基于归一化雷达特征的南方丘陵区水稻提取研究

doi:10.19754/j.nyyjs.20260730002

摘要/Abstract

摘要： 水稻是我国主要作物之一，国家对粮食安全高度重视，准确提取水稻空间分布至关重要。南方地区是全国种植水稻主要地区，但南方多丘陵地带，地块偏破碎化，且南方丘陵地区受云雨天气影响，稠密长时序光学遥感数据获取困难，现有研究大多依赖于传统方法和水稻生长经验，未准确捕捉水稻的关键物候期，并且很少聚焦到南方丘陵区进行水稻提取。针对以上问题，本文结合 Sentinel-1SAR 数据和 Sentinel-2 数据识别水稻淹水信号，构建动态阈值窗口来确定淹水期，提取雷达 VH 和 VV 后向散射系数归一化特征（NMTCvv/NMTCvh）引入特征组合，从而实现在多云、多雨、低纬度地区的水稻地图绘制。结果表明，提取准确的关键物候期后，基于多源数据集的随机森林水稻提取方法可以更加有效地提高水稻种植信息提取精度，提高 4% 左右，在南方丘陵地区的水稻提取精度超过了 90%，总体精度和 Kappa 系数分别达到 93.50% 和 0.91。研究结果可为多雨的南方地区水稻种植提取提供参考，具有一定的应用价值。

中图分类号:

. 基于归一化雷达特征的南方丘陵区水稻提取研究[J]. 农业与技术, 2026, 46(7): 6-12.

参考文献

[1] 陈政，陈国生。湖南省森林植被空间分布及影响因子 [J]. 中南林业科技大学学报，2022, 42 (08): 128-136. [2] Xiao X, Boles S, Liu J, et al. Mapping paddy rice agriculture in southern China using multi-temporal MODIS images [J]. Remote sensing of environment, 2005, 95 (4): 480-492. [3] 孙华生，黄敬峰，李波，等。中国水稻遥感信息获取区划研究 [J]. 中国农业科学，2008, 41 (12): 4039-4047. [4] 杨闫君，占玉林，田庆久，等。基于 GF-1/WFV NDVI 时间序列数据的作物分类 [J]. 农业工程学报，2015, 31 (24): 155-161. [5] Mansaray L R, Huang W, Zhang D, et al. Mapping rice fields in urban Shanghai, southeast China, using Sentinel-1A and Landsat 8 datasets [J]. Remote Sensing, 2017, 9 (3): 257. [6] Zhan P, Zhu W, 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. [7] 甘聪聪，邱炳文，张建阳，等。基于 Sentinel-1/2 动态耦合移栽期特征的水稻种植模式识别 [J]. 地球信息科学学报，2023, 25 (01): 153-162. [8] Peng F, Peng Q, Lu J, et al. Extraction of paddy rice planting areas based on feature optimization and phenological information [J]. Journal of Applied Remote Sensing, 2024, 18 (3): 034512. [9] Zhao Z, Dong J, Zhang G, et al. Improved phenology-based rice mapping algorithm by integrating optical and radar data [J]. Remote Sensing of Environment, 2024, 315: 114460. [10] Sun L, Lou Y, Zhang L. Spatial domain transfer: Cross-regional paddy rice mapping with a few samples based on Sentinel-1 and Sentinel-2 data on GEE [J]. International Journal of Applied Earth Observation and Geoinformation, 2024, 128: 103762. [11] 田欣媛，张永红，刘睿，等。考虑植被红边信息的多时相 Sentinel-2 大范围冬小麦提取研究 [J]. 遥感学报，2022, 26 (10): 1988-2000. [12] 李俐，谢小曼，朱德海，等。去除土壤后向散射影响的 SAR 数据玉米留茬方式识别 [J]. 遥感学报，2023, 27 (11): 2628-2639. [13] Tucker C J. Red and photographic infrared linear combinations for monitoring vegetation [J]. Remote sensing of Environment, 1979, 8 (2): 127-150. [14] Huete A, Didan K, Miura T, et al. Overview of the radiometric and biophysical performance of the MODIS vegetation indices [J]. Remote sensing of environment, 2002, 83 (1-2): 195-213. [15] Lobell D B, Thau D, Seifert C, et al. A scalable satellite-based crop yield mapper [J]. Remote Sensing of Environment, 2015, 164: 324-333. [16] Xu H. A study on information extraction of water body with the modified normalized difference water index (MNDWI) [J]. Journal of Remote Sensing-Beijing, 2005, 9 (5): 595. [17] Merzlyak M N, Gitelson A A, Chivkunova O B, et al. Non-destructive optical detection of pigment changes during leaf senescence and fruit ripening [J]. Physiologia plantarum, 1999, 106 (1): 135-141. [18] Kee Y W, Shariff A R M, Sood A M, et al. Application of SAR data for oil palm tree discrimination [C]. IOP Conference Series: Earth and Environmental Science. IOP Publishing, 2018, 169 (1): 012065. [19] Lin S, Qi Z, Li X, et al. A phenological – knowledge – independent method for automatic paddy rice mapping with time series of polarimetric SAR images [J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2024, 218: 628-644. [20] Breiman L. Random forests [J]. Machine learning, 2001, 45 (1): 5-32. [21] Schuster C, Schmidt T, Conrad C, et al. Grassland habitat mapping by intra–annual time series analysis – Comparison of RapidEye and TerraSAR – X satellite data [J]. International journal of applied earth observation and geoinformation, 2015, 34: 25-34. [22] Degenhardt F, Seifert S, Szymczak S. Evaluation of variable selection methods for random forests and omics data sets [J]. Briefings in bioinformatics, 2019, 20 (2): 492-503. [23] Cao J, Cai X, Tan J, et al. Mapping paddy rice using Landsat time series data in the Ganfu Plain irrigation system, Southern China, from 1988–2017 [J]. International Journal of Remote Sensing, 2021, 42 (4): 1556-1576. [24] Campos-Taberner M, García-Haro F J, Martínez B, et al. Understanding deep learning in land use classification based on Sentinel-2 time series [J]. Scientific reports, 2020, 10 (1): 17188. [25] Goodchild M F, Li W. Replication across space and time must be weak in the social and environmental sciences [J]. Proceedings of the National Academy of Sciences, 2021, 118 ( 35 ): e2015759118.