Scholarlink

This study investigates the efficacy of machine learning (ML) algorithms in providing crop recommendations based on key input parameters such as NPK levels, rainfall, humidity, and pH. Five classification algorithms were employed to utilize a dataset from the Kaggle repository encompassing soil pH, NPK levels, and meteorological variables for 22 agricultural crops. Random Forest emerged as the top-performing algorithm with an accuracy rate of 99.7%, closely followed by Naive Bayes at 99.4%. This research aims to predict crop selection and advocate sustainable agricultural practices by referencing optimal conditions determined from various sources. Recommendations for sustainable practices include the System of Rice Intensification for rice cultivation, which is particularly beneficial for areas with low soil fertility and water availability. This study underscores the potential of ML techniques in guiding agricultural decision-making and promoting environmentally conscious farming practices.

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

Optimizing Crop Productivity Through Sustainable Practices: A Machine Learning Approach

  • 会议论文

  • 发表日期：

    2025年

查看全文
  • Ashvini C. Ladekar,
  • Sourabh Magdum,
  • Ajinkya Patil,
  • Deokumar Manwar

摘要

This study investigates the efficacy of machine learning (ML) algorithms in providing crop recommendations based on key input parameters such as NPK levels, rainfall, humidity, and pH. Five classification algorithms were employed to utilize a dataset from the Kaggle repository encompassing soil pH, NPK levels, and meteorological variables for 22 agricultural crops. Random Forest emerged as the top-performing algorithm with an accuracy rate of 99.7%, closely followed by Naive Bayes at 99.4%. This research aims to predict crop selection and advocate sustainable agricultural practices by referencing optimal conditions determined from various sources. Recommendations for sustainable practices include the System of Rice Intensification for rice cultivation, which is particularly beneficial for areas with low soil fertility and water availability. This study underscores the potential of ML techniques in guiding agricultural decision-making and promoting environmentally conscious farming practices.