Hybrid Analysis of Biochar Production from Pyrolysis of Agriculture Waste Using Statistical and Artificial Intelligent-Based Modeling Techniques
Biochar is gaining recognition as a sustainable material, with several applications in soil amendment, carbon sequestration, nutrient dynamics, the remediation of organic contaminants from soil, and water filtration. However, understanding its characteristics is limited due to its intricate structur...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-01-01
|
| Series: | Agronomy |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2073-4395/15/1/181 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832589403194654720 |
|---|---|
| author | Hani Hussain Sait Ramesh Kanthasamy Bamidele Victor Ayodele |
| author_facet | Hani Hussain Sait Ramesh Kanthasamy Bamidele Victor Ayodele |
| author_sort | Hani Hussain Sait |
| collection | DOAJ |
| description | Biochar is gaining recognition as a sustainable material, with several applications in soil amendment, carbon sequestration, nutrient dynamics, the remediation of organic contaminants from soil, and water filtration. However, understanding its characteristics is limited due to its intricate structure. This study used response surface methodology (RSM) and artificial neural networks (ANNs) to optimize and predict the production of biochar from the pyrolysis of palm kernel shells. To determine how residence time, nitrogen flow rate, and pyrolysis temperature affected biochar production, a Box–Behnken experimental design was employed. The prediction of the biochar yield was modeled using four different models of ANNs: narrow, medium, wide, and optimum. The physicochemical properties of the biochar produced at pyrolysis temperatures ranging from 400 to 800 °C were determined using X-ray diffraction (XRD), energy dispersive X-ray spectroscopy (EDX), nitrogen (N<sub>2</sub>) physisorption analysis, and field emission scanning electron microscopy (FESEM). With a <i>p</i>-value significantly lower than 0.05, the response surface quadratic model was found to be the most suitable to optimize the biochar yield obtained from the PKS pyrolysis. Biochar production was very sensitive to the three operating parameters: pyrolysis temperature, nitrogen flow rate, and pyrolysis time. With a coefficient of determination (R<sup>2</sup>) of 0.900, root mean square error (RMSE) of 0.936, and mean absolute error (MAE) of 0.743, the optimized ANN outperformed the other three ANN models tested. When compared to the optimized ANN, the response surface quadratic model with an R<sup>2</sup> of 0.989 had better prediction of biochar yield. At optimized experimental conditions for nitrogen flow rate (150.01 mL/min), temperature (799.71 °C), and pyrolysis time (107.61 min), a biochar yield of 37.87% was obtained at a desirability function of 1. |
| format | Article |
| id | doaj-art-60649ae265db4d24ad6b23662fc89dd4 |
| institution | Kabale University |
| issn | 2073-4395 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Agronomy |
| spelling | doaj-art-60649ae265db4d24ad6b23662fc89dd42025-01-24T13:17:04ZengMDPI AGAgronomy2073-43952025-01-0115118110.3390/agronomy15010181Hybrid Analysis of Biochar Production from Pyrolysis of Agriculture Waste Using Statistical and Artificial Intelligent-Based Modeling TechniquesHani Hussain Sait0Ramesh Kanthasamy1Bamidele Victor Ayodele2Department of Mechanical Engineering, Faculty of Engineering Rabigh, King Abdulaziz University, Rabigh 21911, Saudi ArabiaDepartment of Chemical and Materials Engineering, Faculty of Engineering Rabigh, King Abdulaziz University, Rabigh 21911, Saudi ArabiaDepartment of Chemical Engineering, Universiti Teknologi PETRONAS, Seri Iskandar 32610, Perak, MalaysiaBiochar is gaining recognition as a sustainable material, with several applications in soil amendment, carbon sequestration, nutrient dynamics, the remediation of organic contaminants from soil, and water filtration. However, understanding its characteristics is limited due to its intricate structure. This study used response surface methodology (RSM) and artificial neural networks (ANNs) to optimize and predict the production of biochar from the pyrolysis of palm kernel shells. To determine how residence time, nitrogen flow rate, and pyrolysis temperature affected biochar production, a Box–Behnken experimental design was employed. The prediction of the biochar yield was modeled using four different models of ANNs: narrow, medium, wide, and optimum. The physicochemical properties of the biochar produced at pyrolysis temperatures ranging from 400 to 800 °C were determined using X-ray diffraction (XRD), energy dispersive X-ray spectroscopy (EDX), nitrogen (N<sub>2</sub>) physisorption analysis, and field emission scanning electron microscopy (FESEM). With a <i>p</i>-value significantly lower than 0.05, the response surface quadratic model was found to be the most suitable to optimize the biochar yield obtained from the PKS pyrolysis. Biochar production was very sensitive to the three operating parameters: pyrolysis temperature, nitrogen flow rate, and pyrolysis time. With a coefficient of determination (R<sup>2</sup>) of 0.900, root mean square error (RMSE) of 0.936, and mean absolute error (MAE) of 0.743, the optimized ANN outperformed the other three ANN models tested. When compared to the optimized ANN, the response surface quadratic model with an R<sup>2</sup> of 0.989 had better prediction of biochar yield. At optimized experimental conditions for nitrogen flow rate (150.01 mL/min), temperature (799.71 °C), and pyrolysis time (107.61 min), a biochar yield of 37.87% was obtained at a desirability function of 1.https://www.mdpi.com/2073-4395/15/1/181artificial intelligence-based modelingresponse surface methodologypalm kernel shellbiocharpyrolysis |
| spellingShingle | Hani Hussain Sait Ramesh Kanthasamy Bamidele Victor Ayodele Hybrid Analysis of Biochar Production from Pyrolysis of Agriculture Waste Using Statistical and Artificial Intelligent-Based Modeling Techniques Agronomy artificial intelligence-based modeling response surface methodology palm kernel shell biochar pyrolysis |
| title | Hybrid Analysis of Biochar Production from Pyrolysis of Agriculture Waste Using Statistical and Artificial Intelligent-Based Modeling Techniques |
| title_full | Hybrid Analysis of Biochar Production from Pyrolysis of Agriculture Waste Using Statistical and Artificial Intelligent-Based Modeling Techniques |
| title_fullStr | Hybrid Analysis of Biochar Production from Pyrolysis of Agriculture Waste Using Statistical and Artificial Intelligent-Based Modeling Techniques |
| title_full_unstemmed | Hybrid Analysis of Biochar Production from Pyrolysis of Agriculture Waste Using Statistical and Artificial Intelligent-Based Modeling Techniques |
| title_short | Hybrid Analysis of Biochar Production from Pyrolysis of Agriculture Waste Using Statistical and Artificial Intelligent-Based Modeling Techniques |
| title_sort | hybrid analysis of biochar production from pyrolysis of agriculture waste using statistical and artificial intelligent based modeling techniques |
| topic | artificial intelligence-based modeling response surface methodology palm kernel shell biochar pyrolysis |
| url | https://www.mdpi.com/2073-4395/15/1/181 |
| work_keys_str_mv | AT hanihussainsait hybridanalysisofbiocharproductionfrompyrolysisofagriculturewasteusingstatisticalandartificialintelligentbasedmodelingtechniques AT rameshkanthasamy hybridanalysisofbiocharproductionfrompyrolysisofagriculturewasteusingstatisticalandartificialintelligentbasedmodelingtechniques AT bamidelevictorayodele hybridanalysisofbiocharproductionfrompyrolysisofagriculturewasteusingstatisticalandartificialintelligentbasedmodelingtechniques |