Logo PTI Logo FedCSIS

Proceedings of the 21st Conference on Computer Science and Intelligence Systems (FedCSIS)

Annals of Computer Science and Information Systems, Volume 47

End-to-End Sugar Beet Management Optimisation via DSSAT Repair and Quadratic Surrogate Programming

,

DOI: http://dx.doi.org/10.15439/2026F4933

Citation: Ahmed Amine Tabbassi,

Full text

Abstract. Sugar beet production involves a fundamental trade-off: nitrogen fertilisation increases root yield but decreases sugar concentration. Optimising total sugar yield requires balancing multiple management levers under agronomic and regulatory constraints. Widely-used process-based crop models such as the Decision Support System for Agrotechnology Transfer (DSSAT) and the Agricultural Production Systems Simulator (APSIM) cannot directly solve this problem for sugar beet because their sugar beet modules do not provide a complete management-to-sugar-yield optimisation workflow. We present an end-to-end framework that combines a nitrogen-response correction via DSSAT's soil productivity factor, a machine-learning model for sugar content prediction, per-field quadratic surrogate surfaces, and constrained continuous optimisation over nitrogen amount and split timing, planting date, and irrigation. The completed experiments indicate a baseline fresh-yield mean absolute error (MAE) of 6.4 t/ha, a median fresh-yield error of -1.2\%, and 88.5\% of fields within a ±20\% error band. For sugar prediction, pooled cross-validation achieved an MAE of 0.75 and R² = 0.61, while the year-ahead hold-out on 2025 yielded root mean square error (RMSE) 0.82, MAE 0.68, and R² = 0.54. End-to-end loss on observed sugar yield shows that the DSSAT-coupled pipeline outperforms simpler variants (MAE 0.467 vs 0.805 for no-DSSAT vs 1.017 for multiple linear regression (MLR)). Held-out surrogate diagnostics on random test points remain strong (MAE approximately 0.201; RMSE 0.251; R² = 0.979). Under the main optimisation scenarios, model-estimated gains over the advisory baseline were 2.71\% unconstrained, 2.45\% under the EU nitrogen limit, and 2.10\% under the budget constraint; a prospective paired dataset further shows +0.71 t/ha observed sugar-yield uplift (+5.37\%).

References

  1. CEFS, “The european sugar sector,” 2026, accessed: 2026. [Online]. Available: https://cefs.org/the-european-sugar-sector/
  2. Eurostat, “Sugar beet production statistics in the european union,” 2026, accessed: 2026. [Online]. Available: https://ec.europa.eu/eurostat/
  3. A. P. Draycott, Sugar Beet. Oxford, UK: Blackwell Publishing, 2006.
  4. H.-J. Koch, S. Heuer, O. Tomanova, and B. Marlander, “Cumulative effect of annually repeated passes of heavy agricultural machinery on soil structural properties and sugar beet yield under two tillage systems,” Soil and Tillage Research, vol. 101, no. 1–2, pp. 69–77, 2009.
  5. R. Gebbers and V. I. Adamchuk, “Precision agriculture and food security,” Science, vol. 327, no. 5967, pp. 828–831, 2010.
  6. J. W. Jones, G. Hoogenboom, C. H. Porter, K. J. Boote, W. D. Batchelor, L. A. Hunt, P. W. Wilkens, U. Singh, A. J. Gijsman, and J. T. Ritchie, “The DSSAT cropping system model,” European Journal of Agronomy, vol. 18, no. 3–4, pp. 235–265, 2003.
  7. D. P. Holzworth, N. I. Huth, P. G. de Voil, E. J. Zurcher, N. I. Herrmann, G. McLean, K. Chenu, E. J. van Oosterom, V. Snow, C. Murphy, A. D. Moore, H. Brown, J. P. M. Whish, S. Verrall, J. Fainges, L. W. Bell, A. S. Peake, P. L. Poulton, Z. Hochman, P. J. Thorburn, D. S. Gaydon, N. P. Dalgliesh, D. Rodriguez, H. Cox, S. Chapman, A. Doherty, E. Teixeira, J. Sharp, R. Cichota, I. Vogeler, F. Y. Li, E. Wang, G. L. Hammer, M. J. Robertson, J. P. Dimes, A. M. Whitbread, J. Hunt, H. van Rees, T. McClelland, P. S. Carberry, J. N. G. Hargreaves, N. MacLeod, C. McDonald, J. Harsdorf, S. Wedgwood, and B. A. Keating, “APSIM – evolution towards a new generation of agricultural systems simulation,” Environmental Modelling & Software, vol. 62, pp. 327–350, 2014.
  8. A. de Wit, H. Boogaard, D. Fumagalli, S. Janssen, R. Knapen, D. van Kraalingen, I. Supit, R. van der Wijngaart, and K. van Diepen, “25 years of the WOFOST cropping systems model,” Agricultural Systems, vol. 168, pp. 154–167, 2019.
  9. D. Romero, “DSSATTools: A Python library for DSSAT crop model simulation,” 2023, python Package Index. [Online]. Available: https://pypi.org/project/DSSATTools/
  10. M. R. Anwar, D. L. Liu, R. Farquharson, I. Macadam, A. Abadi, J. Finlayson, B. Wang, and T. Ramilan, “Climate change impacts on phenology and yields of five broadacre crops at four climatologically distinct farm locations in Australia,” Agricultural Systems, vol. 132, pp. 133–144, 2015.
  11. E. A. Mitscherlich, “Das gesetz des minimums und das gesetz des abnehmenden bodenertrages,” Landwirtschaftliche Jahrb"ucher, vol. 38, pp. 537–552, 1909.
  12. J. H. Friedman, “Greedy function approximation: A gradient boosting machine,” The Annals of Statistics, vol. 29, no. 5, pp. 1189–1232, 2001.
  13. M. D. McKay, R. J. Beckman, and W. J. Conover, “A comparison of three methods for selecting values of input variables in the analysis of output from a computer code,” Technometrics, vol. 21, no. 2, pp. 239– 245, 1979.
  14. Gurobi Optimization, LLC, Gurobi Optimizer Reference Manual, 2026. [Online]. Available: https://www.gurobi.com
  15. Council of the European Union, “Council directive 91/676/EEC concerning the protection of waters against pollution caused by nitrates from agricultural sources,” 1991, official Journal L 375, 31/12/1991, pp. 1–8.
  16. L. Poggio, L. M. de Sousa, N. H. Batjes, G. B. M. Heuvelink, B. Kempen, E. Ribeiro, and D. Rossiter, “SoilGrids 2.0: Producing soil information for the globe with quantified spatial uncertainty,” SOIL, vol. 7, no. 1, pp. 217–240, 2021.
  17. K. E. Saxton and W. J. Rawls, “Soil water characteristic estimates by texture and organic matter for hydrologic solutions,” Soil Science Society of America Journal, vol. 70, no. 5, pp. 1569–1578, 2006.
  18. Open-Meteo, “Open-meteo historical weather API,” 2026, accessed: 2026. [Online]. Available: https://open-meteo.com/en/docs/ historical-weather-api
  19. G. A. F. Seber and A. J. Lee, Linear Regression Analysis, 2nd ed. Hoboken, NJ: Wiley, 2003.
  20. IndexBox, “Urea price in germany - 2025,” 2026, reports a German average urea FOB export price of 572 USD/t in May 2025; accessed: 2026. [Online]. Available: https://www.indexbox.io/search/ urea-price-germany/
  21. Praxis-Agrar and de Witte, Thomas, “Wirtschaftlichkeit der feldbewaesserung,” 2026, summarises German field-irrigation economics, including 0.4 kWh/m3 for mobile irrigation systems and full costs of 3.17-4.00 EUR per mm and hectare; accessed: 2026. [Online]. Available: https://www.praxis-agrar.de/pflanze/bewaesserung/ wirtschaftlichkeit-der-feldbewaesserung/
  22. BDEW, “Bdew-strompreisanalyse januar 2026,” 2026, reports a 2025 electricity price of 15.8 ct/kWh for medium-sized industry customers in Germany; accessed: 2026. [Online]. Available: https: //www.bdew.de/service/daten-und-grafiken/bdew-strompreisanalyse/
  23. X. Huang, D. Kroening, W. Ruan, J. Sharp, Y. Sun, E. Thamo, M. Wu, and X. Yi, “A survey of safety and trustworthiness of deep neural networks: Verification, testing, adversarial attack and defence, and interpretability,” Computer Science Review, vol. 37, p. 100270, 2020. [Online]. Available: https://www.sciencedirect.com/science/article/pii/ S1574013719302527
  24. R. F. Woolson, “Wilcoxon signed-rank test,” in Wiley Encyclopedia of Clinical Trials, 2008, pp. 1–3. [Online]. Available: https: //onlinelibrary.wiley.com/doi/abs/10.1002/9780471462422.eoct979
  25. W. Tan, K. Li, D. Liu, and W. Xing, “Cercospora leaf spot disease of sugar beet,” Plant Signaling & Behavior, vol. 18, no. 1, p. 2214765, 2023, pMID: 37209061.
  26. E. Memic, S. Graeff-Hönninger, O. Hensel, and W. D. Batchelor, “Extending the csm-ceres-beet model to simulate impact of observed leaf disease damage on sugar beet yield,” Agronomy, vol. 10, no. 12, pp. 1–20, 2020.
  27. V. Misra, S. Srivastava, A. K. Mall, and S. Srivastava, Foliar Sugar Beet Diseases and Their Management Approaches in India. Singapore: Springer Nature Singapore, 2022, pp. 541–564. [Online]. Available: https://doi.org/10.1007/978-981-19-2730-0_26
  28. S. Vakhtang, J. Hansen, V. Sharda, C. Porter, P. Aggarwal, C. J. Wilkerson, and G. Hoogenboom, “A multi-scale and multi-model gridded framework for forecasting crop production, risk analysis, and climate change impact studies,” Environmental Modelling and Software, vol. 115, pp. 144–154, 2019.