Estimation of SPAD value in waterlogged winter wheat based on characteristic indices of hyperspectral and digital image

doi:10.13287/j.1001-9332.202103.009

Abstract

Abstract: To explore the optimal monitoring method for soil and plant analyzer development (SPAD) of winter wheat under waterlogging stress based on hyperspectral and digital image techno-logy, the correlations between SPAD of the waterlogged winter wheat and fifteen indices of hyperspectral characteristic and fourteen indices of digital image feature were analyzed under a micro-plot which could be irrigated and drainage separately. Then, the BP neural network models for SPAD estimation were constructed based on the optimal monitoring feature indices. Compared with the normal winter wheat, SPAD and the value of hyperspectral reflectance did not change under short-term waterlogging (less than 7 d), whereas the SPAD was significantly decreased after more than 12 d waterlogging treatment with the value being close to zero at the late stage of growth. The estimation accuracy based on the digital image characteristics of green minus red, excess red index, norma-lized redness index and excess green index showed similar results compared to that using the BP network model based on the characteristics of the corresponding hyperspectral band. The highest R² between the measured value and the predicted value was 0.86, while the root mean square error (RMSE) was 3.98. Compared with the BP network models built with the digital image feathers, the accuracy of the models based on the four hyperspectral characteristic indices (carotenoid reflex index, yellow edge amplitude, normalized difference vegetation index and structure insensitive pigment index) for SPAD was significantly improved, with the highest R² of 0.97 and the lowest RMSE of 1.95. Our results suggest that both hyperspectral and digital image technology could be used to estimate SPAD value of waterlogged winter wheat and that the BP network model based on hyperspectral characteristic indices performed better in the estimation accuracy.

Key words: hyperspectral, digital image, SPAD, winter wheat, waterlogging

GAO Xiao-mei, LI Yan-li, LU Bi-lin, XIONG Qin-xue, WU Qi-xia, LI Ji-fu. Estimation of SPAD value in waterlogged winter wheat based on characteristic indices of hyperspectral and digital image[J]. Chinese Journal of Applied Ecology, 2021, 32(3): 959-966.

References 28

[1]	吴启侠, 朱建强, 程伦国, 等. 基于地下水埋深的江汉平原冬小麦防涝渍排水指标确定. 农业工程学报, 2017, 33(3): 121-127 [Wu Q-X, Zhu J-Q, Cheng L-G, et al. Determination of groundwater depth-based drainage index against waterlogging and submergence for winter wheat in Jianghan Plain. Transactions of the Chinese Society of Agricultural Engineering, 2017, 33(3): 121-127]
[2]	吴洪颜, 张佩, 徐敏, 等. 长江中下游地区冬小麦春季涝渍害灾损风险时空分布特征. 长江流域资源与环境, 2018, 27(5): 1152-1158 [Wu H-Y, Zhang P, Xu M, et al. Spatial-temporal variations of the risk of winter wheat loss suffered from spring waterlogging disaster in the middle and lower Yangtze River reaches. Resources and Environment in the Yangtze Basin, 2018, 27(5): 1152-1158]
[3]	Nijat K, Shi QD, Wang J, et al. Estimation of spring wheat chlorophyll content based on hyperspectral features and PLSR model. Transactions of the Chinese Society of Agricultural Engineering, 2017, 33: 208-216
[4]	Hao ZS, Zheng ZM. High symbol-rate polarization interference cancelation for satellite-to-ground remote sensing data transmission system. EURASIP Journal on Wireless Communications and Networking, 2018, 2018(1): https://doi.org/10.1186/s13638-018-1305-0
[5]	Zhang L, Rao Z, Ji H. NIR hyperspectral imaging technology combined with multivariate methods to study the residues of different concentrations of omethoate on wheat grain surface. Sensors, 2019, 19: 3147
[6]	依尔夏提·阿不来提, 白灯莎·买买提艾力, 买买提·沙吾提, 等. 基于高光谱和BP神经网络的棉花冠层叶绿素含量联合估算. 光学学报, 2019, 39(9): 372-380 [Ershat A, Baidengsha M, Mamat S, et al. Combined estimation of chlorophyll content canopy based on hyperspectral parameters and back propagation neural network. Acta Optica Sinica, 2019, 39(9): 372-380]
[7]	李长春, 陈鹏, 陆国政, 等. 基于无人机高清数码影像和高光谱遥感数据反演大豆典型生育期氮平衡指数. 应用生态学报, 2018, 29(4): 1225-1232 [Li C-C, Chen P, Lu G-Z, et al. The inversion of nitrogen balance index in typical growth period of soybean based on high definition digital image and hyperspectral data on unmanned aerial vehicles. Chinese Journal of Applied Ecology, 2018, 29(4): 1225-1232]
[8]	李燕丽, 李磊, 吴启侠, 等. 基于数字图像特征的冬小麦渍害监测研究. 麦类作物学报, 2019, 39(6): 747-752 [Li Y-L, Li L, Wu Q-X, et al. Monitoring winter wheat waterlogging based on the features of digital image. Journal of Triticeae Crops, 2019, 39(6): 747-752]
[9]	Barbedo JGA. Detection of nutrition deficiencies in plants using proximal images and machine learning: A review. Computers and Electronics in Agriculture, 2019, 162: 482-492
[10]	李燕丽, 雷仁清, 宋潇, 等. 渍害胁迫下基于数字图像的小麦叶绿素估算研究. 湖北农业科学, 2019, 58(23): 197-201 [Li Y-L, Lei R-Q, Song X, et al. Estimation of wheat chlorophyll under waterlogging stress based on digital image technology. Hubei Agricultural Sciences, 2019, 58(23): 197-201]
[11]	Kyu JL, Byun WL. Estimation of rice growth and nitrogen nutrition status using color digital camera image analysis. European Journal of Agronomy, 2013, 48: 57-65
[12]	Liu J, Pattey E, Admiral S. Assessment of in situ crop LAI measurement using unidirectional view digital photography. Agricultural & Forest Meteorology, 2013, 169: 25-34
[13]	Torres SJ, Pea JM, de Castro AI, et al. Multi-temporal mapping of the vegetation fraction in early-season wheat fields using images from UAV. Computers & Electronics in Agriculture, 2014, 103: 104-113
[14]	Wang Y, Wang D, Zhang G, et al. Estimating nitrogen status of rice using the image segmentation of G-R thresholding method. Field Crops Research, 2013, 149: 33-39
[15]	滕佳昆, 刘宇, 丁明涛. 基于RGB图像的刺槐季节变化监测适用指数研究. 遥感技术与应用, 2018, 33(3): 476-485 [Teng J-K, Liu Y, Ding M-T. The eva-luation of efficiency of color metrics in monitoring Robiuia pseudoacacia phenology based on RGB images. Remote Sensing Technology and Application, 2018, 33(3): 476-485]
[16]	Guijarro M, Pajares G, Riomoros I, et al. Automatic segmentation of relevant textures in agricultural images. Computers & Electronics in Agriculture, 2011, 75: 75-83
[17]	Carter GA, Dell TR, Cibula WG. Spectral reflectance characteristics and digital imagery of a pine needle blight in the southeastern United States. Canadian Journal of Forest Research, 1996, 26: 402-407
[18]	徐悦, 刘卫国, 霍举颂, 等. 基于光谱指数的古尔班通古特优势种沙蒿叶绿素含量的估算模型. 人民珠江, 2018, 39(10): 83-91 [Xu Y, Liu W-G, Huo J-S, et al. A model for estimating chlorophyll content of sand sagebrush of Gurbantongout dominant species based on spectral indexes. Pearl River, 2018, 39(10): 83-91]
[19]	马岩川, 刘浩, 陈智芳, 等. 基于高光谱指数的棉花冠层等效水厚度估算. 中国农业科学, 2019, 52(24): 4470-4483 [Ma Y-C, Liu H, Chen Z-F, et al. Canopy equivalent water thickness estimation of cotton based on hyperspectral index. Scientia Agricultura Sinica, 2019, 52(24): 4470-4483]
[20]	Li YY, Chang QR, Liu XY, et al. Estimation of maize leaf SPAD value based on hyperspectrum and BP neural network. Transactions of the Chinese Society of Agricultural Engineering, 2016, 32: 135-142
[21]	田永超, 杨杰, 姚霞, 等. 估测水稻叶层氮浓度的新型蓝光氮指数. 应用生态学报, 2010, 21(4): 966-972 [Tian Y-C, Yang J, Yao X, et al. A newly deve-loped blue nitrogen index for estimating canopy leaf nitrogen concentration of rice. Chinese Journal of Applied Ecology, 2010, 21(4): 966-972]
[22]	熊勤学, 王晓玲, 王有宁. 小麦渍害光谱特征分析. 光谱学与光谱分析, 2016, 36(8): 2558-2561 [Xiong Q-X, Wang X-L, Wang Y-N. Spectral characteristics analysis of wheat damaged by subsurface waterlogging. Spectroscopy and Spectral Analysis, 2016, 36(8): 2558-2561]
[23]	吴启侠, 晏军, 朱建强, 等. 花后浅地下水埋深对小麦高光谱特征的影响及叶绿素估算模型. 灌溉排水学报, 2018, 37(9): 29-35 [Wu Q-X, Yan J, Zhu J-Q, et al. Effects of the depth of shallow groundwater table during post-anthesis stage on hyperspectral characteristics of winter wheat as well as model for predicting leaf chlorophyll content. Journal of Irrigation and Drai-nage, 2018, 37(9): 29-35]
[24]	刘雪松, 葛亮, 王斌, 等. 基于最大信息量的高光谱遥感图像无监督波段选择方法. 红外与毫米波学报, 2012, 31(2): 166-170 [Liu X-S, Ge L, Wang B, et al. An unsupervised band selection algorithm for hyperspectral imagery based on maximal information. Journal of Infrared and Millimeter Waves, 2012, 31(2): 166-170]
[25]	翁海勇, 岑海燕, 何勇. 直接校正算法的柑橘溃疡病高光谱模型传递. 光谱学与光谱分析, 2018, 38(1): 235-239 [Weng H-Y, Cen H-Y, He Y. Hyperspectral model transfer for citrus canker detection based on direct standardization algorithm. Spectroscopy and Spectral Analysis, 2018, 38(1): 235-239]
[26]	李岚涛, 张萌, 任涛, 等. 应用数字图像技术进行水稻氮素营养诊断. 植物营养与肥料学报, 2015, 21(1): 259-268 [Li L-T, Zhang M, Ren T, et al. Diagnosis of N nutrition of rice using digital processing technique. Journal of Plant Nutrition and Fertilizers, 2015, 21(1): 259-268]
[27]	张影, 赵小娟, 王迪. 基于高光谱遥感的农作物分类研究进展. 中国农业信息, 2019, 31(5): 1-12 [Zhang Y, Zhao X-J, Wang D. Research advances on crop identification using hyperspectral remote sensing. China Agricultural Informatics, 2019, 31(5): 1-12]
[28]	束美艳, 顾晓鹤, 孙林, 等. 倒伏胁迫下的玉米冠层结构特征变化与光谱响应解析. 光谱学与光谱分析, 2019, 39(11): 3553-3559 [Shu M-Y, Gu X-H, Sun L, et al. Structural characteristics change and spectral response analysis of maize canopy under lodging stress. Spectroscopy and Spectral Analysis, 2019, 39(11): 3553-3559]