Abstract
The El Niño–Southern Oscillation (ENSO) has, in recent years, contributed to increases in the yields of major agricultural (annual) crops like wheat and barley in Canada. How such forcing alters the pattern of yield variation across different geographic scales and across large agricultural landscapes like the Canadian Prairies is less understood. Yet, such questions are of major importance in forecasting future cereal crop production. We explore the potential impact of ENSO on wheat and barley across the Canadian Prairies/Western Canada using a multi-scale, cluster-based principal component analysis (PCA) model that integrates machine-learning (K-means clustering) to predict areas of high climate risk. These risk areas are separable clusters of subregions that show similar ENSO-yield correlation response (spatial coherency). Benchmarking this spatial model to non-spatial models indicates that spatial coherency leads to gains in prediction skill. Incorporating spatial coherency increased the skill in predicting crop yield; reducing RMSE error by up to 26–34% (spring wheat) and 2–4% (barley). We infer that accounting for spatial coherency improves the accuracy and reliability of crop yield forecasts.
Similar content being viewed by others
Notes
International Organization of Vine and Wine (OIV).
G20 Action Plan on global food price volatility, http://www.foodsecurityportal.org/g20-action-plan-highlights-agriculture-and-food-price-volatility.
References
Abdi H, Williams L (2010) Principal component analysis. Wiley Interdiscip Rev Comput Stat 2(4):433–459
Axelson J, Sauchyn D, Barichivich J (2009) New reconstructions of streamflow variability in the South Saskatchewan River Basin from a network of tree ring chronologies, Alberta, Canada. Water Resour Res 45(9):W09422. doi:10.1029/2008WR007639
Bickel P, Diggle P, Fienberg S, Krickeberg K, Olkin I, Wermuth N, Zeger S (2002) Principal component analysis. Springer 2:37–52
Bonner S, Newlands N, Heckman N (2014) Modeling regional impacts of climate teleconnections using functional data analysis. Environ Ecol Stat 21(1):1–26
Bonsal B, Shabbar A (2011) Large-scale climate oscillations influencing Canada, 1900–2008. Tech. rep., Canadian biodiversity: ecosystem status and trends 2010, report 4
Bornn L, Zidek J (2012) Efficient stabilization of crop yield prediction in the Canadian Prairies. Agric For Meteorol 152:223–232
Cai R, Mullen J, Bergstrom J, Shurley W, Wetzstein M (2013) Using a climate index to measure crop yield response. J Agric Appl Econ 45(4):719–737
Cannon AJ (2015) Revisiting the nonlinear relationship between ENSO and winter extreme station precipitation in North America. Int J Climatol 35(13):4001–4014
Caruana R, Elhawary M, Nguyen N, Smith C (2006) Meta clustering. In: Proceedings of the sixth international conference on data mining (ICDM '06). IEEE Computer Society, Washington, DC, USA, pp 107–118. doi:10.1109/ICDM.2006.103
Ceglar A, Turco M, Toreti A, Doblas-Reyes F (2017) Linking crop yield anomalies to large-scale atmospheric circulation in Europe. Agric For Meteorol 240:35–45
Chipanshi A, Zhang Y, Kouadio L, Newlands N, Davidson A, Hand Hill R, Warren Qian B, Daneshfar B, Bedard F (2015) Evaluation of the integrated canadian crop yield forecaster (ICCYF) model for in-season prediction of crop yield across the Canadian agricultural landscape. Agric For Meteorol 206:137–150
Deryng D, Conway D, Ramankutty N, Price J, Warren R (2014) Global crop yield response to extreme heat stress under multiple climate change futures. Environ Res Lett 9(3):034011
Ding C, He X (2004) K-means clustering via principal component analysis. In: Proceedings of the twenty-first international conference on machine learning, ACM, New York, NY, USA, p 29
Dofine S (1992) Growth, phenology, and yield components of barley and wheat grown in Alaska. Can J Plant Sci 72(4):1227–1230
Garnett E, Khandekar M, Babb J (1998) On the utility of ENSO and PNA indices for long-lead forecasting of summer weather over the crop-growing region of the Canadian Prairies. Theor Appl Climatol 60(1):37–45
Gobena A, Gan T (2006) Low-frequency variability in Southwestern Canadian stream flow: links with large-scale climate anomalies. Int J Climatol 26(13):1843–1869
Harris P, Brunsdon C, Charlton M (2011) Geographically weighted principal components analysis. Int J Geogr Inf Sci 25(10):1717–1736
Hartigan J, Wong M (1979) Algorithm AS 136: a k-means clustering algorithm. J R Stat Soc Ser C Appl Stat 28(1):100–108
Hoffmann H, Zhao G, Asseng S, Bindi M, Biernath C, Constantin J, Coucheney E, Dechow R, Doro L, Eckersten H (2016) Impact of spatial soil and climate input data aggregation on regional yield simulations. PloS One 11(4):e0151782
Holzworth D, Huth N, Zurcher E, Herrmann N, McLean G, Chenu K, van Oosterom E, Snow V, Murphy C, Moore A (2014) APSIM-evolution towards a new generation of agricultural systems simulation. Environ Model Softw 62:327–350
Hsiang S, Meng K (2015) Tropical economics. Am Econ Rev Pap Proc 105(5):257–261
Hsieh W, Tang B, Garnett E (1999) Teleconnections between Pacific sea surface temperatures and Canadian prairie wheat yield. Agric For Meteorol 96(4):209–217
Hussein S, Puri M, Tonge P, Benevento M, Corso A, Clancy J, Mosbergen R, Li M, Lee DS, Cloonan N (2014) Genome-wide characterization of the routes to pluripotency. Nature 516(7530):198–206
Iizumi T, Ramankutty N (2016) Changes in yield variability of major crops for 1981–2010 explained by climate change. Environ Res Lett 11(3):034003
Iizumi T, Luo JJ, Challinor A, Sakurai G, Yokozawa M, Sakuma H, Brown M, Yamagata T (2014) Impacts of El Niño Southern Oscillation on the global yields of major crops. Nat Commun 5:3712. doi:10.1038/ncomms4712
Johnson M, Hsieh W, Cannon A, Davidson A, Bédard F (2016) Crop yield forecasting on the Canadian Prairies by remotely sensed vegetation indices and machine learning methods. Agric For Meteorol 218:74–84
Jolliffe I (2002) Principal component analysis, 2nd edn. Springer, New York, p 518
Kalnay E, Kanamitsu M, Kistler R, Collins W, Deaven D, Gandin L, Iredell M, Saha S, White G, Woollen J (1996) The NCEP/NCAR 40-year reanalysis project. Bull Am Meteorol Soc 77(3):437–471
Kanungo T, Mount D, Netanyahu N, Piatko C, Silverman R, Wu A (2002) An efficient k-means clustering algorithm: analysis and implementation. IEEE Trans Pattern Anal Mach Intell 24(7):881–892
Kim KY, Hamlington B, Na H (2015) Theoretical foundation of cyclostationary EOF analysis for geophysical and climatic variables: concepts and examples. Earth Sci Rev 150:201–218
Koij F, Saba J (2015) Using cluster analysis and principal component analysis to group lines and determine important traits in white bean. Proced Environ Sci 29:38–40
Kouadio L, Newlands N, Potgieter A, McLean G, Hill H (2015) Exploring the potential impacts of climate variability on spring wheat yield with the APSIM decision support tool. Agric Sci 6(7):686
Maadooliat M, Huang J, Hu J (2015) Integrating data transformation in principal components analysis. J Comput Gr Stat 24(1):84–103
Maraun D, Wetterhall F, Ireson A, Chandler R, Kendon E, Widmann M, Brienen S, Rust H, Sauter T, Themeßl M (2010) Precipitation downscaling under climate change: Recent developments to bridge the gap between dynamical models and the end user. Rev Geophys 48(3):RG3003
Meng T, Carew R, Florkowski W, Klepacka A (2017) Analyzing temperature and precipitation influences on yield distributions of Canola and spring wheat in Saskatchewan. J Appl Meteorol Climatol 56(4):897–913
Mkhabela M, Bullock P, Raj S, Wang S, Yang Y (2011) Crop yield forecasting on the Canadian Prairies using MODIS NDVI data. Agric For Meteorol 151(3):385–393
Moore FC, Lobell DB (2015) The fingerprint of climate trends on European crop yields. Proc Natl Acad Sci 112(9):2670–2675
Newlands N, Stephens D (2015) Increasing confidence in agricultural crop forecasts and climate adaptation decisions with causality analysis, vol 112, no. 9. Tech. rep., University of British Columbia (UBC), pp 2670–2675. doi:10.1073/pnas.1409606112
Newlands NK, Espino-Hernández G, Erickson RS (2012) Understanding crop response to climate variability with complex agroecosystem models. Int J Ecol 2012:1–13. doi:10.1155/2012/756242
Newlands NK, Zamar DS, Kouadio LA, Zhang Y, Chipanshi A, Potgieter A, Toure S, Hill HS (2014) An integrated, probabilistic model for improved seasonal forecasting of agricultural crop yield under environmental uncertainty. Front Environ Sci 2:17
Porter JR, Gawith M (1999) Temperatures and the growth and development of wheat: a review. Eur J Agron 10(1):23–36
Potgeiter A, Hammer G, Butler D (2002) Spatial and temporal patterns in Australian wheat yield and their relationship with ENSO. Aust J Agric Res 53:77–89
Quiring S, Blair D (1999) The utility of global teleconnection indices for long-range crop forecasting on the Canadian Prairies. PhD thesis, University of Winnipeg
Ramsay J, Silverman B (2005) Functional data analysis. Springer, New York
Ray D, Gerber J, MacDonald G, West P (2015) Climate variation explains a third of global crop yield variability. Nat Commun 6:5989
Ray S, Turi RH (1999) Determination of number of clusters in k-means clustering and application in colour segmentation. In: The 4th international conference on advances in pattern recognition and digital techniques, pp 137–143
Rodríguez-Fonseca B, Suárez-Moreno R, Ayarzagüena B, López-Parages J, Gómara I, Villamayor J, Mohino E, Losada T, Castaño-Tierno A (2016) A review of ENSO influence on the North Atlantic: a non-stationary signal. Atmosphere 7:87
Saib MS, Caudeville J, Beauchamp M, Carré F, Ganry O, Trugeon A, Cicolella A (2015) Building spatial composite indicators to analyze environmental health inequalities on a regional scale. Environ Health 14(1):68
Sauchyn D, Kerr S (2016) Vulnerability and adaptation: the Canadian Prairies and South America. University of Calgary Press, Calgary. Chap Past and future drought: lessons from climate science: Canadian Prairies drought from a paleoclimate perspective
Scherm H, Yang X (1995) Interannual variations in wheat rust development in China and the United States in relation to the El Niño/Southern Oscillation. Phytopathology 85(9):970–976
Shabbar A, Skinner W (2004) Summer drought patterns in Canada and the relationship to global sea surface temperatures. J Clim 17(14):2866–2880
Shabbar A, Bonsal B, Khandekar M (1997) Canadian precipitation patterns associated with the Southern Oscillation. J Clim 10(12):3016–3027
Sohn SJ, Tam CY, Jeong HI (2016) How do the strength and type of ENSO affect SST predictability in coupled models. Sci Rep 6:33790. doi:10.1038/srep33790
St George S, Sauchyn D (2006) Paleoenvironmental perspectives on drought in Western Canada—introduction. Can Water Resour J 31(4):197–204
Stone R, Hammer G, Marcussen T (1996) Prediction of global rainfall probabilities using phases of the Southern Oscillation Index. Nature 384:252–255
Sun L, Mitchell SW, Davidson A (2012) Multiple drought indices for agricultural drought risk assessment on the Canadian Prairies. Int J Climatol 32(11):1628–1639
Thompson B (2005) Canonical correlation analysis. In: Everitt BS, Howell D (eds) Encyclopedia of statistics in behavioral science, vol 1. Wiley, West Sussex, UK, pp 192–196
Trenberth KE, Dai A, Van Der Schrier G, Jones PD, Barichivich J, Briffa KR, Sheffield J (2014) Global warming and changes in drought. Nat Clim Chang 4(1):17–22
Wagstaff K, Cardie C, Rogers S, Schrödl S (2001) Constrained k-means clustering with background knowledge. In: ICML ’01 proceedings of the eighteenth international conference on machine learning, pp 577–584
Wang S, Huang J, He Y, Guan Y (2014) Combined effects of the Pacific decadal oscillation and El Nino–Southern oscillation on global land dry–wet changes. Sci Rep 4:6651
Watson J, Challinor A, Fricker T, Ferro C (2015) Comparing the effects of calibration and climate errors on a statistical crop model and a process-based crop model. Clim Change 132(1):93–109
Wigley T, Qipu T (1983) Crop-climate modeling using spatial patterns of yield and climate. Part 1: background and an example from Australia. J Clim Appl Meteorol 22(11):1831–1841.
Xie P, Arkin PA (1996) Analyses of global monthly precipitation using gauge observations, satellite estimates, and numerical model predictions. J Clim 9(4):840–858
Yu B, Zhang X, Lin H, Yu JY (2015) Comparison of wintertime North American climate impacts associated with multiple ENSO indices. Atmos Ocean 53(4):426–445
Zheng B, Chenu K, DM F, Chapman S (2012) Breeding for the future: what are the potential impacts of future frost and heat events on sowing and flowering time requirements for Australian bread wheat (Triticum aestivium) varieties? Glob Chang Biol 18(9):2899–2914
Acknowledgements
This study was funded by the Growing Forward Two Federal Research Program (Agriculture and Agri-Food Canada, AAFC) (Project No. J-000179.001.02) and assistance of Canada’s Federal Research Affiliate Program (RAP). Agro-climatic and CAR crop yield data used in this study were provided by partners in Statistics Canada and Environment and Climate Change Canada (ECCC). We thank Dr. Aston Chipanshi (AAFC) and Dr. Tracy A. Porcelli for their helpful review and feedback on earlier manuscript drafts, and Dr. Alex Cannon (ECCC) for input data guidance, and anonymous reviewers for their providing thoughtful comments and suggestions.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Lu, W., Atkinson, D.E. & Newlands, N.K. ENSO climate risk: predicting crop yield variability and coherence using cluster-based PCA. Model. Earth Syst. Environ. 3, 1343–1359 (2017). https://doi.org/10.1007/s40808-017-0382-0
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s40808-017-0382-0