Explainable machine learning methods for predicting water treatment plant features under varying weather conditions

Results in Engineering, Год журнала: 2024, Номер 21, С. 101930 - 101930

Опубликована: Март 1, 2024

Accurately predicting key features in WWTPs is essential for optimizing plant performance and minimizing operational costs. This study assesses the potential of various machine learning models inflow to anoxic sludge reactors. Firstly, it conducts a comprehensive evaluation diverse models, including k-Nearest Neighbors (kNN), Random Forest (RF), XGBoost, CatBoost, LightGBM, Decision Tree Regression (DTR), flow into Anoxic section under weather conditions (dry, rainy, stormy). Secondly, introduces parsimonious guided by variable importance from XGBoost algorithm. Furthermore, employs SHAP (SHapley Additive exPlanations) elucidate model predictions, providing insights contribution each feature. Data COST Benchmark Simulation Model (BSM1) used verify investigated models' effectiveness. Each dataset consists 14 days influent data at 15-minute intervals, with 80% training. Results show that ensemble methods, particularly CatBoost demonstrate satisfactory predictive results presence increased variability rainy stormy conditions. Notably, achieve average Mean Absolute Percentage Error values 1.33% 1.59%, outperforming other methods.

Язык: Английский

---

Hybrid XGB model for predicting unconfined compressive strength of solid waste-cement-stabilized cohesive soil

Construction and Building Materials, Год журнала: 2024, Номер 449, С. 138242 - 138242

Опубликована: Сен. 13, 2024

Язык: Английский

---

Performance evaluation of regular and radial-fin-integrated pipe sections buried in soft clayey seabed under uplift buckling

Ocean Engineering, Год журнала: 2025, Номер 319, С. 120269 - 120269

Опубликована: Янв. 6, 2025

Язык: Английский

---

Efficient prediction of California bearing ratio in solid waste-cement-stabilized soil using improved hybrid extreme gradient boosting model

Materials Today Communications, Год журнала: 2025, Номер 43, С. 111627 - 111627

Опубликована: Янв. 15, 2025

Язык: Английский

---

Evaluation of compression index of red mud by machine learning interpretability methods

Computers and Geotechnics, Год журнала: 2025, Номер 181, С. 107130 - 107130

Опубликована: Фев. 10, 2025

Язык: Английский

---

Ensemble learning for predicting average thermal extraction load of a hydrothermal geothermal field: A case study in Guanzhong Basin, China

Energy, Год журнала: 2024, Номер 296, С. 131146 - 131146

Опубликована: Апрель 3, 2024

Язык: Английский

---

Seismic fragility analysis of RC frame structures based on IDA analysis and machine learning

Structures, Год журнала: 2024, Номер 65, С. 106774 - 106774

Опубликована: Июнь 24, 2024

Язык: Английский

---

Deep learning to evaluate seismic-induced soil liquefaction and modified transfer learning between various data sources

Underground Space, Год журнала: 2025, Номер unknown

Опубликована: Янв. 1, 2025

Язык: Английский

---

Evaluation and Future Prospects of Data‐Driven Intelligence‐Based Framework for Predicting Cyclic Behavior of Reconstituted Sand

International Journal for Numerical and Analytical Methods in Geomechanics, Год журнала: 2025, Номер unknown

Опубликована: Янв. 15, 2025

ABSTRACT Most of the robust artificial intelligence (AI)‐based constitutive models are developed with synthetic datasets generated from traditional models. Therefore, they fundamentally rely on rather than laboratory test results. Also, their potential use within geotechnical engineering communities is limited due to unavailability along model code files. In this study, data‐driven using only databases and deep learning (DL) techniques. The database was prepared by conducting cyclic direct simple shear (CDSS) tests reconstituted sand, that is, PDX sand. stacked long short‐term memory (LSTM) network its variants considered for developing predictive strain ( γ [%]) excess pore pressure ratio r u ) time histories. suitable input parameters (IPs) selected based physics behind generation (%) liquefiable sands. predicted responses agree well in most cases used predict dynamic soil properties same modeling framework extended other sand compared existing AI‐based verify practical applicability. summary, it observed though trained histories reasonably well; however, struggled hysteresis loops at higher cycles. more research needed enhance predictability future before them practice simulating response.

Язык: Английский

---

Frontier trends and risk control research on bauxite dynamic separation during sea transport: A review

Marine Georesources and Geotechnology, Год журнала: 2025, Номер unknown, С. 1 - 29

Опубликована: Янв. 19, 2025

Язык: Английский

---