Scholarlink

In this paper, tomato cultivation is significantly influenced by soil-related factors, presenting challenges in effective crop management. This study proposes a Decision-Making System (DMS) leveraging Geographic Information Systems (GIS) and Deep Learning to optimize tomato cultivation practices. The system integrates spatial data with advanced machine learning models to assess land suitability for tomato crops, thereby enhancing precision agriculture. India's tomato production exceeds 25 million metric tons, In Andhra Pradesh being one of the top 10 producing states, Madanapalli is a critical region for tomato cultivation in AP. The research utilizes Sentinel-2 satellite data spanning from 2014 to 2023, complemented by ground truth data collected in 2023. The remote sensing data undergoes processing in QGIS to derive critical indices, including the Normalized Difference Vegetation Index (NDVI) and Soil Moisture content. These indices serve as inputs to a hybrid Convolutional Neural Network-Long Short-Term Memory (CNN-LSTM) model designed to deliver informed decisions on tomato cultivation practices. By analyzing soil moisture and NDVI, the system aids farmers in determining optimal planting periods, ultimately reducing crop losses and enhancing yield efficiency. This innovative approach underscores the potential of integrating Remote Sensing and deep learning for sustainable agricultural practices in tomato cultivation.

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

A Decision Making System Based on Remote Sensing for Tomato Crop Cultivation Using Deep Learning

  • 会议论文

  • 发表日期：

    2025年

查看全文
  • Anuradha Govada,
  • Rohith Kumar Madduri,
  • Ippili Naya Srujana,
  • Nizampatnam Anand Veera Sesha Sai

摘要

In this paper, tomato cultivation is significantly influenced by soil-related factors, presenting challenges in effective crop management. This study proposes a Decision-Making System (DMS) leveraging Geographic Information Systems (GIS) and Deep Learning to optimize tomato cultivation practices. The system integrates spatial data with advanced machine learning models to assess land suitability for tomato crops, thereby enhancing precision agriculture. India's tomato production exceeds 25 million metric tons, In Andhra Pradesh being one of the top 10 producing states, Madanapalli is a critical region for tomato cultivation in AP. The research utilizes Sentinel-2 satellite data spanning from 2014 to 2023, complemented by ground truth data collected in 2023. The remote sensing data undergoes processing in QGIS to derive critical indices, including the Normalized Difference Vegetation Index (NDVI) and Soil Moisture content. These indices serve as inputs to a hybrid Convolutional Neural Network-Long Short-Term Memory (CNN-LSTM) model designed to deliver informed decisions on tomato cultivation practices. By analyzing soil moisture and NDVI, the system aids farmers in determining optimal planting periods, ultimately reducing crop losses and enhancing yield efficiency. This innovative approach underscores the potential of integrating Remote Sensing and deep learning for sustainable agricultural practices in tomato cultivation.