地球信息科学学报 ›› 2023, Vol. 25 ›› Issue (3): 654-668.doi: 10.12082/dqxxkx.2023.220522

• 遥感科学与应用技术 • 上一篇    下一篇

基于时序遥感影像的西南山区地块尺度作物类型识别

秦肖伟1,2(), 程博1,2, 杨志平3, 李林3, 董文2,*(), 张新2, 杨树文1,4,5, 靳宗义6, 薛庆1   

  1. 1.兰州交通大学测绘与地理信息学院,兰州 730070
    2.中国科学院空天信息创新研究院,北京 100094
    3.重庆市农业信息中心,重庆 401121
    4.地理国情监测技术应用国家地方联合工程研究中心,兰州 730070
    5.甘肃省地理国情监测工程实验室,兰州 730070
    6.北京师范大学地理科学学部,北京 100875
  • 收稿日期:2022-07-18 修回日期:2022-09-09 出版日期:2023-03-25 发布日期:2023-04-19
  • 通讯作者: * 董文(1983— ),女,湖北宜昌人,助理研究员,主要从事遥感地学时空分析及其精准应用研究。 E-mail: dongwen200436@aircas.ac.cn
  • 作者简介:秦肖伟(1997— ),女,山东聊城人,硕士生,主要从事遥感数据处理与应用研究。E-mail: 2356742929@qq.com
  • 基金资助:
    国家重点研发计划项目(2021YFB3900501);重庆市农业产业数字化地图项目(21C00346);国家自然科学基金项目(72073125);国家自然科学基金项目(42161069);兰州交通大学优秀平台项目(201806)

Identification of Parcel-Scale Crop Types in Southwestern Mountainous Area based on Time Series Remote Sensing Images

QIN Xiaowei1,2(), CHENG Bo1,2, YANG Zhiping3, LI Lin3, DONG Wen2,*(), ZHANG Xin2, YANG Shuwen1,4,5, JIN Zongyi6, XUE Qing1   

  1. 1. Faculty of Geomatics, Lanzhou Jiaotong University, Lanzhou 730070, China
    2. Aerospace Information Research innovation Institute, Chinese Academy of Sciences, Beijing 100094, China
    3. The Center of Agriculture Information of Chongqing, Chongqing 401121, China
    4. National-Local Joint Engineering Research Center of Technologies and Applications for National Geographic State Monitoring, Lanzhou 730070, China
    5. Gansu Provincial Engineering Laboratory for National Geographic State Monitoring, Lanzhou 730070, China
    6. Faculty of Geographic Sciences, Beijing Normal University, Beijing 100875, China
  • Received:2022-07-18 Revised:2022-09-09 Online:2023-03-25 Published:2023-04-19
  • Contact: DONG Wen
  • Supported by:
    National Key Research and Development Program of China(2021YFB3900501);Chongqing Agricultural Industry Digital Map Project(21C00346);National Natural Science Foundation of China(72073125);National Natural Science Foundation of China(42161069);Excellent Platform Project of Lanzhou Jiaotong University(201806)

摘要:

西南山区地块破碎且复杂,种植类型多样,且该地区多云多雨,可利用遥感数据有限,利用单一的光谱特征或植被指数难以实现作物的有效识别。物候特征能够反映作物的生长周期规律,可用于复杂地区作物的精细监测。本研究以重庆市潼南区为例,基于多时相中分辨率的Sentinel-2和Landsat8遥感影像,对地块尺度的NDVI、EVI等 6个植被指数进行时间序列构建并提取其物候特征,通过特征优选构建多维数据,利用随机森林分类模型对柠檬、油菜、水稻、玉米等作物进行识别。结合植被指数与物候特征进行作物分类,总体精度达94.52%,Kappa系数为0.90,柠檬、油菜、玉米、水稻的精度分别为89.88%、87.30%、84.98%和95.57%。研究表明,利用时序遥感数据的植被指数与物候特征能够有效进行地块尺度的作物识别,为复杂种植结构地区获取大范围作物分布制图提供参考。

关键词: 遥感, 时间序列, 地块尺度, 西南山区, 植被指数, 物候特征, 随机森林, 作物识别

Abstract:

The distribution of crop planting structure can directly reflect the form and location of farmland, which is of great significance for the development of precision agriculture and inventory of agricultural resources. In the southwestern mountainous area in China, the farmland parcel is small and fragmented, with complex planting types, and thus the image visual characteristics are fuzzy and diverse. Due to the complexity of climate and terrain surface, it is difficult to identify crop types in this area. The arrival of the era of high-resolution remote sensing has promoted the rapid development of object-oriented crop extraction methods. Classification based on object segmentation combing spectral, contextual, and other features can effectively overcome the shortcomings of pixel-based classification methods and better serve the field farming management and land ownership management. Therefore, this study uses high-resolution remote sensing images to extract farmland parcels. Taking parcels as the spatial constraints, six time-series vegetation indices including NDVI, EVI, RVI, DVI, GNDVI, and SAVI, are constructed at the scale of parcels based on multi-temporal medium-resolution Sentinel-2 and Landsat8 OLI remote sensing images. Their phenological characteristics are also extracted using these remote sensing images. The multi-dimensional data are constructed through the importance evaluation of classification features, and the random forest classification model is used to identify crop types (i.e., lemon, rape, rice, corn, and other crops) combined with field sampling data. By comparing the classification accuracy using vegetation indices or phenological characteristics alone and that combining vegetation indices and phenological characteristics together, we found that the classification accuracy combining vegetation indices and phenological characteristics is the highest. The overall accuracy is 94.52%, and the Kappa coefficient is 0.90. The accuracy of lemon, rape, corn, rice, and others is 89.88%, 87.30%, 84.98%, 95.57%, and 98.05%, respectively. There are 90 348 lemon parcels, 30 173 rape parcels, 271 606 corn parcels, 146 113 rice parcels, and 16 406 other parcels, accounting for 10.96%, 36.40%, 32.94%, 17.72%, and 1.99% of the total farmland in Tongnan area, respectively. The planting area accounted for 14.82%, 18.44%, 35.37%, 29.92% and 1.45%, respectively. Our results indicate that the vegetation indices and phenological characteristics extracted from time-series remote sensing data can be used for crop identification at the parcel scale, which provides reference for obtaining large-scale crop mapping in the region with complex planting structures.

Key words: remote sensing, time series, parcel scale, southwestern mountainous, vegetation index, phenological characteristics, random forest, crop identification