Artificial neural network model for water consumption prediction in dairy farms

Márcia Regina Osaki; Julio Cesar Pascale Palhates; Fernando Guimarães Aguiar

doi:10.14393/BJ-v40n0a2024-68845

Authors

Márcia Regina Osaki Universidade Virtual do Estado de São Paulo
Julio Cesar Pascale Palhates Embrapa Pecuária Sudeste https://orcid.org/0000-0002-9757-3061
Fernando Guimarães Aguiar Universidade Federal de São Carlos

DOI:

https://doi.org/10.14393/BJ-v40n0a2024-68845

Keywords:

Lactating Cows, Semi-confined, Water Efficiency, Water Meter.

Abstract

This work presents a model based on artificial neural network (ANN) applied to predict water consumption in Brazilian dairy farms. Inputs were simple process data such as number of lactating cows, milk productivity, type of management, among others, with low computational cost and satisfactory data prediction. Data used for ANN training was acquired during two years from 31 farms in semi-confined dairy production. The analysis of the results was based on the following statistical models’ indicators: R² (Coefficient of determination), BIAS (trend coefficient), MAE (mean absolute error), RMSE (Root-mean-square deviation), NRMSE (percentage of the mean of the observations) and RAE (Relative absolute error). After performing the ANN training, the results showed good accuracy to predict water consumption in Brazilian dairy farms, with an average absolute error of 28.4% being obtained. On the other hand, considering the dataset used for ANN validation, an average absolute error of 48% was obtained.

Downloads

Download data is not yet available.

References

Agência Nacional de Águas e Saneamento (ANA). Conjuntura dos recursos hídricos no Brasil 2020: informe anual. https://www.snirh.gov.br/portal/centrais-de-conteudos/conjuntura-dos-recursos-hidricos/conjuntura-2020

Agricultural Water Withdrawals 2017. NYDEC (New York State Department of Environmental Conservation). Available at: http://www.dec.ny.gov/lands/86747.html

CARRA, S.H.Z., et al. The effect of best crop practices in the pig and poultry production on water productivity in a Southern Brazilian Watershed. Water. 2020, 12(11), 3014. https://doi.org/10.3390/w12113014

CHATURVEDI, S. and YADAV, R.L. Life Time Milk Amount Prediction in Dairy Cows using. Artificial Neural Networks. 2013, 1, 1–6.

CHUA, L. O. and YANG, L. Cellular neural networks: applications. Transactions on Circuits and Systems. 1988, 35(10), 1273–1290. https://doi.org/10.1109/31.7601

ROSA, R., et al. Towards combining data prediction and internet of things to manage milk production on dairy cows. Computers and Electronics in Agriculture. 2020, 169, 105-156. http://dx.doi.org/10.1016/j.compag.2019.105156

Dairy Farmers of Canada (DFC) 2016. ProAction—Targets & Achievements (Environment). https://www.dairyfarmers.ca/proaction/targets-achievements/environment

Food and Agriculture Organization of the United Nations (FAO). 2016. Environmental performance of animal feeds supply chains: Guidelines for assessment. Livestock Environmental Assessment and Performance Partnership. FAO, Rome, Italy. http://www.fao.org/partnerships/leap/en/

FRANCO, A.M., et al. Effects of lipid and starch supplementation as water intake mitigation techniques on performance and efficiency of nursing Holstein calves. Translational Animal Science. 2021, 5. https://doi.org/10.1093/tas/txab103

GUYON, I. Neural networks and applications tutorial. Physics Reports. 1991, 207(3–5), 215–259. http://dx.doi.org/10.1016/0370-1573(91)90146-D

HAYKIN, S. Redes Neurais: princípios e prática. Edited by Bookman. Porto Alegre.

HIGHAM, C.D., et al. Water use on nonirrigated pasture-based dairy farms: combining detailed monitoring and modeling to set benchmarks. Journal of Dairy Science. 2007, 100(1), 828–840. http://dx.doi.org/10.3168/jds.2016-11822

International Dairy Federation (IDF). 2016. Water footprint. http://www.fil-idf.org/idf-standing-committee-environment/life-cycle-assessment/water-footprint/

INSTITUTO BRASILEIRO DE GEOGRAFIA E ESTATISTICA (IBGE). Comunicado Técnico - Pesquisa Pecuária Municipal 2020. Rio de Janeiro, 20, 1-12, 2020. https://biblioteca.ibge.gov.br/visualizacao/periodicos/84/ppm_2020_v48_br_informativo.pdf

MCCULLOCH, W.S. and PITTS, W. A Logical Calculus of the Ideas Immanent in Nervous Activity. Bulletin of Mathematical Biophysics. 1943, 5, 115–133. http://dx.doi.org/10.1007/978-3-030-01370-7_61

MURPHY, E., et al. Predicting freshwater demand on Irish dairy farms using farm data. Journal of Cleaner Production. 2017, 166, 58–65. http://dx.doi.org/10.1016/j.jclepro.2017.07.240

National Water Security Plan / National Water Agency - 2019. https://pnsh.ana.gov.br/pdf/ingles.pdf - p. 39

OECD-FAO. Agricultural Outlook 2021-2030 p. 50. https://doi.org/10.1787/19991142

PALHARES, J.C.P., et al. Comparison of two water measurement systems for feedlot beef cattle. Revista Ambiente e Água. 2021, 16(4). https://doi.org/10.4136/ambi-agua.2729

PALHARES, J.C.P., et al. Best practice production to reduce the water footprint of dairy milk. Revista Ambiente & Água. 2020, 15, 1. https://doi.org/10.4136/ambi-agua.2454

PALHARES, J.C.P. and PEZZOPANE, J.R.M. Water footprint accounting and scarcity indicators of conventional and organic dairy production systems. Journal Of Cleaner Production. 2015, 93, 299-307. http://dx.doi.org/10.1016/j.jclepro.2015.01.035

PICCININI, G. The first computational theory of mind and brain: A close look at McCulloch and Pitts’s “logical calculus of ideas immanent in nervous activity. Synthese. 2004, 141(2), 175–215. http://dx.doi.org/10.1023/B:SYNT.0000043018.52445.3e

ROBINSON, A., et al. Usage and attitudes of water conservation on Ontario dairy farms. The Professional Animal Scientist. 2016, 32, 236-242. http://dx.doi.org/10.15232/pas.2015-01468

RUMELHART, D.E. and HINTONT, G.E. Learning Representations by Back-Propagating Errors. Cognitive Modeling. 2019, 2, 3–6. https://doi.org/110.7551/mitpress/1888.003.0013

SABER, A.Y., et al. Efficient Water Quality Prediction Models Based on Machine Learning Algorithms for Nainital Lake, Uttarakhand. 2017 IEEE Symposium Series on Computational Intelligence, SSCI 2017 – Proceedings. 2022, 9(2), 79–82. https://doi.org/10.1016/j.matpr.2021.12.334

SHEN, W., et al. Assessment of Dairy Cow Feed Intake Based on BP Neural Network with Polynomial Decay Learning Rate.” Information Processing in Agriculture. 2022, 9(2), 266–75. https://doi.org/10.1016/j.inpa.2021.04.008

SHINE, P., ET AL. Global Review of Monitoring, Modeling, and Analyses of Water Demand in Dairy Farming. Sustainability. 2020, 12(17), 7201. https://doi.org/10.3390/su12177201

SHINE, P., et al. Machine-learning algorithms for predicting on-farm direct water and electricity consumption on pasture based dairy farms. Computers and Electronics in Agriculture. 2018a, 150, 74–87. https://doi.org/110.1016/j.compag.2018.03.023

SHINE, P., et al. Electricity & direct water consumption on Irish pasture based dairy farms: A statistical analysis. Applied Energy. 2018b, 210, 529-537. https://doi.org/10.1016/j.apenergy.2017.07.029

SHINE, P., et al. Multiple linear regression modelling of on-farm direct water and electricity consumption on pasture based dairy farms. Computers and Electronics in Agriculture. 2018c, 148, 337–346. https://doi.org/10.1016/j.compag.2018.02.020

VANDERZAAG, A.C., et al. Case Study: Water budget of a dairy farm with a tie-stall barn for milk cows and summer pasturing of heifers and dry cows. Applied Animal Science. 2018, 34(1), 108–117. https://doi.org/10.15232/pas.2017-01654

ZHANG, F., et al. An automatic model configuration and optimization system for milk production forecasting. Computers and Electronics in Agriculture. 2016, 128, 100–111. https://doi.org/110.1016/j.compag.2016.08.016

WILLMOTT, C.J. and MATSUURA, K. Advantages of the Mean Absolute Error (MAE) over the Root Mean Square Error (RMSE) in Assessing Average Model Performance. Climate Research. 2005, 30(1), 79–82.