Retrieval of total suspended matter concentration in the yellow river estuary offshore area based on QAA-RF model DOI Creative Commons

Lianwei Li,

Zhi Zheng,

Cunjin Xue

et al.

International Journal of Remote Sensing, Journal Year: 2024, Volume and Issue: 45(24), P. 9421 - 9442

Published: Oct. 8, 2024

Total suspended matter is one of the crucial water quality parameters for both inland and marine environments, a key role in evaluating estuaries offshore areas. Each year, Yellow River carries significant amount sediment into semi-enclosed Bohai Sea, results prolonged high concentration total areas Estuary. This study focuses on region Estuary China. Utilizing Sentinel-2 satellite imagery data from 2020 to 2023 in-situ measured August 2022, address lack physical mechanisms currently studied machine learning retrieval methods, model that integrates physics-driven Quasi-Analytical Algorithm (QAA) data-driven Random Forest (RF) employed area. The fused (QAA-RF) compared analysed against regression models standalone models. indicate accuracy consistently higher than QAA-RF demonstrates highest (R2 = 0.87, MAE 5.01 mg L−1, RMSE 6.39 L−1). Based data, monthly conducted indicates that: (1) concentrations primarily concentrated near estuary region, with decreasing as distance increases. (2) exhibits distribution pattern values spring winter, lower summer autumn. (3) shows relatively small fluctuations at annual scale 2023.

Language: Английский

Applications of XGBoost in water resources engineering: A systematic literature review (Dec 2018–May 2023) DOI
Majid Niazkar, Andrea Menapace, Bruno Brentan

et al.

Environmental Modelling & Software, Journal Year: 2024, Volume and Issue: 174, P. 105971 - 105971

Published: Feb. 10, 2024

Language: Английский

Citations

77
A stacking ANN ensemble model of ML models for stream water quality prediction of Godavari River Basin, India DOI Creative Commons
Nagalapalli Satish, Jagadeesh Anmala,

K. Rajitha

et al.

Ecological Informatics, Journal Year: 2024, Volume and Issue: 80, P. 102500 - 102500

Published: Jan. 28, 2024

The importance of water quality models has increased as their inputs are critical to the development risk assessment framework for environmental management and monitoring rivers. However, with advent a plethora recent advances in ML algorithms better predictions possible. This study proposes causal effect model by considering climatological such temperature precipitation along geospatial information related agricultural land use factor (ALUF), forest (FLUF), grassland usage (GLUF), shrub (SLUF), urban (ULUF). All these factors included input data, whereas four Stream Water Quality parameters (SWQPs) Electrical Conductivity (EC), Biochemical Oxygen Demand (BOD), Nitrate, Dissolved (DO) from 2019 2021 taken outputs predict Godavari River Basin quality. In preliminary investigation, out SWQPs, nitrate's coefficient variation (CV) is high, revealing close association climate practices across sampling stations. authors' earlier study, using single-layer Feed-Forward Neural Network (FFNN) showed improved performance predicting cause linked metrics. To achieve prediction, stacked ANN meta-model nine conventional machine learning (ML) models, including Extreme Gradient Boosting (XGB), Extra Trees (ET), Bagging (BG), Random Forest (RF), AdaBoost or Adaptive (ADB), Decision Tree (DT), Highest (HGB), Light Method (LGBM), (GB), were compared this study. According study's findings, outperformed stand-alone FFNN same dataset superior predictive capabilities terms accuracy forecasting variable interest. For instance, during testing, determination (R2) (BOD) 0.72 0.87. Furthermore, Artificial (ANN) meta that was reinforced (ET) base performed than individual (from R2 = 0.87 0.91 BOD testing). By new framework, effort hyperparameter tuning can be minimized.

Language: Английский

Citations

23
Towards greener futures: SVR-based CO2 prediction model boosted by SCMSSA algorithm DOI Creative Commons
Oluwatayomi Rereloluwa Adegboye, Afi Kekeli Feda,

Ephraim Bonah Agyekum

et al.

Heliyon, Journal Year: 2024, Volume and Issue: 10(11), P. e31766 - e31766

Published: May 22, 2024

This research presents the utilization of an enhanced Sine cosine perturbation with Chaotic and Mirror imaging strategy-based Salp Swarm Algorithm (SCMSSA), which incorporates three improvement mechanisms, to enhance convergence accuracy speed optimization algorithm. The study assesses SCMSSA algorithm's performance against other algorithms using six test functions show efficacy enhancement strategies. Furthermore, its in improving Support Vector Regression (SVR) models for CO

Language: Английский

Citations

9
Comparative analysis of different machine learning algorithms for predicting trace metal concentrations in soils under intensive paddy cultivation DOI
Mehmet Taşan, Yusuf Demir, Sevda Taşan

et al.

Computers and Electronics in Agriculture, Journal Year: 2024, Volume and Issue: 219, P. 108772 - 108772

Published: March 2, 2024

Language: Английский

Citations

6
Investigating First Flush Occurrence in Agro-Urban Environments in Northern Italy DOI Open Access
Majid Niazkar, Margherita Evangelisti, Cosimo Peruzzi

et al.

Water, Journal Year: 2024, Volume and Issue: 16(6), P. 891 - 891

Published: March 20, 2024

The first flush (FF) phenomenon is commonly associated with a relevant load of pollutants, raising concerns about water quality and environmental management in agro-urban areas. An FF event can potentially transport contaminated into receiving body by activating combined sewer overflow (CSO) systems present the drainage urban network. Therefore, accurately characterizing events crucial for effective limiting degradation. Given ongoing controversy literature regarding delineation occurrences, there an unavoidable necessity further investigations, especially experimental-based ones. This study presents outcomes almost two-year field campaign focused on assessing quantity two Northern Italy. For this purpose, various hydro-meteorological variables, including precipitation, flow rate, temperature, solar radiation, addition to analytics, were measured continuously capture stormwater events. Throughout monitoring period, sixteen identified analyzed using five indices usually adopted identify occurrences. results indicate that strong positive correlation between mass ratios calculated nutrients three factors, maximum rainfall intensity, antecedent dry weather period. Furthermore, duration was found possess negative nutrients. However, same event, occurrence has never been unanimously confirmed examined study. Moreover, different macro-groups pollutants behave differently. Thus, it becomes apparent relying solely priori analyses, without support data from experimental campaigns, poses risk when designing actions mitigation

Language: Английский

Citations

5
Estimating the water quality index based on interpretable machine learning models DOI Creative Commons
Shiwei Yang, Ruifeng Liang,

Junguang Chen

et al.

Water Science & Technology, Journal Year: 2024, Volume and Issue: 89(5), P. 1340 - 1356

Published: March 1, 2024

Abstract The water quality index (WQI) is an important tool for evaluating the status of lakes. In this study, we used WQI to evaluate spatial characteristics Dianchi Lake. However, calculation time-consuming, and machine learning models exhibit significant advantages in terms timeliness nonlinear data fitting. We a model with optimized parameters predict WQI, light gradient boosting achieved good predictive performance. trained based on entire Lake coefficient determination (R2), mean square error, absolute error values 0.989, 0.228, 0.298, respectively. addition, Shapley additive explanations (SHAP) method interpret analyse identified main parameter that affects as NH4+-N. Within range Lake, SHAP NH4+-N varied from −9 3. Thus, future environmental governance, it necessary focus changes. These results can provide reference treatment lake environments.

Language: Английский

Citations

4
Comprehensive analysis of multiple classifiers for enhanced river water quality monitoring with explainable AI DOI Creative Commons

S. Ramya,

S Srinath,

Pushpa Tuppad

et al.

Case Studies in Chemical and Environmental Engineering, Journal Year: 2024, Volume and Issue: 10, P. 100822 - 100822

Published: June 27, 2024

Monitoring river water quality is crucial for safeguarding public health, protecting ecosystems, and ensuring economic sustainability. It helps detect contaminants, ensures drinking safety, facilitates early intervention environmental protection legal compliance. The objective of this study to evaluate multiple machine learning algorithms analyze parameters in computing index (WQI) classification thereof, aiming devise a reliable method forecasting with high accuracy. In study, fourteen classifiers applied include Support Vector Machine (SVM), Random Forest (RF), Logistic Regression (LR), Decision Tree (DT), Multilayer Perceptron (MLP), K-Nearest Neighbor (KNN), Naïve Bayes, Gradient boosting, AdaBoost, Bagging, Extra Trees, Quadratic Discriminant Analysis (QDA), XGBoost, CATBoost. A total 1096 sample data was used where each consists nineteen analytical parameters. To assess the performance various classifiers, several evaluation techniques were utilized including confusion matrices, reports detailing precision accuracy ratios, Receiver Operating Characteristic (ROC) curves. also utilizes explainable AI (LIME SHAP) provide clear insights into decision-making processes classify quality. results indicated that all ML models demonstrate satisfactory predicting WQI. Among used, Boosting achieves highest Accuracy (99.64 %), Precision (0.95), Recall (0.96), F1-Score indicating its superior ability correctly instances suggesting balanced across different metrics. analysis presented article holds promise providing accurate researchers, thereby enhancing monitoring effectiveness through application techniques.

Language: Английский

Citations

4
Groundwater quality assessment using machine learning models: a comprehensive study on the industrial corridor of a semi-arid region DOI

Loganathan Krishnamoorthy,

V. Lakshmanan

Environmental Science and Pollution Research, Journal Year: 2024, Volume and Issue: unknown

Published: July 4, 2024

Language: Английский

Citations

4
Comparative analysis of Sentinel-2 and PlanetScope imagery for chlorophyll-a prediction using machine learning models DOI Creative Commons
Eden T. Wasehun, Leila Hashemi-Beni, Courtney A. Di Vittorio

et al.

Ecological Informatics, Journal Year: 2024, Volume and Issue: unknown, P. 102988 - 102988

Published: Dec. 1, 2024

Language: Английский

Citations

4
A Water Quality Prediction Model Based on Modal Decomposition and Hybrid Deep Learning Models DOI Open Access
Shuo Zhao,

Ruru Liu,

Yahui Liu

et al.

Water, Journal Year: 2025, Volume and Issue: 17(2), P. 184 - 184

Published: Jan. 10, 2025

When the total nitrogen content in water sources exceeds standard, it can promote rapid proliferation of algae and other plankton, leading to eutrophication body also causing damage ecological environment source area. Therefore, making timely accurate predictions quality at is vital importance. Since data exhibit non-stationary characteristics, predicting them quite challenging. This study proposes a novel hybrid deep learning model based on modal decomposition, ERSCB (EMD-RBMO-SVMD-CNN-BiGRU), enhance accuracy forecasting. The first employs Empirical Mode Decomposition (EMD) technology decompose original data. Subsequently, quantifies complexity subsequences obtained from EMD using Sample Entropy (SE) further decomposes most complex Sequential Variational (SVMD). To address matter selecting balanced parameters SVMD, this introduces Red-Billed Blue Magpie Optimization (RBMO) algorithm optimize hyperparameters SVMD. On basis, forecasting constructed by integrating Convolutional Neural Networks (CNN) Bidirectional Gated Recurrent Unit (BiGRU) networks. experimental results show that, compared existing prediction models, has an improved 4.0% 3.1% for KaShi River GongNaiSi areas, respectively.

Language: Английский

Citations

0