融合无人机光谱与纹理信息的玉米氮素营养估测

doi:10.3864/j.issn.0578-1752.2024.16.005

摘要/Abstract

摘要：

【目的】作物氮素营养状况是表征玉米冠层绿色程度和健康状态的关键指标，为比较玉米氮素营养估测模型中单一光谱指数模型与融合纹理信息模型精度的差异，探究基于无人机多光谱与纹理信息融合的玉米氮素营养估测模型的精准性与可靠性。【方法】采用Matrice 300 RTK多旋翼飞行器搭载MS600 Pro多光谱传感器，获取2年间6个氮素水平下玉米抽雄-吐丝期的多光谱影像数据，提取植被指数和纹理特征信息，综合分析植被指数、单纹理特征、组合纹理指数及植被指数和纹理指数融合的相关性，优选信息量最大的植被指数、归一化差值纹理指数（NDTI）及其组合信息，利用多元逐步回归（MSR）、随机森林（RF）、支持向量机（SVM）和灰狼优化的卷积神经网络（GWO-CNN）对比估测玉米叶片氮含量（LNC）、植株氮含量（PNC）、叶片氮积累（LNA）和植株氮积累（PNA）4个氮素营养参数。【结果】（1）不同氮素处理下玉米原始光谱反射率之间存在差异，红波段R（660 nm）、蓝波段B（450 nm）和近红外波段NIR（840 nm）波段差异较为显著。（2）基于无人机多光谱影像提取的植被指数（EVI、GARI、REOSAVI、SIPI和MCARI）、单纹理特征（var₄₅₀、var₆₆₀、mean₈₄₀、dis₇₂₀和hom₈₄₀）和组合纹理指数NDTI均可用于VT-R1阶段玉米LNC、PNC、LNA及PNA估测，其中基于植被指数的GWO-CNN模型对LNC、PNC、LNA和PNA的估测效果优于单纹理特征和纹理指数模型，R²分别为0.831、0.761、0.826和0.770。（3）融合植被指数和纹理指数的GWO-CNN模型对LNC、PNC、LNA和PNA估测精度明显高于植被指数和纹理指数，R²分别为0.921、0.901、0.917和0.892，较单一光谱信息最优估测模型精度R²分别提高了9.77%、15.54%、9.92%和13.68%。【结论】融合多光谱的植被指数和纹理指数能够有效提高玉米氮素营养估测精度，较好地评估玉米氮素分布情况，为田块尺度下基于无人机平台的玉米氮肥精准管理提供新思路。

关键词: 玉米, 氮素, 多光谱, 植被指数, 纹理信息

Abstract:

【Objective】Crop nitrogen nutrition status is a key indicator to characterize the green degree and health status of maize canopy. In order to compare the accuracy of single spectral index model and texture information fusion model in maize nitrogen nutrition estimation model, this investigated the accuracy and reliability of maize nitrogen nutrition estimation model based on UAV multispectral information and texture information fusion. 【Method】 Matrice-300 RTK multi-rotor aircraft equipped with MS600 Pro multi-spectral sensor was used to obtain multi-spectral images of maize tasseling-silking stages under six nitrogen levels in two years. By extracting vegetation index and texture features, the correlation between vegetation index, single texture feature, combined texture index and fusion information of vegetation index and texture index, was comprehensively analyzed. The vegetation index, normalized difference texture index (NDTI) and their combined parameters with the largest amount of information were selected. Four nitrogen nutrition parameters of maize leaf nitrogen content (LNC), plant nitrogen content (PNC), leaf nitrogen accumulation (LNA), and plant nitrogen accumulation (PNA) were compared and estimated by multiple stepwise regression (MSR), random forest (RF), support vector machine (SVM), and grey wolf optimized convolutional neural network ( GWO-CNN ). 【Result】 (1) There were differences in the original spectral reflectance of maize under different nitrogen treatments, and the differences in the red band R (660 nm), blue band B (450 nm) and near-infrared band NIR (840 nm) were significant. (2) The vegetation indices (EVI, GARI, REOSAVI, SIPI, and MCARI), single texture features (var₄₅₀, var₆₆₀, mean₈₄₀, dis₇₂₀, and hom₈₄₀) and combined texture index NDTI extracted from UAV multispectral images could be used for LNC, PNC, LNA and PNA estimation of maize in VT-R1 stage. The GWO-CNN model based on vegetation index had better estimation effect on LNC, PNC, LNA and PNA than single texture feature and texture index model, and its R² were 0.831, 0.761, 0.826 and 0.770, respectively. (3) The accuracy of GWO-CNN model with vegetation index and texture index for LNC, PNC, LNA and PNA estimation was significantly higher than that of vegetation index and texture index, and its R² was 0.921, 0.901, 0.917 and 0.892, respectively, which was 9.77%, 15.54%, 9.92% and 13.68% higher than that of single spectral information optimal estimation model. 【Conclusion】 Fusion of multi-spectral vegetation index and texture index could effectively improve the estimation accuracy of maize nitrogen nutrition, and better evaluate the distribution of maize nitrogen distribution, which provided new ideas for precise maize nitrogen fertilizer management based on UAV platform at field scale.

Key words: maize, nitrogen, multi-spectral, vegetation index, texture features

运彬媛, 谢铁娜, 李虹, 岳翔, 吕明玥, 王佳琦, 贾彪. 融合无人机光谱与纹理信息的玉米氮素营养估测[J]. 中国农业科学, 2024, 57(16): 3154-3170.

YUN BinYuan, XIE TieNa, LI Hong, YUE Xiang, LÜ MingYue, WANG JiaQi, JIA Biao. Nitrogen Nutrition Estimation of Maize Based on UAV Spectrum and Texture Information[J]. Scientia Agricultura Sinica, 2024, 57(16): 3154-3170.

图/表 17

图1

表1

图2

表2

表3

表4

图3

图4

图5

表5

图6

表6

图7

表7

表8

图8

图9

参考文献 39

[1]	郝子源, 杨玮, 李浩, 于滈, 李民赞. 基于多源信息和深度学习的多作物叶面积指数预测模型研究. 光谱学与光谱分析, 2023, 43(12): 3862-3870.
	HAO Z Y, YANG W, LI H, YU H, LI M Z. Study on prediction models for leaf area index of multiple crops based on multi-source information and deep learning. Spectroscopy and Spectral Analysis, 2023, 43(12): 3862-3870. (in Chinese)
[2]	马俊伟, 陈鹏飞, 孙毅, 谷健, 王李娟. 基于无人机多光谱影像和机器学习方法的玉米叶面积指数反演研究. 作物学报, 2023, 49(12): 3364-3376. doi: 10.3724/SP.J.1006.2023.33001
	MA J W, CHEN P F, SUN Y, GU J, WANG L J. Comparing different machine learning methods for maize leaf area index (LAI) prediction using multispectral image from unmanned aerial vehicle(UAV). Acta Agronomica Sinica, 2023, 49(12): 3364-3376. (in Chinese)
[3]	邵亚杰, 汤秋香, 崔建平, 李晓娟, 王亮, 林涛. 融合无人机光谱信息与纹理特征的棉花叶面积指数估测. 农业机械学报, 2023, 54(6): 186-196.
	SHAO Y J, TANG Q X, CUI J P, LI X J, WANG L, LIN T. Cotton leaf area index estimation combining UAV spectral and textural features. Transactions of the Chinese Society for Agricultural Machinery, 2023, 54(6): 186-196. (in Chinese)
[4]	王伟康, 张嘉懿, 汪慧, 曹强, 田永超, 朱艳, 曹卫星, 刘小军. 基于固定翼无人机多光谱影像的水稻长势关键指标无损监测. 中国农业科学, 2023, 56(21): 4175-4191. doi: 10.3864/j.issn.0578-1752.2023.21.004.
	WANG W K, ZHANG J Y, WANG H, CAO Q, TIAN Y C, ZHU Y, CAO W X, LIU X J. Non-destructive monitoring of rice growth key indicators based on fixed-wing UAV multispectral images. Scientia Agricultura Sinica, 2023, 56(21): 4175-4191. doi: 10.3864/j.issn.0578-1752.2023.21.004. (in Chinese)
[5]	WANG J G, WANG H J, TIAN T, CUI J, SHI X Y, SONG J H, LI T S, LI W D, ZHONG M T, ZHANG W X. Construction of spectral index based on multi-angle spectral data for estimating cotton leaf nitrogen concentration. Computers and Electronics in Agriculture, 2022, 201: 107328.
[6]	魏鹏飞, 徐新刚, 李中元, 杨贵军, 李振海, 冯海宽, 陈帼, 范玲玲, 王玉龙, 刘帅兵. 基于无人机多光谱影像的夏玉米叶片氮含量遥感估测. 农业工程学报, 2019, 35(8): 126-133, 335.
	WEI P F, XU X G, LI Z Y, YANG G J, LI Z H, FENG H K, CHEN G, FAN L L, WANG Y L, LIU S B. Remote sensing estimation of nitrogen content in summer maize leaves based on multispectral images of UAV. Transactions of the Chinese Society of Agricultural Engineering, 2019, 35(8): 126-133, 335. (in Chinese)
[7]	JIANG J, ATKINSON P M, ZHANG J Y, LU R H, ZHOU Y Y, CAO Q, TIAN Y C, ZHU Y, CAO W X, LIU X J. Combining fixed-wing UAV multispectral imagery and machine learning to diagnose winter wheat nitrogen status at the farm scale. European Journal of Agronomy, 2022, 138: 126537.
[8]	LEE H, WANG J F, LEBLON B. Using linear regression, random forests, and support vector machine with unmanned aerial vehicle multispectral images to predict canopy nitrogen weight in corn. Remote Sensing, 2020, 12(13): 2071.
[9]	KHOSRAVI I, ALAVIPANAH S K. A random forest-based framework for crop mapping using temporal, spectral, textural and polarimetric observations. International Journal of Remote Sensing, 2019, 40(18): 7221-7251.
[10]	ZHENG H B, MA J F, ZHOU M, LI D, YAO X, CAO W X, ZHU Y, CHENG T. Enhancing the nitrogen signals of rice canopies across critical growth stages through the integration of textural and spectral information from unmanned aerial vehicle (UAV) multispectral imagery. Remote Sensing, 2020, 12(6): 957.
[11]	陈鹏飞, 梁飞. 基于低空无人机影像光谱和纹理特征的棉花氮素营养诊断研究. 中国农业科学, 2019, 52(13): 2220-2229. doi: 10.3864/j.issn.0578-1752.2019.13.003.
	CHEN P F, LIANG F. Cotton nitrogen nutrition diagnosis based on spectrum and texture feature of images from low altitude unmanned aerial vehicle. Scientia Agricultura Sinica, 2019, 52(13): 2220-2229. doi: 10.3864/j.issn.0578-1752.2019.13.003. (in Chinese)
[12]	贾丹, 陈鹏飞. 低空无人机影像分辨率对冬小麦氮浓度反演的影响. 农业机械学报, 2020, 51(7): 164-169.
	JIA D, CHEN P F. Effect of low-altitude UAV image resolution on inversion of winter wheat nitrogen concentration. Transactions of the Chinese Society for Agricultural Machinery, 2020, 51(7): 164-169. (in Chinese)
[13]	陈鹏, 冯海宽, 李长春, 杨贵军, 杨钧森, 杨文攀, 刘帅兵. 无人机影像光谱和纹理融合信息估算马铃薯叶片叶绿素含量. 农业工程学报, 2019, 35(11): 63-74.
	CHEN P, FENG H K, LI C C, YANG G J, YANG J S, YANG W P, LIU S B. Estimation of chlorophyll content in potato using fusion of texture and spectral features derived from UAV multispectral image. Transactions of the Chinese Society of Agricultural Engineering, 2019, 35(11): 63-74. (in Chinese)
[14]	魏永康, 杨天聪, 臧少龙, 贺利, 段剑钊, 谢迎新, 王晨阳, 冯伟. 基于无人机多光谱影像特征融合的小麦倒伏监测. 中国农业科学, 2023, 56(9): 1670-1685. doi: 10.3864/j.issn.0578-1752.2023.09.005.
	WEI Y K, YANG T C, ZANG S L, HE L, DUAN J Z, XIE Y X, WANG C Y, FENG W. Monitoring wheat lodging based on UAV multi-spectral image feature fusion. Scientia Agricultura Sinica, 2023, 56(9): 1670-1685. doi: 10.3864/j.issn.0578-1752.2023.09.005. (in Chinese)
[15]	宋晓宇, 王纪华, 杨贵军, 崔贝, 常红. 基于叶片及冠层叶绿素参数的冬小麦籽粒蛋白质含量预测研究. 光谱学与光谱分析, 2014, 34(7): 1917-1921.
	SONG X Y, WANG J H, YANG G J, CUI B, CHANG H. Winter wheat GPC estimation based on leaf and canopy chlorophyll parameters. Spectroscopy and Spectral Analysis, 2014, 34(7): 1917-1921. (in Chinese)
[16]	万亮, 杜晓月, 陈硕博, 于丰华, 朱姜蓬, 许童羽, 何勇, 岑海燕. 基于无人机多源图谱融合的水稻稻穗表型监测. 农业工程学报, 2022, 38(9): 162-170.
	WAN L, DU X Y, CHEN S B, YU F H, ZHU J P, XU T Y, HE Y, CEN H Y. Rice panicle phenotyping using UAV-based multi-source spectral image data fusion. Transactions of the Chinese Society of Agricultural Engineering, 2022, 38(9): 162-170. (in Chinese)
[17]	高开秀, 高雯晗, 明金, 李岚涛, 汪善勤, 鲁剑巍. 无人机载多光谱遥感监测冬油菜氮素营养研究. 中国油料作物学报, 2019, 41(2): 232-242. doi: 10.7505/j.issn.1007-9084.2019.02.011
	GAO K X, GAO W H, MING J, LI L T, WANG S Q, LU J W. Monitoring of nitrogen nutrition in winter rapeseed using UAV - borne multispectral data. Chinese Journal of Oil Crop Sciences, 2019, 41(2): 232-242. (in Chinese)
[18]	陈震, 程千, 徐洪刚, 黄修桥. 不同水肥处理下夏玉米株高、生物量响应特征及光谱反演. 干旱地区农业研究, 2023, 41(4): 198-207.
	CHEN Z, CHENG Q, XU H G, HUANG X Q. Inversion model of summer maize plant height and biomass under different water and fertilizer treatments based on UAV spectra. Agricultural Research in the Arid Areas, 2023, 41(4): 198-207. (in Chinese)
[19]	魏青, 张宝忠, 魏征, 韩信, 段晨斐. 基于无人机多光谱遥感的冬小麦冠层叶绿素含量估测研究. 麦类作物学报, 2020, 40(3): 365-372.
	WEI Q, ZHANG B Z, WEI Z, HAN X, DUAN C F. Estimation of canopy chlorophyll content in winter wheat by UAV multispectral remote sensing. Journal of Triticeae Crops, 2020, 40(3): 365-372. (in Chinese)
[20]	王来刚, 贺佳, 郑国清, 郭燕, 张彦, 张红利. 基于无人机多光谱遥感的玉米FPAR估算. 农业机械学报, 2022, 53(10): 202-210.
	WANG L G, HE J, ZHENG G Q, GUO Y, ZHANG Y, ZHANG H L. Estimation of maize FPAR based on UAV multispectral remote sensing. Transactions of the Chinese Society for Agricultural Machinery, 2022, 53(10): 202-210. (in Chinese)
[21]	WANG X L, LU Y L, HE G Z, HAN J Y, WANG T Y. Exploration of relationships between phytoplankton biomass and related environmental variables using multivariate statistic analysis in a eutrophic shallow lake: a 5-year study. Journal of Environmental Sciences (China), 2007, 19(8): 920-927.
[22]	郭燕, 井宇航, 王来刚, 黄竞毅, 贺佳, 冯伟, 郑国清. 基于无人机影像特征的冬小麦植株氮含量预测及模型迁移能力分析. 中国农业科学, 2023, 56(5): 850-865. doi: 10.3864/j.issn.0578-1752.2023.05.004.
	GUO Y, JING Y H, WANG L G, HUANG J Y, HE J, FENG W, ZHENG G Q. UAV multispectral image-based nitrogen content prediction and the transferability analysis of the models in winter wheat plant. Scientia Agricultura Sinica, 2023, 56(5): 850-865. doi: 10.3864/j.issn.0578-1752.2023.05.004. (in Chinese)
[23]	张伏, 王新月, 崔夏华, 曹炜桦, 张晓东, 张亚坤. 可见/近红外光谱结合GWO-SVM对千禧番茄的分类鉴别. 光谱学与光谱分析, 2022, 42(10): 3291-3297.
	ZHANG F, WANG X Y, CUI X H, CAO W H, ZHANG X D, ZHANG Y K. Classification of Qianxi tomatoes by visible/near infrared spectroscopy combined with GMO-SVM. Spectroscopy and Spectral Analysis, 2022, 42(10): 3291-3297. (in Chinese)
[24]	尹航, 李斐, 杨海波, 李渊. 基于无人机高光谱影像的马铃薯叶绿素含量估测. 植物营养与肥料学报, 2021, 27(12): 2184-2195.
	YIN H, LI F, YANG H B, LI Y. Estimation of canopy chlorophyll in potato based on UAV hyperspectral images. Journal of Plant Nutrition and Fertilizers, 2021, 27(12): 2184-2195. (in Chinese)
[25]	王娇娇, 宋晓宇, 梅新, 杨贵军, 李振海, 李贺丽, 孟炀. 基于高斯回归分析的水稻氮素敏感波段筛选及含量估算. 光谱学与光谱分析, 2021, 41(6): 1722-1729.
	WANG J J, SONG X Y, MEI X, YANG G J, LI Z H, LI H L, MENG Y. Sensitive bands selection and nitrogen content monitoring of rice based on Gaussian regression analysis. Spectroscopy and Spectral Analysis, 2021, 41(6): 1722-1729. (in Chinese)
[26]	张东彦, 韩宣宣, 林芬芳, 杜世州, 张淦, 洪琪. 基于多源无人机影像特征融合的冬小麦LAI估算. 农业工程学报, 2022, 38(9): 171-179.
	ZHANG D Y, HAN X X, LIN F F, DU S Z, ZHANG G, HONG Q. Estimation of winter wheat leaf area index using multi-source UAV image feature fusion. Transactions of the Chinese Society of Agricultural Engineering, 2022, 38(9): 171-179. (in Chinese)
[27]	YANG H B, HU Y H, ZHENG Z Z, QIAO Y C, HOU B R, CHEN J. A new approach for nitrogen status monitoring in potato plants by combining RGB images and SPAD measurements. Remote Sensing, 2022, 14(19): 4814.
[28]	万亮, 岑海燕, 朱姜蓬, 张佳菲, 杜晓月, 何勇. 基于纹理特征与植被指数融合的水稻含水量无人机遥感监测. 智慧农业, 2020, 2(1): 58-67.
	WAN L, CEN H Y, ZHU J P, ZHANG J F, DU X Y, HE Y. Using fusion of texture features and vegetation indices from water concentration in rice crop to UAV remote sensing monitor. Smart Agriculture, 2020, 2(1): 58-67. (in Chinese) doi: 10.12133/j.smartag.2020.2.1.201911-SA002
[29]	XU S Z, XU X G, ZHU Q Z, MENG Y, YANG G J, FENG H K, YANG M, ZHU Q L, XUE H Y, WANG B B. Monitoring leaf nitrogen content in rice based on information fusion of multi-sensor imagery from UAV. Precision Agriculture, 2023, 24(6): 2327-2349.
[30]	FU Z P, YU S S, ZHANG J Y, XI H, GAO Y, LU R H, ZHENG H B, ZHU Y, CAO W X, LIU X J. Combining UAV multispectral imagery and ecological factors to estimate leaf nitrogen and grain protein content of wheat. European Journal of Agronomy, 2022, 132: 126405.
[31]	石浩磊, 曹红霞, 张伟杰, 朱珊, 何子建, 张泽. 基于无人机多光谱的棉花多生育期叶面积指数反演. 中国农业科学, 2024, 57(1): 80-95. doi: 10.3864/j.issn.0578-1752.2024.01.007.
	SHI H L, CAO H X, ZHANG W J, ZHU S, HE Z J, ZHANG Z. Leaf area index inversion of cotton based on drone multi-spectral and multiple growth stages. Scientia Agricultura Sinica, 2024, 57(1): 80-95. doi: 10.3864/j.issn.0578-1752.2024.01.007. (in Chinese)
[32]	沈思聪, 张靖雪, 陈鸣晖, 李志威, 孙盛楠, 严学兵. 基于无人机多光谱估测不同品种紫花苜蓿的地上生物量和叶绿素含量. 光谱学与光谱分析, 2023, 43(12): 3847-3852.
	SHEN S C, ZHANG J X, CHEN M H, LI Z W, SUN S N, YAN X B. Estimation of above-ground biomass and chlorophyll content of different alfalfa varieties based on UAV multi-spectrum. Spectroscopy and Spectral Analysis, 2023, 43(12): 3847-3852. (in Chinese)
[33]	李华森, 夏晨真, 张星宇, 王寅, 张月. 基于无人机多光谱影像的完熟期玉米倒伏信息提取. 干旱地区农业研究, 2023, 41(5): 198-206, 216.
	LI H S, XIA C Z, ZHANG X Y, WANG Y, ZHANG Y. Extraction of maize lodging information at mature stage based on UAV multispectral images. Agricultural Research in the Arid Areas, 2023, 41(5): 198-206, 216. (in Chinese)
[34]	杭艳红, 苏欢, 于滋洋, 刘焕军, 官海翔, 孔繁昌. 结合无人机光谱与纹理特征和覆盖度的水稻叶面积指数估算. 农业工程学报, 2021, 37(9): 64-71.
	HANG Y H, SU H, YU Z Y, LIU H J, GUAN H X, KONG F C. Estimation of rice leaf area index combining UAV spectrum, texture features and vegetation coverage. Transactions of the Chinese Society of Agricultural Engineering, 2021, 37(9): 64-71. (in Chinese)
[35]	边明博, 马彦鹏, 樊意广, 陈志超, 杨贵军, 冯海宽. 融合无人机多源传感器的马铃薯叶绿素含量估算. 农业机械学报, 2023, 54(8): 240-248.
	BIAN M B, MA Y P, FAN Y G, CHEN Z C, YANG G J, FENG H K. Estimation of potato chlorophyll content based on UAV multi-source sensor. Transactions of the Chinese Society for Agricultural Machinery, 2023, 54(8): 240-248. (in Chinese)
[36]	ZHENG H B, CHENG T, ZHOU M, LI D, YAO X, TIAN Y C, CAO W X, ZHU Y. Improved estimation of rice aboveground biomass combining textural and spectral analysis of UAV imagery. Precision Agriculture, 2019, 20(3): 611-629.
[37]	张泽, 马露露, 洪帅, 林皎, 张立福, 吕新. 滴灌棉田植株氮营养指数的高光谱诊断研究. 棉花学报, 2020, 32(5): 392-403. doi: 10.11963/1002-7807.zzlx.20200716
	ZHANG Z, MA L L, HONG S, LIN J, ZHANG L F, LÜ X. Study on hyperspectral diagnosis of nitrogen nutrition index among different cotton varieties under drip irrigation. Cotton Science, 2020, 32(5): 392-403. (in Chinese)
[38]	张晓东, 毛罕平. 油菜氮素光谱定量分析中水分胁迫与光照影响及修正. 农业机械学报, 2009, 40(2): 164-169.
	ZHANG X D, MAO H P. Effect and correction of water stress and lighting factor on rape nitrogen content spectral analysis. Transactions of the Chinese Society for Agricultural Machinery, 2009, 40(2): 164-169. (in Chinese)
[39]	凌琪涵, 孔发明, 宁强, 魏勇, 柳展, 代明珠, 张跃强, 石孝均, 王洁, 周宇. 基于无人机多光谱影像的水稻氮营养监测. 农业工程学报, 2023, 39(13): 160-170.
	LING Q H, KONG F M, NING Q, WEI Y, LIU Z, DAI M Z, ZHANG Y Q, SHI X J, WANG J, ZHOU Y. Rice nitrogen nutrition monitoring based on unmanned aerial vehicle multispectral image. Transactions of the Chinese Society of Agricultural Engineering, 2023, 39(13): 160-170. (in Chinese)

年份 Year	pH	有机质 OM (g·kg^-1)	全氮 Total N (g·kg^-1)	全磷 Total P (g·kg^-1)	碱解氮 Avail. N (mg·kg^-1)	速效磷 Avail. P (mg·kg^-1)	速效钾 Avail. K (mg·kg^-1)
2021	7.71	12.56	0.73	0.51	36.00	15.37	99.54
2022	8.14	14.15	0.80	0.60	37.65	16.31	108.41

光谱波段 Band	中心波长 Center band-length (nm)	波宽 Band width (nm)	灰板反射率 Gray plate reflectivity (%)
红Red (R)	660	10	51.2
绿Green (G)	555	20	51.2
蓝Blue (B)	450	20	51.2
近红外Near infrared reflectance (NIR)	840	40	51.0
红边Red edge (RE)	720	10	51.2

指数Index	公式Formula	来源 Reference
归一化植被指数 NDVI	(NIR−R)/(NIR+R)	[13]
改进比值植被指数 MSR	(NIR/R−1) /(NIR/R+1)^0.5	[13]
增强型植被指数 EVI	2.5(NIR−R)/(NIR+6R−7.5B+1)	[11]
归一化绿色植被指数NGI	G/(NIR+G+RE)	[17]
绿色大气阻力植被指数 GARI	NIR−[G−1.7(B−R)]/ NIR+[G−1.7(B−R)]	[8]
结构不敏感色素指数 SIPI	(NIR−B)/(NIR−R)	[18]
修正型叶绿素吸收反射率植被指数 MCARI	[(NIR−RE) −0.2(NIR−R) ]( NIR/RE)	[8]
红边重归一化差值植被指数RERDVI	(NIR−RE)/(NIR+RE)	[19]
红边优化土壤调节植被指数REOSAVI	(1+0.16)( NIR−RE) /(NIR+RE+0.16)	[19]

指数Index	公式Formula
均值Mean (mean)	$\text{mean=}\sum{_{i,j}^{N-\text{1}}i{{P}_{i,j}}}$
方差Variance (var)	$\text{var=}\sum{_{i,j=0}^{N-\text{1}}i{{P}_{i,j}}}{{(i-mean)}^{2}}$
同质性Homogeneity (hom)	$\text{hom=}\sum{_{i,j=0}^{N-\text{1}}i}\frac{{{P}_{i,j}}}{1+{{(i-j)}^{2}}}$
对比度Contrast (con)	$\text{con=}\sum{_{i,j=0}^{N-\text{1}}i}{{P}_{i,j}}{{(i-j)}^{2}}$
相异性Dissimilarity (dis)	$~\text{dis=}\sum{_{i,j=0}^{N-\text{1}}i}{{P}_{i,j}}\|i-j\|$
墒Entropy (ent)	$\text{ent=}\sum{_{i,j=0}^{N-\text{1}}i}{{P}_{i,j}}(-\ln {{P}_{i,j}})$
二阶矩Second moment (sm)	$\text{sm=}\sum{_{i,j=0}^{N-\text{1}}i}{{P}_{i,j}}^{2}$
自相关Correlation (cor)	$\operatorname{corr}=\sum_{i, j=0}^{N-1} i P_{i, j}\left[\frac{(i-\text { mean })(j-\text { mean })}{\sqrt{\operatorname{var}_{i} \times \operatorname{var}_{j}}}\right]$

模型 Model	LNC		PNC		LNA		PNA
模型 Model	R²	RMSE	R²	RMSE	R²	RMSE	R²	RMSE
MSR	0.771	0.998	0.664	0.734	0.759	7.314	0.701	12.677
RF	0.795	0.876	0.747	0.848	0.783	6.294	0.751	11.858
SVM	0.802	0.917	0.721	0.391	0.798	7.286	0.759	12.387
GWO-CNN	0.831	0.723	0.761	0.336	0.826	6.299	0.770	11.387