A novel approach for multivariate time series interval prediction of water quality at wastewater treatment plants

Water Science & Technology, Год журнала: 2024, Номер 90(10), С. 2813 - 2841

Опубликована: Ноя. 12, 2024

ABSTRACT This study proposes a novel approach for predicting variations in water quality at wastewater treatment plants (WWTPs), which is crucial optimizing process management and pollution control. The model combines convolutional bi-directional gated recursive units (CBGRUs) with adaptive bandwidth kernel function density estimation (ABKDE) to address the challenge of multivariate time series interval prediction WWTP quality. Initially, wavelet transform (WT) was employed smooth data, reducing noise fluctuations. Linear correlation coefficient (CC) non-linear mutual information (MI) techniques were then utilized select input variables. CBGRU applied capture temporal correlations series, integrating Multiple Heads Attention (MHA) mechanism enhance model's ability comprehend complex relationships within data. ABKDE employed, supplemented by bootstrap establish upper lower bounds intervals. Ablation experiments comparative analyses benchmark models confirmed superior performance point prediction, analysis forecast period, fluctuation detection Also, this verifies broad applicability robustness anomalous contributes significantly improved effluent efficiency control WWTPs.

Язык: Английский

---

Multi-Agent Large Language Model Frameworks: Unlocking New Possibilities for Optimizing Wastewater Treatment Operation

Environmental Research, Год журнала: 2025, Номер unknown, С. 121401 - 121401

Опубликована: Март 1, 2025

Язык: Английский

---

From Policy to Prediction: Assessing Forecasting Accuracy in an Integrated Framework with Machine Learning and Disease Models

Journal of Computational Biology, Год журнала: 2024, Номер 31(11), С. 1104 - 1117

Опубликована: Авг. 2, 2024

To improve the forecasting accuracy of spread infectious diseases, a hybrid model was recently introduced where commonly assumed constant disease transmission rate actively estimated from enforced mitigating policy data by machine learning (ML) and then fed to an extended susceptible-infected-recovered forecast number infected cases. Testing only one ML model, that is, gradient boosting (GBM), work left open whether other models would perform better. Here, we compared GBMs, linear regressions, k-nearest neighbors, Bayesian networks (BNs) in COVID-19-infected cases United States Canadian provinces based on indices future 35 days. There no significant difference mean absolute percentage errors these over combined dataset [ H(3)=3.10,p=0.38]. In two provinces, observed H(3)=8.77,H(3)=8.07,p<0.05], yet posthoc tests revealed pairwise comparisons. Nevertheless, BNs significantly outperformed most training datasets. The results put forward have equal power overall, are best for data-fitting applications.

Язык: Английский

---

Predicting COD and TN in A2O+AO Process Considering Influent and Reactor Variability: A Dynamic Ensemble Model Approach

Water, Год журнала: 2024, Номер 16(22), С. 3212 - 3212

Опубликована: Ноя. 8, 2024

The prediction of the chemical oxygen demand (COD) and total nitrogen (TN) in integrated anaerobic–anoxic–oxic (A2O) anoxic–oxic (AO) processes (i.e., A2O+AO process) was achieved using a dynamic ensemble model that reflects dynamics wastewater treatment plants (WWTPs). This effectively captures variability influent characteristics fluctuations within each reactor process. By employing time-lag approach based on hydraulic retention time (HRT), artificial intelligence (AI) selects suitable input pH, temperature, dissolved solid (TDS), NH3-N, NO3-N) output (COD TN) data pairs for training, minimizing error between predicted observed values. Data collected over two years from actual process were utilized. adopted machine learning-based XGBoost COD TN predictions. outperformed static model, with mean absolute percentage (MAPE) ranging 9.5% to 15.2%, compared model’s range 11.4% 16.9%. For TN, errors ranged 9.4% 15.5%, while showed lower specific reactors, particularly anoxic oxic stages due their stable characteristics. These results indicate is predicting water quality WWTPs, especially as may increase external environmental factors future.

Язык: Английский

---

Sliding mode variable structure control for wastewater treatment based on an improved linear extended observer

Journal of Water Process Engineering, Год журнала: 2024, Номер 68, С. 106435 - 106435

Опубликована: Ноя. 15, 2024

Язык: Английский

---