Publications

Tan, ZT; Tan, ZY; Luo, JH; Duan, HT (2023). Mapping 30-m cotton areas based on an automatic sample selection and machine learning method using Landsat and MODIS images. GEO-SPATIAL INFORMATION SCIENCE.

Abstract
Cotton is one of the most significant cash crops in the world, and it is also the main source of natural fiber for textiles. It is crucial for cotton management to identify the spatiotemporal distribution of cotton planting areas timely and accurately on a fine scale. However, previous research studies have predominantly concentrated on specific years using remote sensing data. Challenges still exist in the extraction of cotton areas for long time series with high accuracy. To address this issue, a novel cotton sample selection method was proposed and the machine learning method is employed to effectively identify the long time series cotton planting areas at a 30-m resolution scale. Bortala and Shuanghe in Xinjiang, China, were selected as the study cases to demonstrate the approach. Specifically, the cropland in this study was extracted by using an object-oriented classification method with Landsat images and the results were optimized as the vectorized boundary of croplands. Then, the cotton samples were selected using the Normalized Difference Vegetation Index (NDVI) series of Moderate Resolution Imaging Spectroradiometer (MODIS) based on its phenological characteristics. Next, cotton was identified based on the croplands from 2000 to 2020 by using the machine learning model. Finally, the performance was evaluated, and the spatiotemporal distribution characteristics of cotton planting areas were analyzed. The results showed that the proposed approach can achieve high accuracy at a fine spatial resolution. The performance evaluation indicated the applicability and suitability of the method, there is a good correlation between the extracted cotton areas and statistical data, and the cotton area of the study area showed an increasing trend. The cotton spatial distribution pattern developed from dispersion to agglomeration. The proposed approach and the derived 30-m cotton maps can provide a scientific reference for the optimization of agricultural management.

DOI:
10.1080/10095020.2023.2275622

ISSN:
1993-5153