Smart-Phone Application in Situ Grassland Biomass Estimation
TAO HaiYu,, ZHANG AiWu,, PANG HaiYang, KANG XiaoYanCenter for Geographic Environment Research and Education, Capital Normal University/Key Laboratory of 3D Information Acquisition and Application, Ministry of Education, Capital Normal University, Beijing 100048
Abstract 【Objective】Biomass is the material and energy basis of grassland ecosystem and the most basic ecological parameter. In the past, the quantitative grassland biomass retrieval based on aerospace and aerial remote sensing was too specialized to be popularized among herders. Therefore, this paper proposed a method for estimating grassland biomass by using true color images taken on the phone near the ground, and constructing a grassland biomass estimation model, which provided a theoretical basis and technical support for herders to easily, quickly and non-destructively grasp the growth of grassland in their own pasture. 【Method】 Firstly, the feature sets of grassland biomass estimation were constructed based on vegetation index, texture features and combined vegetation index and texture features by using the ultra-high resolution true color images of mobile phones. Secondly, in order to prevent dimensional disaster caused by excessive feature extraction, this paper proposed a feature selection algorithm (XGB-SFS) that combined XGBoost and sequence forward selection to perform feature selection and optimal subset construction. Finally, random forest regression and leave-one-out cross-validation were used to compare the biomass estimation effects of different feature sets to build models, and analyze the role of different types of features and XGB-SFS algorithm in grassland AGB estimation.【Result】 (1) Compared with the model constructed by single-type features, the estimation model based on spatial texture features (R2 = 0.76) was better than the estimation model based on spectral vegetation index (R2 = 0.73), indicating that texture features had a certain role in the ultra-high-resolution grassland AGB estimation; (2) Compared with the model after feature selection, the combined spatial spectrum multi-type feature construction model was superior to any single-type feature model (R2 = 0.83, RMSE = 127.57 g·m -2, MAE= 81.25 g·m -2), indicating that multi-type feature construction model could improve the accuracy of grassland AGB estimation to a certain extent. (3) Comparing the models building before and after feature selection, the model after feature selection by estimating the AGB effect was significantly better than the model without feature selection, and there was a high correlation between the selected features and grassland biomass, indicating that XGB-SFS could reduce the data dimension and improve the accuracy of grassland AGB estimation.【Conclusion】The ultra-high-resolution true color images of mobile phones could accurately estimate the grassland biomass. The XGB-SFS algorithm proposed in this paper could also select the features with high correlation with the grassland biomass from many features and improve the model estimation accuracy. Compared with the previous professional remote sensing quantitative inversion of grassland biomass, this method had the advantages of facing the public, low cost, and easy to use. The study combined the data collected on the phone with remote sensing and machine learning methods, which could open up new perspectives and support the development of agricultural informatization. Keywords:biomass;smart-phone;texture features;XGBoost;grassland
PDF (2035KB)元数据多维度评价相关文章导出EndNote|Ris|Bibtex收藏本文 本文引用格式 陶海玉, 张爱武, 庞海洋, 康孝岩. 智能手机原位牧草生物量估算[J]. 中国农业科学, 2021, 54(5): 933-944 doi:10.3864/j.issn.0578-1752.2021.05.006 TAO HaiYu, ZHANG AiWu, PANG HaiYang, KANG XiaoYan. Smart-Phone Application in Situ Grassland Biomass Estimation[J]. Scientia Acricultura Sinica, 2021, 54(5): 933-944 doi:10.3864/j.issn.0578-1752.2021.05.006
由于本文样本数量不多,为保证模型稳定性和可靠性,在训练过程中采用留一法交叉验证(LOOCV)获得预测结果。27个样本数据,每次取其中26个样本建模,1个做预测,如此反复27次得到27个预测结果与原始数据进行精度验证。采用常用的决定系数(coefficient of determination,R2)、均方根误差(root mean square error,RMSE)、平均绝对误差(mean absolute error,MAE)来评价模型的拟合效果。一般来说R2越高,RMSE和MAE数值越小模型预测越准确。本文技术流程如图2所示。
(a)原始植被指数模型,(b)原始纹理特征模型,(c)原始联合植被指数-纹理特征模型,(d)XGB-SFS特征选择植被指数模型,(e)XGB-SFS特征选择纹理特征模型,(f)XGB-SFS特征选择联合植被指数-纹理特征模型。下同 Fig. 5Comparison of measured and predicted values in six experiments
(a) RGBVIs, (b)Textures, (c)VI-Textures, (d)Selected RGBVIs, (e)Selected Textures, (f)Selected VI-Textures. The same as below
ANH B, LIF, ZHAOM L, LIUY J. Optimized spectral indices based estimation of forage grass biomass Spectroscopy and Spectral Analysis, 2015,35(11):3155-3160. (in Chinese) [本文引用: 1]
YAOX C, QUT T, CHANGW J, YINJ, LIY J, SUNZ Z, ZENGH. Estimation of grassland biomass using MODIS data and plant community characteristics. Chinese Journal of Eco-Agriculture, 2017,25(4):530-541. (in Chinese) [本文引用: 1]
LIH, LIA N, YING F, NANX, BIANJ H. Retrieval of grassland aboveground biomass through inversion of the prosail model with modis imagery , 2019,11(13):1597. [本文引用: 1]
SUNS Z, WANGC J, YINX J, WANGW Q, LIUW, ZHANGY, ZHAOQ Z. Estimating aboveground biomass of natural grassland based on multispectral images of unmanned aerial vehicles Journal of Remote Sensing, 2017,22(5):848-856. (in Chinese) [本文引用: 1]
LUSSEMU, BOLTENA, GNYPM L, JASPERJ, BARETHG. Evaluation of RGB-based vegetation indices from UAV imagery to estimate forage yield in grassland//The ISPRS Technical Commission III Midterm Symposium on “Developments, Technologies and Applications in Remote Sensing” , 2018: 5. [本文引用: 1]
YUEJ, YANGG, TIANQ J, FENGH K, XUK J, ZHOUC Q. Estimate of winter-wheat above-ground biomass based on UAV ultrahigh-ground-resolution image textures and vegetation indices , 2019,150:226-244. [本文引用: 1]
WUB F, ZHANGX, ZENGH W, ZHANGM, TIANF Y. Big data methods for environmental data Bulletin of the Chinese Academy of Sciences, 2018,33(8):804-811. (in Chinese) [本文引用: 1]
SHANJ. Remote sensing: From trained professionals to general public Acta Geodaetica et Cartographica Sinica, 2017,46(10):1434-1446. (in Chinese) [本文引用: 1]
SONGD J, ZHANGC M, YANGX X, LIF, HANY J, GAOS, DONGH Y. Extracting winter wheat spatial distribution information from gf-2 image Journal of Remote Sensing, 2018,24(5):596-608. (in Chinese) [本文引用: 1]
ZHANGZ J, LIA N, BIANJ H, ZHAOW, NANX, JINH A, TANJ B, LEIG B, XIAH M, YANGY S, SUNM J. Estimating aboveground biomass of grassland in zoige by visible vegetation index derived from unmanned aerial vehicle image Remote Sensing Technology and Application, 2016,31(1):51-62. (in Chinese) URL [本文引用: 1]
ZHANGL X, CHENY Q, LIY X, MAJ C, DUK M, ZHENGF X, SUNZ F. Estimating above ground biomass of winter wheat at early growth stages based on visual spectral Spectroscopy and Spectral Analysis, 2019,39(8):2501-2506. (in Chinese) URL [本文引用: 1]
ZHANGA W, ZHANGS, GUOC F, LIUL L, HUS X, CHAIS T. Grass biomass inversion based on Landsat 8 spectral derived data classification system Spectroscopy and Spectral Analysis, 2020,40(1):239-246. (in Chinese) [本文引用: 1]
BASTINJ, POLOSANM, PIALLATB, KRACKP, BOUGEROLT, CHABARDESS, DAVIDO. Changes of oscillatory activity in the subthalamic nucleus during obsessive-compulsive disorder symptoms: Two case reports , 2014,60:145-150. URL [本文引用: 1]
KELSEYK, NEFFJ. Estimates of aboveground biomass from texture analysis of Landsat imagery , 2014,6(7):6407-6422. [本文引用: 1]
LIJ, VEERANAMPALAYAMSIVAKUMARA, BHATTAM, GARSTN D, STOLLH, BAENZIGERP S, BELAMKARV, HOWARDR, GEY F, SHIY Y. Principal variable selection to explain grain yield variation in winter wheat from features extracted from UAV imagery , 2019,15(1):1-13. [本文引用: 1]
LIUC, YANGG J, LIZ H, TANGF Q, WANGJ W, ZHANGC L, ZHANGL Y. Biomass estimation in winter wheat by UAV spectral information and texture information fusion Scientia Agricultura Sinica, 2018,51(16):3060-3073. (in Chinese) URL [本文引用: 1]
WANGN, LIQ Z, DUX, ZHANGY, ZHAOL C, WANGH Y. Identification of main crops based on the univariate feature selection in Subei Journal of Remote Sensing, 2017,21(4):519-530. (in Chinese) [本文引用: 1]
Department of Animal Husbandry and Veterinary Medicine, Ministry of Agriculture of the People's Republic of China and National Animal Husbandry and Veterinary Station. China Grassland Resources. Beijing: China Science and Technology Press, 1996. (in Chinese) [本文引用: 1]
WOEBBECKED M, MEYERG E, VONBARGEN K, MORTENSEND A. Color indices for weed identification under various soil, residue, and lighting conditions , 1995,38(1):259-269.
SELLAROR, CREPYM, TRUPKINS A, KARAYEKOVE, BUCHOVSKYA S, ROSSIC, CASALJ J. Cryptochrome as a sensor of the Blue/Green ratio of natural radiation in Arabidopsis , 2010,154(1):401-409. URLPMID:20668058
PENUELASJ, GAMONJ A, GRIFFINK L, FIELDC B. Assessing community type, plant biomass, pigment composition, and photosynthetic efficiency of aquatic vegetation from spectral reflectance , 1993,46(2):110-118.
HUNTE R, CAVIGELLIM A, DAUGHTRYC S T, MCMURTREYJ E, WALTHALLC L. Evaluation of digital photography from model aircraft for remote sensing of crop biomass and nitrogen status , 2005,6(4):359-378. URL
HAGUET, TILLETTN D, WHEELERH. Automated crop and weed monitoring in widely spaced cereals , 2006,7(1):21-32. URL
BENDIGJ, YUK, AASENH, BOLTENA, BENNERTZS, BROSCHEITJ, GNYPM L, BARETHG. Combining UAV-based plant height from crop surface models, visible, and near infrared vegetation indices for biomass monitoring in barley , 2015,39:79-87.
VERRELSTJ, SCHAEPMANM E, KOETZB, KNEUBUHLERM. Angular sensitivity analysis of vegetation indices derived from CHRIS/PROBA data , 2008,112(5):2341-2353.
MEYERG E, NETOJ C. Verification of color vegetation indices for automated crop imaging applications , 2008,63(2):282-293.
WANGX Q, WANGM M, WANGS Q, WUY D. Extraction of vegetation information from visible unmanned aerial vehicle images Transactions of the Chinese Society of Agricultural Engineering, 2015,31(5):152-159. (in Chinese) URL
GITELSONA A, KAUFMANY J, STARKR, RUNDQUISTD. Novel algorithms for remote estimation of vegetation fraction , 2002,80(1):76-87.
HUANGX. Multiscale texture and shape feature extraction and object-oriented classification for very high resolution remotely sensed imagery [D]. Wuhan: Wuhan University, 2009. (in Chinese) [本文引用: 1]
HARALICKR M, SHANMUGAMK, DINSTEINI H. Textural features for image classification , 1973 (6):610-621. [本文引用: 1]
SARKERL R, NICHOLJ E. Improved forest biomass estimates using ALOS AVNIR-2 texture indices , 2011,115(4):968-977. URL [本文引用: 1]
ZHANGA W, DONGZ, KANGX Y. Feature selection algorithms of airborne LiDAR combined with hyperspectral images based on XGBoost Chinese Journal of Lasers, 2019,46(4):0404003. (in Chinese) [本文引用: 1]
WANGL A, MAC, ZHOUX D, ZIY, ZHUX K, GUOW S. Estimation of wheat leaf SPAD value using RF algorithmic model and remote sensing data Transactions of the Chinese Society for Agricultural Machinery, 2015,46(1):259-265. (in Chinese) [本文引用: 1]
ZHAOJ, LIZ M, LUL Q, JIAP, YANGH B, LANY B. Weed identification in maize field based on multi-spectral remote sensing of unmanned aerial vehicle Scientia Agricultura Sinica, 2020,53(8):1545-1555. (in Chinese) URL [本文引用: 1]
ZHENGH, CHENGT, ZHOUM, LID, YAOX, TIANY C, ZHUY. Improved estimation of rice aboveground biomass combining textural and spectral analysis of UAV imagery , 2019,20(3):611-629. [本文引用: 1]
LIUY, LIUS, LIJ, GUOX Y, WANGS Q, LUJ W. Estimating biomass of winter oilseed rape using vegetation indices and texture metrics derived from UAV multispectral images , 2019,166:105026. [本文引用: 1]
SIBANDAM, MUTANGAO, ROUGETM, KUMARL. Estimating biomass of native grass grown under complex management treatments using worldview-3 spectral derivatives , 2017,9(1):55. [本文引用: 1]
American Society for Photogrammetry and Remote Sensing. Manual of Remote Sensing ., 1999. [本文引用: 1]
CHOM A, SKIDMOREA, CORSIF, WIERENS E V, SOBHANI. Estimation of green grass/herb biomass from airborne hyperspectral imagery using spectral indices and partial least squares regression , 2007,9(4):414-424. URL [本文引用: 1]
LIM S, TANY, PANJ, PENGS K. Modeling forest aboveground biomass by combining the spectrum, textures with topographic features Remote Sensing Information, 2006,2006(6):6-9. (in Chinese) [本文引用: 1]
ECKERTS. Improved forest biomass and carbon estimations using texture measures from WorldView-2 satellite data , 2012,4(4):810-829. [本文引用: 1]
CHENP, FENGH K, LIC C, YANGG J, YANGJ S, YANGW P, LIUS 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) URL [本文引用: 1]