Integrating heterogeneous across-country data for proxy-based random forest prediction of enteric methane in dairy cattle

Enyew Negussie*, Oscar González-Recio, Mara Battagin, Ali Reza Bayat, Tommy Boland, Yvette de Haas, Aser Garcia-Rodriguez, Philip C. Garnsworthy, Nicolas Gengler, Michael Kreuzer, Björn Kuhla, Jan Lassen, Nico Peiren, Marcin Pszczola, Angela Schwarm, Hélène Soyeurt, Amélie Vanlierde, Tianhai Yan, Filippo Biscarini

*Corresponding author for this work

Research output: Contribution to journalArticleAcademicpeer-review

Abstract

Direct measurements of methane (CH4) from individual animals are difficult and expensive. Predictions based on proxies for CH4 are a viable alternative. Most prediction models are based on multiple linear regressions (MLR) and predictor variables that are not routinely available in commercial farms, such as dry matter intake (DMI) and diet composition. The use of machine learning (ML) algorithms to predict CH4 emissions from across-country heterogeneous data sets has not been reported. The objectives were to compare performances of ML ensemble algorithm random forest (RF) and MLR models in predicting CH4 emissions from proxies in dairy cows, and assess effects of imputing missing data points on prediction accuracy. Data on CH4 emissions and proxies for CH4 from 20 herds were provided by 10 countries. The integrated data set contained 43,519 records from 3,483 cows, with 18.7% missing data points imputed using k-nearest neighbor imputation. Three data sets were created, 3k (no missing records), 21k (missing DMI imputed from milk, fat, protein, body weight), and 41k (missing DMI, milk fat, and protein records imputed). These data sets were used to test scenarios (with or without DMI, imputed vs. nonimputed DMI, milk fat, and protein), and prediction models (RF vs. MLR). Model predictive ability was evaluated within and between herds through 10-fold cross-validation. Prediction accuracy was measured as correlation between observed and predicted CH4, root mean squared error (RMSE) and mean normalized discounted cumulative gain (NDCG). Inclusion of DMI in the model improved within and between-herd prediction accuracy to 0.77 (RMSE = 23.3%) and 0.58 (RMSE = 31.9%) in RF and to 0.50 (RMSE = 0.327) and 0.13 (RMSE = 42.71) in MLR, respectively than when DMI was not included in the predictive model. When missing DMI records were imputed, within and between-herd accuracy increased to 0.84 (RMSE = 18.5%) and 0.63 (RMSE = 29.9%), respectively. In all scenarios, RF models out-performed MLR models. Results suggest routinely measured variables from dairy farms can be used in developing globally robust prediction models for CH4 if coupled with state-of-the-art techniques for imputation and advanced ML algorithms for predictive modeling.

Original languageEnglish
Pages (from-to)5124-5140
JournalJournal of Dairy Science
Volume105
Issue number6
Early online date26 Mar 2022
DOIs
Publication statusPublished - Jun 2022

Keywords

  • enteric methane
  • machine learning
  • prediction models
  • proxies for methane

Fingerprint

Dive into the research topics of 'Integrating heterogeneous across-country data for proxy-based random forest prediction of enteric methane in dairy cattle'. Together they form a unique fingerprint.

Cite this