Abstract
Accurate milk supply forecasting for the dairy sector, covering 1000 s of farms with low resolution data, is a key challenge in achieving a sustainable, precision agriculture that can improve farm management, balancing costs, energy use and environmental protection. We show that case-based reasoning (CBR) can meet this sustainability challenge, by supplementing a time series prediction model on a full-year-forecasting task. Using a dataset of three years of milk supply from Irish dairy farms (N = 2,479), we produce accurate full-year forecasts for each individual farm, by augmenting that farm’s data with data from nearest-neighboring farms, based on the similarity of their time series profiles (using Dynamic Time Warping). A study comparing four methods (Seasonal Naïve, LSTM, Prophet, \(Prophet^{NN}\)) showed that the method using CBR data-augmentation \((Prophet^{NN})\) outperformed the other evaluated methods. We also demonstrate the utility of CBR in providing farmers with novel prefactual explanations for forecasting that could help them to realize actions that could boost future milk yields and profitability.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Aha, D.W., Kibler, D., Albert, M.K.: Instance-based learning algorithms. Mach. Learn. 6(1), 37–66 (1991). https://doi.org/10.1007/BF00153759
Berndt, D.J., Clifford, J.: Using dynamic time warping to find patterns in time series. In: KDD Workshop, vol. 10, pp. 359–370. Seattle, WA, USA (1994)
Boichard, D.: Estimation of the economic value of conception rate in dairy cattle. Livest. Prod. Sci. 24(3), 187–204 (1990)
Branting, K., Hastings, J.D., Lockwood, J.A.: Carma: a case-based range management advisor. In: IAAI, pp. 3–10 (2001)
Byrne, R.M., Egan, S.M.: Counterfactual and prefactual conditionals. Can. J. Exp. Psychol./Revue Can. de Psychol. Expérimentale 58(2), 113 (2004)
Cerqueira, V., Torgo, L., Mozetič, I.: Evaluating time series forecasting models: an empirical study on performance estimation methods. Mach. Learn. 109(11), 1997–2028 (2020). https://doi.org/10.1007/s10994-020-05910-7
Chollet, F., et al.: Keras (2015). https://github.com/fchollet/keras
Dai, X., Keane, M.T., Shalloo, L., Ruelle, E., Byrne, R.M.: Counterfactual explanations for prediction and diagnosis in xai. In: To appear in AIES 2022 (2022)
Delaney, E., Greene, D., Keane, M.T.: Instance-based counterfactual explanations for time series classification. In: Sánchez-Ruiz, A.A., Floyd, M.W. (eds.) ICCBR 2021. LNCS (LNAI), vol. 12877, pp. 32–47. Springer, Cham (2021). https://doi.org/10.1007/978-3-030-86957-1_3
Epstude, K., Scholl, A., Roese, N.J.: Prefactual thoughts: mental simulations about what might happen. Rev. Gen. Psychol. 20(1), 48–56 (2016)
Fdez-Riverola, F., Corchado, J.M.: Fsfrt: forecasting system for red tides. Appl. Intell. 21(3), 251–264 (2004). https://doi.org/10.1023/B:APIN.0000043558.52701.b1
Feely, C., Caulfield, B., Lawlor, A., Smyth, B.: Using case-based reasoning to predict marathon performance and recommend tailored training plans. In: Watson, I., Weber, R. (eds.) ICCBR 2020. LNCS (LNAI), vol. 12311, pp. 67–81. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58342-2_5
Gee, A.H., Garcia-Olano, D., Ghosh, J., Paydarfar, D.: Explaining deep classification of time-series data with learned prototypes. CEUR Workshop Proc. 2429, 15–22 (2019)
Gowing, P., Dunne, J.: Cost control for 2022 (2022). https://www.teagasc.ie/news--events/daily/dairy/cost-control-for-2022.php
Hastings, J., Branting, K., Lockwood, J.: Carma: a case-based rangeland management adviser. AI Mag. 23(2), 49–49 (2002)
Herweijer, C., Combes, B., Gillham, J.: How AI can enable a sustainable future. PwC report (2018)
Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9(8), 1735–1780 (1997)
Horan, B., Dillon, P., Berry, D., O’Connor, P., Rath, M.: The effect of strain of holstein-friesian, feeding system and parity on lactation curves characteristics of spring-calving dairy cows. Livest. Prod. Sci. 95(3), 231–241 (2005)
Hyndman, R.J., Athanasopoulos, G.: Forecasting: principles and practice. OTexts (2018)
Hyndman, R.J., Koehler, A.B.: Another look at measures of forecast accuracy. Int. J. Forecast. 22(4), 679–688 (2006)
Keane, M.T., Kenny, E.M., Delaney, E., Smyth, B.: If only we had better counterfactual explanations: five key deficits to rectify in the evaluation of counterfactual xai techniques. In: IJCAI-21 (2021)
Keane, M.T., Smyth, B.: Good Counterfactuals and where to find them: a case-based technique for generating counterfactuals for explainable AI (XAI). In: Watson, I., Weber, R. (eds.) ICCBR 2020. LNCS (LNAI), vol. 12311, pp. 163–178. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58342-2_11
Kenny, E.M., Ford, C., Quinn, M., Keane, M.T.: Explaining black-box classifiers using post-hoc explanations-by-example: the effect of explanations and error-rates in xai user studies. Artif. Intell. 294, 103459 (2021)
Kenny, E.M., et al.: Bayesian case-exclusion and personalized explanations for sustainable dairy farming. In: IJCAI, pp. 4740–4744 (2021)
Kenny, E.M., Ruelle, E., Geoghegan, A., Shalloo, L., O’Leary, M., O’Donovan, M., Keane, M.T.: Predicting grass growth for sustainable dairy farming: a CBR system using bayesian case-exclusion and Post-Hoc, personalized explanation-by-example (XAI). In: Bach, K., Marling, C. (eds.) ICCBR 2019. LNCS (LNAI), vol. 11680, pp. 172–187. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-29249-2_12
Kim, B., Khanna, R., Koyejo, O.O.: Examples are not enough, learn to criticize! criticism for interpretability. In: Advances in Neural Information Processing Systems, pp. 2280–2288 (2016)
Kok, A., Chen, J., Kemp, B., Van Knegsel, A.: Dry period length in dairy cows and consequences for metabolism and welfare and customised management strategies. Animal 13(S1), s42–s51 (2019)
Mahato, V., O’Reilly, M., Cunningham, P.: A comparison of k-nn methods for time series classification and regression. In: AICS, pp. 102–113 (2018)
Makridakis, S., Spiliotis, E., Assimakopoulos, V.: Statistical and machine learning forecasting methods: concerns and ways forward. PLoS One 13(3), e0194889 (2018)
Molnar, C.: Interpretable machine learning. Lulu.com (2020)
Mueen, A., Keogh, E.: Extracting optimal performance from dynamic time warping. In: Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 2129–2130 (2016)
Murphy, M.D., O’Mahony, M.J., Shalloo, L., French, P., Upton, J.: Comparison of modelling techniques for milk-production forecasting. J. Dairy Sci. 97(6), 3352–3363 (2014)
Nakhaeizadeh, G.: Learning prediction of time series. A theoretical and empirical comparison of CBR with some other approaches. In: Wess, S., Althoff, K.-D., Richter, M.M. (eds.) EWCBR 1993. LNCS, vol. 837, pp. 65–76. Springer, Heidelberg (1994). https://doi.org/10.1007/3-540-58330-0_77
Petitjean, F., Forestier, G., Webb, G.I., Nicholson, A.E., Chen, Y., Keogh, E.: Dynamic time warping averaging of time series allows faster and more accurate classification. In: 2014 IEEE international conference on data mining, pp. 470–479. IEEE (2014)
Shalloo, L., Cromie, A., McHugh, N.: Effect of fertility on the economics of pasture-based dairy systems. Animal 8(s1), 222–231 (2014)
Shalloo, L., Creighton, P., O’Donovan, M.: The economics of reseeding on a dairy farm. Irish J. Agric. Food Res. 50(1), 113–122 (2011)
Smyth, B., Cunningham, P.: A novel recommender system for helping marathoners to achieve a new personal-best. In: Proceedings of the Eleventh ACM Conference on Recommender Systems, pp. 116–120 (2017)
Taylor, S.J., Letham, B.: Forecasting at scale. Am. Stat. 72(1), 37–45 (2018)
Teagasc: Teagasc national farm survey 2020 - dairy enterprise fact-sheet (2020). https://www.teagasc.ie/media/website/publications/2021/NFS_Dairy_Factsheet2020.pdf
Temraz, M., Kenny, E.M., Ruelle, E., Shalloo, L., Smyth, B., Keane, M.T.: Handling climate change using counterfactuals: using counterfactuals in data augmentation to predict crop growth in an uncertain climate future. In: Sánchez-Ruiz, A.A., Floyd, M.W. (eds.) ICCBR 2021. LNCS (LNAI), vol. 12877, pp. 216–231. Springer, Cham (2021). https://doi.org/10.1007/978-3-030-86957-1_15
Upton, J., Murphy, M., De Boer, I., Koerkamp, P.G., Berentsen, P., Shalloo, L.: Investment appraisal of technology innovations on dairy farm electricity consumption. J. Dairy Sci. 98(2), 898–909 (2015)
Vinuesa, R., et al.: The role of artificial intelligence in achieving the sustainable development goals. Nat. Commun. 11(1), 1–10 (2020)
Wiratunga, N., Wijekoon, A., Nkisi-Orji, I., Martin, K., Palihawadana, C., Corsar, D.: Actionable feature discovery in counterfactuals using feature relevance explainers. Case-based reasoning for the explanation of intelligent systems, Third Workshop on XCBR (2021)
Zhang, F., Murphy, M.D., Shalloo, L., Ruelle, E., Upton, J.: An automatic model configuration and optimization system for milk production forecasting. Comput. Electron. Agric. 128, 100–111 (2016)
Zhang, F., Shine, P., Upton, J., Shaloo, L., Murphy, M.D.: A review of milk production forecasting models: past & future methods (2020)
Acknowledgements
This publication has emanated from research conducted with the financial support of (i) Science Foundation Ireland (SFI) to the Insight Centre for Data Analytics under Grant Number 12/RC/2289_P2 and (ii) SFI and the Department of Agriculture, Food and Marine on behalf of the Government of Ireland under Grant Number 16/RC/3835 (VistaMilk).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Delaney, E., Greene, D., Shalloo, L., Lynch, M., Keane, M.T. (2022). Forecasting for Sustainable Dairy Produce: Enhanced Long-Term, Milk-Supply Forecasting Using k-NN for Data Augmentation, with Prefactual Explanations for XAI. In: Keane, M.T., Wiratunga, N. (eds) Case-Based Reasoning Research and Development. ICCBR 2022. Lecture Notes in Computer Science(), vol 13405. Springer, Cham. https://doi.org/10.1007/978-3-031-14923-8_24
Download citation
DOI: https://doi.org/10.1007/978-3-031-14923-8_24
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-14922-1
Online ISBN: 978-3-031-14923-8
eBook Packages: Computer ScienceComputer Science (R0)