Register      Login
Crop and Pasture Science Crop and Pasture Science Society
Plant sciences, sustainable farming systems and food quality
Shopping Cart: ( empty )
You are here: Home > Journals > CP > AR05443
RESEARCH ARTICLE
Contents Vol 58(2)

A Bayesian modelling approach for long lead sugarcane yield forecasts for the Australian sugar industry

Y. L. Everingham A B E , N. G. Inman-Bamber A , P. J. Thorburn C and T. J. McNeill D
+ Author Affiliations
- Author Affiliations

A CSIRO Sustainable Ecosystems, Davies Laboratory, Townsville, Qld 4814, Australia.

B School of Mathematical and Physical Sciences, James Cook University, Townsville, Qld 4814, Australia.

C CSIRO Sustainable Ecosystems, Queensland Bioscience Precinct, 306 Carmody Rd, St Lucia, Qld 4067, Australia.

D Sugar InSite Pty Ltd, Kangaroo Pt, Brisbane, Qld 4169, Australia.

E Corresponding author. Email: yvette.everingham@jcu.edu.au

Australian Journal of Agricultural Research 58(2) 87-94 https://doi.org/10.1071/AR05443
Submitted: 19 December 2005  Accepted: 27 October 2006   Published: 22 February 2007

Abstract

For marketers, advance knowledge on sugarcane crop size permits more confidence in implementing forward selling, pricing, and logistics activities. In Australia, marketing plans tend to be initialised in December, approximately 7 months prior to commencement of the next harvest. Improved knowledge about crop size at such an early lead time allows marketers to develop and implement a more advanced marketing plan earlier in the season. Producing accurate crop size forecasts at such an early lead time is an on-going challenge for industry. Rather than trying to predict the exact size of the crop, a Bayesian discriminant analysis procedure was applied to determine the likelihood of a small, medium, or large crop across 4 major sugarcane-growing regions in Australia: Ingham, Ayr, Mackay, and Bundaberg. The Bayesian model considers simulated potential yields, climate forecasting indices, and the size of the crop from the previous year. Compared with the current industry approach, the discriminant procedure provided a substantial improvement for Ayr and a moderate improvement over current forecasting methods for the remaining regions, with the added advantage of providing probabilistic forecasts of crop categories.

Additional keywords: crop model, simulate, discriminant, prediction, climate, APSIM.


Acknowledgments

Funding for this research was provided by Queensland Sugar Limited and the Australian government through the Sugar Research and Development Corporation. Rainfall data were obtained from the Australian Bureau of Meteorology patched point dataset. Productivity data were provided by Queensland Sugar Limited. The first author was employed by CSIRO whilst this research was undertaken. The authors thank Carla Chen (JCU) for assisting with the preparation of this manuscript.


References


Argete J (1983) Sugarcane production estimates using LANDSAT MSS data and agrometeorological models. Proceedings Philippines Sugar Technologists Association 30, 583–596. open url image1

Bezuidenhout CN, Schulze RE (2005) Application of seasonal climate outlooks to forecast sugarcane production in South Africa. Climate Research 30, 239–246. open url image1

Bezuidenhout CN , Singels A (2001) The use of simulation crop modelling to forecast sugarcane yield. Proceedings of a SASTA workshop on the integration of appropriate technology to provide practical solutions to burn/harvest to crush delays and crop estimating in the South African sugar industry. In ‘Proceedings South African Sugar Technologists Association’. 8 November 2001, Mount Edgcome, South Africa. pp. 20–29. (CD-ROM)

Cheeroo-Nayamuth FC, Robertson MJ, Wegener MK, Nayamuth ARH (2000) Using a simulation model to assess potential and attainable cane yield in Mauritius. Field Crops Research 66, 225–243.
| Crossref | GoogleScholarGoogle Scholar | open url image1

Clarke AJ, Van Gorder S (2003) Improving El Niño prediction using a space-time integration of Indo-Pacific winds and equatorial Pacific upper ocean heat content. Geophysical Research Letters 30,
| Crossref | GoogleScholarGoogle Scholar | open url image1

Everingham YL, Inman-Bamber NG, Ticehurst C, Barrett D, Lowe K, McNeill T (2005) Yield forecasting for marketers. Proceedings Australian Society of Sugar Technologists Association 27, 51–60. open url image1

Everingham YL, Muchow RC, Stone RC (2001) Forecasting Australian sugar yields using phases of the southern oscillation index. Proceedings International Congress on Modelling and Simulation 4, 1781–1786. open url image1

Everingham YL, Muchow RC, Stone RC, Coomans DH (2003) Enhancing sugarcane yield forecasting capability using SOI phases: a case study for northeastern Australia. International Journal of Climatology 23, 1211–1218.
| Crossref | GoogleScholarGoogle Scholar | open url image1

Everingham YL, Muchow RC, Stone RC, Inman-Bamber NG, Singels A, Bezuidenhout CN (2002) Enhanced risk management and decision-making capability across the sugar industry value chain based on seasonal climate forecasts. Agricultural Systems 74, 459–477.
| Crossref | GoogleScholarGoogle Scholar | open url image1

Fisher RA (1936) The use of multiple measurements in taxonomic problems. Annals of Eugenics 7, 179–188. open url image1

Hansen JW, Jones JW (2000) Scaling-up crop models for climate variability applications. Agricultural Systems 65, 43–72.
| Crossref | GoogleScholarGoogle Scholar | open url image1

Inman-Bamber NG , Everingham YL , Muchow RC (2001) Modelling water stress response in sugarcane: validation and application of the APSIM-Sugarcane model. In ‘10th Australian Agronomy Conference’. 28 Jan.–1 Feb. 2001, Hobart, Tas.

Johnson RA , Wichern DW (1988) ‘Applied multivariate statistical analysis.’ (Prentice Hall: Englewood Cliffs, NJ)

Keating BA, Robertson MJ, Muchow RC, Huth NI (1999) Modelling sugarcane production systems. I: Description and validation of the sugarcane module. Field Crops Research 61, 253–271.
| Crossref | GoogleScholarGoogle Scholar | open url image1

Kiker GA (2000) CANEGRO-DSSAT linkages with geographic information systems: Applications in climate change research for South Africa. In ‘International CANEGRO Workshop’. Mount Edgecombe, South Africa. (Eds GJ O’Leary, GA Kiker) South African Sugar Association Experiment Station.

Kuhnel I (1994) Relationship between the Southern Oscillation Index and Australian sugarcane yields. Australian Journal of Agricultural Research 45, 1557–1568.
| Crossref | GoogleScholarGoogle Scholar | open url image1

de Lange J, Singels A (2003) Using the internet-based Canesim model for crop estimation in the Umfolozi mill supply area. Proceedings South African Sugar Technologists Association 77, 592–595. open url image1

Lee-Lovick G, Kirchner L (1990) The application of remotely sensed (Landsat TM) data to monitor the growth and predict yields in sugarcane. Proceedings Australian Society of Sugar Cane Technologists 12, 65–72. open url image1

Lee-Lovick G, Kirchner L (1991) Limitation of Landsat TM data in monitoring growth and predicting yields in sugarcane. Proceedings Australian Society of Sugar Cane Technologists 13, 124–130. open url image1

Lumsden TG, Lecler NL, Schulze RE (1998) Simulation of sugarcane yield at the scale of a mill supply area. Proceedings South African Sugar Technologists Association 72, 12–17. open url image1

McBride JL, Nicholls N (1983) Seasonal relationships between Australian rainfall and the southern oscillation. Monthly Weather Report 111, 1998–2004.
| Crossref | GoogleScholarGoogle Scholar | open url image1

McGlinchey MG (1999) Computer crop model applications: developments in Swaziland. Proceedings South African Sugar Technologists Association 73, 35–38. open url image1

Noonan M (1999) ‘Classification of fallow and yields using Landsat TM data in the sugarcane lands of the Herbert River Catchment.’ (Herbert Resource Information Centre, Qld) www.hric.org.au

Pittock AB (1975) Climatic change and the patterns of variation in Australian rainfall. Search 6, 498–504. open url image1

Potgieter AB, Everingham YL, Hammer GL (2003) Measuring quality of a commodity forecasting system that incorporates seasonal climate forecasts. International Journal of Climatology 23,  1195–1210.
| Crossref | GoogleScholarGoogle Scholar | open url image1

Potgieter AB, Hammer GL, Meinke H, Stone RC, Goddard L (2005) Three putative types of El Nino revealed by spatial variability in impact on Australian wheat yield. Journal of Climate 18, 1566–1574.
| Crossref | GoogleScholarGoogle Scholar | open url image1

Promburom P, Jintrawet A, Ekasingh M (2001) Estimating sugarcane yields with 5 Oy-Thai Interface. Proceedings International Society of Sugar Cane Technologists 24, 81–86. open url image1

Ropelewski CF, Halpert MS (1987) Global and regional scale precipitation patterns associated with the El Niño/Southern Oscillation. Monthly Weather Review 115, 1606–1626.
| Crossref | GoogleScholarGoogle Scholar | open url image1

Scarpari MS, Beauclair EGF (2004) Sugarcane maturity estimation through edaphic-climatic parameters. Scientia Agricola 61, 486–491. open url image1

Schmidt EJ, Narciso G, Frost P, Gers C (2000) Application of remote sensing technology in the SA Sugar Industry—a review of recent research findings. Proceedings South African Sugar Technologists Association 74, 192–201. open url image1

Singels A, Bezuidenhout CN (1998) ENSO, the South African climate and sugarcane production. Proceedings South African Sugarcane Technologists Association 72, 10–11. open url image1

Singels A, Bezuidenhout CN (1999) The relationship between ENSO and rainfall and yield in the South African sugar industry. South African Journal of Plant and Soil 16, 96–101. open url image1

S-PLUS (2002) ‘S-PLUS 6 for Windows guide to statistics, Vol. 2.’ (Insightful Corp.: Seattle, WA)

SRDC (1995) ‘Research and development plan 1995–2000.’ (Sugar and Research Development Corp.: Brisbane, Qld)

Stone R, Auliciems A (1992) SOI phase relationships with rainfall in eastern Australia. International Journal of Climatology 12, 625–636.
| Crossref |
open url image1

Stone RC, Hammer G, Marcussen T (1996) Prediction of global rainfall probabilities using phases of the Southern Oscillation Index. Nature 384, 252–255.
| Crossref | GoogleScholarGoogle Scholar | open url image1

Trenberth KE, Caron JM (2000) The southern oscillation revisited: sea level pressures, surface temperatures and precipitation. Journal of Climate 13, 4358–4365.
| Crossref | GoogleScholarGoogle Scholar | open url image1