Detecting advanced stages of winter wheat yellow rust and aphid infection using RapidEye data in North China Plain

Figures & data

Figure 8. Spatial distribution of YR infected winter wheat derived by SVM with the RapidEye images acquired on May 10 and 23, 2017. Areas in white represent non-wheat fields.

Figure 1. Study area and sample distribution.

Table 1. Specifications of the RapidEye Multi-spectral imager bands.

Spectral band	Wavelength range (nm)
Blue (B)	440–510
Green (G)	520–590
Red (R)	630–685
Red Edge (RE)	690–730
Near-InfraRed (NIR)	760–850
More information of RapidEye can be found at “https://www.planet.com/”

Table 2. Specifications of RapidEye data acquisitions and corresponding phenological stage of winter wheat.

Date	Satellite number	Solar elevation angle (º)	Solar azimuth angle (º)	Sensor view angle (º)	Sensor azimuth angle (º)	Phenological stage of winter wheat
4 December, 2016	3	32.04	169.20	6.76	279.12	Over-wintering
6 December, 2016	5	32.16	170.60	−2.58	101.81	Over-wintering
7 May, 2017	5	69.10	146.97	0.19	279.52	Milk ripening
10 May, 2017	3	69.29	144.61	3.49	279.33	Milk ripening
23 May, 2017	2	72.48	141.41	13.65	278.50	Maturation

Table 3. List of selected vegetation indices.

Vegetation index	Formula	References
Normalized Difference Vegetation Index (NDVI)	$\frac{NIR-R}{NIR+R}$	Rouse et al. (1973)
Enhanced Vegetation Index (EVI)	$2.5\times \frac{NIR-R}{NIR+6\times R-7.5\times B+1}$	Huete et al. (2002)
Green Normalized Difference Vegetation Index (GNDVI)	$\frac{NIR-G}{NIR+G}$	Gitelson and Merzlyak (1996)
Triangular Vegetation Index (TVI)*	$0.5\times \left[120\times \left(\mathrm{N}\mathrm{I}\mathrm{R}-\mathrm{G}\right)-200\times \left(\mathrm{R}-\mathrm{G}\right)\right]$	Broge and Leblanc (2001)
Green Vegetation Index (VIGreen)	$\frac{G-R}{G+R}$	Gitelson et al. (2002)
Green Chlorophyll Index (GCI)	$\frac{NIR}{G}-1$	Gitelson et al. (2005)
Structural Independent Pigment Index (SIPI)*	$\frac{NIR-B}{NIR-R}$	Peñuelas and Inoue (1999)
Normalized Difference Red Edge Index (NDVIRE)	$\frac{NIR-RE}{NIR+RE}$	Gitelson and Merzlyak (1994)
Red-Edge Chlorophyll Index (CIRE)	$\frac{NIR}{RE}-1$	Gitelson et al. (2005)
Simplified Canopy Chlorophyll Content Index (SCCCI)	$\frac{NDV{I}_{RE}}{NDVI}$	Barnes et al. (2000)
Yellow Rust Index (YRI)*	$\frac{G-RE}{G+RE}-0.5\times \mathrm{R}\mathrm{E}$	Mahlein et al. (2013)
Aphid Index 1 (AI1)*	$\frac{B-RE}{B+RE}+0.5\times \mathrm{B}$	Huang et al. (2014)
Aphid Index 2 (AI2)*	$\frac{RE-B}{RE+B}-0.5\times \mathrm{R}\mathrm{E}$	Shi et al. (2017)

*Indices developed for hyper-spectral data.

Table 4. Summary for the use of sampling plots.

	Number of plots
Experiment/image dates	Healthy	YR	AH	Total
Detection of YR infection/10 May, 2017	26	19	/	45
Detection of YR infection/May 10 & 23, 2017	21	15	/	36
Detection of AH infection/7 May, 2017	19	/	13	32
Detection of AH infection/May 7 & 23, 2017	19	/	13	32
Discrimination between YR & AH infection/23 May 2017	47	21	18	86

Table 5. Correlation coefficient between different vegetation indices.

	NDVI	EVI	GNDVI	TVI	VIGreen	GCI	SIPI	NDVIRE	CIRE	SCCCI	YRI	AI1	AI2
NDVI	1.00
EVI	0.91	1.00
GNDVI	0.95	0.84	1.00
TVI	0.88	0.97	0.82	1.00
VIGreen	0.73	0.71	0.49	0.67	1.00
GCI	0.92	0.83	0.98	0.81	0.46	1.00
SIPI	0.88	0.73	0.90	0.80	0.53	0.87	1.00
NDVIRE	0.94	0.85	0.95	0.82	0.57	0.93	0.85	1.00
CIRE	0.91	0.84	0.93	0.81	0.55	0.94	0.83	0.99	1.00
SCCCI	0.62	0.55	0.72	0.53	0.20	0.71	0.59	0.85	0.86	1.00
YRI	−0.14	−0.18	−0.26	−0.25	0.16	−0.27	−0.26	0.04	0.06	0.31	1.00
AI1	−0.21	−0.05	−0.23	−0.23	−0.11	−0.23	−0.58	−0.06	−0.05	0.17	0.53	1.00
AI2	0.24	0.04	0.27	0.19	0.12	0.27	0.60	0.12	0.10	−0.11	−0.46	−0.98	1.00

Figure 2. Average canopy reflectance of the three classes of winter wheat samples derived from the 23 May 2017 RapidEye image. Vertical error bars represent the standard deviation.

Figure 3. Average vegetation indices of the three classes of winter wheat samples derived from the May 23, 2017 RapidEye image; vertical error bars represent the standard deviation.

Figure 4. Importance of variables for disease/pest identification, computed using RF. The left panel is for YR detection using RapidEye image acquired on 10 May 2017, and the right panel is for AH detection using RapidEye image acquired on 7 May 2017.

Figure 5. Boxplots of the overall accuracy (OA) of the three algorithms for detection of YR infection using RapidEye image acquired on 10 May 2017, using the10-fold cross-validation. The thick horizontal lines represent the median, the top and bottom of the box represent the 25th and 75th percentiles, and the whiskers are 1.5 times of the box height towards upper and lower from the median. Dark circles represent the average of OA.

Figure 6. Distribution of YR infected winter wheat area derived from SVM using the RapidEye imagery acquired on 10 May 2017. Areas in white represent non-wheat fields.

Figure 7. Boxplots of the overall accuracy (OA) of the three algorithms for detection of YR infection using RapidEye image acquired on May 10 and 23, 2017, using the10-fold cross-validation. The thick horizontal lines represent the median, the top and bottom of the box represent the 25th and 75th percentiles, and the whiskers are 1.5 times of the box height towards upper and lower from the median. Dark circles represent the average of OA.

Figure 9. Boxplots of the overall accuracy (OA) of the three algorithms for detection of AH infection using RapidEye image acquired on 7 May 2017, using the10-fold cross-validation. The thick horizontal lines represent the median, the top and bottom of the box represent the 25th and 75th percentiles, and the whiskers are 1.5 times of the box height towards upper and lower from the median. Dark circles represent the average of OA. Open circles are outliers.

Figure 10. Spatial distribution of AH infected winter wheat derived by SVM with RapidEye imagery acquired on 7 May 2017. Areas in white represent non-wheat fields.

Figure 11. Boxplots of the overall accuracy (OA) of the three algorithms for detection of AH infection using RapidEye image acquired on May 7 and 23, 2017, using the10-fold cross-validation. The thick horizontal lines represent the median, the top and bottom of the box represent the 25th and 75th percentiles, and the whiskers are 1.5 times of the box height towards upper and lower from the median. Dark circles represent the average of OA.

Figure 12. Distribution of AH infected winter wheat derived by SVM with RapidEye imageries acquired on May 7 and 23, 2017. Areas in white represent non-wheat fields.

Figure 13. Boxplots of the overall accuracy (OA) of the three algorithms for detection of AH and YR infection using RapidEye image acquired on May 7 23, 2017, using the10-fold cross-validation. (a) for “AH vs. YR vs. Healthy,” (b) for “Infected vs. Healthy.” The thick horizontal lines represent the median, the top and bottom of the box represent the 25th and 75th percentiles, and the whiskers are 1.5 times of the box height towards upper and lower from the median. Dark circles represent the average of OA. Open circles are outliers.

Figure 14. Distribution of Infected winter wheat derived by SVM with RapidEye image acquired on 23 May 2017. Areas in white represent non-wheat fields.

Rouse, J. W., Jr, R. H. Haas, J. A. Schell, and D. W. Deering. 1973. “Monitoring Vegetation Systems in the Great Plains with Erts.” Nasa Special Publication 351: 309.

 Google Scholar

Huete, A., K. Didan, T. Miura, E. P. Rodriguez, X. Gao, and L. G. Ferreira. 2002. “Overview of the Radiometric and Biophysical Performance of the MODIS Vegetation Indices.” Remote Sensing of Environment 83 (1): 195–213. doi:10.1016/S0034-4257(02)00096-2.

 Web of Science ®Google Scholar

Gitelson, A. A., and M. N. Merzlyak. 1996. “Signature Analysis of Leaf Reflectance Spectra: Algorithm Development for Remote Sensing of Chlorophyll.” Journal of Plant Physiology 148 (3–4): 494–500. doi:10.1016/s0176-1617(96)80284-7.

 Web of Science ®Google Scholar

Broge, N. H., and E. Leblanc. 2001. “Comparing Prediction Power and Stability of Broadband and Hyperspectral Vegetation Indices for Estimation of Green Leaf Area Index and Canopy Chlorophyll Density.” Remote Sensing of Environment 76 (2): 156–172. doi:10.1016/s0034-4257(00)00197-8.

 Web of Science ®Google Scholar

Gitelson, A. A., Y. J. Kaufman, R. Stark, and D. Rundquist. 2002. “Novel Algorithms for Remote Estimation of Vegetation Fraction.” Remote Sensing of Environment 80 (1): 76–87. doi:10.1016/S0034-4257(01)00289-9.

 Web of Science ®Google Scholar

Gitelson, A. A., A. Viña, V. Ciganda, D. C. Rundquist, and T. J. Arkebauer. 2005. “Remote Estimation of Canopy Chlorophyll Content in Crops.” Geophysical Research Letters 32 (8): 93–114. doi:10.1029/2005GL022688.

 Web of Science ®Google Scholar

Peñuelas, J., and Y. Inoue. 1999. “Reflectance Indices Indicative of Changes in Water and Pigment Contents of Peanut and Wheat Leaves.” Photosynthetica 36 (3): 355–360. doi:10.1023/A:1007033503276.

 Web of Science ®Google Scholar

Gitelson, A., and M. N. Merzlyak. 1994. “Quantitative Estimation of Chlororhyll-A Using Reflectance Spectra: Experiments with Autumn Chestnut and Maple Leaves.” Journal of Photochemistry and Photobiology B-Biology 22 (3): 247–252. doi:10.1016/1011-1344(93)06963-4.

 Web of Science ®Google Scholar

Barnes, E. M., T. R. Clarke, S. E. Richards, P. D. Colaizzi, J. Haberland, M. Kostrzewski, P. Waller, C. Choi, E. Riley, and T. Thompson. 2000. “Coincident Detection of Crop Water Stress, Nitrogen Status and Canopy Density Using Ground-Based Multispectral Data.” Paper presented at the International Conference on Precision Agriculture and Other Resource Management July 16-19, 2000, Bloomington, MN USA.

 Google Scholar

Mahlein, A. K., T. Rumpf, P. Welke, H. W. Dehne, L. Plümer, U. Steiner, and E. C. Oerke. 2013. “Development of Spectral Indices for Detecting and Identifying Plant Diseases.” Remote Sensing of Environment 128 (1): 21–30. doi:10.1016/j.rse.2012.09.019.

 Web of Science ®Google Scholar

Huang, W., Q. Guan, J. Luo, J. Zhang, J. Zhao, D. Liang, L. Huang, and D. Zhang. 2014. “New Optimized Spectral Indices for Identifying and Monitoring Winter Wheat Diseases.” IEEE Journal of Selected Topics in Applied Earth Observations & Remote Sensing 7 (6): 2516–2524. doi:10.1109/JSTARS.2013.2294961.

 Web of Science ®Google Scholar

Shi, Y., W. J. Huang, J. H. Luo, L. S. Huang, and X. F. Zhou. 2017. “Detection and Discrimination of Pests and Diseases in Winter Wheat Based on Spectral Indices and Kernel Discriminant Analysis.” Computers and Electronics in Agriculture 141: 171–180. doi:10.1016/j.compag.2017.07.019.

 Web of Science ®Google Scholar