[1]孙新锋,王晶,王晶晶,等.基于Sentinel-2影像与参数优化的随机森林水稻种植分类提取方法[J].江苏农业学报,2026,42(02):325-336.[doi:doi:10.3969/j.issn.1000-4440.2026.02.011]
　SUN Xinfeng,WANG Jing,WANG Jingjing,et al.A method for rice cultivation classification and extraction using Sentinel-2 imagery and parameter-optimized random forest[J].,2026,42(02):325-336.[doi:doi:10.3969/j.issn.1000-4440.2026.02.011]
点击复制

基于Sentinel-2影像与参数优化的随机森林水稻种植分类提取方法()

江苏农业学报[ISSN:1006-6977/CN:61-1281/TN]

卷:
42
期数:
2026年02期
页码:
325-336
栏目:
农业信息工程
出版日期:
2026-02-28

文章信息/Info

Title:
A method for rice cultivation classification and extraction using Sentinel-2 imagery and parameter-optimized random forest
作者:
孙新锋1; 2; 3; 王晶2; 3; 王晶晶2; 3; 李楠2; 3; 任妮2; 3
(1.淮阴工学院计算机与软件工程学院,江苏淮安223003；2.江苏省农业科学院农业信息研究所,江苏南京210014；3.农业农村部长三角智慧农业技术重点实验室,江苏南京210014)
Author(s):
SUN Xinfeng1; 2; 3; WANG Jing2; 3; WANG Jingjing2; 3; LI Nan2; 3; REN Ni2; 3
(1.Faculty of Computer and Software Engineering, Huaiyin Institute of Technology, Huai’an 223003, China；2.Institute of Agricultural Information, Jiangsu Academy of Agricultural Sciences, Nanjing 210014, China；3.Key Laboratory of Smart Agricultural Technology (Yangtze River Delta), Ministry of Agriculture and Rural Affairs, Nanjing 210014, China)
关键词:
多光谱遥感; 水稻面积; 随机森林; Sentinel-2
Keywords:
multispectral remote sensing; rice planting area; random forest; Sentinel-2
分类号:
S127
DOI:
doi:10.3969/j.issn.1000-4440.2026.02.011
文献标志码:
A
摘要:
及时准确地获取大田水稻的种植面积有利于掌握水稻的种植规模、分布,为水稻生长动态监测、预测产量提供基础数据。有效挖掘水稻与其他地物的光谱波段特征是卫星遥感提取水稻种植面积的重要依据。本研究以江苏省镇江市为研究区,选用Sentinel-2卫星遥感影像,将递归特征消除和贝叶斯优化方法结合,分别构建了基于随机森林的水稻单时相(分蘖期)影像和两时相(分蘖期和扬花期)影像的种植面积提取模型,并进行了精度检验。结果表明,水稻单时相影像和两时相影像的种植面积提取模型的总体精度分别为97.39%和98.33%,Kappa系数分别为0.96和0.97。模型提取的水稻面积与实际水稻面积的对比结果表明，本模型可实现扬花期水稻面积高精度提取,同时使用两时相遥感影像构建的模型能够进一步提高分类以及水稻面积提取的精度。
Abstract:
Timely and accurate acquisition of paddy rice planting area is essential for assessing the cultivation scale and spatial distribution, thereby providing fundamental data for monitoring growth dynamics and predicting yield. The effective extraction of spectral band characteristics of rice and other ground objects is a significant basis for mapping rice planting areas using satellite remote sensing. This study focused on Zhenjiang City, Jiangsu province as the research area. Using Sentinel-2 satellite remote sensing imagery and combining recursive feature elimination (RFE) with Bayesian optimization, extraction models for rice planting area were constructed based on random forest, employing both single-temporal (tillering stage) and dual-temporal (tillering and flowering stages) imagery. Accuracy assessments were conducted. The results showed that the overall accuracies of the extraction models using single-temporal and dual-temporal imagery were 97.39% and 98.33%, with Kappa coefficients of 0.96 and 0.97, respectively. A comparison between the model-extracted rice area and the actual rice area indicated that this model can achieve high-precision extraction of rice area at the flowering stage. Furthermore, the model constructed using dual-temporal remote sensing imagery can further improve classification accuracy and the precision of rice area extraction.

参考文献/References:

[1]徐春春,纪龙,陈中督,等. 中国水稻生产、市场与进出口贸易的回顾与展望[J]. 中国稻米,2021,27(4):17-21.
[2]陈岳,寇卫利,李莹,等. 农作物遥感灾损评估研究进展[J]. 江苏农业科学,2022,50(16):12-20.
[3]李卫国,赵春江,王纪华,等. 基于卫星遥感的冬小麦拔节期长势监测[J]. 麦类作物学报,2007,27(3):523-527.
[4]潘力,夏浩铭,王瑞萌,等. 基于Google Earth Engine的淮河流域越冬作物种植面积制图[J]. 农业工程学报,2021,37(18):211-218.
[5]张宏,李卫国,张晓东,等. 基于HJ-1星和GF-1号影像融合特征提取冬小麦种植面积[J]. 中国农业科技导报,2024,26(2):109-119.
[6]金晶,毛星,张欣,等. 基于Sentinel-2影像的淡水养殖水生动物类型识别研究[J]. 河南农业科学,2022,51(4):160-170.
[7]王美月,万红,刘法军,等. 基于哨兵二号红边波段特征的作物分类[J]. 山东农业大学学报(自然科学版),2025,56(1):11-20.
[8]于天祥,樊红. 基于Sentinel-2多时相遥感影像的冬小麦种植面积监测[J]. 江苏农业学报,2024,40(9):1653-1661.
[9]孙庆松,张晓楠,陈利东,等. 基于Sentinel-2时序谐波特征的县域农作物分类[J]. 江苏农业学报,2022,38(4):967-975.
[10]娄轶峰,黄可,杨刚,等. 基于 Sentinel-2 时间序列数据的水稻分布提取方法[J]. 遥感学报,2025,29(5):1260-1272.
[11]NI R G, TIAN J Y, LI X J, et al. An enhanced pixel-based phenological feature for accurate paddy rice mapping with Sentinel-2 imagery in Google Earth Engine[J]. ISPRS Journal of Photogrammetry and Remote Sensing,2021,178:282-296.
[12]NIE H Z, LIN Y C, LUO W F, et al. Rice cropping sequence mapping in the tropical monsoon zone via agronomic knowledge graphs integrating phenology and remote sensing[J]. Ecological Informatics,2025,87:103075.
[13]JIANG Q, TANG Z G, ZHOU L H, et al. Mapping paddy rice planting area in Dongting lake area combining time series sentinel-1 and sentinel-2 images[J]. Remote Sensing,2023,15(11):2794.
[14]朱磊,张伟业,潘自林,等. 基于Sentinel-2的青铜峡灌区春小麦和苜蓿早期识别[J]. 灌溉排水学报,2024,43(5):86-94.
[15]YOU N S, DONG J W, HUANG J X, et al. The 10-m crop type maps in NorthEast China during 2017-2019[J]. Scientific Data,2021,8(1):41.
[16]ZHAN P, ZHU W Q, LI N. An automated rice mapping method based on flooding signals in synthetic aperture radar time series[J]. Remote Sensing of Environment,2021,252:112112.
[17]CHEN Y P, HU J, CAI Z W, et al. A phenology-based vegetation index for improving ratoon rice mapping using harmonized Landsat and Sentinel-2 data[J]. Journal of Integrative Agriculture,2024,23(4):1164-1178.
[18]HUANG S, TANG L N, HUPY J P, et al. A commentary review on the use of normalized difference vegetation index (NDVI) in the era of popular remote sensing[J]. Journal of Forestry Research,2021,32(1):1-6.
[19]SAN BAUTISTA A, FITA D, FRANCH B, et al. Crop monitoring strategy based on remote sensing data (Sentinel-2 and Planet),study case in a rice field after applying glycinebetaine[J]. Agronomy,2022,12(3):708.
[20]MUNYATI C. Detecting the distribution of grass aboveground biomass on a rangeland using Sentinel-2 MSI vegetation indices[J]. Advances in Space Research,2022,69(2):1130-1145.
[21]李元庆,宋宏利,刘欢,等. 基于Sentinel-2的江淮分水岭撂荒地提取[J]. 安徽农业科学,2025,53(3):47-52,76.
[22]BADRUL HISHAM N H, HASHIM N, SARAF N M, et al. Monitoring of rice growth phases using multi-temporal sentinel-2 satellite image[J]. IOP Conference Series:Earth and Environmental Science,2022,1051(1):012021.
[23]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.
[24]SEKERTEKIN A. A survey on global thresholding methods for mapping openwater body using sentinel-2 satellite imagery and normalized difference water index[J]. Archives of Computational Methods in Engineering,2021,28(3):1335-1347.
[25]陈健,李虎,刘玉锋,等. 基于Sentinel-2数据多特征优选的农作物遥感识别研究[J]. 自然资源遥感,2023,35(4):292-300.
[26]PEDREGOSA F, VAROQUAUX G, GRAMFORT A, et al. Scikit-learn:machine learning in Python[J]. The Journal of Machine Learning Research,2011,12:2825-2830.
[27]薛一阳,竞霞,叶启星,等. 利用约束随机森林和贝叶斯优化算法的小麦条锈病遥感监测[J]. 遥感技术与应用,2025,40(1):69-76.
[28]SNOEK J, LAROCHELLE H, ADAMS R P. Practical bayesian optimization of machine learning algorithms[J]. Advances in Neural Information Processing Systems,2012,25:2960-2968.
[29]SHAHRIARI B, SWERSKY K, WANG Z Y, et al. Taking the human out of the loop:a review of Bayesian optimization[J]. Proceedings of the IEEE,2016,104(1):148-175.
[30]SAMADZADEGAN F, TOOSI A, DADRASS JAVAN F. A critical review on multi-sensor and multi-platform remote sensing data fusion approaches:current status and prospects[J]. International Journal of Remote Sensing,2025,46(3):1327-1402.
[31]曹小鸿. 面向对象的遥感影像信息提取方法研究[J]. 测绘与空间地理信息,2022,45(5):116-119,123.
[32]BHATTI M A, SYAM M S, CHEN H F, et al. Utilizing convolutional neural networks (CNN) and U-Net architecture for precise crop and weed segmentation in agricultural imagery:a deep learning approach[J]. Big Data Research,2024,36:100465.

相似文献/References:

[1]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,(02):1060.[doi:10.3969/j.issn.1000-4440.2016.05.018]
[2]巫明焱,董光,税丽,等.基于Landsat 8影像的济宁市春季主要作物种植面积变化监测[J].江苏农业学报,2018,(03):559.[doi:doi:10.3969/j.issn.1000-4440.2018.03.012]
　WU Ming-yan,DONG Guang,SHUI Li,et al.Change detection of main spring crops area in Jining based on Landsat 8 images[J].,2018,(02):559.[doi:doi:10.3969/j.issn.1000-4440.2018.03.012]
[3]夏俊,苏涛,刘丽娜,等.基于多时相Sentinel-1A数据的水稻面积提取[J].江苏农业学报,2022,38(03):666.[doi:doi:10.3969/j.issn.1000-4440.2022.03.012]
　XIA Jun,SU Tao,LIU Li-na,et al.Rice area information extraction based on multi-temporal Sentinel-1A data[J].,2022,38(02):666.[doi:doi:10.3969/j.issn.1000-4440.2022.03.012]

备注/Memo

备注/Memo:
收稿日期：2025-05-21基金项目：江苏省重点研发计划(现代农业)项目(BE2023303)；江苏省农业科技自主创新基金项目[CX(23)3006]；高分辨率对地观测系统国家科技重大专项(74-Y50G12-9001-22/23)作者简介：孙新锋(1999-),男,河南周口人,硕士研究生,研究方向为农业遥感信息技术及应用。(E-mail)19937696739@163.com通讯作者：王晶,(E-mail)wjnj1108@jaas.ac.cn
更新日期/Last Update: 2026-03-16