Answers are grounded in this paper and cite their sources.
Cotton, a major global cash crop, requires accurate mapping approaches to ensure fiber production, food security and environmental sustainability. However, accurate cotton mapping remains challenging due to spectral confusion from phenological overlap with soybean and corn, alongside the limited availability of large, high-quality training samples. To address these challenges, this study proposes a novel Chlorophyll and Water Content Composite Index (CWCCI) for cotton mapping, derived from the Transformed Chlorophyll Absorption in Reflectance Index (TCARI), the Optimized Soil-Adjusted Vegetation Index (OSAVI), and the SWIR2 band, using Sentinel-2 images. By jointly characterizing chlorophyll absorption features and canopy water content while effectively suppressing soil background effects, the CWCCI offers a biophysically interpretable representation of crop properties with enhanced discriminatory capability for distinguishing cotton from other crops. The CWCCI was evaluated using a threshold-based approach across six representative cotton-producing regions with diverse climatic conditions, irrigation regimes, and agricultural landscapes, including four sites in the United States and two sites in China. An optimal time window (DOY ≈135–165) was quantitatively identified through time-series analysis of the CWCCI combined with phenological slope growth rate detection, during which Jeffries–Matusita distance reached its maximum (JM≈2.0). An optimal threshold of 0.11 and 0.12 were estimated for sites in U.S. and China, respectively, and adopted. Compared with two conventional classifiers, Random Forest and Support Vector Machine, the CWCCI-based approach achieved the highest overall accuracy (0.80–0.93) and Kappa coefficients (0.61–0.75) across all sites and years. These results further indicate the strong generalization capability and robustness of the proposed method, even in regions with limited training samples or incomplete reference data. Overall, the proposed CWCCI provides a simple, robust and efficient solution for large-area cotton mapping.
No takes yet. Share an insight, caveat, or question.
Mei et al. (2026) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: