Forschungsdaten – Titel und Zusammenfassungen von Publikationen, extrahierte Daten und Katalogeinträge – erscheinen in ihrer Originalsprache Englisch.
Shamsuddeen Jumande Mohammad, Aliyu Ishaq
This study addresses a critical gap in MFC predictive modeling by integrating feature selection and sensitivity analysis with machine learning algorithms to predict power density output from leachate-based microbial fuel cells. Six ensemble algorithms were evaluated—CatBoost, XGBoost, Random Forest, Gradient Boosting, AdaBoost, and Decision Tree—using environmental variables (time, pH, temperature, NH₄-N concentration) as predictors. CatBoost emerged as the superior model (R²=0.9969, RMSE=6.99 mW/m²), demonstrating enhanced accuracy in capturing nonlinear relationships between environmental factors and MFC performance, with direct applications to sustainable energy generation and wastewater treatment optimization.
Erstellt von der MESSAI-Extraktionspipeline · mit dem Quell-PDF abgleichen
Noch keine extrahierten Parameter – fordern Sie eine KI-Extraktion an, um diese Publikation mit den Literaturverteilungen zu vergleichen.
Öffnen Sie das Modell im Labor, um alle Steuerelemente, die Parameterbearbeitung und Vorlagen-Overlays zu nutzen.
Im Labor öffnen →Noch keine Ergebniskennzahlen extrahiert.
Abstract This research presents an innovative blend of feature selection and sensitivity analysis techniques, which is an essential yet overlooked aspect in the study of MFCs. The study compared predictive models utilizing various machine learning algorithms to assess the impact of time, dosage, pH and temperature on ammonium nitrogen concentration (NH 4 -N) to predict the power density (PD) output of microbial fuel cells using leachate as a substrate for treatment. Evaluation of six machine learning models demonstrates varying levels of predictive accuracy. CatBoost (R2:0.9969, MSE: 48.8430, RMSE:6.9888) emerges as the most accurate model, followed closely by XGBoost (R2:0.9917, MSE:130.1668, RMSE:11.4091) and Random Forest (R2:0.9830, MSE:267.0929, RMSE:16.3430). Time series plots illustrate the performance of different models in predicting PD over a period, indicating good alignment with observed data. Comparison of Mean Squared Error (MSE) highlights significant variations in prediction accuracy, with CatBoost demonstrating the greatest enhancement and precision. The study directly tackles the deficiencies in existing MFC predictive modeling by incorporating the CatBoost algorithm, which provides enhanced accuracy and a deeper understanding of the nonlinear connections between environmental variables and power density.