[1]洪国军,张灵,付仙兵,等.基于GEE的多源遥感影像特征优选方法的水稻种植区信息提取[J].江苏农业学报,2025,(06):1159-1168.[doi:doi:10.3969/j.issn.1000-4440.2025.06.012]
　HONG Guojun,ZHANG Ling,FU Xianbing,et al.Feature selection of multi source remote sensing images based on GEE for rice planting area information extraction[J].,2025,(06):1159-1168.[doi:doi:10.3969/j.issn.1000-4440.2025.06.012]
点击复制

基于GEE的多源遥感影像特征优选方法的水稻种植区信息提取()
分享到：

江苏农业学报[ISSN:1006-6977/CN:61-1281/TN]

卷:
期数:
2025年06期
页码:
1159-1168
栏目:
农业信息工程
出版日期:
2025-06-30

文章信息/Info

Title:
Feature selection of multi source remote sensing images based on GEE for rice planting area information extraction
作者:
洪国军1; 张灵1; 付仙兵1; 喻彩丽2
(1.江西科技学院区域发展研究院,江西南昌330200；2.汕尾职业技术学院海洋学院,广东汕尾516600)
Author(s):
HONG Guojun1; ZHANG Ling1; FU Xianbing1; YU Caili2
(1.Regional Development Research Institute, Jiangxi University of Technology, Nanchang 330200, China;2.School of Marine Science and Technology, Shanwei Institute of Technology, Shanwei 516600, China)
关键词:
多源遥感; 水稻; 江西省; 特征优选; 随机森林法
Keywords:
multi-source remote sensing; rice; Jiangxi province; feature selection; random forest method
分类号:
TP79;S127
DOI:
doi:10.3969/j.issn.1000-4440.2025.06.012
文献标志码:
A
摘要:
多时相Sentinel-1/2数据在识别和监测复杂山地丘陵地区和多云多雨环境下的水稻种植信息方面具有显著优势,为水稻识别提供丰富的信息。然而,过多的特征变量可能会导致维度灾难和信息冗余。本研究采用特征优选的方法,利用Sentinel-1/2的多光谱、多时相数据,评估5种特征组合方案（光谱特征、光谱特征+植被指数、光谱特征+植被指数+纹理特征、光谱特征+植被指数+纹理特征+雷达信息、特征优选）对水稻种植区域的识别精度,并分析其在空间制图精度上的表现。研究结果表明,结合特征优选的方案5在水稻识别中表现最优,总体精度为92.60%,Kappa系数达0.903 0,F1分数为92.40%。与《江西统计年鉴》2024年水稻种植面积数据比较,方案5对江西省的水稻面积估算精度高达98.73%,相对误差较方案1～方案4显著降低。本研究结果证实综合应用多源遥感数据和多时相特征优选方法能有效减少数据冗余,提高水稻面积提取的准确性和精确度。
Abstract:
Multi-temporal Sentinel-1/2 data demonstrate significant advantages in identifying and monitoring rice cultivation in complex mountainous and hilly areas, as well as in cloudy and rainy environments, which provide rich information for rice identification. However, an excessive number of feature variables may lead to dimensional disasters and information redundancy. In this study, a feature selection method was employed to evaluate the recognition accuracy of five feature combination schemes (spectral features, spectral features + vegetation indices, spectral features + vegetation indices + texture features, spectral features + vegetation indices + texture features + radar information, and feature selection) for rice cultivation area, using Sentinel-1/2 multi-spectral and multi-temporal data. The spatial mapping accuracy of each scheme was also analyzed. The results indicated that Scheme five, which incorporated feature selection, performed the best in rice identification, with an overall accuracy of 92.60%, a Kappa coefficient of 0.903 0, and an F1 score of 92.40%. Compared with the rice cultivation area data in 2024 from the Jiangxi Statistical Yearbook, Scheme five achieved a high accuracy of 98.73% in estimating the rice area in Jiangxi province, with a significantly lower relative error compared to Scheme one-Scheme four. The results of this study confirm that the integrated application of multi-source remote sensing data and multi-temporal feature selection methods can effectively reduce data redundancy and enhance the accuracy and precision of rice area extraction.

参考文献/References:

[1]钟钰,王曦照,巴雪真,等. 全方位夯实粮食安全根基:战略内涵、现实制约与突破路径[J]. 农业经济与管理,2024(1):12-22.
[2]刘通,任鸿瑞. GEE平台下利用物候特征进行面向对象的水稻种植分布提取[J]. 农业工程学报,2022,38(12):189-196.
[3]HUANG D, XU L J, ZOU S L, et al. Mapping paddy rice in rice-wetland coexistence zone by integrating sentinel-1 and sentinel-2 data[J]. Agriculture,2024,14(3):345.
[4]ZHANG T, TANG B H, HUANG L, et al. Rice and greenhouse identification in plateau areas incorporating Sentinel-1/2 optical and radar remote sensing data from google earth engine[J]. Remote Sensing, 2022, 14(22): 5727.
[5]蔡玉林,刘照磊,孟祥磊,等. 基于HRNet和自注意力机制的多源遥感影像水稻提取[J]. 农业工程学报,2024,40(4):186-193.
[6]于飞,吕争,隋正伟,等. 基于特征优选的多时相SAR数据水稻信息提取方法[J]. 农业机械学报,2023,54(3):259-265,327.
[7]甘聪聪,邱炳文,张建阳,等. 基于Sentinel-1/2动态耦合移栽期特征的水稻种植模式识别[J]. 地球信息科学学报,2023,25(1):153-162.
[8]WALEED M, MUBEEN M, AHMAD A, et al. Evaluating the efficiency of coarser to finer resolution multispectral satellites in mapping paddy rice fields using GEE implementation[J]. Scientific Reports,2022,12(1):13210.
[9]TARIQ A, YAN J G, GAGNON A S, et al. Mapping of cropland,cropping patterns and crop types by combining optical remote sensing images with decision tree classifier and random forest[J]. Geo-spatial Information Science,2023,26(3):302-320.
[10]CHOUDHARY K, SHI W, DONG Y, et al. Random forest for rice yield mapping and prediction using Sentinel-2 data with google earth engine[J]. Advances in Space Research,2022,70(8):2443-2457.
[11]姚园,毋亭,李一凡,等. 基于水稻物候参数及面向对象算法的稻田识别[J]. 农业工程学报,2024,40(11):150-158.
[12]李恒凯,贺明华,王秀丽. 时序SAR与光学影像的南方丘陵区水稻种植识别[J]. 测绘科学,2023,48(5):78-86.
[13]LIU Y F, XIAO D Q, YANG W T. An algorithm for early rice area mapping from satellite remote sensing data in southwestern Guangdong in China based on feature optimization and random forest[J]. Ecological Informatics,2022,72:101853.
[14]SUN B, QIN P Y, LI C L, et al. Integrating vegetation phenological characteristics and polarization features with object-oriented techniques for grassland type identification[J]. Geo-spatial Information Science,2024,27(3):794-810.
[15]ZHAO G B, WANG L, ZHENG J H, et al. Optimized extraction method of fruit planting distribution based on spectral and radar data fusion of key time phase[J]. Remote Sensing,2023,15(17):4140.
[16]TRIVEDI M B, MARSHALL M, ESTES L, et al. Cropland mapping in tropical smallholder systems with seasonally stratified sentinel-1 and sentinel-2 spectral and textural features[J]. Remote Sensing,2023,15(12):3014.
[17]曾学亮,郭熙,钟亮,等. 基于多源遥感特征融合与卷积神经网络(CNN)的丘陵地区水稻识别[J]. 江苏农业学报,2024,40(1):93-102.
[18]孟浩然,李存军,郑翔宇,等. 综合光谱纹理和时序信息的油茶遥感提取研究[J]. 光谱学与光谱分析,2023,43(5):1589-1597.
[19]CHENG G, DING H, YANG J, et al. Crop type classification with combined spectral,texture,and radar features of time-series Sentinel-1 and Sentinel-2 data[J]. International Journal of Remote Sensing,2023,44(4):1215-1237.
[20]王李娟,孔钰如,杨小冬,等. 基于特征优选随机森林算法的农耕区土地利用分类[J]. 农业工程学报,2020,36(4):244-250.
[21]LYU Y, FENG W, WANG S, et al. An ensemble-based framework for sophisticated crop classification exploiting google earth engine[J]. Remote Sensing,2024,16(5):917.
[22]HUANG C H, YOU S, LIU A X, et al. High-resolution national-scale mapping of paddy rice based on sentinel-1/2 data[J]. Remote Sensing,2022,15:4055.
[23]潘建平,安新永,崔伟,等. 基于GEE平台的水稻种植范围识别研究:以黑龙江省为例[J]. 测绘地理信息,2024,49(3):101-106.
[24]张征云,江文渊,张彦敏,等. 基于哨兵SAR数据和多光谱数据的水稻识别研究[J]. 生态与农村环境学报,2023,39(4):556-564.
[25]高心怡,池泓,黄进良,等. 水稻遥感制图研究综述[J]. 遥感学报,2024,28(9):2144-2169.
[26]SUAREZ L A, ROBSON A, BRINKHOFF J. Early-Season forecasting of citrus block-yield using time series remote sensing and machine learning:a case study in Australian orchards[J]. International Journal of Applied Earth Observation and Geoinformation,2023,122:103434.
[27]陈媛媛,郭莹莹,魏翀,等. 基于多源时序遥感影像和GEE的滨海湿地分类与比较[J]. 长江流域资源与环境,2024,33(8):1691-1701.
[28]乔树亭,叶回春,黄文江,等. 基于Sentinel-1/2影像的水稻种植面积提取方法研究:以三江平原为例[J]. 遥感技术与应用,2023,38(1):78-89.
[29]FANG W J, ZHU H F, LI S, et al. Rapid identification of main vegetation types in the lingkong mountain nature reserve based on multi-temporal modified vegetation indices[J]. Sensors,2023,23(2):659.
[30]MENG H R, LI C J, LIU Y, et al. Corn land extraction based on integrating optical and SAR remote sensing images[J]. Land,2023,12(2):398.
[31]张馨予,蔡志文,杨靖雅,等. 时序滤波对农作物遥感识别的影响[J]. 农业工程学报,2022,38(4):215-224.
[32]钟怡琪,李家国,韩杰,等. 基于哨兵影像与多特征优选的溧阳市上兴镇水稻识别[J]. 江苏农业学报,2023,39(8):1688-1697.
[33]CLAUSS K, OTTINGER M, KNZER C. Mapping rice areas with Sentinel-1 time series and superpixel segmentation[J]. International Journal of Remote Sensing,2018,39(5):1399-1420.
[34]ZAFAR Z, ZUBAIR M, ZHA Y Y, et al. Performance assessment of machine learning algorithms for mapping of land use/land cover using remote sensing data[J]. The Egyptian Journal of Remote Sensing and Space Sciences,2024,27(2):216-226.

相似文献/References:

[1]王士磊,丁正权,黄海祥.水稻隐性早熟突变体ref早熟性的遗传分析和基因定位[J].江苏农业学报,2016,(04):721.[doi:10.3969/j.issn.100-4440.2016.04.001]
　WANG Shi-lei,DING Zheng-quan,HUANG Hai-xiang.Inheritance and gene mapping of recessive earliness in rice (Oryza sativa L.)[J].,2016,(06):721.[doi:10.3969/j.issn.100-4440.2016.04.001]
[2]王在满,郑乐,张明华,等.不同播种方式对直播水稻倒伏指数和根系生长的影响[J].江苏农业学报,2016,(04):725.[doi:10.3969/j.issn.100-4440.2016.04.002]
　WANG Zai-man,ZHENG Le,ZHANG Ming-hua,et al.Effects of seeding manners on lodging index and root growth of directseeded rice[J].,2016,(06):725.[doi:10.3969/j.issn.100-4440.2016.04.002]
[3]易能,薛延丰,石志琦,等.微囊藻毒素对水稻种子萌发和幼苗生长的胁迫作用[J].江苏农业学报,2016,(04):729.[doi:10.3969/j.issn.100-4440.2016.04.003]
　YI Neng,XUE Yan-feng,SHI Zhi-qi,et al.Inhibitory effect of microcystins on seed germination and seedling growth of rice[J].,2016,(06):729.[doi:10.3969/j.issn.100-4440.2016.04.003]
[4]刘凯,王爱民,严国红,等.一个水稻显性矮秆突变体的遗传特性与降株高能力[J].江苏农业学报,2016,(05):968.[doi:10.3969/j.issn.1000-4440.2016.05.002]
　LIU Kai,WANG Ai-min,YAN Guo-hong,et al.Genetic analysis and plant height reduction of a dominant dwarf mutant of rice[J].,2016,(06):968.[doi:10.3969/j.issn.1000-4440.2016.05.002]
[5]王红,杨镇,裴文琪,等.功能性微生物制剂对镉胁迫下水稻生长及生理特性的影响[J].江苏农业学报,2016,(05):974.[doi:10.3969/j.issn.1000-4440.2016.05.003]
　WANG Hong,YANG Zhen,PEI Wen-qi,et al.Growth and physiological characteristics of cadmium-stressed rice influenced by functional microorganism agent[J].,2016,(06):974.[doi:10.3969/j.issn.1000-4440.2016.05.003]
[6]孙玲,单捷,毛良君,等.基于遥感和Moran's I指数的水稻面积变化空间自相关性研究[J].江苏农业学报,2016,(05):1060.[doi:10.3969/j.issn.1000-4440.2016.05.017]
　SUN Ling,SHAN Jie,MAO Liang-jun,et al.Spatial autocorrelation of changes in paddy rice area based on remote sensing and Moran’s I index[J].,2016,(06):1060.[doi:10.3969/j.issn.1000-4440.2016.05.017]
[7]张晓忆,李卫国,景元书,等.多种光谱指标构建决策树的水稻种植面积提取[J].江苏农业学报,2016,(05):1060.[doi:10.3969/j.issn.1000-4440.2016.05.018]
　ZHANG Xiao-yi,LI Wei-guo,JING Yuan-shu,et al.Extraction of paddy rice area by constructing the decision tree with multiple spectral indices[J].,2016,(06):1060.[doi:10.3969/j.issn.1000-4440.2016.05.018]
[8]裔传灯,李玮,王德荣,等.水稻GW5基因的1212-bp Indel变异对粒形的影响[J].江苏农业学报,2016,(06):1201.[doi:doi:10.3969/j.issn.1000-4440.2016.06.001]
　YI Chuan-deng,LI Wei,WANG De-rong,et al.Effect of 1212-bp Indel variation of gene GW5 on rice grain shape[J].,2016,(06):1201.[doi:doi:10.3969/j.issn.1000-4440.2016.06.001]
[9]刘红江,陈虞雯,张岳芳,等.不同播栽方式对水稻叶片光合特性及产量的影响[J].江苏农业学报,2016,(06):1206.[doi:doi:10.3969/j.issn.1000-4440.2016.06.002]
　LIU Hong-jiang,CHEN Yu-wen,ZHANG Yue-fang,et al.Effects of planting pattern on leaf photosynthetic characteristics and yield of rice[J].,2016,(06):1206.[doi:doi:10.3969/j.issn.1000-4440.2016.06.002]
[10]郭保卫,许轲,魏海燕,等.钵苗机插水稻茎秆的抗倒伏能力[J].江苏农业学报,2016,(06):1280.[doi:doi:10.3969/j.issn.1000-4440.2016.06.014]
　GUO Bao-wei,XU Ke,WEI Hai-yan,et al.Culm lodging resistance characteristics of bowl seedling mechanical-transplanting rice[J].,2016,(06):1280.[doi:doi:10.3969/j.issn.1000-4440.2016.06.014]

备注/Memo

备注/Memo:
收稿日期：2024-10-10作者简介：洪国军(1995-),男,江西乐平人,硕士研究生,研究方向为遥感与数字农业。(E-mail)hgj950603@163.com通讯作者：喻彩丽,(E-mail)purejade@163.com
更新日期/Last Update: 2025-07-16