Optimizing Variable-Rate Linear Move Irrigation Systems Using Edge-AI and Hydrological Modeling: A Case Study of the Danube-Tisa-Danube Canal Basin in Vojvodina

Yazarlar

Anahtar Kelimeler:

variable rate irrigation- edge ai- Precision Agriculture

Öz

Vojvodina, Serbia's principal agricultural region, faces escalating irrigation demand driven by climate change-induced summer droughts. The 929 km Danube-Tisa-Danube (DTD) canal network, supplying up to 510,000 ha of arable land, is under pressure to improve water allocation precision. This paper evaluates an integrated optimization framework for variable-rate irrigation (VRI) linear move systems supplied by the DTD network, combining three components: (i)A SWAT+ hydrological model of the DTD basin calibrated on 2011–2022 discharge and water-level records. (ii) A field-scale, LSTM-based soil moisture and reference evapotranspiration ($ET_0$) prediction module driven by IoT sensors and near-real-time weather data. (iii)An Edge-AI prescription engine deployed on an NVIDIA Jetson Nano unit mounted on the irrigation machine. In validation, the SWAT+ model achieved a Nash-Sutcliffe Efficiency (NSE) of 0.81 and $R^2$ of 0.87. The LSTM module predicted 48-hour soil moisture with an RMSE of 0.028 $m^3/m^3$. Field trials on maize (Zea mays L.) and sunflower (Helianthus annuus L.) across four sites in Bačka demonstrated a 22.4% reduction in seasonal water application compared to uniform-rate management. Meanwhile, grain yields improved (maize +3.1%, sunflower +1.8%), confirming the operational viability of data-driven VRI optimization.

Referanslar

[1] Danube–Tisa–Danube Hydrosystem (Hs DTD), SUNDANSE Project Serbia Site Description, Vode Vojvodine Public Water Management Company, Novi Sad, Serbia, 2022. [Online]. Available: https://sundanseproject.eu/serbia

[2] G. Mimic, B. Zivaljevic, D. Blagojevic, B. Pejak, and S. Brdar, "Quantifying the effects of drought using the crop moisture stress as an indicator of maize and sunflower yield reduction in Serbia," Atmosphere, vol. 13, no. 11, pp. 1880, Nov. 2022.

[3] Z. M. Alomari and T. J. Alfatlawi, "Performance assessment of variable (VRI) versus constant rate irrigation (CRI): Review," Int. J. Des. Nat. Ecodyn., vol. 19, no. 2, pp. 1–12, 2024.

[4] E. A. Abioye, O. Hensel, T. J. Esau, O. Elijah, M. S. Z. Abidin, A. S. Ayobami, O. Yerima, and A. Nasirahmadi, "Precision irrigation management using machine learning and digital farming solutions," AgriEngineering, vol. 4, no. 1, pp. 70–103, Feb. 2022.

[5] A. Nguyen, A. L. Thompson, K. A. Sudduth, and E. D. Vories, "Automatic management zone delineation for center pivot variable rate irrigation using field data," J. ASABE, vol. 66, no. 6, pp. 1527–1545, Dec. 2023.

[6] Z. M. Alomari and T. J. Alfatlawi, "Performance assessment of variable (VRI) versus constant rate irrigation (CRI): Review," Int. J. Des. Nat. Ecodyn., vol. 19, no. 2, pp. 1–12, 2024.

[7] R. G. Evans, J. LaRue, K. C. Stone, and B. A. King, "Adoption of site-specific variable rate sprinkler irrigation systems," Irrig. Sci., vol. 31, no. 4, pp. 871–887, 2012.

[8] J. Serrano, S. Shahidian, J. Marques da Silva, L. Paixão, F. Moral, R. Carmona-Cabezas, S. Garcia, J. Palha, and J. Noéme, "Mapping management zones based on soil apparent electrical conductivity and remote sensing for implementation of variable rate irrigation—case study of corn under a center pivot," Water, vol. 12, no. 12, pp. 3427, Dec. 2020.

[9] E. Bwambale, F. K. Abagale, and G. K. Anornou, "Data-driven modelling of soil moisture dynamics for smart irrigation scheduling," Smart Agric. Technol., vol. 5, pp. 100251, Aug. 2023.

[10] R. Togneri, D. dos Santos Gonçalves, G. Camargo Junior, C. A. Kamienski, D. Soininen, P. Alencar, J. R. de Aquino, and C. Braga, "Soil moisture forecast for smart irrigation: The primacy of sensitivity analysis and smart pooling of training data," Expert Syst. Appl., vol. 207, pp. 117653, Nov. 2022.

[11] E. A. Abioye, M. S. Z. Abidin, M. S. A. Mahmud, S. Buyamin, M. H. I. Ishak, M. K. I. A. Rahman, A. O. Otuoze, P. Onotu, and M. S. A. Ramli, "A review on monitoring and advanced control strategies for precision irrigation," Comput. Electron. Agric., vol. 173, pp. 105441, Jun. 2020.

[12] M. S. Hossain, "Advanced machine learning techniques for irrigation optimisation in canal systems," Water Resour. Manag., vol. 37, pp. 3241–3258, 2023.

[13] K. Bieger, J. G. Arnold, H. Rathjens, M. J. White, D. D. Bosch, P. M. Allen, M. Volk, and R. Srinivasan, "Introduction to SWAT+, a completely restructured version of the Soil and Water Assessment Tool," J. Am. Water Resour. Assoc., vol. 53, no. 1, pp. 115–130, Feb. 2017.

[14] International Commission for the Protection of the Danube River (ICPDR), Danube River Basin Management Plan 2021 Update. Vienna, Austria: ICPDR, 2021.

[15] J. G. Arnold, D. N. Moriasi, P. W. Gassman, K. C. Abbaspour, M. J. White, R. Srinivasan, C. Santhi, R. D. Harmel, A. van Griensven, M. W. Van Liew, N. Kannan, and M. K. Jha, "SWAT: Model use, calibration, and validation," Trans. ASABE, vol. 55, no. 4, pp. 1491–1508, 2012.

[16] O. Debauche, S. Mahmoudi, P. Manneback, and F. Lebeau, "Edge AI-IoT pivot irrigation, plant diseases, and pests identification," Procedia Comput. Sci., vol. 177, pp. 40–48, 2020.

[17] European Parliament and Council, Directive 2000/60/EC of the European Parliament and of the Council establishing a framework for Community action in the field of water policy, Official Journal of the European Communities, Luxembourg, 2000.

Yayınlanmış

2024-12-01

Sayı

Bölüm

Araştırma Makalesi

Nasıl Atıf Yapılır

Optimizing Variable-Rate Linear Move Irrigation Systems Using Edge-AI and Hydrological Modeling: A Case Study of the Danube-Tisa-Danube Canal Basin in Vojvodina. (2024). Aintelia Science Notes, 3(2), 26-33. https://journal.bauderpress.org.tr/index.php/asnj/article/view/80