首页 >  , Vol. , Issue () : -

摘要

全文摘要次数: 225 全文下载次数: 308
引用本文:

DOI:

10.11834/jrs.20211070

收稿日期:

2021-02-08

修改日期:

2021-05-16

PDF Free   EndNote   BibTeX
基于物候窗口和多源中高分辨率影像的稻虾田提取方法研究
魏浩东1, 杨靖雅1, 蔡志文1, 陈云坪2, 张馨予1, 徐保东1, 胡琼3
1.华中农业大学 资源与环境学院 宏观农业研究院;2.华中农业大学 植物科学技术学院;3.华中师范大学 城市与环境科学学院
摘要:

由于显著的经济效益和生态效益,近年来稻虾共作模式分布面积迅猛扩张。准确获取稻虾田空间分布信息,对于水稻种植结构调整、产量估算和水资源管理具有重要意义。本文以“小龙虾之乡”—湖北省潜江市为研究区域,基于Google Earth Engine平台协同Landsat 7/8和Sentinel-2卫星数据,通过分析稻虾田的农业耕作管理和季相节律特征,提取了稻虾田区别其他农作物的关键“水淹”信号和“植被”信号。基于实地稻虾田样本统计分析关键特征的阈值,构建稻虾田规则集识别模型,提取了湖北省潜江市2019年稻虾田空间分布。最后,基于实地样本验证该物候窗口特征方法的精度,并评估和比较了该方法与随机森林和基于水体季相差异方法的表现。结果表明:物候窗口1月1日~4月30日内的水淹信号(LSWI > NDVI或EVI)、物候窗口7月15日~9月30日内的植被信号(NDVI或EVI > LSWI)和物候窗口11月10日~12月31日内的水淹信号是稻虾田遥感识别的典型特征。基于该方法提取的2019年潜江市稻虾田制图精度和用户精度分别为90.74%、 94.69%,显著高于水体季相差异方法和随机森林方法的精度。基于关键物候窗口的稻虾田提取方法具有较高的泛化能力,能以较少的实地样本进行时空尺度的延展,从而为大尺度长时序稻虾田遥感制图提供重要的方法支撑。

Rice-crayfish mapping based on phenology windows and integrations of multi-source medium/high resolution images
Abstract:

Rice-crayfish co-culture is a kind of comprehensive ecological agriculture pattern. Due to the outstanding ecological and economic benefits, rice-crayfish has been expanded rapidly in China in the past decade. The accurate spatial distribution information for this newly emerging agricultural pattern is of great significance for growth monitoring, yield estimation and water resources management. However, at present, most researches focused on the field-level research of farmland ecosystem, the rice-crayfish mapping at regional or larger scale received less attention. In this study, Qianjiang City in Hubei Province, known as the "Hometown of Crayfish" was selected as the test area. The cloud computing approach was used for all the available Landsat 7/8 and Sentinel-2 imagery in 2019 with the Google Earth Engine (GEE) platform. Based on the analysis of farming characteristics and spectral curves of rice-crayfish fields, we identified the crucial phenology windows and classification features (i.e. flooding signal and vegetation signal) for rice-crayfish mapping. Based on the key phenological characteristics and associated frequency thresholds derived from field samples, we developed a rule-based algorithm for rice-crayfish mapping and generated the rice-crayfish map in Qianjiang City in 2019. In addition, to further evaluate the potential of our proposed method, we compared it with the random forest method and a method based on seasonal difference of water body. The spectral analysis of time series images showed that the unique phenological characteristics of rice-crayfish co-culture were flooding signal (LSWI > NDVI or LSWI > EVI) in phenology window 1 (from January 1 to April 30), vegetation signal (NDVI > LSWI or EVI > LSWI) in phenology window 2 (from July 15 to September 30) and flooding signal in phenology window 3 (from November 10 to December 31). With the mapping result, the total area of rice-crayfish planting in Qianjiang City in 2019 was estimated to 575.58 km2 and rice-crayfish were mainly distributed in the southwest. The producer’s accuracy of the classification result was 90.74%, the user’s accuracy was 94.69%, and the overall accuracy was 95.23%. The method based on phenology window features showed less commission errors when compared to the random forest, and less omission errors when compared to the method based on water seasonal difference. Moreover, among the three methods, the proposed method presented the highest overall classification accuracy. Based on phenology windows, flooding signal and vegetation signal, the rice-crayfish mapping method shows high separability. Because of the strong physical interpretation for the rice-crayfish, the method based on phenology windows can be easily generalized to other regions and other images. On one hand, this method has relatively low dependence on training samples. On the other hand, as long as the key phenology window can be obtained, other medium-high resolution images, such as GF-1 and GF-6, can achieve high-accuracy mapping results of rice-crayfish. Therefore, the method based on the phenology window can be effectively extended to a larger area and a longer time series, providing essential information for rice production management and the decision-making of crayfish industry.

本文暂时没有被引用!

欢迎关注学报微信

遥感学报交流群 分享按钮