To integrate leaf reflectance spectra with Bayesian models for identifying damage levels of Cnaphalocrocis medinalis, rice plants infested with Cnaphalocrocis medinalis were studied. Rice leaves were collected during the pest outbreak period, and the leaf reflectance spectra and physicochemical parameters were determined to further categorize pest damage levels. Raw parameters and order derivatives were employed to select sensitive features, while competitive adaptive reweighted sampling (CARS) was used to identify characteristic spectral bands for constructing spectral indices. Correlations between the above indices and damage levels were analyzed, and the Bayesian model was used to establish a diagnostic framework for C. medinalis damage assessment. The results indicate that: 1) The spectral reflectance of rice leaves in the green and near-infrared bands decrease with increasing C. medinalis damage levels, while reflectance in the red band increased; leaf water content and chlorophyll content also decreased significantly with pest severity. 2) Six vegetation indices (soil-adjusted vegetation index, enhanced vegetation index, blue-band-free enhanced vegetation index, transformed chlorophyll index, spectral absorption index and transformed chlorophyll absorption index) and three sensitive band reflectance values (R562 nm,R576 nm andR660 nm) were selected; six feature parameters were selected based on trilateral parameters (blue-edge amplitude, blue-edge slope, yellow-edge slope, yellow-edge amplitude, red-edge slope, red-edge amplitude); six spectral indices were selected based on CARS (EVI, RI_0, NDI_0, RI_0.25, RI_0.75, NDI_0.75) were identified, with RI_0 exhibiting the highest correlation (0.92) with C. medinalis damage severity. 3) A Bayesian diagnostic model for C. medinalis damage levels was constructed. The optimal input variable combination was determined via inverse feature elimination, included EVI, RI_0, NDI_0, RI_0.25, RI_0.75, NDI_0.75. Three-fold cross-validation accuracy reached 95.83%±4.17%. In summary, this diagnostic model enables timely and accurate acquisition of field damage characteristics for C. medinalis, providing scientific references for early warning of damage trends and decision-making in pest control.
ZhangX, XuX, JiangT, LiB, ChenW J, GuoJ X, ZhouR R, TianJ. Status of rice production and soil quality assessment in Quzhou City, Zhejiang Province[J]. Journal of China Agricultural University, 2024, 29(12): 33-44 (in Chinese)
LiaoJ, TaoW Y, ZangY, ZengH Y, WangP, LuoX W. Research progress and prospect of key technologies in crop disease and insect pest monitoring[J]. Transactions of the Chinese Society for Agricultural Machinery, 2023, 54(11): 1-19 (in Chinese)
YuJ L, ZhangG, ZhaoL C, YaoK B, LuoG H, FangJ C, ZhangJ H, JiaoY, ShuZ L. Control effects of different seed treatments on the rice leaf folder under machine-planting condition[J]. Crops, 2021(6): 224-229 (in Chinese)
TianM L, BanS T, YuanT, WangY Y, MaC, LiL Y. Monitoring of rice damage by rice leaf roller using UAV-based remote sensing[J]. Acta Agriculturae Shanghai, 2020, 36(6): 132-137 (in Chinese)
[19]
ShiY, HuangW J, YeH C, RuanC, XingN C, GengY, DongY Y, PengD L. Partial least square discriminant analysis based on normalized two-stage vegetation indices for mapping damage from rice diseases using PlanetScope datasets[J]. Sensors, 2018, 18(6): 1901
[20]
HuangJ R, LiaoH J, ZhuY B, SunJ Y, SunQ H, LiuX D. Hyperspectral detection of rice damaged by rice leaf folder ( Cnaphalocrocis medinalis )[J]. Computers and Electronics in Agriculture, 2012, 82: 100-107
HuangW J, ZhangJ C, ShiY, DongY Y, LiuL Y. Progress in monitoring and forecasting of crop pests and diseases by remote sensing[J]. Journal of Nanjing University of Information Science & Technology: Natural Science Edition, 2018, 10(1): 30-43 (in Chinese)
[28]
LongT, WangZ Y, XueB W, LiD, ZhengH B, YaoX, ZhuY, CaoW X, and ChengT. A disease-specific spectral index tracks Magnaporthe oryzae infection in paddy rice from ground to space[J]. Remote sensing of environment, 2023, 285: 113384
[29]
GitelsonA A, KeydanG P, MerzlyakM. N. Three-band model for noninvasive estimation of chlorophyll, carotenoids, and anthocyanin contents in higher plant leaves [J]. Geophysical Research Letters, 2006, 33(11): 2006GL026457
[30]
ZhuY Q, QuY H, LiuS H, ChenS B. A reflectance spectra model for copper-stressed leaves: Advances in the PROSPECT model through addition of the specific absorption coefficients of the copper ion [J]. International Journal of Remote Sensing, 2014, 35(4): 1356-1373
[31]
ZhaoH L, GanS, YuanX P, HuL, WangJ J, LiuS. Application of a fractional order differential to the hyperspectral inversion of soil iron oxide[J]. Agriculture, 2022, 12(8): 1163
ShangT H, ChenR H, ZhangJ H, WangY J. Estimation of soil organic matter content in Yinchuan Plain based on fractional derivative combined with spectral indices[J]. Chinese Journal of Applied Ecology, 2023, 34(3): 717-725 (in Chinese)
[34]
RichardsonsA J, WiegandA. Distinguishing vegetation from soil background information[J]. Photogrammetric Engineering and Remote Sensing, 1977, 43: 1541-1552
[35]
RouseJ W, HaasR H, DeeringD W, SchellJ A, HarlanJ C. Monitoring the vernal advancement and retrogradation (green wave effect) of natural vegetation. NASA/GSFCT Type Ⅲ final report [R], NASA, 1974
[36]
PearsonR L, MillerL D. Remote mapping of standing crop biomass for estimation of the productivity of the shortgrass prairie, Pawnee National Grasslands, Colorado [C] In: Proceedings of the 8th international symposium on remote sensing of the environment. Ann Arbor: Environmental Research Institute of Michigan, 1972: 1355-1379
[37]
RoujeanJ L, BreonF M. Estimating PAR absorbed by vegetation from bidirectional reflectance measurements[J]. Remote Sensing of Environment, 1995, 51(3): 375-384
[38]
HueteA R. A soil-adjusted vegetation index (SAVI)[J]. Remote Sensing of Environment, 1988, 25(3): 295-309
[39]
KaufmanY J, TanreD. Atmospherically resistant vegetation index (ARVI)for EOS-MODIS [J]. IEEE Transaction on Geoscience and Remote Sensing, 1992, 30(2): 261-270
[40]
PenuelasJ, BaretF, FilellaI. Semi-empirical indices to assess carotenoids/chlorophyll a ratio from leaf spectral reflectance[J]. Photosynthetica, 1995, 31(2): 221-230
[41]
KohzumaK, HikosakaK. Physiological validation of photochemical reflectance index (PRI) as a photosynthetic parameter using Arabidopsis thaliana mutants [J]. Biochemical and Biophysical Research Communications, 2018, 498(1): 52-57
[42]
GitelsonA A, KaufmanY J, StarkR, RundquistD. Novel algorithms for remote estimation of vegetation fraction[J]. Remote Sensing of Environment, 2002, 80(1): 76-87
[43]
PandaS S, AmesD P, PanigrahiS. Application of vegetation indices for agricultural crop yield prediction using neural network techniques[J]. Remote Sensing, 2010, 2(3): 673–696
[44]
RufoR, SorianoJ M, VillegasD, RoyoC, BellvertJ. Using unmanned aerial vehicle and ground-based RGB indices to assess agronomic performance of wheat landraces and cultivars in a mediterranean-type environment [J]. Remote Sensing, 2021, 13(6): 1187
[45]
MiuraT, HueteA R, YoshiokaH. Evaluation of sensor calibration uncertainties on vegetation indices for MODIS[J]. IEEE Transactions on Geoscience and Remote Sensing, 2000, 38(3): 1399-1409
[46]
DaughtryC S T, GalloK P, GowardS N, PrinceS D, KustasW P. Spectral estimates of absorbed radiation and phytomass production in corn and soybean canopies[J]. Remote Sensing of Environment, 1992, 39(2): 141-152
[47]
FitzgeraldG, RodriguezD, O’LearyG. Measuring and predicting canopy nitrogen nutrition in wheat using a spectral index: The canopy chlorophyll content index (CCCI)[J]. Field Crops Research, 2010, 116(3): 318-324
[48]
RondeauxG, StevenM, BaretF. Optimization of soil-adjusted vegetation indices[J]. Remote Sensing of Environment, 1996, 55(2): 95-107
[49]
ChenA, Orlov-LevinV, MeronM. Applying high-resolution visible-channel aerial imaging of crop canopy to precision irrigation management [J]. Agricultural Water Management, 2019, 216: 196-205
[50]
DaughtryC S T, WalthallC L, KimM S, de ColstounE B, McMurtreyIII J E. Estimating corn leaf chlorophyll concentration from leaf and canopy reflectance[J]. Remote Sensing of Environment, 2000, 74(2): 229-239
[51]
HaboudaneD, MillerJ R., PatteyE, Zarco-TejadaP J, StrachanI B. Hyperspectral vegetation indices and novel algorithms for predicting green LAI of crop canopies: Modeling and validation in the context of precision agriculture[J]. Remote Sensing of Environment, 2004, 90(3): 337-352
[52]
GitelsonA A, ViñaA, CigandaV, RundquistD C, ArkebauerT J. Remote estimation of canopy chlorophyll content in crops[J]. Geophysical Research Letters, 2005, 32(8): 2005GL022688
WangJ N, ZhengL F, TongQ X. The spectral absorption identification model and mineral mapping by imaging spectrometer data[J]. National Remote Sensing Bulletin, 1996(1): 20-31, T001 (in Chinese)
ShiB Q, ZhangX L, BaiX Q, ZhangX X. Chlorophyll estimation model of Pinus tabulaeformis based on “Sanbian” parameters [J]. Journal of Northeast Forestry University, 2015, 43(5): 80-83 (in Chinese)
[57]
BachH, MauserW. Improvements of plant parameter estimations with hyperspectral data compared to multispectral data[J]. Remote Sensing of Vegetation and Sea, 1997, 2959: 59-67
[58]
CurranP J, WindhamW R, GholzH L. Exploring the relationship between reflectance red edge and chlorophyll concentration in slash pine leaves[J]. Tree Physiology, 1995, 15(3): 203-206
[59]
GitelsonA A, MerzlyakM N. Signature analysis of leaf reflectance spectra: Algorithm development for remote sensing of chlorophyll[J]. Journal of Plant Physiology, 1996, 148(3-4): 494-500
[60]
Bonham-CarterG F. Numerical procedures and computer program for fitting an inverted Gaussian model to vegetation reflectance data[J]. Computers & Geosciences, 1988, 14(3): 339-356
[61]
GongP, PuR, HealdR C. Analysis of in situ hyperspectral data for nutrient estimation of giant Sequoia[J]. International Journal of Remote Sensing, 2002, 23(9): 1827-1850
GongM, ZhuS L, LiW J, WangD B, ZhouS H. Method for evaluating the stability of soil-like slopes based on Naive Bayes[J]. Mining Research and Development, 2021, 41(12): 41-47
ZhongY Q. Research on rice identification and change based on machine learning in Shangxing Town, Liyang City[D]. Nanjing: Nanjing University of Information Science & Technology, 2023. (in Chinese)
[69]
ZhangG S, XuT Y, TianY W, FengS, ZhaoD X, GuoZ H. Classification of rice leaf blast severity using hyperspectral imaging[J]. Scientific Reports, 2022, 12: 19757
GeW B, HuG, LuM H, JiangY Y, ZhaiB P. Long-term models suitable in China for forecasting rice leaf folder Cnaphalocrocis medinalis [J]. Journal of Plant Protection, 2020, 47(2): 403-416 (in Chinese)
[72]
DattB. Remote sensing of chlorophyll a, chlorophyll b, chlorophyll a+b, and total carotenoid content in Eucalyptus leaves [J]. Remote Sensing of Environment, 1998, 66(2): 111-121