Evaluation of Several Spectral Indices for Estimation of Canola Yield using Sentinel-2 Sensor Images

Document Type : Research Article

Authors

• N. Loveimi ¹
• A. Akram ¹
• N. Bagheri ²
• A. Hajiahmad ¹

¹ Department of Agricultural Machinery Engineering, Faculty of Agricultural Engineering and Technology, College of Agriculture & Natural Resources, University of Tehran, Karaj, Iran

² Agricultural Engineering Research Institute, Agricultural Research, Education and Extension Organization (AREEO), Karaj, Iran

https://doi.org/10.22067/jam.v11i2.80232

Abstract

Introduction
Remote sensing and using satellite images have been widely considered due to the high speed of measurement and great area of coverage. Canola is a source of edible oil and its cultivation in Iran and the world is developing. Comparing with other crops, canola, because of its yellow flowers, has a different canopy color, and only a few researches have been carried out in order to assess the spectral indices for prediction of its yield. Therefore, the main objective of this research is to evaluate some spectral vegetation indices to estimate the yield of canola in different growth stages.
Materials and Methods
The study was performed in 2016-2017 in Karaj, Iran. Three canola farms were chosen for the evaluation of the relationship between yield and some vegetation indices derived from the Sentinel-2 sensor. The sensor data were processed in five stages: before flowering, early flowering, peak of flowering, green and dry maturity, and the vegetation indices were extracted for each of them. This research was pixel-based and the pixels network of each studied farm was determined by RTKGPS. During harvesting time, for measurement of grain yield, five samples, four from the corners and one from the center of the pixel, were taken and their average was considered as the representative amount of the pixel. Totally, 112 pixels from three studied farms were used to calibrate the predictive models. By using Simple Linear Regression (SLR) models, ten new and conventional vegetation indices were assessed. Also, Multivariate Linear Regression (MLR) models and Artificial Neural Net (ANN) models with four bands, three visible bands and NIR band, as inputs, were used to predict the canola yield. In order to validate the SLR and MLR models, the "K-Fold" method of cross-validation was used, and for the validation of ANN models, 15% of data were used; 70% for the train, 15% for validation, and 15% for the test.
Results and Discussion
The results showed that, on the basis of SLR models, among the growth stages, the highest coefficient of determination (R2) in each of the vegetation indices belonged to one of the two stages: the peak of flowering and green maturity. According to SLR models, among the vegetation indices in different stages, the NDYI in the peak of the flowering stage had the highest correlation with yield (R² = 73%). Also, the RVI with 29%, BNDVI with 52%, NDVI with 56%, and GNDVI with 35% had the highest R2 in the before flowering, early flowering, peak of flowering, green and dry maturity stages, respectively. MLR models resulted to the best yield predictive model at the peak of flowering stage (R² = 76% for the calibration and R² = 73% and RMSE = 0.641 for the validation). For ANN models, the strongest model achieved at peak of flowering stage (R² = 92% for the calibration (train) and R² = 77% and RMSE = 0.612 for the validation (test)). It seems that the results are affected by yellow flowers of canola, and absorption of blue light by their petals. Therefore, in the peak of the flowering stage, the reflection of the blue light is more likely to belong to green leaves and stems. Therefore, any index such as NDYI, which the blue reflection is subtracted in its equation, represents better the number of flowers, and since the density of flowers is directly related to the yield, the yield will be predicted with more precision.
 Conclusion
The results of the analysis of the indices by SLR models showed that the correlation of each of the vegetation indices with the canola yield, in different stages of growth, has a considerable difference. Based on this model, the highest R² in each of these indices happened in the peak of flowering or green maturity stage, and among these indices in different stages, the NDYI in the peak of the flowering stage had the highest R². Finally, in both of the MLR and ANN models, with four bands, three visible bands and near-infrared band, as inputs, the best yield predictive model resulted in the peak of the flowering stage.

Keywords

• Normalized Difference Yellowness Index (NDYI)
• Remote sensing
• Sentinel-2 sensor
• Vegetation Index
• Yield prediction

20.1001.1.22286829.1400.11.2.24.9

Open Access

©2021 The author(s). This article is licensed under Creative Commons Attribution 4.0 International License (CC BY 4.0), which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source.

References

1. Ahamed, T., L. Tian, Y. Zhang, and K. C. Ting. 2011. A review of remote sensing methods for biomass feedstock production. Biomass and Bioenergy 35: 2455-2469.

2. Alavipanah, S. K. 2016. Fundamentals of modern remote sensing and interpretation of Satellite images and aerial photos. University of Tehran. Tehran. (In Farsi).

3. Alizadeh Rabie, H. 2014. Remote Sensing (Principles and Application). Samt Press. Tehran.

4. Aparicio, N., D. Villegas, J. Casadesus, J. L. Araus, and C. Royo. 2000. Spectral vegetation indices as nondestructive tools for determining durum wheat yield. Agronomy Journal 92 (1): 83-91.

5. Ash, M. 2017. Canola Production and Processing. Available at: https://www.ers.usda.gov/topics/crops/soybeans-oil-crops/canola.aspx. Accessed 27 March 2018.

6. Basnyat, P., B. McConkey, G. P. Lafond, A. Moulin, and Y. Pelcat. 2004. Optimal time for remote sensing to relate to crop grain yield on the Canadian prairies. Canadian Journal of Plant Science 84 (1): 97-103.

7. Birth, G. S., and G. R. McVey. 1968. Measuring color of growing turf with a reflectance spectrophotometer. Agronomy Journal 60: 640-649.

8. Boschetti, M., S. Bocchi, and P. A. Brivio. 2007. Assessment of pasture production in the Italian Alps using spectrometric and remote sensing information. Agriculture, Ecosystems & Environment 118: 267-272.

9. Buschmann, C., and E. Nagel. 1993. In vivo spectroscopy and internal optics of leaves as basis for remote sensing of vegetation. International Journal of Remote Sensing 14: 711-722.

10. Clevers, J. G. P. W., G. W. A. M. Van Der Heijden, S. Verzakov, and M. E. Schaepman. 2007. Estimating grassland biomass using SVM band shaving of hyperspectral data. Data Photogrammetric Engineering & Remote Sensing 73 (10): 1141-1148.

11. Cowley, R. B., D. J. Luckett, J. S. Moroni, and S. Diffey. 2014. Use of remote sensing to determine the relationship of early vigour to grain yield in canola (Brassica napus L.) germplasm. Crop & Pasture Science 65: 1288-1299.

12. Dominguez, J. A., J. Kumhalova, and P. Novak. 2017. Assessment of the relationship between spectral indices from satellite remote sensing and winter oilseed rape yield. Agronomy Research 15 (1): 055-068.

13. Gallego, J., E. Carfagna, and B. Baruth. 2010. Accuracy, objectivity and efficiency of remote sensing for agricultural statistics. PP 193-211 in R. Benedetti., M. Bee., G. Espa and F. Piersimoni eds. Agricultural Survey Methods. John Wiley & Sons Inc., New York.

14. Gitelson, A. A., Y. J. Kaufman, R. Stark, and D. Rundquist. 2002. Novel algorithms for remote estimation of vegetative fraction. Remote Sensing of Environment 80: 76-87.

15. Goel, P. K., S. O. Prasher, J. A. Landry, R. M. Patel, A. A. Viau, and J. R. Miller. 2003. Estimation of crop biophysical parameters through airborne and field hyperspectral remote sensing. Transactions of the ASAE 46 (4): 1235-1246.

16. Haboudane, D., J. R. Miller, E. Pattey, P. J. Zarco Tejada, and I. B. Strachan. 2004. Hyperspectral vegetation indices and novel algorithms for predicting green LAI of crop canopies: Modeling and validation in the context of precision agriculture. Remote Sensing of Environment 90: 337-352.

17. Huete, A. R., C. Justice, and W. Van Leeuwen. 1996. MODIS vegetation index (mod13). Algorithm theoretical basis document. Version 2. NASA Goddard Space Flight Center. Washington D. C.

18. Jago, R. A., M. E. J. Cutler, and P. J. Curran. 1999. Estimating canopy chlorophyll concentration from field and airborne spectra. Remote Sensing of Environment 68 (3): 217-224.

19. Jiang, Z., A. R. Huete, K. Didan, and T. Miura. 2008. Development of a two-band enhanced vegetation index without a blue band. Remote Sensing of Environment 112: 3833-3845.

20. Jin, X., L. Kumar, Z. Li, X. Xu, G. Yang, and J. Wang. 2016. Estimation of winter wheat biomass and yield by combining the aquacrop model and field hyperspectral data. Remote Sensing 8. Available at: http://https://doi.org/10.3390/rs8120972. Accessed 4 March 2019.

21. Johnson, D. M. 2016. A comprehensive assessment of the correlations between field crop yields and commonly used MODIS products. International Journal of Applied Earth Observation and Geo information 52: 65-81.

22. Johnson, L., F. Roczen, D. Youkhana, R. Nemani, and D. Bosch. 2003. Mapping vineyard leaf area with multispectral satellite imagery. Computers and Electronics in Agriculture 38: 33-44.

23. Kaab, A., M. Sharifi, H. Mobli, A. Nabavi-Pelesaraei, and K. Chau. 2019. Combined life cycle assessment and artificial intelligence for prediction of output energy and environmental impacts of sugarcane production. Science of the Total Environment 664: 1005-1019.

24. Kazem, M., S. Mirzaei, and B. Maadi. 2016. Canola cultivation. Taak Press. Tehran. (In Farsi).

25. Khalili, S. M., A. Rezaee, and A. Haji Ahmad. 2016. Ripe detection and estimation of rapeseed crop yield based on remote sensing image processing. Thesis of Master of Science. University of Tehran. (In Farsi).

26. Languille, F., A. Gaudel1, B. Vidal, R. Binet, V. Poulain, and T. Tremas, 2017. Sentinel-2B Image Quality commissioning phase results and Sentinel2 constellation performances. Conference on Sensors, Systems, and Next-Generation Satellites XXI Location: Warsaw, POLAND Date: SEP 11-14, 2017.

27. Lee, K. S., W. B. Cohen, R. E. Kennedy, T. K. Maiersperger, and S. T. Gower. 2004. Hyperspectral versus multispectral data for estimating leaf area index in four different biomes. Remote Sensing of Environment 91: 508-520.

28. Li, A., S. Liang, A. Wang, and J. Qin. 2007. Estimating Crop Yield from Multi-temporal Satellite Data Using Multivariate Regression and Neural Network Techniques. Photogrammetric Engineering & Remote Sensing 73 (10): 1149-1157.

29. Li, F., M. L. Gnyp, L. Jia, Y. Miaoa, Z. Yua, W. Koppe, G. Bareth, X. Chen, and F. Zhang. 2008. Estimating N status of winter wheat using a handheld spectrometer in the North China Plain. Field Crops Research 106 (1): 77-85.

30. Loveimi, N., A. Akram, N. Bagheri, and A. Haji Ahmad. 2019. Prediction of canola yield in some of growth stages by using Landsat satellite, OLI sensor. Journal of Iran Biosystems Engineering 50 (1): 101-113. (In Farsi).

31. Mkhabela, M. S., P. Bullock, S. Raj, S. Wang, and Y. Yang. 2011. Crop yield forecasting on the Canadian Prairies using MODIS NDVI data. Agricultural and Forest Meteorology 151: 385-393.

32. Mcbratney, A., B. Whelan, T. Ancev, and J. Bouma. 2005. Future Directions of Precision Agriculture. Journal of Precision Agriculture 6 (1): 7-23.

33. Norgholipor, F., H. Rezaei, K. Mirzashahi, and H. Haghighatnia. 2014. Integrative management instruction of soil fertility and canola feeding. Soil and Water Research Institute. Tehran. (In Farsi).

34. Panda, S. S., D. P. Ames, and S. Panigrahi. 2010. Application of Vegetation Indices for Agricultural Crop Yield Prediction Using Neural Network Techniques. Remote Sensing 2: 673-696.

35. Piekarczyk, J. 2011. Winter oilseed-rape yield estimates from hyperspectral radiometer measurements. Journal of Quaestiones Geographicae 30 (1): 77-84.

36. Pratt, S. 2013. Satellite crop estimate too low: Analysts. The Western Producer. Available at: https://www.producer.com/2013/10/satellite-crop-estimate-too-low-analysts. Accessed 28 March 2018.

37. Raun, W. R., J. B. Solie, M. L. Stone, E. V. Lukina, W. E. Thomason, and J. S. Schepers. 2001. In-season prediction of potential grain yield in winter wheat using canopy reflectance. Agronomy Journal 93: 131-138.

38. Rezaei, A., and S. A. Mirmohammadi. 2011. Statistics and probability, application in agriculture. Jahad Daneshgahi Sanati Esfahan Press. Tehran. (In Farsi).

39. Rischbeck, R., S. Elsayed, B. Mistele, G. Barmeier, K. Heil, and U. Schmidhalter. 2016. Data fusion of spectral, thermal and canopy height parameters for improved yield prediction of drought stressed spring barley. European Journal of Agronomy 78: 44-59.

40. Roodi, D., S. Rahmanpoor, and F. Javidfar. 2004. Cultivation of canola. Seed Breeding Research Institute. Tehran. (In Farsi).

41. Rostami, M. A., and H. Afzali Gorouh. 2017. Remote sensing of residue management in farms using Landsat 8 sensor imagery. Journal of Agricultural Machinery 7 (2): 388-400. (In Farsi).

42. Rouse, J. W., R. H. Haas, J. A. Schell, and D. W. Deering. 1974. Monitoring vegetation systems in the Great Plains with ERTS. Third Earth Resources Technology Satellite (ERTS) Symposium, NASA SP-351 I: 309-317. Washington D. C. USA.

43. Sanaeinejad, H., M. Nassiri Mahallati, H. Zare, N. Salehnia, and M. Ghaemi. 2014. Wheat yield estimation using Landsat images and observation. Journal of Plant Production 20 (4): 45-63. (In Farsi).

44. Schwalbert, R. A., T. J. C. Amado, L. Nieto, S. Varela, G. M. Corassa, T. A. N. Horbe, C. W. Rice, N. R. Peralta, and I. A. Ciampitti. 2018. Forecasting maize yield at field scale based on high-resolution satellite imagery. Biosystems Engineering 171: 179-192.

45. Shanahan, J. F., J. S. Schepers, D. D. Francis, G. E. Varvel, W. W. Wilhelm, J. M. Tringe, M. R. Schlemmer, and D. J. Major. 2001. Use of remote-sensing imagery to estimate corn grain yield. Agronomy Journal 93: 583-589.

46. Sicre, C. M., J. Inglada, R. Fieuzal, F. Baup, S. Valero, J. Cros, M. Huc, and V. Demarez. 2016. Early Detection of Summer Crops Using High Spatial Resolution Optical Image Time Series. Remote Sensing 8 (7): 591. Available at: http://doi:10.3390/rs8070591. Accessed 3 March 2019.

47. Sulik, J. J., and D. S. Long. 2016. Spectral considerations for modeling yield of canola. Remote Sensing of Environment 184: 161-174.

48. Vigneau, N., M. Ecarnot, G. Rabatel, and P. Roumet. 2011. Potential of field hyperspectral imaging as a nondestructive method to assess leaf nitrogen content in wheat. Field Crops Research 122: 25-31.

49. Weber, V. S., J. L. Araus, J. E. Cairns, C. Sanchez, A. E. Melchinger, and E. Orsini. 2012. Prediction of grain yield using reflectance spectra of canopy and leaves in maize plants grown under different water regimes. Field Crops Research 128: 82-90.

50. Yamamoto, K., W. Guo, Y. Yoshioka, and S. Ninomiya. 2014. On plant detection of intact tomato fruits using image analysis and machine learning methods. Journal of Sensors (Basel) 14 (7): 12191-12206.

51. Zahirnia, A., H. R. Matinfar, and M. Zinvand. 2016. Prediction of canola yield base on Landsat-8 in west south of Khouzestan province. 4th International conference on applied research in agricultural sciences. Tehran. (In Farsi).

52. Zhang, X., and He, Y. 2013. Rapid estimation of seed yield using hyperspectral images of oilseed rape leaves. Journal of Industrial Crops and Products 42: 416-420.

53. Zou, X. B., J. Y. Shi, L. M. Hao, J. W. Zhao, H. P. Mao, Z. W. Chen, Y. X. Li, and M. Holmes. 2011. In vivo noninvasive detection of chlorophyll distribution in cucumber (Cucumis sativus) leaves by indices based on hyperspectral imaging. Journal of Analytica Chimica Acta 706: 105-112.