Irrigation and Water Engineering

Irrigation and Water Engineering

Monitoring nitrogen and leaf sheath moisture in sugarcane fields using satellite images and artificial intelligence (Case study: Amir Kabir Agro Industrial)

Document Type : Original Article

Authors
Elahe Zoratipour 1
aryan heidari 1
Amir Soltani Mohammadi 2
1 Phd Student of Irrigation and drainage, Shahid Chamran University of Ahvaz, Ahvaz, Iran .
2 Professor, Irrigation and Drainage Department, Shahid Chamran University of Ahvaz, Ahvaz, Iran
10.22125/iwe.2024.482662.1835
Abstract
The purpose of this research is to evaluate the amount of nitrogen and leaf sheath moisture using remote sensing and artificial intelligence models. For this purpose, three models of Support Vector Machine , Random Forest (RF) and Artificial Neural Network were used, It should be noted that the sensitivity analysis of all input parameters to simulate nitrogen and leaf sheath moisture values was done before running the model using Pearson correlation and only those factors that were more important on nitrogen or leaf sheath moisture were considered. Single bands B2, B3, B4, B5, B6, B7, B11, B12 and NDVI vegetation index and in the simulation of leaf sheath moisture in bands B2, B3, B4, B5, B6, B7, B11, B12 and vegetation indices NDVI, NDMI and LAI are more important and were considered as inputs to the models. Also, among the models, the random forest (RF) model in nitrogen simulation with R2 equal to 0.88 and RMSE equal to 0.06 in the training phase and R2 equal to 0.93 and RMSE equal to 0.05 in the validation phase had the best performance. In addition, leaf sheath moisture with R2 equal to 0.88 and RMSE equal to 0.71 in the training phase and R2 equal to 0.92 and RMSE equal to 0.59 had a better performance in simulation. The results showed that the combined use of vegetation index, sentinel 2 satellite bands and artificial intelligence models gives an acceptable estimate of the amount of nitrogen and leaf sheath moisture in sugarcane fields.
Keywords
Remote Sensing
Sentinel 2
Vegetation index
Crop Monitoring
Subjects
بهروان، ح. ر. 1386. نقش درصد رطوبت غلاف برگ نیشکر در توصیه‎های کودی با سیستم کراپ‎لاگ(Croplogging). مجموعه مقالات دهمین کنگره علوم خاک ایران.
بهی فر، الف.، م. حدادی و ف. متکان. 1398. ارزیابی اثر اشباع شاخص های گیاهی در محاسبه شاخص سطح برگ محصولات زراعی. نشریه سنجش از دور و GIS ایران، 11(1)، 33-48.
حیدری مطلق, آ, نصرالهی, ع, ویسی, ش و شریفی پور, م. 1401. تاثیر به‌کارگیری الگوریتم‌های مختلف دمای سطح زمین در برآورد مقادیر تبخیر-تعرق واقعی. تحقیقات آب و خاک ایران، 53 (12)، 2720-2701.
سلطانی کاظمی، م.، س. مینایی، ح. شفیع زاده مقدم و ع.ر. مهدویان. 1403. مقایسة چهار الگوریتم PLSR، RF، GRNN و SVR به‌منظور برآورد رطوبت غلاف نیشکر در طول دورة رشد با استفاده از تصاویر ماهوارة سنتینل-2. نشریه سنجش از دور و GIS ایران, 16(3)، 47-68.
عباسی، ف. و شینی‎دشتگل، ع. 1395. توصیه‎هایی برای مصرف بهینه کود در مزارع نیشکر. نشر آموزش کشاورزی، چاپ اول.
ویسی، ش.، ع.ع. ناصری و س. حمزه. 1397. رابطه بین رطوبت غلاف برگ گیاه نیشکر و شاخص تنش آبی با استفاده از دماسنج مادون قرمز. علوم و مهندسی آبیاری، 40(4)، 77-90.‎
 
Allen, R.G., M. Tasumi, R. Trezza, R.Waters and W.G.M. Bastiaanssen. 2002. Surface Energy Balance Algorithms for Land, Advance Training and Users Manual–Idaho Implementation. version 1, 97 p.
Asrar, G.Q., M. Fuchs, E.T. Kanemasu, and J.L. Hatfield. 1984, Estimating Absorbed Photosynthetic Radiation and Leaf Area Index from Spectral Reflectance in Wheat 1. Agronomy journal, 76(2), 300-306.
Baret, F., V. Houlès, M. Guérif. 2007. Quantification of plant stress using remotesensing observations and crop models: the case of nitrogen management. J.Exp. Bot. 58, 869–880.
Ballester, C., J. Brinkhoff, W.C. Quayle and J. Hornbuckle. 2019. Monitoring the Effects of Water Stress in Cotton Using the Green Red Vegetation Index and Red Edge Ratio.Remote Sensing. 11: 7. 873: 1-21
Bernardino, P. N., R. S. Oliveira, K. Van Meerbeek, M. Hirota, M. N. Furtado, I. A. Sanches. and B. Somers. 2024. Estimating vegetation water content from Sentinel-1 C-band SAR data over savanna and grassland ecosystems. Environmental Research Letters, 19(3), 034019.
Bo, W., B. Fu, G. Qin, G. Xing. and Y. Wang 2017. Evaluation of drought resistance in Iris germanica L. based on subordination function and principal component analysis. Emirates Journal of Food and Agriculture (EJFA), 29(10).
Breiman, L. 1996. Bagging predictors. Mach Learn. 26,123–140.
Choat, B., T.J. Brodribb, C.R. Brodersen, R.A. R. Duursma, López and B.E. Medlyn. 2018 Triggers of tree mortality under drought. Nature, 558 531–9.
Chandrasekar, K., P. Srikanth, A. Chakraborty, K. Choudhary and K. V. Ramana. 2022. Response of crop water indices to soil wetness and vegetation water content. Advances in Space Research.
Chen, S., C. He, Z. Huang, X. Xu, T. Jiang, Z. He, ... and J. He. 2022. Using support vector machine to deal with the missing of solar radiation data in daily reference evapotranspiration estimation in China. Agricultural and Forest Meteorology, 316, 108864.
Chen, H., J. Jeanne Huang and E. McBean. 2019. Partitioning of daily evapotranspiration using a modified shuttleworthwallace model, random Forest and support vector regression, for a cabbage farmland. Agricultural Water Management. 105923, 1-12.
Clevers, J.G and A.A.Gitelson. 2013. Remote estimation of crop and grass chlorophyll and nitrogen content using red-edge bands on Sentinel-2 and .3 -International Journal of Applied Earth Observation and Geoinformation, 23, 344-351.
Dugo, V., J.L. Durand and F. Gastal. 2010. Water deficit and nitrogen nutrition of crops. A review. Agronomy for Sustainable Development. 30, 529-544.
Feldman, A. F. 2024. Emerging methods to validate remotely sensed vegetation water content. Geophysical Research Letters, 51(14), e2024GL110505.
Hurcom, S. J and A. R. Harrison. 1998. The NDVشکلI and spectral decomposition for semi-arid vegetation abundance estimation. International Journal of Remote Sensing, 19(16), 3109 -3125.
Jung, J., M. Maeda, A. Chang, M. Bhandari, A. Ashapure and J. Landivar-Bowles. 2021. The potential of remote sensing and artificial intelligence as tools to improve the resilience of agriculture production systems. Current Opinion in Biotechnology, 70, 15-22.
Katimbo, A., D. R. Rudnick, J. Zhang, Y. Ge, K. C. DeJonge, T. E. Franz ... and J. Duan. 2023. Evaluation of artificial intelligence algorithms with sensor data assimilation in estimating crop evapotranspiration and crop water stress index for irrigation water management. Smart Agricultural Technology, 4, 100176.
Konings, A.G. 2021. Detecting forest response to droughts with global observations of vegetation water content Glob. Change Biol. 27 6005–24.
Liu, L. Y. Li and T. Wu. 2021. Monitoring of Leaf Nitrogen Content in A Citrus Orchard by Landsat 8 OLI Imagery. Twelfth International Conference on Signal Processing Systems. 11719(1171905).
Miphokasap, P., K. Honda, C. Vaiphasa, M. Souris and M. Nagai. 2012. Estimating canopy nitrogen concentration in sugarcane using field imaging spectroscopy. Remote Sensing, 4(6), 1651-1670.
Reuben Mwinuka, P., B. Mbilinyi, W. Mbungu, S. Mourice, H.F. Mahoo and P. Schmitter. 2021. The feasibility of hand-held thermal and UAV-based multispectral imaging for canopy water status assessment and yield prediction of irrigated African eggplant (Solanum aethopicum L). Agricultural Water Management. 245(106584): 1-11.
Running, S. W., R. R. Nemani, F. A. Heinsch, M. Zhao, M. Reeves and H. Hashimoto. 2004. A continuous satellite‐derived measure of global terrestrial primary production. BioScience, 54(6), 547–560.
Sheng Chou, J., C. Kuo Chiu, M. Farfoura and I. Al-Taharwa. 2011. Optimizing the Prediction Accuracy of Concrete Compressive Strength Based on a Comparison of Data-Mining Techniques. Journal of Computing in Civil Engineering. 25,242-253.
Tucker, C. J. 1979. Red and photographic infrared linear combinations for monitoring vegetation. Remote Sensing of Environment, 8(2), 127–150.
Vapnik, V.N. 1996. The nature of statistical learning theory. Technometrics 38 (4), 409.
Veysi, S., A. A. Naseri, S. Hamzeh and H. Bartholomeus. 2017. A satellite based crop water stress index for irrigation scheduling in sugarcane fields. Agricultural water management, 189, 70-86.
Virnodkar, S., V. K. Pachghare,  V. C. Patil and S. K. Jha. 2021. Performance evaluation of RF and SVM for sugarcane classification using sentinel-2 NDVI time-series. In Progress in Advanced Computing and Intelligent Engineering: Proceedings of ICACIE 2019, Volume 2 (pp. 163-174). Springer Singapore.
Viña, A., A.A. Gitelson, A.L. Nguy-Robertson, Y. Peng. 2011. Comparison of different vegetation indices for the remote assessment of green leaf area index of crops. Remote Sensing of Environment, 115(12), 3468-3478.
Wang, L., J.J. Qu, X. Hao and E.R. Hunt. 2011. Estimating dry matter content from spectral reflectance for green leaves of different species. International Journal of Remote Sensing. 32, 7097–7109.
Wu, W., M. FenLi, X. Xu, X. PingTang, C. Yang and H. Bin Liu. 2021. The transferability of random forest and support vector machine for estimating daily global solar radiation using sunshine duration over different climate zones. Theoretical and Applied Climatology. 1-11.
Zahedyan, A., A. Aboutalebi Jahromi, A. Zakerin, V. Abdossi and A. Mohammadi Torkashv. 2021. Nitroxin bio-fertilizer improves growth parameters, physiological and biochemical attributes of cantaloupe (Cucumis melo L.) under water stress conditions. Journal of the Saudi Society of Agricultural Sciences. 1-13.
Zhen-wen, Z and Q. Yao. 2005. Application of the principle component analysis on mango storage characteristic. Subtropical Plant Science, 34(02), 25.
Zhou, Z., Y. Majeed, G. Diverres Naranjo and E. Gambacorta. 2021. Assessment for crop water stress with infrared thermal imagery in precision agriculture: A review and future prospects for deep learning applications. Computers and Electronics in Agriculture. 182(106019): 1-10.