Scholarlink

Soil management plays a crucial role in agricultural productivity and sustainability. However, traditional soil analysis and crop recommendation methods rely on laboratory testing, which is costly, time-consuming, and inefficient, often delaying critical farming decisions. This paper introduces an IoT-enabled soil management system integrating real-time soil sensors and machine learning to provide instant soil health assessments and crop recommendations. The system employs a Random Forest model, achieving 98% accuracy in predicting optimal crops. Additionally, this work offers soil improvement suggestions, helping users optimize nutrient levels through guided fertilizer recommendations. The Streamlit-based client application provides an interactive dashboard for real-time monitoring, historical data tracking, and community-based knowledge sharing. Experimental validation confirms the system’s high reliability, reducing soil analysis time from days to seconds. By eliminating reliance on expensive lab-based testing, the proposed system enhances efficiency, sustainability, and precision in agriculture, making it ideal for farmers, agronomists, and home gardeners.

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

Sustainable Precision Agriculture: IoT-Based Soil Monitoring and ML-Driven Crop Recommendations

  • 会议论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年

查看全文
  • Basnt Melibari,
  • Jomana Alhothly,
  • Joud Alshareef,
  • Lenah Alsaeedi,
  • Arwa Alsubhi,
  • Sarah Al-Shareef

摘要

Soil management plays a crucial role in agricultural productivity and sustainability. However, traditional soil analysis and crop recommendation methods rely on laboratory testing, which is costly, time-consuming, and inefficient, often delaying critical farming decisions. This paper introduces an IoT-enabled soil management system integrating real-time soil sensors and machine learning to provide instant soil health assessments and crop recommendations. The system employs a Random Forest model, achieving 98% accuracy in predicting optimal crops. Additionally, this work offers soil improvement suggestions, helping users optimize nutrient levels through guided fertilizer recommendations. The Streamlit-based client application provides an interactive dashboard for real-time monitoring, historical data tracking, and community-based knowledge sharing. Experimental validation confirms the system’s high reliability, reducing soil analysis time from days to seconds. By eliminating reliance on expensive lab-based testing, the proposed system enhances efficiency, sustainability, and precision in agriculture, making it ideal for farmers, agronomists, and home gardeners.