摘要
在较大范围中更准确地提取小微湿地,对于进一步加强生态文明建设具有重要意义。本文结合物候特征与合成孔径雷达SAR(Synthetic Aperture Radar)影像特性建立了湿地的分类体系,并运用MultiRocket-RF时序分类模型,基于地物在不同物候期对Sentinel-1雷达波束的散射差异实现湿地提取;此外,在以5 hm^(2)为面积阈值界定小微湿地的基础上,提出了一种缓解湿地斑块粘连问题的方法,以减少小微湿地被误分为非小微湿地;最后,以长三角生态绿色一体化发展示范区为例,分析与验证了小微湿地提取模型的有效性。结果表明:(1)SAR时序数据与MultiRocket-RF多元时序分类模型的结合能够较好地适应基于物候的湿地分类体系,对各类湿地的提取效果优良,总体精度达93.6%,Kappa系数达0.888,Macro-F1得分达0.804,尤其对于小微湿地中的淹水草本与木本植被、季节性淹没区的提取更具优势;(2)对湿地斑块粘连问题的缓解能够提升对小微湿地的提取精度,虽然Kappa系数没有显著变化,但Macro-F1得分由0.798提升至0.804,且混淆矩阵中各类小微湿地的提取准确率整体更优;(3)模型较适用于提取1 hm^(2)以上的小微湿地,而由于斑点噪声、几何失真等影响,对于1 hm^(2)以下小微湿地提取的效果欠佳。综上,本研究拓展了SAR数据应用领域,也为小微湿地的提取提供了一种新的技术思路。
Accurately extracting small wetlands over large areas is of great significance for enhancing the efficiency of wetland monitoring and conservation,as well as further promoting ecological civilization construction.From the perspective of phenology,this study first established a classification system for wetlands,including permanent water bodies,flooded herbaceous vegetation,flooded woody vegetation,seasonal inundation areas,and paddy fields,based on the characteristics of Synthetic Aperture Radar(SAR)images.It then constructed the time series of backscatter coefficients and coherence coefficients from Sentinel-1 VV and VH polarization modes.Subsequently,the MultiRocket-RF time series classification model was applied to extract wetlands on the basis of the scattering differences of radar beams from various land cover types during different phenological periods.In addition,by using 5 hm^(2)as an area threshold to divide small and large wetlands,this study proposed a morphological method to alleviate the problem of wetland patch adhesion and reduce the misclassification of small wetlands as large wetlands.Finally,considering the natural attribute of extensive wetlands and floodplains,as well as the social development characteristic of being committed to exploring new mechanisms for sustainable development,this work selected the Yangtze River Delta Ecological Green Integrated Development Demonstration Area as the study area and the entire year of 2021 as the sample period.By comparing the performance of the models across various data sources and different sizes of small wetlands,this study analyzed and verified the effectiveness of the proposed small wetland extraction method,which combines SAR time-series images with the MultiRocket-RF model.Results are as follows(1)The combination of SAR time-series data and MultiRocket-RF time series classification model could better adapt to the phenology-based wetland classification system in comparison with other methods and had excellent performance in extracting various types of wetlands.The overall accuracy reached 93.6%,the Kappa coefficient reached 0.888,and the macro-F1 score reached 0.804.The model was particularly advantageous for identifying flooded herbaceous vegetation,flooded woody vegetation,and seasonal submerged areas in small wetlands.(2)The problem of wetland patch adhesion could be effectively alleviated by applying moderate morphological dilation and erosion to sever small,narrow,and connected wetland patches,leading to an improvement in the accuracy of small wetland extraction.Although the Kappa coefficient did not change significantly,the macro-F1 score increased from 0.798 to 0.804,and the extraction accuracy for various small wetlands in the confusion matrix was generally great.(3)The model presented in this paper was suitable for extracting small wetlands larger than 1 hm^(2).However,owing to the speckle noise,geometric distortion,and other negative effects caused by the side-looking characteristics and imaging principles of SAR satellites,the performance in extracting wetlands smaller than 1 hm²was suboptimal,with a significant deviation from the true distribution.This study not only expanded the application fields of SAR data but also provided a new technical idea for the extraction of small wetlands,which contributes to further promoting the refined and holistic development of wetland ecological conservation and scientific management.
作者
俞钦平
林文鹏
史怡雯
YU Qinping;LIN Wenpeng;SHI Yiwen(School of Environmental and Geographical Sciences,Shanghai Normal University,Shanghai 200234,China;Yangtze River Delta Urban Wetland Ecosystem National Field Scientific Observation and Research Station,Shanghai 200234,China)
出处
《遥感学报》
北大核心
2025年第9期2841-2857,共17页
NATIONAL REMOTE SENSING BULLETIN
基金
上海市自然科学基金(编号:23ZR1446700)。
