Prediction of energy content of biomass based on hybrid machine learning ensemble algorithm
In this study, three novel ensemble algorithms, namely, simple averaging, weighted averaging, and meta-learning ensemble algorithms were employed to predict the higher heating value of biomass. These strategies were implemented in two main stages. In the first stage, four heterogeneous standalone mo...
Main Authors: | , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Elsevier
2022-12-01
|
Series: | Energy Nexus |
Subjects: | |
Online Access: | http://www.sciencedirect.com/science/article/pii/S2772427122001127 |
_version_ | 1811298174084579328 |
---|---|
author | Usman Alhaji Dodo Evans Chinemezu Ashigwuike Jonas Nwachukwu Emechebe Sani Isah Abba |
author_facet | Usman Alhaji Dodo Evans Chinemezu Ashigwuike Jonas Nwachukwu Emechebe Sani Isah Abba |
author_sort | Usman Alhaji Dodo |
collection | DOAJ |
description | In this study, three novel ensemble algorithms, namely, simple averaging, weighted averaging, and meta-learning ensemble algorithms were employed to predict the higher heating value of biomass. These strategies were implemented in two main stages. In the first stage, four heterogeneous standalone models: an artificial neural network, a multivariate regression, a support vector regression, and an adaptive neuro-fuzzy inference system (ANFIS) were developed to predict the higher heating value. In the second stage, the outputs of the standalone models were aggregated for ensemble learning implementation. Seven input combinations of the biomass proximate analysis components formed the proposed models’ inputs. In the pre-ensemble phase, the ANFIS model having ash and volatile matter as an input combination presented the most accurate performance based on the Willmott's index of agreement of 0.9741 and the mean square error of 0.0032. The ensemble algorithms demonstrated improvement in the overall prediction performances with the meta-learning ensemble ranked superior for an average error decrease of up to 15% when ash, volatile matter, and fixed carbon served as the model's input combination. The findings of this work provide a robust foundation for the use of ensemble algorithms in the prediction of the biomass higher heating value. |
first_indexed | 2024-04-13T06:16:42Z |
format | Article |
id | doaj.art-dae2f3cb2e8844cdb65bd3d8a1182215 |
institution | Directory Open Access Journal |
issn | 2772-4271 |
language | English |
last_indexed | 2024-04-13T06:16:42Z |
publishDate | 2022-12-01 |
publisher | Elsevier |
record_format | Article |
series | Energy Nexus |
spelling | doaj.art-dae2f3cb2e8844cdb65bd3d8a11822152022-12-22T02:58:49ZengElsevierEnergy Nexus2772-42712022-12-018100157Prediction of energy content of biomass based on hybrid machine learning ensemble algorithmUsman Alhaji Dodo0Evans Chinemezu Ashigwuike1Jonas Nwachukwu Emechebe2Sani Isah Abba3Department of Electrical and Electronics Engineering, Faculty of Engineering, University of Abuja, Nigeria; Department of Electrical and Computer Engineering, Faculty of Engineering, Baze University, Abuja, Nigeria; Corresponding author at: Department of Electrical and Computer Engineering, Faculty of Engineering, Baze University, Abuja, Federal Capital Territory, Nigeria.Department of Electrical and Electronics Engineering, Faculty of Engineering, University of Abuja, NigeriaDepartment of Electrical and Electronics Engineering, Faculty of Engineering, University of Abuja, NigeriaInterdisciplinary Research Centre for Membrane and Water Security, King Fahd University of Petroleum and Minerals Dhahran 31261, Saudi ArabiaIn this study, three novel ensemble algorithms, namely, simple averaging, weighted averaging, and meta-learning ensemble algorithms were employed to predict the higher heating value of biomass. These strategies were implemented in two main stages. In the first stage, four heterogeneous standalone models: an artificial neural network, a multivariate regression, a support vector regression, and an adaptive neuro-fuzzy inference system (ANFIS) were developed to predict the higher heating value. In the second stage, the outputs of the standalone models were aggregated for ensemble learning implementation. Seven input combinations of the biomass proximate analysis components formed the proposed models’ inputs. In the pre-ensemble phase, the ANFIS model having ash and volatile matter as an input combination presented the most accurate performance based on the Willmott's index of agreement of 0.9741 and the mean square error of 0.0032. The ensemble algorithms demonstrated improvement in the overall prediction performances with the meta-learning ensemble ranked superior for an average error decrease of up to 15% when ash, volatile matter, and fixed carbon served as the model's input combination. The findings of this work provide a robust foundation for the use of ensemble algorithms in the prediction of the biomass higher heating value.http://www.sciencedirect.com/science/article/pii/S2772427122001127BiomassEnsemble learningHigher heating valueMachine learningProximate analysis |
spellingShingle | Usman Alhaji Dodo Evans Chinemezu Ashigwuike Jonas Nwachukwu Emechebe Sani Isah Abba Prediction of energy content of biomass based on hybrid machine learning ensemble algorithm Energy Nexus Biomass Ensemble learning Higher heating value Machine learning Proximate analysis |
title | Prediction of energy content of biomass based on hybrid machine learning ensemble algorithm |
title_full | Prediction of energy content of biomass based on hybrid machine learning ensemble algorithm |
title_fullStr | Prediction of energy content of biomass based on hybrid machine learning ensemble algorithm |
title_full_unstemmed | Prediction of energy content of biomass based on hybrid machine learning ensemble algorithm |
title_short | Prediction of energy content of biomass based on hybrid machine learning ensemble algorithm |
title_sort | prediction of energy content of biomass based on hybrid machine learning ensemble algorithm |
topic | Biomass Ensemble learning Higher heating value Machine learning Proximate analysis |
url | http://www.sciencedirect.com/science/article/pii/S2772427122001127 |
work_keys_str_mv | AT usmanalhajidodo predictionofenergycontentofbiomassbasedonhybridmachinelearningensemblealgorithm AT evanschinemezuashigwuike predictionofenergycontentofbiomassbasedonhybridmachinelearningensemblealgorithm AT jonasnwachukwuemechebe predictionofenergycontentofbiomassbasedonhybridmachinelearningensemblealgorithm AT saniisahabba predictionofenergycontentofbiomassbasedonhybridmachinelearningensemblealgorithm |