Winter wheat Segmentation using AI

In this research, a newly modified UNet (Fast-UNet) was implemented to segment winter wheat from time series Sentinel-2 images for the years 2021 and 2023. These images were converted to NDVI and utilized to identify wheat fields by tracking the wheat phenology from sowing to harvesting. The main satellite image that was used in this research was Sentinel-2. It is considered important, and free optical remote sensing satellite data is provided by the European Space Agency (ESA). Sentinel-2A and Sentinel-2B were launched in June 2015 and March 2017, respectively. They have a spatial resolution that varies between 10 m and 60 m depending on the wavelength. Sentinel-2A has a temporal resolution of 10 days, which can become 5 days with the combination of Sentinel-2B. The clipped image has a size of 6764 × 9018 pixels and comprises bands 3, 4, and 8, which correspond to green, red, and near-infrared. The bands were chosen for their high spatial resolution (10 meters) and their representation of the crop’s photosynthesis process. Sentinel-2 images were selected from March to July 2021 and 2023 for two reasons: to reduce the cloud cover effect (less than 5% of the image size) and to separate wheat from other vegetation based on the phenology progress of these crops. Normally, farmers prefer to make a turnaround between planting winter wheat and potatoes for this reason recent odd years were selected.

在本项研究中，一种新改进的 UNet 模型（Fast-UNet）被应用于从时间序列 Sentinel-2 图像中分割 2021 年和 2023 年的冬小麦。这些图像被转换为归一化植被指数（NDVI），并用于追踪从播种到收割的小麦物候变化，以此识别麦田。本研究主要使用的卫星图像为 Sentinel-2，该卫星数据由欧洲空间局（ESA）提供，具有至关重要的意义，并且是免费的光学遥感卫星数据。Sentinel-2A 和 Sentinel-2B 分别于 2015 年 6 月和 2017 年 3 月发射。它们的空间分辨率根据波长变化，介于 10 米至 60 米之间。Sentinel-2A 的时序分辨率为 10 天，通过 Sentinel-2B 的结合，这一分辨率可以缩短至 5 天。裁剪后的图像尺寸为 6764 × 9018 像素，包含 3、4 和 8 波段，分别对应绿色、红色和近红外波段。这些波段被选中是因为其高空间分辨率（10 米）以及其对作物光合作用过程的表征。Sentinel-2 图像在 2021 年和 2023 年的 3 月至 7 月期间被选中，基于两个原因：一是为了减少云层覆盖效应（图像面积小于 5%），二是基于这些作物的物候进展，将小麦与其他植被区分开来。通常情况下，农民倾向于在种植冬小麦和土豆之间进行轮作，因此选择了近年的奇数年份。