|本期目录/Table of Contents|

[1]林陈捷,刘振华,张小媛,等.基于红边指数的耕地质量遥感制图[J].江苏农业科学,2022,50(20):233-240.
 Lin Chenjie,et al.Remote sensing mapping of cultivated land quality based on red edge index[J].Jiangsu Agricultural Sciences,2022,50(20):233-240.
点击复制

基于红边指数的耕地质量遥感制图(PDF)
分享到:

《江苏农业科学》[ISSN:1002-1302/CN:32-1214/S]

卷:
第50卷
期数:
2022年第20期
页码:
233-240
栏目:
农业工程与信息技术
出版日期:
2022-10-20

文章信息/Info

Title:
Remote sensing mapping of cultivated land quality based on red edge index
作者:
林陈捷123刘振华123张小媛123胡月明12345刘洛123
1.华南农业大学资源环境学院,广东广州 510642; 2.广东省土地信息工程技术研究中心,广东广州 510642;3.广东省土地利用与整治重点实验室,广东广州 510642; 4.广州市华南自然资源科学技术研究院,广东广州 510642;5.海南大学热带作物学院,海南海口 570228
Author(s):
Lin Chenjieet al
关键词:
红边指数耕地质量变量筛选模型构建广州市遥感制图
Keywords:
-
分类号:
F323.211;S127
DOI:
-
文献标志码:
A
摘要:
耕地是农业生产的基本物质条件,耕地质量评价对耕地保护有重要意义。遥感技术的发展,为解决当前耕地质量评价周期长、效率低的问题带来了新思路。目前基于植被遥感指标的耕地质量评价的研究中,尚未考虑利用作物红边波段评价耕地质量。因此,本研究尝试建立红边指数(red edge index,REI)和耕地质量的光谱响应模型,从Sentinel-2影像中提取14个红边指数,并使用梯度提升树(gradient boosting decision tree,GBDT)算法结合方差膨胀因子(variance inflation factor,VIF)筛选对耕地质量敏感的最佳红边指数;利用偏最小二乘回归(partial least squares regression,PLSR)、岭回归(ridge regression,RR)和BP神经网络(back propagation neural network,BPNN)算法构建红边波段与耕地质量之间的光谱响应模型,比较3个模型的精度从而确定最佳模型,并结合Sentinel-2影像完成耕地质量制图。结果表明,REI-BPNN光谱响应模型为耕地质量最佳预测模型,其建模精度决定系数(R2)为0.70,归一化均方根误差(NRMSE)为10.00%,优于其他2种线性模型,其耕地质量的制图误差NRMSE为14.80%,对比前人研究有所提高,表明通过红边指数反演耕地质量具有较大的潜力,为耕地质量评价提供了新思路。
Abstract:
-

参考文献/References:

[1]李因帅,张颖,赵庚星,等. 鲁中南山丘区耕地地力的遥感反演模型与应用[J]. 农业工程学报,2020,36(23):269-278.
[2]张紫妍,苏友波,字春光,等. 耕地质量评价体系研究进展[J]. 安徽农业科学,2018,46(31):1-3,7.
[3]胡凤桂. 寿县主要耕作区耕地质量调查与评价[J]. 安徽农学通报,2020,26(13):119-123.
[4]李卓倩,赵贤妤,张莉坤,等. 基于LESA综合评价模型的耕地质量定级方法[J]. 水土保持研究,2020,27(4):363-367,375.
[5]Liu S S,Peng Y P,Xia Z Q,et al. The GA-BPNN-based evaluation of cultivated land quality in the PSR framework using Gaofen-1 satellite data[J]. Sensors,2019,19(23):5127.
[6]李因帅,赵庚星,王卓然,等. 基于SWCI-NDVI特征空间的县域耕地地力遥感反演[J]. 应用生态学报,2021,32(1):252-260.
[7]官炎俊,邹自力,张晓平,等. 基于归一化植被指数的耕地质量反演模型研究[J]. 土壤通报,2018,49(4):779-787.
[8]马佳妮,张超,吕雅慧,等. 基于长时间序列遥感数据反演NPP的耕地质量评价[J]. 农业机械学报,2019,50(1):202-208.
[9]Zhu M B,Liu S S,Xia Z Q,et al. Crop growth stage GPP-driven spectral model for evaluation of cultivated land quality using GA-BPNN[J]. Agriculture,2020,10(8):318.
[10]Xia Z Q,Peng Y P,Liu S S,et al. The optimal image date selection for evaluating cultivated land quality based on Gaofen-1 images[J]. Sensors,2019,19(22):4937.
[11]胡昊,白由路,杨俐苹,等. 不同氮营养冬小麦冠层光谱红边特征分析[J]. 植物营养与肥料学报,2009,15(6):1317-1323.
[12]Gitelson A A,Gritz Y,Merzlyak M N.Relationships between leaf chlorophyll content and spectral reflectance and algorithms for non-destructive chlorophyll assessment in higher plant leaves[J]. Journal of Plant Physiology,2003,160(3):271-282.
[13]Wu C Y,Niu Z,Tang Q,et al. Estimating chlorophyll content from hyperspectral vegetation indices:modeling and validation[J]. Agricultural and Forest Meteorology,2008,148(8/9):1230-1241.
[14]Dash J,Curran P J. Evaluation of the MERIS terrestrial chlorophyll index (MTCI)[J]. Advances in Space Research,2007,39( 1):100-104.
[15]Navarro G,Caballero I,Silva G,et al. Evaluation of forest fire on Madeira Island using Sentinel-2A MSI imagery[J]. International Journal of Applied Earth Observation and Geoinformation,2017,58:97-106.
[16]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.
[17]Zhang Z J,Liu M L,Liu X N,et al. A new vegetation index based on multitemporal Sentinel-2 images for discriminating heavy metal stress levels in rice[J]. Sensors,2018,18(7):2172.
[18]Guyot G,Baret F,Jacquemoud S. Imaging spectroscopy for vegetation studies[C]//Tosellli F,Bodechtel J. Imaging spectroscopy:Fundamentals and prospective applications,Dordrecht. The Nethelands: Kluwer Academic,1992:145-165.
[19]Xiao C W,Li P,Feng Z M,et al. Sentinel-2 red-edge spectral indices (RESI) suitability for mapping rubber boom in Luang Namtha Province,northern Lao PDR[J]. International Journal of Applied Earth Observation and Geoinformation,2020,93:102176.
[20]Carson N,Rosenbaum R S,Moscovitch M,et al. Self-referential processing improves memory for narrative information in healthy aging and amnestic Mild Cognitive Impairment[J]. Neuropsychologia,2019,134:107179.
[21]张宏鸣,刘雯,韩文霆,等. 基于梯度提升树算法的夏玉米叶面积指数反演[J]. 农业机械学报,2019,50(5):251-259.
[22]金秀,朱先志,李绍稳,等. 基于梯度提升树的土壤速效磷高光谱回归预测方法[J]. 激光与光电子学进展,2019,56(13):141-150.
[23]Salmerón Gómez R,García Pérez J,López Martín M D M,et al. Collinearity diagnostic applied in ridge estimation through the variance inflation factor[J]. Journal of Applied Statistics,2016,43(10):1831-1849.
[24]Kang J,Jin R,Li X,et al. Spatial upscaling of sparse soil moisture observations based on ridge regression[J]. Remote Sensing,2018,10(2):192.
[25]Li Z,Hu Y M,Wu Z,et al. Estimation methods for soil mercury content using hyperspectral remote sensing[J]. Sustainability,2018,10(7):2474-2487.
[26]吕雅慧,郧文聚,张超,等. 基于TOPSIS和BP神经网络的高标准农田综合识别[J]. 农业机械学报,2018,49(3):196-204.
[27]高玉明,张仁津. 基于遗传算法和BP神经网络的房价预测分析[J]. 计算机工程,2014,40(4):187-191.
[28]Razakamanarivo R H,Grinand C,Razafindrakoto M A,et al. Mapping organic carbon stocks in Eucalyptus plantations of the central highlands of Madagascar:a multiple regression approach[J]. Geoderma,2011,162(3/4):335-346.
[29]欧东璟. 基于多分类器融合的高光谱遥感图像分类[D]. 济南:山东大学,2019.
[30]Khosravi V,Doulati Ardejani F,Yousefi S,et al. Monitoring soil lead and zinc contents via combination of spectroscopy with extreme learning machine and other data mining methods[J]. Geoderma,2018,318:29-41.
[31]范峻恺,徐建刚. 基于神经网络综合建模的区域城市群发展脆弱性评价:以滇中城市群为例[J]. 自然资源学报,2020,35(12):2875-2887.

相似文献/References:

[1]马立军,陈召亚,杨哲.基于生态安全的耕地质量安全评价 ——以河北省卢龙县为例[J].江苏农业科学,2016,44(03):358.
 Ma Lijun,et al.Evaluation of cultivated land quality and safety based on ecological safety—Taking Lulong County of Hebei Province as an example[J].Jiangsu Agricultural Sciences,2016,44(20):358.
[2]叶达,吴克宁,赵华甫,等.不同限制因子组合区土壤改良对耕地质量等级的影响[J].江苏农业科学,2016,44(04):427.
 Ye Da,et al.Effect of soil improvement on arable land quality grade in different limiting factor combination zone[J].Jiangsu Agricultural Sciences,2016,44(20):427.
[3]魏洪斌,吴克宁,赵华甫,等.我国两大粮食主产区耕地等别空间分布特征分析[J].江苏农业科学,2016,44(01):443.
 Wei Hongbin,et al.Analysis of spatial distribution characteristics of cultivated land quality gradation of Chinas two main grain production areas[J].Jiangsu Agricultural Sciences,2016,44(20):443.
[4]匡丽花,叶英聪,赵小敏.南方水稻主产区土地整治区域耕地质量等级变化[J].江苏农业科学,2015,43(05):362.
 Kuang Lihua,et al.Cultivated land quality grade change of land reclamation area in main rice producing areas of southern China[J].Jiangsu Agricultural Sciences,2015,43(20):362.
[5]肖轶,尹珂.综合国土整治前后的耕地质量评价[J].江苏农业科学,2015,43(01):333.
 Xiao Yi,et al.Quality evaluation of cultivated land before and after integrated land consolidation—Taking Dalu Town of Chongqing City as an example[J].Jiangsu Agricultural Sciences,2015,43(20):333.
[6]陈学砧,高星,赵华甫.土地整治项目区耕地质量提升评价[J].江苏农业科学,2016,44(12):405.
 Chen Xuezhen,et al.Evaluation and study on arable land quality enhancement in land consolidation areas[J].Jiangsu Agricultural Sciences,2016,44(20):405.
[7]董莉莉,吴克宁,魏洪斌,等.我国中部粮食主产区耕地质量等别限制因素及提升对策[J].江苏农业科学,2016,44(12):419.
 Dong Lili,et al.Limiting factors and promotion strategies of cultivated land gradation in major grain producing areas of middle China[J].Jiangsu Agricultural Sciences,2016,44(20):419.
[8]戴文举,刘振杰,刘洛,等.近5年广东省耕地质量时空格局[J].江苏农业科学,2017,45(24):289.
 Dai Wenju,et al.Temporal and spatial pattern of cultivated land quality in Guangdong Province in recent five years[J].Jiangsu Agricultural Sciences,2017,45(20):289.
[9]张晗,郭熙,赵小敏.基于空间质量差异的县域耕地质量等别监测样点布局研究 ——以江西省南昌县为例[J].江苏农业科学,2018,46(02):190.
 Zhang Han,et al.Study on monitoring sample points distribution of county arable land quality grade based on space quality differences—Taking Nanchang County, Jiangxi Province as an example[J].Jiangsu Agricultural Sciences,2018,46(20):190.
[10]郭硕,魏明欢,简卿,等.县域耕地质量监测样点布设研究——以河北省昌黎县为例[J].江苏农业科学,2018,46(12):227.
 Guo Shuo,et al.Study on layout of sample points of cultivated land quality monitoring at county level—Taking Changli County of Hebei Province as an example[J].Jiangsu Agricultural Sciences,2018,46(20):227.

备注/Memo

备注/Memo:
收稿日期:2021-11-08
基金项目:国家重点研发计划(编号:2020YFD1100203);国家自然科学基金(编号:U1901601);广东省农业科技创新及推广项目(编号:2022KJ102)。
作者简介:林陈捷(1996—),男,广东湛江人,硕士研究生,主要从事土地监测和遥感技术研究。E-mail:1606432650@qq.com。
通信作者:胡月明,博士,教授,主要从事土地资源监测评价。E-mail:yueminghugis@163.com。
更新日期/Last Update: 2022-10-20