[1]喻彩丽,陆健强,窦旭峰,等.基于GEE的多源遥感影像青梅种植信息提取[J].江苏农业学报,2024,(08):1455-1463.[doi:doi:10.3969/j.issn.1000-4440.2024.08.010]
　YU Caili,LU Jianqiang,DOU Xufeng,et al.Extraction of greengage planting information from multi-source remote sensing images based on GEE[J].,2024,(08):1455-1463.[doi:doi:10.3969/j.issn.1000-4440.2024.08.010]
点击复制

基于GEE的多源遥感影像青梅种植信息提取()
分享到：

江苏农业学报[ISSN:1006-6977/CN:61-1281/TN]

卷:
期数:
2024年08期
页码:
1455-1463
栏目:
农业信息工程
出版日期:
2024-08-30

文章信息/Info

Title:
Extraction of greengage planting information from multi-source remote sensing images based on GEE
作者:
喻彩丽1; 陆健强2; 窦旭峰3; 洪国军4
(1.汕尾职业技术学院海洋学院,广东汕尾516600；2.华南农业大学电子工程学院(人工智能学院),广东广州510642；3.塔里木大学生命科学与技术学院,新疆阿拉尔843300；4.江西科技学院区域发展研究院,江西南昌330200)
Author(s):
YU Caili1; LU Jianqiang2; DOU Xufeng3; HONG Guojun4
(1.College of Ocean, Shanwei Institute of Technology, Shanwei 516600, China;2.College of Electronic Engineering & College of Artificial Intelligence, South China Agricultural University, Guangzhou 510642, China;3.College of Life Science and Technology, Tarim University, Alaer 843300, China;4.Institute of Regional Development, Jiangxi University of Technology， Nanchang 330200, China)
关键词:
青梅; 多源遥感; 随机森林算法; Google Earth Engine
Keywords:
greengage; multi-source remote sensing; random forest algorithm; Google Earth Engine
分类号:
S127；Q949.758.6
DOI:
doi:10.3969/j.issn.1000-4440.2024.08.010
文献标志码:
A
摘要:
针对粤东青梅种植区多为山地、丘陵兼有的复杂地形,实地测量青梅种植面积及其空间分布存在一定难度,本研究聚焦广东省汕尾市和揭阳市,利用Sentinel-1和Sentinel-2多光谱遥感影像数据,采用随机森林算法,探索4种不同特征组合在青梅分类精度方面的表现,并对Sentinel-1、Sentinel-2影像在空间制图中的精度进行了深入分析。研究结果表明,Sentinel-1、Sentinel-2影像采用组合4（光谱特征+植被指数+VV/VH+纹理特征）并运用随机森林算法获得了最优青梅分类精度,总体精度、Kappa系数和制图精度分别高达96.55%、0.957 6和98.03%；与官方统计数据相比,在揭阳市普宁市和汕尾市陆河县应用组合4估算青梅种植面积的精度分别高达99.70%和99.20%。研究发现,综合利用Sentinel-1、Sentinel-2多源遥感数据和多种特征的分类方法可以精准识别青梅的种植面积并提高制图精度。本研究结果不仅为粤东地区青梅种植者提供准确的种植面积估算和空间分布信息,而且为青梅种植管理和病虫害防治策略的制定提供技术参考。
Abstract:
The planting area of greengage in eastern Guangdong is mostly a complex terrain with both mountains and hills. It is difficult to measure the planting area and spatial distribution of greengage in the field. This study focused on Shanwei City and Jieyang City, and used the random forest algorithm to explore the performance of four different feature combinations in the classification accuracy of greengage based on Sentinel-1 and Sentinel-2 multi-spectral remote sensing image data. In addition, the accuracy of Sentinel-1 and Sentinel-2 images in spatial mapping was analyzed in depth. The results showed that the optimal classification accuracy of greengage was obtained when Sentinel-1 and Sentinel-2 images were processed by combination 4 (spectral feature + vegetation index + VV/VH + texture feature) and random forest algorithm. The overall accuracy, Kappa coefficient and mapping accuracy were 96.55%, 0.957 6 and 98.03%, respectively. Compared with the official statistics, the accuracy of estimating the planting area of greengage by using combination 4 in Puning City of Jieyang City and Luhe County of Shanwei City was 99.70% and 99.20%, respectively. The comprehensive utilization of Sentinel-1 and Sentinel-2 multi-source remote sensing data and the classification methods using multiple features could accurately identify the planting area of greengage and improve the mapping accuracy. The results of this study not only provide accurate planting area estimation and spatial distribution information for greengage growers in eastern Guangdong, but also provide technical reference for the formulation of greengage planting management and pest control strategies.

参考文献/References:

[1]吴和原,方书远,方凯华,等. 青梅优良新株系——普宁矮白梅的选育报告[J]. 中国南方果树,2001(4):39.
[2]马红雨,李仙岳,孙亚楠,等. 基于无人机遥感的不同控释肥夏玉米SPAD差异性[J]. 排灌机械工程学报,2023,41(12):1261-1267.
[3]李长春,翟伟广,王春阳,等. 基于Sentinel-1A影像的原阳县玉米和水稻分类时间窗选择[J]. 江苏农业学报,2023,39(2):413-422.

[4]JIA K, WU B F, LI Q Z. Crop classification using HJ satellite multispectral data in the North China Plain[J]. Journal of Applied Remote Sensing,2013,7(1):73576.
[5]XU F, LI Z F, ZHANG S Y, et al. Mapping winter wheat with combinations of temporally aggregated Sentinel-2 and Landsat-8 data in Shandong Province, China[J]. Remote Sensing,2020,12(12):2065.
[6]姚金玺,肖成志,张志,等. 基于GEE多源遥感数据的干旱区植被地物类型提取[J]. 干旱区研究,2024,41(1):157-168.
[7]张颖,何贞铭,吴贞江. 基于多源遥感影像的农作物分类提取[J]. 山东农业大学学报(自然科学版),2021,52(4):615-618.
[8]胡春霞,聂翔宇,林聪,等. 利用多特征协同深度网络的高分遥感影像分类[J]. 测绘通报,2023(10):74-79,104.
[9]姚金玺,王浪,李建忠,等. 青海诺木洪地区多源遥感及多特征组合地物分类[J]. 农业工程学报,2022,38(3):247-256.
[10]王文静,张霞,赵银娣,等. 综合多特征的Landsat 8时序遥感图像棉花分类方法[J]. 遥感学报,2017,21(1):115-124.
[11]孟月波,王菲,刘光辉,等. 多元特征提取与表征优化的遥感多尺度目标检测[J]. 光学精密工程,2023,31(16):2465-2482.
[12]卢献健,张焕铃,晏红波,等. 协同Sentinel-1/2多特征优选的甘蔗提取方法[J]. 自然资源遥感,2024,36(1):86-94.
[13]关士英,袁占良,谢传节. 基于多特征的高分时序冬小麦提取研究[J]. 地理空间信息,2020,18(5):14-19,6.
[14]HAO P Y, ZHAN Y L, SHAKIR M. Feature selection of time series MODIS data for early crop classification using random forest:a case study in Kansas, USA[J]. Remote Sensing,2015,7(5):5347-5369.
[15]洪国军,周保平,李明哲,等. 基于GEE的Landsat-8与Sentinel-2影像在棉花种植提取中差异性分析及提取方法对比研究[J]. 江苏农业科学,2024,52(4):223-230.
[16]王春玲,樊怡琳,庞勇,等. 基于GEE与Sentinel-2影像的落叶针叶林提取[J]. 北京林业大学学报,2023,45(8):1-15.
[17]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.
[18]张悦琦,任鸿瑞. 融合特征优选与随机森林算法的GF-6影像东北一季稻遥感提取[J]. 遥感学报,2023,27(9):2153-2164.
[19]范莉,王妍,祝好,等. 多种光谱指数联合地形特征对复杂地形区主要粮食作物种植面积的遥感识别[J]. 中国农业气象,2023,44(9):845-856.
[20]梁锦涛,陈超,孙伟伟,等. 长时序Landsat和GEE云平台的杭州湾土地利用/覆被变化时空格局演变[J]. 遥感学报,2023,27(6):1480-1495.
[21]赵月,孟丹,丁凤,等. 基于GEE云平台的2000-2022年雄安新区生态质量动态评价[J]. 地球物理学进展,2023,38(5):2023-2036.
[22]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.
[23]王振兴,刘东，王敏. 基于GEE平台和多维特征优选的粮食作物提取——以西辽河流域为例[J]. 江苏农业科学,2023,51(21):200-208.
[24]吕伟,宋轩,杨欢. 基于深度学习和多源遥感数据的玉米种植面积提取[J]. 江苏农业科学, 2023,51(23):171-178.
[25]闫柏琨,甘甫平,印萍,等. 1989-2021年中国大陆海岸带潮滩、海岸线、养殖水体遥感观测[J]. 自然资源遥感,2023,35(3):53-63.
[26]ZHANG L, ZHANG Z, LUO Y, et al. Integrating satellite-derived climatic and vegetation indices to predict smallholder maize yield using deep learning[J]. Agricultural and Forest Meteorology,2021,311:108666.
[27]梁晨欣,黄启厅,王思,等. 基于多时相遥感植被指数的柑橘果园识别[J]. 农业工程学报,2021,37(24):168-176.
[28]王建步,张杰,马毅,等. 基于高分一号WFV卫星影像的黄河口湿地草本植被生物量估算模型研究[J]. 激光生物学报,2014,23(6):604-608.
[29]JABRI K A, AL-MULLA Y A, MELGANI F, et al. Remote sensing analysis for vegetation assessment of a Large-Scale constructed wetland treating produced water polluted with oil hydrocarbons[J]. Remote Sensing,2023,15(24):5632.
[30]MARCO V. PlanetScope, Sentinel-2, and sentinel-1 data integration for object-based land cover classification in Google Earth Engine[J]. Remote Sensing,2022,14(11):2628.
[31]潘胜权,陈凯,解印山,等. 基于多纹理特征融合的麦田收割边界检测[J]. 农业工程学报,2023,39(12):123-131.

相似文献/References:

[1]林子晶,李卫国,申双和,等.ＨＪ 星和 ＧＦ１ 号数据在水稻种植面积提取中的应用ＨＪ 星和 ＧＦ１ 号数据在水稻种植面积提取中的应用[J].江苏农业学报,2016,(01):111.[doi:10.3969/j.issn.1000-4440.2016.01.017 ]
　LIN Zi-jing,LI Wei-guo,SHEN Shuang-he,et al.Application of HJ and GF1 image data to extract rice planting area[J].,2016,(08):111.[doi:10.3969/j.issn.1000-4440.2016.01.017 ]
[2]王兴娜,汪晶,黄午阳,等.青梅果实不同极性组分的抗氧化活性[J].江苏农业学报,2016,(01):211.[doi:10.3969/j.issn.1000-4440.2016.01.033 ]
　WANG Xing-na,WANG Jing,HUANG Wu-yang,et al.Antioxidative activities of different polar extracts from Prunus mume fruits[J].,2016,(08):211.[doi:10.3969/j.issn.1000-4440.2016.01.033 ]

备注/Memo

备注/Memo:
收稿日期：2024-03-23基金项目：广东省普通高校重点领域专项(2021ZDZX4111)；国家自然科学基金地区基金项目(42061046)作者简介：喻彩丽(1989-),女,河南周口人,硕士研究生,讲师,研究方向为遥感与数字农业。(E-mail)purejade@163.com通讯作者：洪国军,(E-mail)hgj950603@163.com
更新日期/Last Update: 2024-09-18