Scholarlink

<p>The scale of agricultural production systems is one strategy to keep an eye on illness, and the phenology is to protect agricultural goods from experiencing a&#xa0;significant loss in production due to illnesses. Remote sensing (RS) data fusion has developed as an important tool for agricultural management and monitoring. This paper investigates the significant impact of remote sensing data integration techniques on agricultural activities. The article explains the various fusion approaches used and their consequences for applications in agriculture by conducting a&#xa0;thorough study of the available research. In this work, we present a&#xa0;deep learning (DL) model that uses innovative image processing techniques to precisely classify prevalent diseases in paddy. The complex multi-layer architecture of our model, which is designed to efficiently handle high pixel images across three colour bands (RGB), sets it apart. Convolutional Neural Networks (CNNs), which are highly effective at object detection and image classification, are ideally suited for this purpose. Spectral indices obtained from data collected by remote sensing provide Particular characteristics that distinguish between healthy crops and those with infections, enabling the strategic application to be easier. The moderate resolution image spectroradiometer (MODIS) and spectral analysis of land surface temperature are used to assess the incidence of leaf blasts. Normalised Difference Vegetation Index (NDVI) measures and improved Normalised Difference Moisture Index (NDMI), and soil-adjusted vegetation index (SAVI). A&#xa0;model based on deep learning is created to evaluate the state at the field level of rice blast disease. Our proposed model using deep learning yielded 91.04%, 86.31% validation accuracy and training accuracy. The profound Using remote sensing images, a&#xa0;learning model may evaluate the leaf blast event as it happens in real time.</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

Rice Blast Disease Detection and Assessment Using Deep Learning Techniques of Using Remote Sensing Methods

  • 期刊论文

  • 发表日期：

    2025年10月9日

查看全文
  • Prateeksha S.G,
  • Vijayalakshmi A. Lepakshi

摘要

The scale of agricultural production systems is one strategy to keep an eye on illness, and the phenology is to protect agricultural goods from experiencing a significant loss in production due to illnesses. Remote sensing (RS) data fusion has developed as an important tool for agricultural management and monitoring. This paper investigates the significant impact of remote sensing data integration techniques on agricultural activities. The article explains the various fusion approaches used and their consequences for applications in agriculture by conducting a thorough study of the available research. In this work, we present a deep learning (DL) model that uses innovative image processing techniques to precisely classify prevalent diseases in paddy. The complex multi-layer architecture of our model, which is designed to efficiently handle high pixel images across three colour bands (RGB), sets it apart. Convolutional Neural Networks (CNNs), which are highly effective at object detection and image classification, are ideally suited for this purpose. Spectral indices obtained from data collected by remote sensing provide Particular characteristics that distinguish between healthy crops and those with infections, enabling the strategic application to be easier. The moderate resolution image spectroradiometer (MODIS) and spectral analysis of land surface temperature are used to assess the incidence of leaf blasts. Normalised Difference Vegetation Index (NDVI) measures and improved Normalised Difference Moisture Index (NDMI), and soil-adjusted vegetation index (SAVI). A model based on deep learning is created to evaluate the state at the field level of rice blast disease. Our proposed model using deep learning yielded 91.04%, 86.31% validation accuracy and training accuracy. The profound Using remote sensing images, a learning model may evaluate the leaf blast event as it happens in real time.