A new approach to extract the upright maize straw from Sentinel-2 satellite imagery using new straw indices

Abstract

Unharvested upright maize straw is highly susceptible to burning in winter or in spring of the following year, contributing significantly to air pollution. The rapid and accurate acquisition of the spatial distribution of upright maize straw holds great importance for agricultural and environmental protection departments. This study introduces a new approach that focuses on extracting upright maize straw using Sentinel-2 satellite images. Initially, the Sentinel-2 images from the Botou and Hejian regions underwent preprocessing. To minimize interference during straw extraction, the normalized difference vegetation index (NDVI) was utilized to extract and eliminate built-up land and woodland areas. Subsequently, utilizing the spectral characteristics of maize straw across various bands including short-wave infrared, red edge, and near-infrared, three new indices were proposed and computed: the accumulation infrared straw index (AIRSI), the product near-infrared straw index (PNISI), and the normalized difference short-wave infrared straw index (NDSSI). Finally, the decision tree classification method was implemented to establish classification rules and extract the spatial distribution of upright maize straw. The study results revealed that the proposed new straw indices achieved an extraction accuracy of over 90% for upright maize straw. This new approach effectively enhances the identification accuracy of upright maize straw, providing valuable support for scientific supervision, comprehensive utilization, and prevention and control measures against maize straw burning.