Journal of Biosystems Engineering

Korean Society for Agricultural Machinery (한국농업기계학회)
권호 표지
DOI QR코드

DOI QR Code

Integrating UAV Remote Sensing with GIS for Predicting Rice Grain Protein

  • Sarkar, Tapash Kumar (Department of Bio-Systems Engineering, College of Agricultural and Life Science, Gyeongsang National University) ;
  • Ryu, Chan-Seok (Department of Bio-Systems Engineering, College of Agricultural and Life Science, Gyeongsang National University) ;
  • Kang, Ye-Seong (Department of Bio-Systems Engineering, College of Agricultural and Life Science, Gyeongsang National University) ;
  • Kim, Seong-Heon (Department of Bio-Systems Engineering, College of Agricultural and Life Science, Gyeongsang National University) ;
  • Jeon, Sae-Rom (Department of Bio-Systems Engineering, College of Agricultural and Life Science, Gyeongsang National University) ;
  • Jang, Si-Hyeong (Department of Bio-Systems Engineering, College of Agricultural and Life Science, Gyeongsang National University) ;
  • Park, Jun-Woo (Department of Bio-Systems Engineering, College of Agricultural and Life Science, Gyeongsang National University) ;
  • Kim, Suk-Gu (Geomatics Total Service) ;
  • Kim, Hyun-Jin (Geomatics Total Service)
  • Received : 2018.03.21
  • Accepted : 2018.05.31
  • Published : 2018.06.01
Download PDF
⟨ Previous Next ⟩

Abstract

Purpose: Unmanned air vehicle (UAV) remote sensing was applied to test various vegetation indices and make prediction models of protein content of rice for monitoring grain quality and proper management practice. Methods: Image acquisition was carried out by using NIR (Green, Red, NIR), RGB and RE (Blue, Green, Red-edge) camera mounted on UAV. Sampling was done synchronously at the geo-referenced points and GPS locations were recorded. Paddy samples were air-dried to 15% moisture content, and then dehulled and milled to 92% milling yield and measured the protein content by near-infrared spectroscopy. Results: Artificial neural network showed the better performance with $R^2$ (coefficient of determination) of 0.740, NSE (Nash-Sutcliffe model efficiency coefficient) of 0.733 and RMSE (root mean square error) of 0.187% considering all 54 samples than the models developed by PR (polynomial regression), SLR (simple linear regression), and PLSR (partial least square regression). PLSR calibration models showed almost similar result with PR as 0.663 ($R^2$) and 0.169% (RMSE) for cloud-free samples and 0.491 ($R^2$) and 0.217% (RMSE) for cloud-shadowed samples. However, the validation models performed poorly. This study revealed that there is a highly significant correlation between NDVI (normalized difference vegetation index) and protein content in rice. For the cloud-free samples, the SLR models showed $R^2=0.553$ and RMSE = 0.210%, and for cloud-shadowed samples showed 0.479 as $R^2$ and 0.225% as RMSE respectively. Conclusion: There is a significant correlation between spectral bands and grain protein content. Artificial neural networks have the strong advantages to fit the nonlinear problem when a sigmoid activation function is used in the hidden layer. Quantitatively, the neural network model obtained a higher precision result with a mean absolute relative error (MARE) of 2.18% and root mean square error (RMSE) of 0.187%.

Keywords

References

  1. Arai, K., M. Sakashita, O. Shigetomi and Y. Miura. 2014. Estimation of protein content in rice crop and nitrogen content in rice leaves through regression analysis with NDVI derived from camera mounted radiocontrol helicopter. International Journal of Advanced Research in Artificial Intelligence 3(3): 12-19. https://dx.doi.org/10.14569/IJARAI.2014.030303
  2. Blackmer, T. M., J. S. Schepers, G. E. Varvel and E. A. Walter-Shea. 1996. Nitrogen deficiency detection using shortwave radiation from irrigated corn canopies. Agronomy Journal 88(1): 1-5. https://doi.org/10.2134/agronj1996.00021962008800010001x
  3. Boken, V. K. and C. F. Shaykewich. 2002. Improving an operational wheat yield model using phenological phase-based Normalized Difference Vegetation Index. International Journal of Remote Sensing 23(20): 4155-4168. https://doi.org/10.1080/014311602320567955
  4. Bonham-Carter, G. F. 1988. Numerical procedures and computer program for fitting an inverted gaussian model to vegetation reflectance data. Computers & Geosciences ,14(3): 339-356. https://doi.org/10.1016/0098-3004(88)90065-9
  5. Chang, C. W., D. A. Laird, M. J. Mausbach and C. R. Hurburgh, Jr. 2001. Near-infrared reflectance spectroscopy-Principal components regression analyses of soil properties. Soil Science Society of America Journal 65(2): 480-490. https://doi.org/10.2136/sssaj2001.652480x
  6. Diker, K. and W. C. Bausch. 2003. Potential use of nitrogen reflectance index to estimate plant parameters and yield of maize. Biosystems Engineering 85(4): 437-447. https://doi.org/10.1016/S1537-5110(03)00097-7
  7. Downey, G., P. McIntyre and A. Davies. 2002. Detecting and quantifying sunflower oil adulteration in extra virgin olive oils from the eastern mediterranean by visible and near-infrared spectroscopy. Journal of Agricultural and Food Chemistry 50(20): 5520-5525. https://doi.org/10.1021/jf0257188
  8. Esbensen, K. H. 2002. Multivariate Data Analysis - in practice, Oslo, Norway: CAMO Software AS.
  9. Filella, I., L. Serrano, J. Serra and J. Penuelas. 1995. Evaluating wheat nitrogen status with canopy reflectance indices and discriminate analysis. Crop Science 35: 1400-1405. https://doi.org/10.2135/cropsci1995.0011183X003500050023x
  10. Gitelson, A. A. and M. N. Merzlyak. 1997. Remote estimation of chlorophyll content in higher plant leaves. International Journal of Remote Sensing 18(12): 2691-2697. https://doi.org/10.1080/014311697217558
  11. Gorr, W. L., D. Nagin and J. Szczypula. 1994. Comparative study of artificial neural network and statistical models for predicting student grade point averages. International Journal of Forecasting 10(1): 17-34. https://doi.org/10.1016/0169-2070(94)90046-9
  12. He, Y., X. L. Li and Y. N. Shao. 2006. Discrimination of varieties of apple using near infrared spectra based on principal component analysis and artificial neural network model. Spectroscopy and Spectral Analysis 26(5): 850-853. (In Chinese, with English abstract).
  13. Hinzman, L. D., M. E. Bauer and C. S. T. Daughtry. 1986. Effects of nitrogen fertilization on growth and reflectance characteristics of winter wheat. Remote Sensing of Environment 19(1): 47-61. https://doi.org/10.1016/0034-4257(86)90040-4
  14. Hoffman, K. and R. Kunze. 1971. Characteristic values. In: Linear Algebra, 2nd ed. 182-190. Englewood Cliffs, NJ, USA: Prentice-Hall Inc.
  15. Holm, A. M., D. G. Burnside and A. A. Mitchell. 1987. The development of a system for monitoring trend in range condition in the arid shrublands of Western Australia. The Australian Rangeland Journal 9(1): 14-20. https://doi.org/10.1071/RJ9870014
  16. Kaul, A.K. and P. Raghaviah. 1975. Influence of nitrogen fertilization on some nutritional quality characters in rice. Plant Foods for Human Nutrition 24(3-4): 391-403. https://doi.org/10.1007/BF01092224
  17. Kimes, D. S., R. F. Nelson, M. T. Manry and A. K. Fung. 1998. Attributes of neural networks for extracting continuous vegetation variables from optical and radar measurements. International Journal of Remote Sensing 19(14): 2639-2663. https://doi.org/10.1080/014311698214433
  18. Kleman, J. and E. Fagerlund. 1987. Influence of different nitrogen and irrigation treatments on spectral reflectance of barley. Remote Sensing of Environment 21(1): 1-14. https://doi.org/10.1016/0034-4257(87)90002-2
  19. Lewis, C. D. 1982. International and Business Forecasting Methods. A practical guide to exponential smoothing and curve fitting. London, UK: Butterworths Scientific Ltd.
  20. Mandal, D. and S. K. Ghosh. 2000. Precision farming - The emerging concept of agriculture for today and tomorrow. Current Science 79(12): 1644-1647.
  21. Marcus, M. and H. Minc. 1988. Introduction to Linear Algebra. Mineola, NY, USA: Dover Publications.
  22. Nwugo, C. C. and A. J. Huerta. 2011. The effect of silicon on the leaf proteome of rice (Oryza sativa L.) plants under cadmium-stress. Journal of Proteome Research 10(2): 518-528. https://doi.org/10.1021/pr100716h
  23. Onoyama, H., C. Ryu, M. Suguri and M. Iida. 2013. Potential of hyperspectral imaging for constructing a yearinvariant model to estimate the nitrogen content of rice plants at the panicle initiation stage. IFAC Proceedings Volumes 46(18): 219-224. https://doi.org/10.3182/20130828-2-SF-3019.00054
  24. Rannar, S., F. Lindgren, P. Geladi and S. Wold. 1994. A PLS kernel algorithm for data sets with many variables and fewer objects. Part 1: Theory and algorithm. Journal of Chemometrics 8(2): 111-125. https://doi.org/10.1002/cem.1180080204
  25. Reeves, J. B. 2001. Near-infrared diffuse reflectance spectroscopy for the analysis of poultry manures. Journal of Agricultural and Food Chemistry 49(5): 2193-2197. https://doi.org/10.1021/jf0013961
  26. Ryu, C., M. Suguri, M. Iida, M. Umeda and C. Lee. 2011. Integrating remote sensing and GIS for prediction of rice protein contents. Precision Agriculture 12(3): 378-394. https://doi.org/10.1007/s11119-010-9179-0
  27. Ryu, C., H. Onoyama, M. Suguri and Y. Kim. 2014. Estimation of the main properties in potherb mustard (Mizuna) using hyperspectral imagery. Journal of Agriculture & Life Science 48(6): 375-386 (In Korean, with English abstract). https://doi.org/10.14397/jals.2014.48.6.375
  28. Sasaki, T. and B. Burr. 2000. International rice genome sequencing project: the effort to completely sequence the rice genome. Current Opinion in Plant Biology 3(2): 138-142. https://doi.org/10.1016/S1369-5266(99)00047-3
  29. Sautter, C., S. Poletti, P. Zhang and W. Gruissem. 2006. Biofortification of essential nutritional compounds and trace elements in rice and cassava. Proceedings of the Nutrition Society 65(2): 153-159. https://doi.org/10.1079/PNS2006488
  30. Sembiring, H., W. R. Raun, G. V. Johnson, M. L. Stone, J. B. Solie and S. B. Phillips. 1998. Detection of nitrogen and phosphorus nutrient status in winter wheat using spectral radiance. Journal of Plant Nutrition 21(6): 1207-1233. https://doi.org/10.1080/01904169809365478
  31. Tenenhaus, M., V. E. Vinzi, Y. M. Chatelin and C. Lauro. 2005. PLS path modeling. Computational Statistics and Data Analysis 48(1): 159-205. https://doi.org/10.1016/j.csda.2004.03.005
  32. The Unscrambler. 2004. Ver. 9.1, Oslo, Norway: CAMO Software AS.
  33. Thomas, J. R. and G. F. Oerther. 1972. Estimating nitrogen content of sweet pepper leaves by reflectance measure ments. Agronomy Journal 64(1): 11-13. https://doi.org/10.2134/agronj1972.00021962006400010004x
  34. Veerasamy, R., H. Rajak, A. Jain, S. Sivadasan1, C. P. Varghese and R. K. Agrawal. 2011. Validation of QSAR models - strategies and importance. International Journal of Drug Design and Discovery 2(3): 511-519.
  35. Vogelmann, T. C. 1993. Plant tissue optics. Annual Review of Plant Physiology and Plant Molecular Biology 44: 231-251. https://doi.org/10.1146/annurev.pp.44.060193.001311
  36. Wang, Y., S. G. Kim., S. T. Kim, G. K. Agrawal, R. Rakwal and K. Y. Kang. 2011. Biotic stress-responsive rice proteome: An overview. Journal of Plant Biology 54: 219-226. https://doi.org/10.1007/s12374-011-9165-8
  37. Yi, Q. X., J. F. Huang, F. M. Wang, X. Z. Wang and Z. Y. Liu. 2007. Monitoring rice nitrogen status using hyperspectral reflectance and artificial neural network. Environmental Science and Technology 41(19): 6770-6775. https://doi.org/10.1021/es070144e
  38. Yi, S. L., L. Deng, S. L. He, Y. Q. Zheng and S. S. Mao. 2010. A spectrum based models for monitoring leaf potassium content of citrus sinensis (L.) cv. Jincheng orange. Scientia Agricultura Sinica 43(4): 780-786. (In Chinese, with English abstract). https://doi.org/10.3864/j.issn.0578-1752.2010.04.015
  39. Zhang, H., H. Hu, X. B. Zhang, L. F. Zhu, K. F. Zheng, Q. Y. Jin and F. P. Zeng. 2011. Estimation of rice neck blasts severity using spectral reflectance based on BP-neural network. Acta Physiologiae Plantarum 33(6): 2461-2466. https://doi.org/10.1007/s11738-011-0790-0
  40. Zhang, H., T. Q. Song, K. L. Wang, G. X. Wang, H. Hu and F. P. Zeng. 2012. Prediction of crude protein content in rice grain with canopy spectral reflectance. Plant, Soil and Environment 58(11): 514-520. https://doi.org/10.17221/526/2012-PSE