Scholarlink

<p>A crucial pre-processing step in restoring optical satellite pictures for scientific study is the precise detection of clouds and cloud shadows. Data analysis is greatly impacted by clouds, which behave as noise in satellite photography. This is particularly pertinent to the cultivation of sugarcane, which takes 12–15&#xa0;months and is difficult in areas like Napane, where it is produced on red soil. Inaccurate monitoring findings can occur due to atmospheric impacts, which should be minimized since they alter the Normalized Difference Vegetation Index (NDVI). A minimal image reducer was used to reduce NDVI time series data, preserving the lowest cloud-free pixel values and enhancing the clarity of the vegetation signal in sugarcane crop analysis. If the cloud percentage is high, the improved method yields better results, as demonstrated by the implementation of the median and mean methods. The farmers are assisted in crop classification, monitoring, yield prediction, and disease identification by the display of NDVI readings before and during atmospheric adjustment.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

An Innovative Method for NDVI Correction and Cloud Removal in Sugarcane Remote Sensing

  • 期刊论文

  • 发表日期：

    2025年9月30日

查看全文
  • Mansi Kambli,
  • Bhakti Palkar

摘要

A crucial pre-processing step in restoring optical satellite pictures for scientific study is the precise detection of clouds and cloud shadows. Data analysis is greatly impacted by clouds, which behave as noise in satellite photography. This is particularly pertinent to the cultivation of sugarcane, which takes 12–15 months and is difficult in areas like Napane, where it is produced on red soil. Inaccurate monitoring findings can occur due to atmospheric impacts, which should be minimized since they alter the Normalized Difference Vegetation Index (NDVI). A minimal image reducer was used to reduce NDVI time series data, preserving the lowest cloud-free pixel values and enhancing the clarity of the vegetation signal in sugarcane crop analysis. If the cloud percentage is high, the improved method yields better results, as demonstrated by the implementation of the median and mean methods. The farmers are assisted in crop classification, monitoring, yield prediction, and disease identification by the display of NDVI readings before and during atmospheric adjustment.