Scientia Silvae Sinicae ›› 2020, Vol. 56 ›› Issue (2): 89-98.doi: 10.11707/j.1001-7488.20200210
• Articles • Previous Articles Next Articles
Zhulin Chen,Xuefeng Wang*
Received:
2018-12-12
Online:
2020-02-25
Published:
2020-03-17
Contact:
Xuefeng Wang
CLC Number:
Zhulin Chen,Xuefeng Wang. Prediction of Total Iron Content in Dalbergia odorifera Leaves Based on Vegetation Index and Multispectral Texture Parameters[J]. Scientia Silvae Sinicae, 2020, 56(2): 89-98.
Table 1
Vegetation indexes and correlation analysis with total nitrogen content in sandalwood leaves"
植被指数 Vegetation index | 公式 Formula | 皮尔森系数 Pearson coefficient(X) | 参考文献 Reference | |||
X=B | X=G | X=R | X=RE | |||
比值植被指数Ratio vegetation index X (RVIX) | NIR/X | 0.604* | 0.530 | 0.597* | 0.635** | |
差值植被指数Difference vegetation index X (DVIX) | NIR-X | 0.610* | 0.582* | 0.606* | 0.644** | |
归一化差值植被指数Normalized difference vegetation index X (NDVIX) | (NIR-X)/(NIR+X) | 0.587* | 0.524 | 0.598* | 0.646** | Buschmann et al., 1993 |
重整化差值植被指数Renormalized difference vegetation index X (RDVIX) | (NIR-X)/(NIR+X)1/2 | 0.605* | 0.560 | 0.599* | 0.646** | Roujean et al., 1995 |
宽动态范围植被指数Wide dynamic range vegetation index X (WDRVIX) | (0.12NIR-X)/(0.12NIR+X) | 0.595* | 0.529 | 0.603* | 0.639** | |
修正归一化差值植被指数Modified normalized difference vegetation index X (MNDVIX) | (NIR-R+2X)/(NIR+R-2X) | -0.366 | -0.588* | - | -0.379 | Sims et al., 2002 |
修正反射率指数的叶绿素吸收率Modified chlorophyll absorption in reflectance index X (MCARIX) | 1.2[2.5(NIR-X)-1.3(NIR-G)] | 0.609* | 0.597* | 0.602* | 0.644** | Haboudane et al., 2004 |
修正三角植被指数Modified triangular vegetation index X (MTVX) | 1.2[1.2(NIR-G)-2.5(X-G)] | 0.597* | 0.592* | 0.596* | 0.594* | Broge et al., 2000 |
Table 2
Spectral reflectance of leaves of D. odorifera under different iron stresses"
施肥梯度Fertilization gradient | 波段Band | ||||
B | G | R | RE | NIR | |
CK | 0.144 1 | 0.205 2 | 0.166 7 | 0.266 2 | 0.385 6 |
F1 | 0.141 8 | 0.218 1 | 0.165 7 | 0.270 3 | 0.430 7 |
F2 | 0.137 8 | 0.222 7 | 0.167 3 | 0.271 6 | 0.465 9 |
F3 | 0.139 1 | 0.211 5 | 0.167 1 | 0.276 8 | 0.500 1 |
Table 3
Significance test between total iron content and mean texture factors in different bands"
波段 Band | 皮尔森相关性系数 Pearson correlation coefficient | |||||||
均值 Mean | 方差 Variance | 同质性 Homogeneity | 对比度 Contrast | 相异性 Dissimilarity | 熵 Entropy | 二阶矩 Second Moment | 相关性 Correlation | |
B | -0.211 | -0.415 | 0.522* | -0.446* | -0.521* | -0.402 | 0.334 | -0.400 |
G | -0.177 | -0.517* | 0.204 | -0.498* | -0.525* | 0.147 | -0.275 | -0.426 |
R | 0.140 | -0.528* | 0.229 | -0.423 | -0.496* | 0.141 | -0.169 | -0.407 |
RE | 0.324 | -0.548** | 0.252 | -0.591** | -0.506* | -0.144 | 0.130 | -0.384 |
NIR | 0.525* | -0.589** | -0.219 | -0.576** | -0.533* | 0.346 | -0.215 | -0.288 |
Table 4
Significance test between total iron content and variance texture factors in different bands"
Band | 皮尔森相关性系数Pearson correlation coefficient | |||||||
均值Mean | 方差Variance | 同质性Homogeneity | 对比度Contrast | 相异性Dissimilarity | 熵Entropy | 二阶矩Second moment | 相关性Correlation | |
B | -0.444** | -0.276 | -0.461** | -0.305 | -0.333 | -0.361* | 0.002 | 0.054 |
G | -0.430* | -0.397* | -0.414* | -0.381* | -0.415* | -0.384* | -0.297 | 0.204 |
R | -0.430* | -0.420* | -0.497** | -0.265 | -0.430* | -0.462** | -0.223 | 0.161 |
RE | -0.465** | -0.410* | -0.091 | -0.435* | -0.451** | 0.000 | -0.003 | 0.093 |
NIR | -0.501** | -0.477** | -0.123 | -0.472** | -0.496** | 0.017 | -0.169 | 0.153 |
Table 5
Texture parameter selection results"
方法Method | 筛选结果Selection result |
相关性分析 Correlation analysis | VIs:红边波段归一化差值植被指数(Normalized difference vegetation of band RE, NDVIRE)、蓝波段修正归一化差值植被指数(Modified normalized difference vegetation index of band B, MNDVIB)、蓝波段修正反射率指数的叶绿素吸收率(Modified chlorophyll absorption in reflectance index of band B, MCARIB) TFMV:B波段同质性(Homogeneity of band B)、RE波段对比度(Contrast of band RE)、NIR波段方差(Variance of band NIR) TFV:R波段同质性(Homogeneity of band R)、NIR波段均值(Mean of band NIR) |
主成分分析 Principal component analysis | 主成分1~8(PC1~PC8) |
平均影响值法 Mean impact value | VIs:红边波段重整化差值植被指数(Renormalized difference vegetation index of band RE, RDVIRE)、红边波段归一化差值植被指数(Normalized difference vegetation of band RE, NDVIRE)、红边波段差值植被指数(Difference vegetation index of band RE, DVIRE)、蓝波段修正归一化差值植被指数(Modified normalized difference vegetation index of band B, MNDVIB)、蓝波段修正反射率指数的叶绿素吸收率(Modified chlorophyll absorption in reflectance indexof band B, MCARIB) TFMV:RE波段对比度(Contrast of band RE)、NIR波段方差(Variance of band NIR) TFV:NIR波段均值(NIR-Mean of band NIR) |
遗传算法 Genetic algorithm | VIs:红边波段重整化差值植被指数(Renormalized difference vegetation index of band RE, RDVIRE)、红边波段归一化差值植被指数(Normalized difference vegetation of band RE, NDVIRE)、蓝波段差值植被指数(Difference vegetation index of band B, DVIB)TFMV:R波段方差(Variance of band R)、RE波段对比度(Contrast of band RE) TFV:B波段同质性(Homogeneity of band B)、R波段熵值(Entropy of band R)、NIR波段均值(Mean of band NIR) |
Table 6
Prediction results of PSO-BP neural network model in different tests"
方法Method | 训练集Sample set (n=65) | 验证集Test set (n=35) | 排序Range | ||||||
R2 | RMSE | ME | MPE(%) | R2 | RMSE | ME | MPE(%) | ||
CA-PSO-BPNN | 0.890 | 46.277 | -4.991 | -3.860 | 0.849 | 49.883 | -3.194 | -3.041 | 1 |
PCA-PSO-BPNN | 0.734 | 67.749 | -12.937 | -6.970 | 0.711 | 73.492 | -13.939 | -7.324 | 4 |
MIV-PSO-BPNN | 0.805 | 58.353 | -7.943 | -3.200 | 0.779 | 56.424 | -8.394 | -3.583 | 3 |
GA-PSO-BPNN | 0.862 | 51.897 | -2.460 | -1.980 | 0.838 | 46.495 | -3.928 | -2.192 | 2 |
Table 7
Prediction results of different feature combination"
方法Method | 特征组合Combination of features | 训练集Sample set | 验证集Test set | 排序Range | ||||||
R2 | RMSE | ME | MPE(%) | R2 | RMSE | ME | MPE(%) | |||
CA-PSO-BPNN | VI | 0.632 | 78.294 | -18.492 | -9.284 | 0.591 | 84.952 | -19.072 | -9.834 | 4 |
VI+TFMV | 0.762 | 59.284 | -7.482 | -5.025 | 0.742 | 65.292 | -8.583 | -5.871 | 3 | |
VI+TFV | 0.863 | 45.294 | -7.284 | -3.764 | 0.818 | 47.898 | -6.284 | -3.329 | 2 | |
VI+TFMV+TFV | 0.890 | 46.277 | -4.991 | -3.860 | 0.849 | 49.883 | -3.194 | -3.041 | 1 | |
GA-PSO-BPNN | VI | 0.677 | 66.294 | -9.284 | -6.587 | 0.642 | 63.758 | -8.294 | -7.294 | 4 |
VI+TFMV | 0.782 | 58.732 | -5.887 | -4.342 | 0.744 | 55.294 | -6.258 | -4.289 | 3 | |
VI+TFV | 0.830 | 50.425 | -3.084 | -2.248 | 0.801 | 47.294 | -3.714 | -1.987 | 2 | |
VI+TFMV+TFV | 0.862 | 51.897 | -2.460 | -1.980 | 0.838 | 46.495 | -3.928 | -2.192 | 1 |
陈思宁, 刘新会, 侯娟, 等. 重金属锌胁迫的白菜叶片光谱响应研究. 光谱学与光谱分析, 2007. 27 (9): 1797- 1801. | |
Chen S N , Liu X H , Hou J , et al. Study on the spectrum response of Brassica Campestris L. leaf to the zinc pollution. Spectroscopy and Spectral Analysis, 2007. 27 (9): 1797- 1801. | |
贾方方, 张黎明, 任天宝, 等. 基于BP神经网络的烟草叶片质体色素高光谱反演. 烟草科技, 2016. 49 (7): 8- 13. | |
Jia F F , Zhang L M , Ren T B , et al. Hyperspectral inversion to estimate plastid pigment contents in tobacco leaves based on BP neural network. Tobacco Science & Technology, 2016. 49 (7): 8- 13. | |
贾良良, 范明生, 张福锁, 等. 应用数码相机进行水稻氮营养诊断. 光谱学与光谱分析, 2009. 29 (8): 2176- 2179.
doi: 10.3964/j.issn.1000-0593(2009)08-2176-04 |
|
Jia L L , Fan M S , Zhang F S , et al. Nitrogen status diagnosis of rice by using a digital camera. Spectroscopy and Spectral Analysis, 2009. 29 (8): 2176- 2179.
doi: 10.3964/j.issn.1000-0593(2009)08-2176-04 |
|
刘耿耿, 陈志盛, 郭文忠, 等. 基于自适应PSO和混合转换策略的X结构Steiner最小树算法. 模式识别与人工智能, 2018. 31 (5): 398- 408. | |
Liu G G , Chen Z S , Guo W Z , et al. Self-adapting PSO algorithm with efficient hybrid transformation strategy for x-architecture steiner minimal tree construction algorithm. Pattern Recognition and Artificial Intelligence, 2018. 31 (5): 398- 408. | |
李哲, 张飞, 陈丽华, 等. 光谱指数的植物叶片叶绿素含量估算模型. 光谱学与光谱分析, 2018. 38 (5): 1533- 1539. | |
Li Z , Zhang F , Chen L H , et al. Research on spectrum variance of vegetation leaves and estimation model for leaf chlorophyll content based on the spectral index. Spectroscopy and Spectral Analysis, 2018. 38 (5): 1533- 1539. | |
马廉洁, 陈杰, 巩亚东, 等. 基于PSO算法改进BP神经网络的氟金云母点磨削工艺参数优化. 中国机械工程, 2016. 27 (6): 761- 766.
doi: 10.3969/j.issn.1004-132X.2016.06.010 |
|
Ma L J , Chen J , Gong Y D , et al. Process parameter optimization based on PSO-BP neural network in point grinding fluorophlogopite. China Mechanical Engineering, 2016. 27 (6): 761- 766.
doi: 10.3969/j.issn.1004-132X.2016.06.010 |
|
苗灵凤, 张丽佳, 蒲玉瑾, 等. WP4C露点水势仪测定植物叶片水势时的影响因素——以降香黄檀为例. 植物科学学报, 2017. 35 (1): 93- 98. | |
Miao L F , Zhang L J , Pu Y J , et al. Factors that affect measurement using the WP4C dewpoint potential mater to determine water potential-illustrated by the case of Dalbergia odorifera. Plant Science Journal, 2017. 35 (1): 93- 98. | |
屈永华, 焦思红, 刘素红, 等. 从高光谱卫星数据中提取植被覆盖区铜污染信息. 光谱学与光谱分析, 2015. 35 (11): 3176- 3181. | |
Qu Y H , Jiao S H , Liu S H , et al. Retrieval of copper pollution information from hyperspectral satellite data in a vegetation cover mining area. Spectroscopy and Spectral Analysis, 2015. 35 (11): 3176- 3181. | |
王慧, 曾路生, 孙永红, 等. 重金属铜和锌胁迫下的小麦冠层反射光谱特征. 农业工程学报, 2017. 33 (2): 171- 176. | |
Wang H , Zeng L S , Sun Y H , et al. Wheat canopy spectral reflectance feature response to heavy metal copper and zinc stress. Transactions of the Chinese Society of Agricultural Engineering, 2017. 33 (2): 171- 176. | |
杨菁, 周国英, 田媛媛, 等. 降香黄檀不同混交林土壤细菌多样性差异分析. 生态学报, 2015. 35 (24): 8117- 8127. | |
Yang J , Zhou G Y , Tian Y Y , et al. Differential analysis of soil bacteria diversity in different mixed forests of Dalbergia odorifera. Acta Ecologica Sinica, 2015. 35 (24): 8117- 8127. | |
颜胜科, 杨辉华, 胡百超, 等. 基于最小角回归与GA-PLS的NIR光谱变量选择方法. 光谱学与光谱分析, 2017. 37 (6): 1733- 1738. | |
Yan S K , Yang H H , Hu B C , et al. Variable selection method of NIR spectroscopy based on least angle regression and GA-PLS. Spectroscopy and Spectral Analysis, 2017. 37 (6): 1733- 1738. | |
袁程, 王月, 韩晓日, 等. 长期定位施肥对土壤铁、锰形态及剖面分布的影响. 植物营养与肥料学报, 2012. 18 (1): 115- 122. | |
Yuan C , Wang Y , Han X R , et al. Effects of long-term fertilization on forms of Fe and Mn and their distributions in soil profiles. Plant Nutrition and Fertilizer Science, 2012. 18 (1): 115- 122. | |
郑坚, 吴朝辉, 陈秋夏, 等. 遮荫对降香黄檀幼苗生长和生理的影响. 林业科学, 2016. 52 (12): 50- 57.
doi: 10.11707/j.1001-7488.20161206 |
|
Zheng J , Wu Z H , Chen Q X , et al. Influence of shading on growth and physiology of Dalbergia odorifera seedlings. Scientia Silvae Sinicae, 2016. 52 (12): 50- 57.
doi: 10.11707/j.1001-7488.20161206 |
|
周晓今, 陈茹梅, 范云六. 植物对铁元素吸收、运输和储存的分子机制. 作物研究, 2012. 26 (5): 605- 610.
doi: 10.3969/j.issn.1001-5280.2012.05.55 |
|
Zhou X J , Chen R M , Fan Y L . Molecular mechanism of iron uptake, translocation and storage in plants. Crop Research, 2012. 26 (5): 605- 610.
doi: 10.3969/j.issn.1001-5280.2012.05.55 |
|
朱云芳, 朱利, 李家国, 等. 基于GF-1 WFV影像和BP神经网络的太湖叶绿素a反演. 环境科学学报, 2017. 37 (1): 130- 137. | |
Zhu Y F , Zhu L , Li J G , et al. The study of inversion of chlorophyll a in Taihu based on GF-1 WFV image and BP neural network. Acta Scientiae Circumstantiae, 2017. 37 (1): 130- 137. | |
Broge N H , Leblanc E . 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, 2001. 76 (2): 156- 172.
doi: 10.1016/S0034-4257(00)00197-8 |
|
Buschmann C , Nagel E . In vivo spectroscopy and internal optics of leaves as basis for remote sensing of vegetation. International Journal of Remote Sensing, 1993. 14 (4): 711- 722.
doi: 10.1080/01431169308904370 |
|
Chen J M . Evaluation of vegetation indices and a modified simple ratio for boreal applications. Canadian Journal of Remote Sensing, 1996. 22 (2): 229- 242. | |
Clevers J G P W, Kooistra L, Salas E A L. 2004. Study of heavy metal contamination in river floodplains using the red-edge position in spectroscopic data. International Journal of Remote Sensing, 25(19): 3883-3895. | |
Gitelson A A . Wide dynamic range vegetation index for remote quantification of biophysical characteristics of vegetation. Journal of Plant Physiology, 2004. 161 (2): 165- 173.
doi: 10.1078/0176-1617-01176 |
|
Haboudane D , Miller J R , Pattey E , et al. 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, 2004. 90 (3): 337- 352.
doi: 10.1016/j.rse.2003.12.013 |
|
Horler D N H , Barber J , Barringer A R . Effects of heavy metals on the absorbance and reflectance of plants. International Journal of Remote Sensing, 1980. 1 (2): 121- 136.
doi: 10.1080/01431168008547550 |
|
Roujean J L , Breon F M . Estimating PAR absorbed by vegetation from bidirectional reflectance measurements. Remote Sensing of Environment, 1995. 51 (3): 375- 384.
doi: 10.1016/0034-4257(94)00114-3 |
|
Sims D A , Gamon J A . Relationships between leaf pigment content and spectral reflectance across a wide range of species, leaf structures and developmental stage. Remote Sensing of Environment, 2002. 81 (2/3): 337- 354. | |
Tucker C J . Red and photographic infrared linear combinations for monitoring vegetation. Remote Sensing of Environment, 1979. 8 (2): 127- 150.
doi: 10.1016/0034-4257(79)90013-0 |
[1] | Lin Dakun, Huang Shiguo, Zhang Feiping, Liang Guanghong, Wu Songqing, Hu xia, Wang Rong. Method of Image Recognition for Lepidopteran Insects Based on Improved Differential Evolution Algorithm [J]. Scientia Silvae Sinicae, 2020, 56(3): 73-81. |
[2] | Song Yining, Liu Wenping, Luo Youqing, Zong Shixiang. Monitoring of Dead Trees in Forest Images Based on Linear Spectral Clustering [J]. Scientia Silvae Sinicae, 2019, 55(4): 187-195. |
[3] | Liu Luxia, Pang Yong, Ren Haibao, Li Zengyuan. Predict Tree Species Diversity from GF-2 Satellite Data in a Subtropical Forest of China [J]. Scientia Silvae Sinicae, 2019, 55(2): 61-74. |
[4] | Zhulin Chen,Xuefeng Wang,Qingjun Guan. Nondestructive Estimation of Total Phosphorus Content in Canopy Leaves of Young Dalbergia odorifera [J]. Scientia Silvae Sinicae, 2019, 55(11): 145-152. |
[5] | Min Zhang,Chunxiang Cao,Wei Chen. Remotely Sensed Diagnosing Temporal and Spatial Variation of Vegetation Coverage in Guangxi Based on MODIS NDVI Data [J]. Scientia Silvae Sinicae, 2019, 55(10): 27-37. |
[6] | Zhang Ying, Zhang Xiaoli, Li Hongzhi, Li Liangcai. A Comparison of Landcover Classification Based on the Improved Transformed Divergence Analysis [J]. Scientia Silvae Sinicae, 2018, 54(8): 88-98. |
[7] | Guo Hui, Wang Xiao, Liu Chuanze, Zhou Yucheng. Research on Defect Extraction of Particleboard Surface Images Based on Gray Level Co-Occurrence Matrix and Hierarchical Clustering [J]. Scientia Silvae Sinicae, 2018, 54(11): 111-120. |
[8] | Zheng Jian, Wu Zhaohui, Chen Qiuxia, Ma Xiaohua, Xia Haitao, Wang Jinwang. Influence of Shading on Growth and Physiology of Dalbergia odorifera Seedlings [J]. Scientia Silvae Sinicae, 2016, 52(12): 50-57. |
[9] | Zhang Qian, Zhou Guoying, Dong Wentong, Yang Lei, Wu Yi. Impact of Community Structure of Dalbergia odorifera Plantations on Foliage Diseases Occurrence [J]. Scientia Silvae Sinicae, 2015, 51(11): 121-127. |
[10] | Zhang Fei;Tashpolat·Tiyip;Ding Jianli;;He Qisheng;Tian Yuan;Mamat·Sawut;Wang Hong;Gui Dongwei;. Dynamically Monitoring Vegetation Cover by Remote Sensing in the Typical Salinization Region of Xinjiang: A Case Study in Delta Oasis of Weigan and Kuqa Rivers [J]. Scientia Silvae Sinicae, 2011, 47(7): 27-35. |
[11] | Dong Dejin;Zhou Guomo;Du Huaqiang;Xu Xiaojun;Cui Ruirui;Shen Zhenming. Effects of Topographic Correction with 6 Correction Models on Phyllostachys praecox Forest Aboveground Biomass Estimation [J]. Scientia Silvae Sinicae, 2011, 47(12): 1-8. |
[12] | Feng Haixia;Hou Yuanzhao;Feng Zhongke. Quantitative Research of Forest Ecological Service of Modulating Temperaturein Shandong Province [J]. Scientia Silvae Sinicae, 2010, 46(5): 20-26. |
[13] | Yu Haipeng;Liu Yixing;Zhang Bin;Li Yongfeng. Application of Spatial Gray Level Cooccurrence Matrix in Wood Surface Texture Quantitative Analysis [J]. Scientia Silvae Sinicae, 2004, 40(6): 121-129. |
[14] | Huang Jianwen;Ju Hongbo;Te Muqin;Song Gang;Zhao Shengguo. Monitoring on Controlling Effect of Rhombomys opimus in Haloxylon Ammodendron Bunge Stands Using Remote Sensing TM Imagery in Alashan [J]. Scientia Silvae Sinicae, 2004, 40(3): 107-110. |
Viewed | ||||||
Full text |
|
|||||
Abstract |
|
|||||