Scholarly record
FORECASTING WEEKLY COW MILK PRODUCTION USING A MULTIVARIATE TIME SERIES APPROACH
Abstract
The continuous rise in global population necessitates the prediction of food resources, among which milk stands out as one of the staples. Dairy farms and processing plants need to know how much milk they will have available to manage their storage and processing capacities efficiently. Overestimating production can lead to wastage, while underestimating can lead to shortages. Knowing the expected milk quantity helps in planning the transportation, processing, and distribution of milk and milk products. This study presents a cutting-edge method for forecasting weekly cow milk production using a multivariate time series approach. Leveraging collected data from IoT devices for environmental variables, genetic data from health diaries, and health metrics alongside traditional temporal data, this research aims to provide a comprehensive model for predicting milk yields. - multivariate time series model SARIMAX was trained, tested and evaluated, focusing on ensuring both accuracy and robustness. The findings demonstrate that by integrating multiple data streams, significant improvements in forecast precision can be achieved. Furthermore, this integrated approach provides insights into the key factors influencing weekly milk production, paving the way for informed strategies in dairy management. The proposed model showcases the potential for scalability across different dairy operations and regions, contributing to the global effort towards food security and sustainable agriculture practices.
Publication Impact Profile
- Captures
- Mendeley - Readers: 2
Publication details
References9
Statistics: Dairy cows. https://www.ciwf.org.uk/media/5235182/Statistics-Dairycows.pdf
Peterson C. B.; Mitloehner F. M. Sustainability of the Dairy Industry: Emissions andMitigation Opportunities, Frontiers in Animal Science, 2021, 2,DOI: 10.3389/fanim.2021.760310
Zhang F., Shine Ph., Upton J., Shaloo L., Murphy M.D. A Review of Milk ProductionForecasting Models: Past & Future Methods. In book: Dairy farming operationsmanagement, animal welfare and milk production, Nova Science Publishers, 2018.
Liseune A., Salamone M., Poel D., Ranst B, Hostens M. Predicting the milk yield curveof dairy cows in the subsequent lactation period using deep learning. Computers andElectronics in Agriculture, 180, 105904 2021,DOI: 10.1016/j.compag.2020.105904
Nguyen Q.T., Fouchereau R., Frenod E., Gerard C., t Sincholle V. Comparison offorecast models of production of dairy cows combining animal and diet parameters.Computers and Electronics in Agriculture, 170, 2020, 105258DOI: 10.1016/j.compag.2020.105258
Zhang, H., Wang, X., Cao, J. et al. A multivariate short-term traffic flow forecastingmethod based on wavelet analysis and seasonal time series. Appl Intell 48, 3827�3838(2018). DOI: 10.1007/s10489-018-1181-7
Blagoev, I. Application of Time Series Techniques for Random Number GeneratorAnalysis. Proceedings of XXII Int. Conference DCCN 2019, 2019, pp. 437-446
Wang R., Pei X., Zhu J., Zhang Z., Huang X., Zhai J., Zhang F. Multivariable timeseries forecasting using model fusion. Information Sciences, 585, 2022, pp. 262-274. DOI: 10.1016/j.ins.2021.11.025
Nyangaresi, V., El-Omari, N., Nyakina, J. �Efficient feature selection and ML algorithmfor accurate diagnostics�. Journal of computer science research, vol. 04, issue 01, 2022,DOI: 10.30564/jcsr.v4i1.3852
View or Download full articleAccess options
SWS access login
Login as SWS Scientific CommitteeLogin as SWS Scientific PartnerLogin as SWS AuthorAuthors and approved SWS contributors will read and export their own linked papers after identity matching by SWS profile, email and SGEM GlobalID.
For librarian assistance: [email protected]
Purchase Instant Access
- Article can be downloaded after successful payment.
- Article may be used according to SWS library access terms.
- Article cannot be redistributed.