Machine learning and GIS based groundwater quality prediction for agricultural practices - A case study form Arjunanadi River basin of South India

Computers and Electronics in Agriculture, Journal Year: 2025, Volume and Issue: 229, P. 109932 - 109932

Published: Jan. 16, 2025

Language: Английский

---

A novel additive regression model for streamflow forecasting in German rivers

Results in Engineering, Journal Year: 2024, Volume and Issue: 22, P. 102104 - 102104

Published: April 10, 2024

Forecasting streamflows, essential for flood mitigation and the efficient management of water resources drinking, agriculture hydroelectric power generation, presents a formidable challenge in most real-world scenarios. In this study, two models, first based on Additive Regression Radial Basis Function Neural Networks (AR-RBF) second stacking with Pace Multilayer Perceptron Random Forest (MLP-RF-PR), were compared prediction short-term (1–3 days ahead) medium-term (7 daily streamflow rates three different rivers Germany: Elbe River at Wittenberge, Leine Herrenhausen, Saale Hof The lagged values rate, precipitation temperature considered modeling. Moreover, Bayesian Optimization (BO) algorithm was used to assess optimal number hyperparameters. Both models showed accurate predictions forecasting, R2 1-day ahead ranging from 0.939 0.998 AR-RBF 0.930 0.996 MLP-RF-PR, while MAPE ranged 2.02 % 8.99 2.14 9.68 when exogeneous variables included. As forecast horizon increased, reduction forecasting accuracy observed. However, both could still predict overall flow pattern, even 7-day-ahead predictions, 0.772 0.871 0.703 0.840 10.60 20.45 10.44 19.65 MLP-RF-PR. Overall, outcomes study suggest that MLP-RF-PR can be reliable tools short- rate prediction, requiring short parameters optimized, making them easy implement reducing calculation time required.

Language: Английский

---

Machine learning predictions for carbon monoxide levels in urban environments

Results in Engineering, Journal Year: 2024, Volume and Issue: 22, P. 102114 - 102114

Published: April 8, 2024

The increasing carbon emissions in Malaysia necessitate accurate methods to track and control pollution levels. This study focuses on predicting monoxide (CO) concentrations Petaling Jaya using various machine learning models, two important parameters, CO concentration time, were considered the analysis. Six distinct models assessed gauge their predictive capabilities. These encompassed a range of regression modeling techniques namely; Linear, Tree, Gaussian Process, Ensemble Trees, Support Vector, Artificial Neural Networks (ANN) modelling. Matern 5/2 Process Regression (GPR) model consistently outperformed other across all scenarios, demonstrating high R2 values low RMSE, MSE, MAE values. Specifically, scenarios 1, 2, 3, 4, exhibited lowest RMSE (0.084-0.088) highest (0.97), highlighting its reliability robustness concentrations. Additionally, Rational Quadratic achieved an 0.97 with 0.088 scenario while SVM excelled 3 0.965 (0.085, 0.007, 0.066). findings provide valuable insights for environmental protection, renewable energy transition, efficiency, sustainable land use planning, public awareness. However, acknowledging study's single-area focus potential limitations representing diverse regions, further research is warranted explore varied areas enhance generalizability findings.

Language: Английский

---

Interpreting optimised data-driven solution with explainable artificial intelligence (XAI) for water quality assessment for better decision-making in pollution management

Environmental Science and Pollution Research, Journal Year: 2024, Volume and Issue: 31(30), P. 42948 - 42969

Published: June 17, 2024

Language: Английский

---

Integrating community perceptions, scientific data and geospatial tools for sustainable water quality management

Results in Engineering, Journal Year: 2024, Volume and Issue: 23, P. 102563 - 102563

Published: July 14, 2024

Globally, ecosystems and human health are at risk due to declining river water quality. The current study focuses on the River Asan, Uttarakhand, which faces significant quality challenges various environmental, industrial, domestic factors. This research presents an exhaustive that intricately blends local community perceptions with scientific data, employing Geographic Information Systems map across seven critical locations along river. Participatory Rural Appraisal (PRA) systematic test methods were applied find objective of this study. highlights importance considering social, cultural, environmental factors in understanding issues. detailed, location-specific analysis, enriched by vast array insights, offers a unique lens through each site examined. Significant findings represent Nayagaon, from 2019 2023, rising temperature (1.6 °C increase) decreasing pH (7.3–6.5) observed. Reduced dissolved oxygen (9.7–6.1 mg/L) aligns concerns about quality, highlighting urgent need for interventions protect Asan its dependent communities. Integrating data provides nuanced issues, emphasizing targeted safeguard ecosystem well-being communities it, thereby offering valuable insights sustainable management.

Language: Английский

---

Analysis of hydrological changes in the Banas River: Analysing Bisalpur Dam impact and trends of the water scarcity

Results in Engineering, Journal Year: 2024, Volume and Issue: 22, P. 101978 - 101978

Published: March 16, 2024

The construction of large-scale infrastructure projects like dams can substantially alter local hydrological systems, prompting concerns about their impacts on river water levels and discharge. This study was undertaken in response to the compelling need investigate analyze potential implications scarcity, particularly within framework Bisalpur Dam located Banas River. uses non-parametric trend analysis tests - Mann-Kendall (MK) Modified (MMK) for discharge level analysis, Sen's Slope Pettit's test detecting changes or trends. Significant shifts these parameters were identified post-construction. From 1960 2011, Dam's led a marked decrease peak (MK/MMK statistics Zc = −3.24; Pc 0.001), with slope −21.51 MCM/year. Before construction, reached maximum 7680 MCM 1981–82. gauge station's significantly decreased −3.46; 0.001) at an annual rate −0.035 m/year. level, peaking 201.59 m 1981–82, declined from average 196.04 m–194.5 findings underscore extensive impact dam parameters. These results hold significant future projects, emphasizing critical comprehensive environmental assessments be conducted before project implementation. understanding aid designing interventions reduced impacts, leading more sustainable development.

Language: Английский

---

Prediction of surface runoff quality and quantity using an integrated model and machine learning under climate change conditions

Stochastic Environmental Research and Risk Assessment, Journal Year: 2025, Volume and Issue: unknown

Published: Jan. 19, 2025

Language: Английский

---

An Interpretable XGBoost-SHAP Machine Learning Model for Reliable Prediction of Mechanical Properties in Waste Foundry Sand-Based Eco-Friendly Concrete

Results in Engineering, Journal Year: 2025, Volume and Issue: unknown, P. 104307 - 104307

Published: Feb. 1, 2025

Language: Английский

---

Integrated machine learning based groundwater quality prediction through groundwater quality index for drinking purposes in a semi-arid river basin of south India

Environmental Geochemistry and Health, Journal Year: 2025, Volume and Issue: 47(4)

Published: March 14, 2025

Language: Английский

---

Integrating Unsupervised Machine Learning, Statistical Analysis, and Monte Carlo Simulation to Assess Toxic Metal Contamination and Salinization in Non-Rechargeable Aquifers

Results in Engineering, Journal Year: 2025, Volume and Issue: unknown, P. 104989 - 104989

Published: April 1, 2025

Language: Английский

---