文献类型： 外文期刊

作者： Wei, Peng ¹ ; Ye, Huichun ² ; Qiao, Shuting ¹ ; Liu, Ronghao ¹ ; Nie, Chaojia ² ; Zhang, Bingrui ⁴ ; Song, Lijuan ⁵ ; Huang, Shanyu ⁷ ;

作者机构： 1.Taiyuan Univ Technol, Coll Water Resources Sci & Engn, Taiyuan 030024, Peoples R China

2.Int Res Ctr Big Data Sustainable Dev Goals, Beijing 100094, Peoples R China

3.Chinese Acad Sci, Aerosp Informat Res Inst, Key Lab Digital Earth Sci, Beijing 100094, Peoples R China

4.China Univ Min & Technol, Coll Geosci & Surveying Engn, Beijing 100083, Peoples R China

5.Heilongjiang Acad Agr Sci, Inst Agr Remote Sensing & Informat, Harbin 150086, Peoples R China

6.Heilongjiang Univ Sci & Technol, Sch Management, Harbin 150022, Peoples R China

7.Acad Agr Planning & Engn, Beijing 100125, Peoples R China

关键词： crops; feature selection; Sentinel-2; earliest identifiable timing; crop mapping

期刊名称：REMOTE SENSING （ 影响因子：5.0； 五年影响因子：5.6 ）

ISSN：

年卷期： 2023 年 15 卷 13 期

页码：

收录情况： SCI

摘要： Early-season crop mapping and information extraction is essential for crop growth monitoring and yield prediction, and it facilitates agricultural management and rapid response to agricultural disasters. However, training classifiers by remote sensing classification features for early crop prediction can be challenging, as early-season mapping can only use remote sensing image data during part of the crop growth period. In order to overcome this limitation, this study takes the Sanjiang Plain as an example to investigate the earliest identification time of rice, maize and soybean based on Sentinel-2 time-series data and the random forest classification algorithm. Crop information extraction was then performed. Following the analysis of the remote sensing classification features by the random forest importance approach and the subsequent normalization, the optimal features greater than or equal to 0.5 have yielded quite results in early crop mapping, and their overall accuracy was the highest in early-season mapping. The overall accuracy was observed to improve by 5% for 10 to 20 days of delay. In addition, rice, maize, and soybean were mapped at the irrigation transplanting period (10 May), jointing stage (9 July) and flowering (29 July), with an overall accuracy of 90.4%, 90.0% and 90.9%, respectively. This study shows that features suitable for early crop classification can be selected by random forest importance analysis as well as the ability of remote sensing to extract crop acreage information within the reproductive period.