结合ASD和无人机高光谱的内蒙古典型草原植被氮反演

金利山; 王秀梅; 董建军; 王若琛; 温贺飞; 孙煜焱; 吴文博; 张智航; 康灿

PDF(3863 KB)

中国环境科学 ›› 2025, Vol. 45 ›› Issue (5) : 2713-2723.

环境生态

结合ASD和无人机高光谱的内蒙古典型草原植被氮反演

金利山¹, 王秀梅¹, 董建军², 王若琛¹, 温贺飞², 孙煜焱¹, 吴文博², 张智航¹, 康灿²

作者信息 +

Vegetation nitrogen inversion of typical grassland in Inner Mongolia combined with ASD and UAV hyperspectral

JIN Li-shan¹, WANG Xiu-mei¹, DONG Jian-jun², WANG Ruo-chen¹, WEN He-fei², SUN Yu-yan¹, WU Wen-bo², ZHANG Zhi-hang¹, KANG Can²

Author information +

文章历史 +

摘要

采用地面遥感与无人机遥感相结合的方式对内蒙古典型草原植被氮含量进行估测.实验于2023年8~9月在内蒙古大学草地生态学研究基地进行,采集了地面ASD光谱数据和无人机Resonon数据.基于ASD数据构建了植被指数、“三边参数”、连续统去除参数以及小波系数4种光谱参数,并运用LASSO进行敏感参数筛选.分别构建多元线性、XGBoost、SVM、ANN和KNN共5种模型对植被氮含量进估测,结果表明基于小波系数的SVM方法为最优模型(验证集R²=0.72,RMSE和MAE分别为0.26和0.18).最后将此模型用于无人机Resonon数据进行反演估算并制图(验证集R²=0.41,RMSE和MAE分别为0.42和0.32).研究显示,将ASD和无人机影像与机器学习算法相结合,能够实现草原植被氮含量的估算,为牧场优化施肥、提高牧草品质提供基础数据与技术支撑.

Abstract

The combination of ground remote sensing and UAV remote sensing was used to estimate the nitrogen content of typical grassland vegetation in Inner Mongolia. This experiment was carried out in the grassland ecology research base of Inner Mongolia University from August to September 2023, and the ground ASD spectral data and UAV Resonon data were collected. Based on ASD data, four spectral parameters of vegetation index, hyperspectral characteristic variable, continuum removal variable and wavelet coefficient were constructed, and LASSO was used to screen sensitive parameters. Five models of multiple linear, XGBoost, SVM, ANN and KNN were constructed to estimate the nitrogen content of vegetation. The results showed that the SVM method based on wavelet coefficients was the optimal model (validation set R² = 0.72, RMSE and MAE were 0.26 and 0.18, respectively). Finally, the model was used to estimate and map the UAV Resonon data (validation set R² = 0.41, RMSE and MAE were 0.42 and 0.32, respectively). The research showed that the combination of ASD and UAV images with machine learning algorithms could be used to realize the estimation of grassland vegetation nitrogen content, and was provided basic data and technical support for optimizing fertilization and improving forage quality.

导出引用

金利山, 王秀梅, 董建军, 王若琛, 温贺飞, 孙煜焱, 吴文博, 张智航, 康灿. 结合ASD和无人机高光谱的内蒙古典型草原植被氮反演[J]. 中国环境科学. 2025, 45(5): 2713-2723

JIN Li-shan, WANG Xiu-mei, DONG Jian-jun, WANG Ruo-chen, WEN He-fei, SUN Yu-yan, WU Wen-bo, ZHANG Zhi-hang, KANG Can. Vegetation nitrogen inversion of typical grassland in Inner Mongolia combined with ASD and UAV hyperspectral[J]. China Environmental Science. 2025, 45(5): 2713-2723

中图分类号： X171 S127

参考文献

[1] Qin P, Sun B, Li Z, et al. Estimation of grassland carrying capacity by applying high spatiotemporal remote sensing techniques in Zhenglan Banner, Inner Mongolia, China[J]. Sustainability, 2021,13(6):3123.
[2] 王秀梅,董建军.基于广义线性模型估算内蒙古荒漠草原及典型草原地上生物量变化[J].草地学报, 2020,28(6):1711-1718. Wang X M, Dong J J. Estimation of the aboveground biomass of desert Steppe ang typical steppe in Inner Mongolia using generalized linear model[J]. Acta Agrestia Sinica, 2020,28(6):1711-1718.
[3] Fay P A, Prober S M, Harpole W S, et al. Grassland productivity limited by multiple nutrients[J]. Nature Plants, 2015,1(7):1-5.
[4] 巴哈提汗·比山.草原畜牧与生态环境保护存在的问题及改进措施[J].畜牧兽医科学(电子版), 2021,(13):194-195. Bahatihan Bishan. Problems and improvement measures of grassland animal husbandry and ecological environment protection in[J]. Graziery Veterinary Sciences (Electronic Version) 2021,(13):194-195.
[5] Riggs C E, Hobbie S E, Bach E M, et al. Nitrogen addition changes grassland soil organic matter decomposition[J]. Biogeochemistry, 2015,125:203-219.
[6] He J S, Wang L, Flynn D F B, et al. Leaf nitrogen: phosphorus stoichiometry across Chinese grassland biomes[J]. Oecologia, 2008, 155:301-310.
[7] Beeri O, Phillips R, Hendrickson J, et al. Estimating forage quantity and quality using aerial hyperspectral imagery for northern mixed- grass prairie[J]. Remote Sensing of Environment, 2007,110(2):216-225.
[8] Mutanga O, Adam E, Adjorlolo C, et al. Evaluating the robustness of models developed from field spectral data in predicting African grass foliar nitrogen concentration using WorldView-2image as an independent test dataset[J]. International Journal of Applied Earth Observation and Geoinformation, 2015,34:178-187.
[9] 王晶晶,孙玲,刘华周,等.基于高光谱的凤眼莲植株氮含量无损监测[J].江苏农业学报, 2014,30(4):752-757. Wang J J, Sun L, Liu H Z, et al. Non-destructive estimation of nitrogen concentration of water hyacinth based on hyperspectral reflectance[J]. Jiangsu Journal of Agricultural Sciences, 2014,30(4): 752-757.
[10] Bao N, Li W, Gu X, et al. Biomass estimation for semiarid vegetation and mine rehabilitation using worldview-3and sentinel-1SAR imagery[J]. Remote Sensing, 2019,11(23):2855.
[11] 田永超,杨杰,姚霞,等.利用叶片高光谱指数预测水稻群体叶层全氮含量[J].作物学报, 2010,36(9):1529-1537. Tian Y C, Yang J, Yao X, et al. Monitoring canopy leaf nitrogen concentration based on leaf hyperspectral indices in rice[J]. Acta Agronomica Sinica, 2010,36(9):1529-1537.
[12] 王念一,于丰华,许童羽,等.基于机器学习的粳稻叶片叶绿素含量高光谱反演建模[J].浙江农业学报, 2020,32(2):359-366. Wang N Y, Yu F H, Xu T Y, et al. Hyperspectral retrieval modelling for chlorophyll contents of japonica-rice leaves based on machine learning[J]. Acta Agriculturae Zhejiangensis, 2020,32(2):359-366.
[13] 冯海宽,樊意广,陶惠林,等.利用无人机高光谱影像的冬小麦氮含量监测[J].光谱学与光谱分析, 2023,43(10):3239-3246. Feng H K, Fan Y G, Tao H L, et al. Monitoring of nitrogen content in winter wheat based on UAV hyperspectral imagery[J]. Spectroscopy and Spectral Analysis, 2023,43(10):3239-3246.
[14] 孙法福,赖宁,耿庆龙,等.基于无人机高光谱影像的冬小麦叶片氮浓度遥感估测[J].干旱区研究, 2024,41(6):1069-1078. Sun F F, Lai N, Geng Q L, et al. Estimation of nitrogen contentration in winter wheat leaves based on hyperspectral images of UAV[J]. Arid Zone Research, 2024,41(6):1069-1078.
[15] Gao J, Meng B, Liang T, et al. Modeling alpine grassland forage phosphorus based on hyperspectral remote sensing and a multi-factor machine learning algorithm in the east of Tibetan Plateau, China[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2019,147:104-117.
[16] Wu N T, Liu G X, Yang Y, et al. Dynamic monitoring of net primary productivity and its response to climate factors in native grassland in Inner Mongolia using a light-use efficiency model[J]. Acta Prataculturae Sinica, 2020,29(11):1-10.
[17] Savitzky A, Golay E J M. Smoothing and differentiation of data by simplified least squares procedures.[J]. Anal Chem, 2002,36(8):1627-1639.
[18] Tucker C J. Red and photographic infrared linear combinations for monitoring vegetation[J]. Remote Sensing of Environment, 1979, 8(2):127-150.
[19] Huete A R. A soil-adjusted vegetation index (SAVI)[J]. Remote Sensing of Environment, 1988,25(3):295-309.
[20] Barnes E M, Clarke T, Richards S E, et al. Coincident detection of crop water stress, nitrogen status and canopy density using ground based multispectral data[C]. proceedings of the Proceedings of the fifth international conference on precision agriculture, Bloomington, MN, USA, 2000:1356.
[21] Rondeaux G, Steven M, Baret F. Optimization of soil-adjusted vegetation indices[J]. Remote sensing of environment, 1996,24: 109-127.
[22] Gitelson A A, Kaufman Y J, Merzlyak N M. Use of a green channel in remote sensing of global vegetation from EOS-MODIS[J]. Remote Sensing of Environment, 1996,58(3):289-298.
[23] Gitelson A A, Gritz Y, Merzlyak N M. Relationships between leaf chlorophyll content and spectral reflectance and algorithms for nondestructive chlorophyll assessment in higher plant leaves[J]. Journal of Plant Physiology, 2003,160(3):271-282.
[24] Rao R N, Garg K P, Ghosh K S, et al. Estimation of leaf total chlorophyll and nitrogen concentrations using hyperspectral satellite imagery[J]. The Journal of Agricultural Science, 2008,146(1):65-75.
[25] Jiang Z Y, Huete R A, Didan K, et al. Development of a two-band enhanced vegetation index without a blue band[J]. Remote Sensing of Environment, 2008,112(10):3833-3845.
[26] Peuelas J, Gamon J A, Fredeen A L, et al. Reflectance indices associated with physiological changes in nitrogen- and water-limited sunflower leaves[J]. Remote Sensing of Environment, 1994,48(2): 135-146.
[27] Gitelson A, Merzlyak M N. Spectral reflectance changes associated with autumn senescence of aesculus hippocastanum l. and acer platanoides l. leaves. spectral features and relation to chlorophyll estimation[J]. Journal of Plant Physiology, 1994,143(3):286-292.
[28] Schleicher T D, Bausch W C, Delgado J A, et al. Evaluation and refinement of the nitrogen reflectance index (nri) for site-specific fertilizer management. proceedings of the 2001ASAE Annual Meeting[C]. 1998.
[29] Gitelson A A, Merzlyak M N, Chivkunova O B. Optical properties and nondestructive estimation of anthocyanin content in plant leaves[J]. Photochemistry and Photobiology 2001,74(1):38-45.
[30] Sims A D, Gamon A J. Relationships between leaf pigment content and spectral reflectance across a wide range of species, leaf structures and developmental stages[J]. Remote Sensing of Environment, 2002,81(2): 337-354.
[31] Dash J, Curran J P. The MERIS terrestrial chlorophyll index[J]. International Journal of Remote Sensing, 2004,25(23):5403-5413.
[32] Haboudane D, Miller R J, Tremblay N, et al. Integrated narrow-band vegetation indices for prediction of crop chlorophyll content for application to precision agriculture[J]. Remote Sensing of Environment, 2002,81(2):416-426.
[33] Broge N, Leblanc E. Comparing prediction power and stability of broadband and hyperspectral vegetation indices for estimation of green leaf area index and canopy chlorophyll density[J]. Remote Sensing of Environment, 2001,76(2):156-172.
[34] Vincini M, Frazzi E, D'alessio P. Angular dependence of maize and sugar beet VIs from directional CHRIS/Proba data[C]. Proceedings of the Proc 4th Esa Chris proba Workshop, 2006.
[35] Huete A, Didan K, Miura T, et al. Overview of the radiometric and biophysical performance of the MODIS vegetation indices[J]. Remote Sensing of Environment, 2002,83(1):195-213.
[36] Wang X, Xu G, Feng Y, et al. Estimation model of rice aboveground dry biomass based on the machine learning and hyperspectral characteristic parameters of the canopy[J]. Agronomy, 2023,13(7):1940.
[37] Li C C, Chen P, Ma C Y, et al. Estimation of potato chlorophyll content using composite hyperspectral index parameters collected by an unmanned aerial vehicle[J]. International Journal of Remote Sensing, 2020,41(21):8176-8197.
[38] Kong B, Yu H, Du R, et al. Quantitative estimation of biomass of alpine grasslands using hyperspectral remote sensing[J]. Rangeland Ecology& Management, 2019,72(2):336-346.
[39] Zhang J C, Pu R L, Loraamm R W, et al. Comparison between wavelet spectral features and conventional spectral features in detecting yellow rust for winter wheat[J]. Computers and Electronics in Agriculture, 2014,100:79-87.
[40] Wang Z L, Chen J X, Fan Y F, et al. Evaluating photosynthetic pigment contents of maize using UVE-PLS based on continuous wavelet transform[J]. Computers and Electronics in Agriculture, 2020, 169:105160.
[41] Gu X, Wang Y, Sun Q, et al. Hyperspectral inversion of soil organic matter content in cultivated land based on wavelet transform[J]. Computers and Electronics in Agriculture, 2019,167:105053.
[42] Zhuang T, Zhang Y, Li D, et al. Coupling continuous wavelet transform with machine learning to improve water status prediction in winter wheat[J]. Precision Agriculture, 2023,24:2171-2129.
[43] Zhang J, Wang W, Qiao H, et al. Estimation of leaf nitrogen content in winter wheat based on continuum removal and discrete wavelet transform[J]. International Journal of Remote Sensing, 2023,44(18): 5523-5547.
[44] Huang Z, Turner B J, Dury S J, et al. Estimating foliage nitrogen concentration from HYMAP data using continuum removal analysis[J]. Remote Sensing of Environment, 2004,93(1/2):18-29.
[45] Tibshirani R. Regression shrinkage and selection via the lasso[J]. Journal of the Royal Statistical Society Series B: Statistical Methodology, 1996,58(1):267-288.
[46] Moghimi A, Pourreza A, Zuniga-Ramirez G, et al. A novel machine learning approach to estimate grapevine leaf nitrogen concentration using aerial multispectral imagery[J]. Remote Sensing, 2020,12(21):3515.
[47] Sudu B, Rong G, Guga S, et al. Retrieving SPAD values of summer maize using UAV hyperspectral data based on multiple machine learning algorithm[J]. Remote Sensing, 2022,14(21):5407.
[48] Cortes C, Vapnik V. Support-vector networks[J]. Machine learning, 1995,20:273-297.
[49] Mountrakis G, Im J, Ogole C. Support vector machines in remote sensing: A review[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2011,66(3):247-259.
[50] Atkinson P M, Tatnall A R. Introduction neural networks in remote sensing[J]. International Journal of Remote Sensing, 1997,18(4):699-709.
[51] Wang L, Chang Q, LI F, et al. Effects of growth stage development on paddy rice leaf area index prediction models[J]. Remote Sensing, 2019,11(3):361.
[52] Cover T, Hart P. Nearest neighbor pattern classification[J]. IEEE Transactions on Information Theory, 1967,13(1):21-27.
[53] Liu X, Zhang Z, Jiang T, et al. Evaluation of the effectiveness of multiple machine learning methods in remote sensing quantitative retrieval of suspended matter concentrations: A case study of Nansi Lake in North China[J]. Journal of Spectroscopy, 2021,2021:1-17.
[54] Yi Q X, Huang J F, Wang F M, et al. Monitoring rice nitrogen status using hyperspectral reflectance and artificial neural network[J]. Environmental Science& Technology, 2007,41(19):6770-6775.
[55] Alexander J, Hubert H, Ellen A H, et al. Investigating the potential of a newly developed UAV-Mounted VNIR/SWIR imaging system for monitoring crop traits—a case study for winter wheat[J]. Remote Sensing, 2021,13(9):1697.
[56] Stroppiana D, Fava F, Boschetti M, et al. Estimation of nitrogen content in herbaceous plants using hyperspectral vegetation indices[M]. Hyperspectral Indices and Image Classifications for Agriculture and Vegetation, 2019.
[57] Murray A B. Reducing model complexity for explanation and prediction[J]. Geomorphology, 2007,90(3/4):178-191.
[58] Clevers J G P W, Kooistra L. Using hyperspectral remote sensing data for retrieving total canopy chlorophyll and nitrogen content[C]. proceedings of the 20113rd Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing (WHISPERS), 2011.
[59] Chakraborty S K, Mahanti N K, Mansuri S M, et al. Non-destructive classification and prediction of aflatoxin-B1concentration in maize kernels using Vis-NIR (400~1000nm) hyperspectral imaging[J]. Journal of Food Science and Technology, 2021,58(2):437-450.
[60] Knox M N, Skidmore K A, Prins H H, et al. Remote sensing of forage nutrients: Combining ecological and spectral absorption feature data[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2012, 72(1):27-35.