基于多时相遥感影像的水稻种植信息提取

来源:用户上传      作者:张红华 赵威成 刘强凯

　　摘要 获取水稻种植信息对于指导水稻生产，监测作物生长及合理分配水资源具有重要意义。针对基于单时相影像提取水稻信息精度有限，以Sentinel-2A/B多时相影像为数据源，构建NDVI、EVI、NDWI和光谱特征4种时序特征数据集并设计6种试验方案，结合随机森林算法对水稻种植信息进行提取。结果表明，NDVI、EVI时序曲线可以较好反映出水稻生育期的物候特征，不同地类的光谱时序曲线和NDWI时序曲线可分离度较高，有利于提高分类精度;基于NDVIr序数据集的分类精度最低，基于光谱时序数据集的分类精度最高，总体精度达95.559 0%，Kappa系数为0.943 3，与基于NDVI的分类结果相比，总体精度、Kappa系数、水稻生产者精度和用户精度分别提高了3.530 4%、0.044 9、8.64%和3.36%，水稻与旱地的混分现象得到有效抑制。该研究为区域水稻种植信息精确提取在数据源选择、时序特征构建方面提供了一种新的思路和技术手段。
　　关键词 Sentinel-2A/B;多时相;时序特征;水稻
　　中图分类号 S127 文献标识码 A 文章编号 0517-6611（2022）07-0234-05
　　doi：10.3969/j.issn.0517-6611.2022.07.056
　　开放科学（资源服务）标识码（OSID）：
　　Rice Planting Information Extraction Based on Multi-temporal Remote Sensing Images
　　ZHANG Hong-hua， ZHAO Wei-cheng， LIU Qiang-kai
　　（Heilongjiang University of Science and Technology， Harbin， Heilongjiang 150022）
　　Abstract Obtaining rice planting information is of great significance for guiding rice production， monitoring crop growth and rational allocation of water resources. In view of the limited accuracy of extracting rice information based on single temporal image， four time-series feature data sets of NDVI， EVI， NDWI and spectral features were created based on sentinel-2A/B multi-temporal images. Six experimental schemes were designed to extract rice planting information combined with random forest algorithm. The results showed that NDVI and EVI time series could better reflect the phenological characteristics of rice growth period， and the spectral time series and NDWI time series of different land types had a high degree of separation， which was conducive to improve the classification accuracy;the classification accuracy based on NDVI time series dataset was the lowest， and the classification accuracy based on spectral time series dataset was the highest， the overall accuracy was 95.559 0%， and the Kappa coefficient was 0.943 3. Compared with the classification results based on NDVI， the overall accuracy， Kappa coefficient， rice producer accuracy and user accuracy were improved by 3.530 4%， 0.044 9， 8.64% and 3.36%， respectively. And the mixing of rice and dry land was effectively controlled. This research provided a new idea and technical means for accurate extraction of regional rice planting information in data sources selection and time series feature construction.
　　Key words Sentinel-2A/B;Multi-temporal;Timing characteristics;Rice
　　准确获取区域水稻种植结构信息，对于作物产量估计、种植结构调整具有重要意义[1]。与传统的田间调查与统计汇总方法相比，利用遥感技术提取作物种植结构，更加直观和准确[2]。水稻常与背景信息在空间上相互交错，由水稻植株、水体和土壤的混合地物组成，这种组合的季相变换带来的光谱信息差异可作为区分水稻田和其他地物的重要依据。作物生育期内，仅基于单时相影像难以将水稻与其他作物区分，可利用多时相影像获取作物的时间序列特征来提取水稻信息。以往研究多是通过构建归一化植被指数（Normalized Difference Vegetation Index，NDVI）时序数据集来进行作物的提取，如利用MODIS NDVI时间序列实现作物的识别[3-5]，基于Sentinel-2[6-8]或GF-1[9-11]数据构建NDVI时间序列，基于多源影像构建NDVI时间序列等[12]。然而，目前利用多时相数据进行水稻提取多局限于构建NDVI时序数据，对其他时序特征很少关注和研究。鉴于此，笔者以黑龙江省五常市龙凤山镇为研究区，利用作物整个生育期内的多时相Sentinel-2A/B遥感影像构建4种不同的时间序列特征，包括光谱特征、归一化植被指数、增强植被指数（Enhanced vegetation index，EVI）、归一化水体指数（Normalized difference water index，NDWI）;同时设计6种时序特征组合方案，结合随机森林分类方法提取水稻空间分布信息，以期提高区域尺度的水稻种植信息的提取精度，为精准农情监测提供参考。

nlc202204211519

转载注明来源:https://www.xzbu.com/1/view-15429077.htm