A hybrid model combining mode decomposition and deep learning algorithms for detecting TP in urban sewer networks

Applied Energy, Journal Year: 2023, Volume and Issue: 333, P. 120600 - 120600

Published: Jan. 5, 2023

Language: Английский

---

A comprehensive evaluation of influencing factors of neonicotinoid insecticides (NEOs) in farmland soils across China: First focus on film mulching

Journal of Hazardous Materials, Journal Year: 2024, Volume and Issue: 470, P. 134284 - 134284

Published: April 13, 2024

Language: Английский

---

Prediction of adsorption performance of ZIF-67 for malachite green based on artificial neural network using L-BFGS algorithm

Journal of Hazardous Materials, Journal Year: 2024, Volume and Issue: 473, P. 134629 - 134629

Published: May 15, 2024

Language: Английский

---

Utilizing machine learning to evaluate heavy metal pollution in the world's largest mangrove forest

The Science of The Total Environment, Journal Year: 2024, Volume and Issue: 951, P. 175746 - 175746

Published: Aug. 23, 2024

Language: Английский

---

The next generation of soil and water bodies heavy metals prediction and detection: New expert system based Edge Cloud Server and Federated Learning technology

Environmental Pollution, Journal Year: 2022, Volume and Issue: 313, P. 120081 - 120081

Published: Sept. 5, 2022

Language: Английский

---

Transcriptome and metabolome association analysis revealed key factors involved in melatonin-mediated copper-stress detoxication in tomato

Journal of Cleaner Production, Journal Year: 2025, Volume and Issue: unknown, P. 144888 - 144888

Published: Jan. 1, 2025

Language: Английский

---

Reserve and proliferation characteristics of antibiotic resistance genes and heavy metal resistance genes in the sewage pipe biofilm under the stress of Cu and Zn

Journal of environmental chemical engineering, Journal Year: 2025, Volume and Issue: unknown, P. 116162 - 116162

Published: March 1, 2025

Language: Английский

---

Deep-Learning-Based Water Quality Monitoring and Early Warning Methods: A Case Study of Ammonia Nitrogen Prediction in Rivers

Electronics, Journal Year: 2023, Volume and Issue: 12(22), P. 4645 - 4645

Published: Nov. 14, 2023

In line with rapid economic development and accelerated urbanization, the increasing discharge of wastewater agricultural fertilizer usage has led to a gradual rise in ammonia nitrogen levels rivers. High concentrations pose significant challenge, causing eutrophication adversely affecting aquatic ecosystems sustainable utilization water resources. Traditional detection methods suffer from limitations such as cumbersome sample handling analysis, low sensitivity, lack real-time dynamic feedback. contrast, automated monitoring prediction technologies offer more efficient accurate solutions. However, existing approaches still have some shortcomings, including processing complexity, interference issues, absence information Consequently, deep learning techniques emerged promising address these challenges. this paper, we propose application neural network model based on Long Short-Term Memory (LSTM) analyze data, enabling high-precision indicators. Moreover, through correlation analysis between quality parameters indicators, identify set key feature indicators enhance efficiency reduce costs. Experimental validation demonstrates potential our proposed approach improve accuracy, timeliness, precision prediction, which could provide support for environmental management resource governance.

Language: Английский

---

Prediction of Dichloroethene Concentration in the Groundwater of a Contaminated Site Using XGBoost and LSTM

International Journal of Environmental Research and Public Health, Journal Year: 2022, Volume and Issue: 19(15), P. 9374 - 9374

Published: July 30, 2022

Chlorinated aliphatic hydrocarbons (CAHs) are widely used in agriculture and industries have become one of the most common groundwater contaminations. With excellent performance deep learning method predicting, LSTM XGBoost were to forecast dichloroethene (DCE) concentrations a pesticide-contaminated site undergoing natural attenuation. The input variables included BTEX, vinyl chloride (VC), five water quality indicators. In this study, predictive performances long short-term memory (LSTM) extreme gradient boosting (XGBoost) compared, influences on models’ evaluated. results indicated was more likely capture DCE variation robust high values, while model presented better accuracy for all wells. well with higher would lower model’s accuracy, its influence evident than LSTM. explanation SHapley Additive exPlanations (SHAP) value each variable consistency rules biodegradation real environment. could predict through only using variables, performed XGBoost.

Language: Английский

---

Experimental study and machine learning simulation of Pb (II) separation from aqueous solutions via a nanocomposite adsorbent

Journal of the Taiwan Institute of Chemical Engineers, Journal Year: 2023, Volume and Issue: 147, P. 104923 - 104923

Published: May 30, 2023

Language: Английский

---