Vegetable Fields Mapping in Northeast China Based on Phenological Features.

Hu, Jialin; Lu, Huimin; Song, Kaishan; Zhu, Bingxue

Developing vegetable agriculture is crucial for ensuring a balanced dietary structure and promoting nutritional health. However, remote sensing extraction in open-field vegetable planting areas faces several challenges, such as the mixing of target crops with natural vegetation caused by differences in climate conditions and planting practices, which hinders the development of large-scale vegetable field mapping. This paper proposes a classification method based on vegetable phenological characteristics (VPC), which takes into account the spatiotemporal heterogeneity of vegetable cultivation in Northeast China. We used a two-step strategy. First, Sentinel-2 satellite images and land use data were utilized to identify the optimal time and key indicators for vegetable detection based on the phenological differences in crop growth. Second, spectral analysis was integrated with three machine learning classifiers, which leveraged phenological and spectral features extracted from satellite images to accurately identify vegetable-growing areas. This combined approach enabled the generation of a high-precision vegetable planting map. The research findings reveal a consistent year-by-year increase in the planting area of vegetables from 2019 to 2023. The overall accuracy (OA) of the results ranges from 0.81 to 0.93, with a Kappa coefficient of 0.83. Notably, this is the first 10 m resolution regional vegetable map in China, marking a significant advancement in economic vegetable crop mapping.

REMOTE-sensing images; CROP growth; VEGETATION mapping; REMOTE sensing; MACHINE learning

Agronomy, 2025, Vol 15, Issue 2, p307

2073-4395

Academic Journal

10.3390/agronomy15020307