Systematic selection of best performing mathematical models for in vitro gas production using machine learning across diverse feeds
Abstract In vitro gas production (GP) is commonly used to evaluate ruminant feed, yet its accurate interpretation requires robust mathematical modeling. This study systematically explores a wide array of nonlinear models to explain GP dynamics across various feed types, addressing the question: how...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2025-08-01
|
| Series: | Scientific Reports |
| Subjects: | |
| Online Access: | https://doi.org/10.1038/s41598-025-15101-w |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849226425563873280 |
|---|---|
| author | Hamed Ahmadi Natascha Titze Katharina Wild Markus Rodehutscord |
| author_facet | Hamed Ahmadi Natascha Titze Katharina Wild Markus Rodehutscord |
| author_sort | Hamed Ahmadi |
| collection | DOAJ |
| description | Abstract In vitro gas production (GP) is commonly used to evaluate ruminant feed, yet its accurate interpretation requires robust mathematical modeling. This study systematically explores a wide array of nonlinear models to explain GP dynamics across various feed types, addressing the question: how can efficient and versatile models that accurately represent GP profiles be identified? We hypothesized that distinct feed types exhibit unique GP characteristics, effectively captured by specific models, and that statistical and machine learning methodologies can streamline model selection. Utilizing a comprehensive dataset derived from 849 unique GP profiles across concentrate feed categories—including cereal and leguminous grains and processed protein feeds—21 candidate models were rigorously evaluated based on their goodness-of-fit metrics, with a particular emphasis on Bayesian Information Criterion (BIC) for model selection. A group of three models—namely Burr XII, Inverse paralogistic, and Log-logistic—consistently emerged as top performers, demonstrating high generalizability and predictive power across feed types. Notably, our analysis indicated that model type significantly influenced GP predictions, surpassing the impact of feed type characteristics. This research establishes a decision-making framework for model selection and sets the stage for further investigations linking in vitro GP parameters to in vivo digestibility, ultimately enhancing ruminant nutrition strategies. |
| format | Article |
| id | doaj-art-5f7693ea68db46d6803758cf849e83eb |
| institution | Kabale University |
| issn | 2045-2322 |
| language | English |
| publishDate | 2025-08-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj-art-5f7693ea68db46d6803758cf849e83eb2025-08-24T11:18:04ZengNature PortfolioScientific Reports2045-23222025-08-0115111810.1038/s41598-025-15101-wSystematic selection of best performing mathematical models for in vitro gas production using machine learning across diverse feedsHamed Ahmadi0Natascha Titze1Katharina Wild2Markus Rodehutscord3Institute of Animal Science, University of HohenheimInstitute of Animal Science, University of HohenheimInstitute of Animal Science, University of HohenheimInstitute of Animal Science, University of HohenheimAbstract In vitro gas production (GP) is commonly used to evaluate ruminant feed, yet its accurate interpretation requires robust mathematical modeling. This study systematically explores a wide array of nonlinear models to explain GP dynamics across various feed types, addressing the question: how can efficient and versatile models that accurately represent GP profiles be identified? We hypothesized that distinct feed types exhibit unique GP characteristics, effectively captured by specific models, and that statistical and machine learning methodologies can streamline model selection. Utilizing a comprehensive dataset derived from 849 unique GP profiles across concentrate feed categories—including cereal and leguminous grains and processed protein feeds—21 candidate models were rigorously evaluated based on their goodness-of-fit metrics, with a particular emphasis on Bayesian Information Criterion (BIC) for model selection. A group of three models—namely Burr XII, Inverse paralogistic, and Log-logistic—consistently emerged as top performers, demonstrating high generalizability and predictive power across feed types. Notably, our analysis indicated that model type significantly influenced GP predictions, surpassing the impact of feed type characteristics. This research establishes a decision-making framework for model selection and sets the stage for further investigations linking in vitro GP parameters to in vivo digestibility, ultimately enhancing ruminant nutrition strategies.https://doi.org/10.1038/s41598-025-15101-wGas productionMathematical modelsModel selectionMachine learning |
| spellingShingle | Hamed Ahmadi Natascha Titze Katharina Wild Markus Rodehutscord Systematic selection of best performing mathematical models for in vitro gas production using machine learning across diverse feeds Scientific Reports Gas production Mathematical models Model selection Machine learning |
| title | Systematic selection of best performing mathematical models for in vitro gas production using machine learning across diverse feeds |
| title_full | Systematic selection of best performing mathematical models for in vitro gas production using machine learning across diverse feeds |
| title_fullStr | Systematic selection of best performing mathematical models for in vitro gas production using machine learning across diverse feeds |
| title_full_unstemmed | Systematic selection of best performing mathematical models for in vitro gas production using machine learning across diverse feeds |
| title_short | Systematic selection of best performing mathematical models for in vitro gas production using machine learning across diverse feeds |
| title_sort | systematic selection of best performing mathematical models for in vitro gas production using machine learning across diverse feeds |
| topic | Gas production Mathematical models Model selection Machine learning |
| url | https://doi.org/10.1038/s41598-025-15101-w |
| work_keys_str_mv | AT hamedahmadi systematicselectionofbestperformingmathematicalmodelsforinvitrogasproductionusingmachinelearningacrossdiversefeeds AT nataschatitze systematicselectionofbestperformingmathematicalmodelsforinvitrogasproductionusingmachinelearningacrossdiversefeeds AT katharinawild systematicselectionofbestperformingmathematicalmodelsforinvitrogasproductionusingmachinelearningacrossdiversefeeds AT markusrodehutscord systematicselectionofbestperformingmathematicalmodelsforinvitrogasproductionusingmachinelearningacrossdiversefeeds |