecosystem sustainability and water management. Indeed, the increasing demands production, coupled with increasingly frequent drought events in many parts world, necessitate a more careful evaluation crop requirements. Artificial Intelligence-based models represent promising alternative most common measurement techniques, e.g. using expensive Eddy Covariance (EC) towers. In this context, main challenges choosing best possible model selecting representative features. The objective research is evaluate two different machine learning algorithms, namely Multi-Layer Perceptron (MLP) Random Forest (RF), predict daily citrus orchard typical Mediterranean feature combinations. With features available coming from infield sensors, thorough analysis was performed measure importance, scatter matrix observations, Pearson's correlation coefficient calculation, which resulted selection 12 were calibrated under regulated deficit irrigation (RDI) conditions estimate ETa save water. On average up 38.5% savings obtained, compared full irrigation. Moreover, among input variables adopted, soil content (SWC) appears have prominent role prediction ETa. presented results show that by appropriate features, accuracy proposed remains acceptable even when number reduced only 4. performance achieved method, seven obtaining root mean square error (RMSE) determination (R2) 0.39 mm/day 0.84, respectively. Finally, joint use SWC, weather satellite data significantly improves forecasts meteorological variables.

Language: Английский

---

Water Quality Index Assessment of River Ganga at Haridwar Stretch Using Multivariate Statistical Technique

Molecular Biotechnology, Journal Year: 2023, Volume and Issue: unknown

Published: Sept. 20, 2023

Language: Английский

---

Integrated PCA–RNN approach for surface water quality assessment in the Mahanadi river system

International Journal of Environmental Science and Technology, Journal Year: 2024, Volume and Issue: 21(11), P. 7701 - 7716

Published: Feb. 27, 2024

Language: Английский

---

Application of artificial intelligence for forecasting surface quality index of irrigation systems in the Red River Delta, Vietnam

ENVIRONMENTAL SYSTEMS RESEARCH, Journal Year: 2023, Volume and Issue: 12(1)

Published: July 4, 2023

Abstract Water sources for irrigation systems in the Red River Delta are crucial to socioeconomic growth of region's communities. Human activities (discharge) have polluted water source recent years, and from upstream is limited. Currently, surface quality index (WQI), which calculated numerous parameters (physical, chemical, microbiological, heavy metals, etc.) frequently used evaluate systems. However, calculation WQI monitoring remains constrained due need a large number relative complexity calculation. To better serve assessment study area, it essential conduct research identify an efficient accurate method calculating WQI. This machine learning deep algorithms calculate with minimal input data (water parameters) reduce cost quality. The Bayes (BMA) select important (BOD 5 , NH 4 + PO 3− turbidity, TSS, coliform, DO). results indicate that model more effective than model, gradient boosting having most prediction because has highest coefficient determination R 2 (0.96). solid scientific basis result application area. also demonstrated potential artificial intelligence improve forecasting compared traditional methods time.

Language: Английский

---

IWQP4Net: An Efficient Convolution Neural Network for Irrigation Water Quality Prediction

Water, Journal Year: 2023, Volume and Issue: 15(9), P. 1657 - 1657

Published: April 24, 2023

With the increasing worldwide population and requirement for efficient approaches to farm care irrigation, demand water is constantly rising, resources are becoming scarce. This has led development of smart management systems that aim improve efficiency management. paper pioneers an effective Irrigation Water Quality Prediction (IWQP) model using a convolution neural architecture can be trained on any general computing device. The developed IWQP4Net assessed several evaluation measurements compared Logistic Regression (LR), Support Vector regression (SVR), k-Nearest Neighbor (kNN) models. results show achieved promising outcome better performance than other comparative

Language: Английский

---

Application of machine learning algorithms and feature selection methods for better prediction of sludge production in a real advanced biological wastewater treatment plant

Journal of Environmental Management, Journal Year: 2023, Volume and Issue: 348, P. 119448 - 119448

Published: Nov. 6, 2023

Language: Английский

---

Evaluation of water quality based on artificial intelligence: performance of multilayer perceptron neural networks and multiple linear regression versus water quality indexes

Environment Development and Sustainability, Journal Year: 2024, Volume and Issue: unknown

Published: June 1, 2024

Abstract A significant problem in the sustainable management of water resources is lack funding and long-term monitoring. Today, this has been greatly reduced by innovative, adaptive, learning methods. Therefore, study, a sample river was selected 14 variables observed at 5 different points for 12 months, traditionally reference values, were calculated multivariate statistical analysis methods to obtain quality index (WQI). The WQI estimated using algorithms including innovatively used multiple linear regression (MLR), multilayer perceptron artificial neural networks (MLP-ANN) various machine estimation (NN), support vector (SVM), gaussian process (GPR), ensemble decision tree approach. By comparing results, most appropriate method selected. determination best (MLR) model. As result MLR modeling, high prediction performance obtained with accuracy values R 2 = 1.0, RMSE 0.0025, MAPE 0.0296. root mean square error (RMSE), percent absolute (MAE), coefficient (R ) determine models. These results confirm that both model can be predict very accuracy. It seems it contribute strengthening management. result, as powerful innovative approaches (MLR MLP-ANN) other assessments, found presence intense anthropogenic pressure study area current situation needs immediate remediation.

Language: Английский

---