您好,欢迎访问中国热带农业科学院 机构知识库!

Spatio-temporal prediction of leaf area index of rubber plantation using HJ-1A/1B CCD images and recurrent neural network

文献类型: 外文期刊

作者: Chen, Bangqian 1 ; Wu, Zhixiang 1 ; Wang, Jikun 1 ; Dong, Jinwei 2 ; Guan, Liming 1 ; Chen, Junming 1 ; Yang, Kai 3 ; Xie 1 ;

作者机构: 1.CATAS, Rubber Res Inst, Minist Agr, Danzhou Invest & Expt Stn Trop Cops, Danzhou 571737, Peoples R China

2.Univ Oklahoma, Ctr Spatial Anal, Dept Microbiol & Plant Biol, Norman, OK 73019 USA

3.China Fdn Poverty Alleviat, CFPA Microfinance, Dept Corp Affairs, Beijing 10086, Peoples R China

关键词: Leaf area index;Rubber plantation;HJ-1A/1B CCD;Recurrent neural network;NARX;Hainan Island

期刊名称:ISPRS JOURNAL OF PHOTOGRAMMETRY AND REMOTE SENSING ( 影响因子:8.979; 五年影响因子:9.948 )

ISSN:

年卷期:

页码:

收录情况: SCI

摘要: Rubber (Hevea brasiliensis) plantations are one of the most important economic forest in tropical area. Retrieving leaf area index (LA!) and its dynamics by remote sensing is of great significance in ecological study and production management, such as yield prediction and post-hurricane damage evaluation. Thirteen HJ-1A/1B CCD images, which possess the spatial advantage of Landsat TM/ETM+ and 2-days temporal resolution of MODIS, were introduced to predict the spatial-temporal LAI of rubber plantation on Hainan Island by Nonlinear AutoRegressive networks with exogenous inputs (NARX) model. Monthly measured LAIs at 30 stands by LAI-2000 between 2012 and 2013 were used to explore the LAI dynamics and their relationship with spectral bands and seven vegetation indices, and to develop and validate model. The NARX model, which was built base on input variables of day of year (DOY), four spectral bands and weight difference vegetation index (WDVI), possessed good accuracies during the model building for the data set of training (N = 202, R-2 = 0.98, RMSE = 0.13), validation (N = 43, R-2 = 0.93, RMSE = 0.24) and testing (N = 43, R-2 = 0.87, RMSE = 031), respectively. The model performed well during field validation (N = 24, R-2 = 0.88, RMSE = 0.24) and most of its mapping results showed better agreement (R-2 = 0.54-0.58, RMSE = 0.47-0.71) with the field data than the results of corresponding stepwise regression models (R-2 = 0.43-0.51, RMSE = 0.52-0.82). Besides, the LAI statistical values from the spatio-temporal LAI maps and their dynamics, which increased dramatically from late March (2.36 +/- 0.59) to early May (3.22 +/-. 0.64) and then gradually slow down until reached the maximum value in early October (4.21 +/- 0.87), were quite consistent with the statistical results of the field data. The study demonstrates the feasibility and reliability of retrieving spatio-temporal LAI of rubber plantations by an artificial neural network (ANN) approach, and provides some insight on the application of HJ-IA/1B CCD images, and data and methods for productivity study of rubber plantation in future. (C) 2014 Published by Elsevier B.V. on behalf of International Society for Photogrammetry and Remote Sensing, Inc. (ISPRS).

  • 相关文献

[1]Estimation of rubber stand age in typhoon and chilling injury afflicted area with Landsat TM data: A case study in Hainan Island, China. Chen, Bangqian,Wang, Jikun,Wu, Zhixiang,Tao, Zhongliang,Chen, Junmin,Yang, Chuan,Xie, Guishui,Chen, Bangqian,Wang, Jikun,Wu, Zhixiang,Tao, Zhongliang,Chen, Junmin,Yang, Chuan,Xie, Guishui,Cao, Jianhua. 2012

[2]Species Diversity in a Naturally Managed Rubber Plantation in Hainan Island, South China. Lan, Guoyu,Wu, Zhixiang,Chen, Bangqian,Xie, Guishui,Lan, Guoyu,Wu, Zhixiang,Chen, Bangqian,Xie, Guishui. 2017

[3]基于综合旱情指数的橡胶林干旱时空变化及其影响因子分析. 李海亮,戴声佩,罗红霞,李世池. 2017

[4]基于HJ-1A/1B CCD数据的海南岛水体提取研究. 李海亮,汪秀华,罗红霞,田光辉. 2016

[5]Mapping tropical forests and rubber plantations in complex landscapes by integrating PALSAR and MODIS imagery. Dong, Jinwei,Xiao, Xiangming,Sheldon, Sage,Biradar, Chandrashekhar,Xie, Guishui.

[6]Variations in Rhizosphere Microbial Communities of Rubber Plantations in Hainan Island, China. Guo, Hai-Chao,Wang, Wen-Bin,Luo, Xue-Hua,Wu, Xiao-Ping. 2013

[7]Change in Soil Microbial Community Compositions and Diversity Following the Conversion of Tropical Forest to Rubber Plantations in Xishuangbanan, Southwest China. Lan, Guoyu,Jatoi, Muhammad Tahir,Wu, Zhixiang,Xie, Guishui,Lan, Guoyu,Li, Yuwu,Wu, Zhixiang,Xie, Guishui,Lan, Guoyu,Wu, Zhixiang,Xie, Guishui,Jatoi, Muhammad Tahir,Tan, Zhenghong. 2017

[8]Soil Bacterial Diversity Impacted by Conversion of Secondary Forest to Rubber or Eucalyptus Plantations: A Case Study of Hainan Island, South China. Lan, Guoyu,Li, Yuwu,Wu, Zhixiang,Xie, Guishui.

[9]Sustainable Land Management Practices for Rubber Plantations in Mountainous Area of Hainan. Cha, ZZ,Lin, ZM,Luo, W,Li, SC,Luo, XH.

[10]Ethnobotanical study on medicinal plants around Limu Mountains of Hainan Island, China. Zheng, Xi-long,Wei, Jian-he,Li, Rong-tao,Zheng, Xi-long,Liu, Shou-bai,Dai, Hao-fu,Sun, Wei. 2013

[11]Object-Oriented Classification of Rubber Plantations from Landsat Satellite Imagery. Dai, ShengPei,Li, HaiLiang,Luo, HongXia,Li, MaoFen,Fang, JiHua,Wang, LingLing,Luo, Wei,Cao, JianHua. 2014

[12]Mapping deciduous rubber plantations through integration of PALSAR and multi-temporal Landsat imagery. Dong, Jinwei,Xiao, Xiangming,Jin, Cui,Biradar, Chandrashekhar,Dong, Jinwei,Xiao, Xiangming,Jin, Cui,Biradar, Chandrashekhar,Chen, Bangqian,Torbick, Nathan,Zhang, Geli.

[13]The Application of GIS in Analysis of Gross Agricultural Production: A Case Study of Hainan Island, China. Cao Zhenmu,Liu Ziji,Wang Dengfeng. 2014

[14]Laboratory virulence and field efficacy of different Heterorhabditis bacteriophora strains against Tetramoera schistaceana. Yue, Jianjun,Bai, Cheng,Long, Haibo,Yue, Jianjun,Bai, Cheng,Long, Haibo,Yue, Jianjun,Bai, Cheng,Long, Haibo,Yue, Jianjun,Bai, Cheng,Long, Haibo.

[15]Endangered Pteridophytes and Their Distribution in Hainan Island, China. Yang, Feng-chun,Zhang, Cui-Ling,Wu, Gang,Liang, Shu-yun,Yang, Feng-chun,Zhang, Cui-Ling,Wu, Gang,Liang, Shu-yun,Zhang, Xian-chun.

作者其他论文 更多>>