English   español  
Please use this identifier to cite or link to this item: http://hdl.handle.net/10261/220538
logo share SHARE logo core CORE   Add this article to your Mendeley library MendeleyBASE

Visualizar otros formatos: MARC | Dublin Core | RDF | ORE | MODS | METS | DIDL | DATACITE
Exportar a otros formatos:


Application of meta-analysis and machine learning methods to the prediction of methane production from in vitro mixed ruminal micro-organism fermentation

AuthorsEllis, J.L.; Alaiz Moretón, H.; Navarro-Villa, A.; McGeough, E.J.; Purcell, P.; Powell, C.D.; O'Kiely, P.; France, J.; López, Secundino
KeywordsIn vitro gas production
Mmachine learning
Neural network
Issue Date2020
PublisherMultidisciplinary Digital Publishing Institute
CitationAnimals 10: 720 (2020)
AbstractIn vitro gas production systems are utilized to screen feed ingredients for inclusion in ruminant diets. However, not all in vitro systems are set up to measure methane CH production, nor do all publications report in vitro CH Therefore, the objective of this study was to develop models to predict in vitro CH production from total gas and volatile fatty acid (VFA) production data and to identify the major drivers of CH production in these systems. Meta-analysis and machine learning (ML) methodologies were applied to a database of 354 data points from 11 studies to predict CH production from total gas production, apparent DM digestibility (DMD), final pH, feed type (forage or concentrate), and acetate, propionate, butyrate and valerate production. Model evaluation was performed on an internal dataset of 107 data points. Meta-analysis results indicate that equations containing DMD, total VFA production, propionate, feed type and valerate resulted in best predictability of CH on the internal evaluation dataset. The ML models far exceeded the predictability achieved using meta-analysis, but further evaluation on an external database would be required to assess generalization ability on unrelated data. Between the ML methodologies assessed, artificial neural networks and support vector regression resulted in very similar predictability, but differed in fitting, as assessed by behaviour analysis. The models developed can be utilized to estimate CH emissions in vitro.
Description18 páginas, 7 tablas, 1 figura.
Publisher version (URL)http://dx.doi.org/10.3390/ani10040720
Appears in Collections:(IGM) Artículos
Files in This Item:
File Description SizeFormat 
Ellis J.L._Application of meta_animals-10-00720 (1).pdf1,49 MBAdobe PDFThumbnail
Show full item record
Review this work

WARNING: Items in Digital.CSIC are protected by copyright, with all rights reserved, unless otherwise indicated.