Scholarlink

<p>The purpose of this study is to examine the possible advantages of using machine learning algorithms into contemporary agriculture. These algorithms’ primary goal is to minimise waste and maximise agricultural yield by assisting in the making of well-informed decisions about crop planting, irrigation, and harvesting. The paper highlights the use of various supervised learning algorithms to address key challenges in agricultural management. Random Forest is employed for crop recommendation, while a combination of SVM and Random Forest tackles fertilizer recommendation. Our supervised learning models achieved high accuracy: Random Forest for crop recommendation (98.90%), SVM and Random Forest for fertilizer recommendation (97.89%).Top performers were SVM and Gradient Boosting, both achieving a result of 0.995 across all metrics through Orange Data Mining Tool. This paper contributes to the growing body of research exploring the applications of machine learning in agriculture. Specifically, it examines the effectiveness of different algorithms in tackling pest management challenges for various crops, offering a pathway towards cost-effective modernization of farming practices.</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

Smart Farming: An Integrated Platform for Crop and Fertilizer Prediction using Machine Learning and Orange Data Mining

  • 期刊论文

  • 发表日期：

    2025年5月30日

查看全文
  • Vipasha Abrol,
  • Gaurav Gupta,
  • Soumya Ranjan Pradhan

摘要

The purpose of this study is to examine the possible advantages of using machine learning algorithms into contemporary agriculture. These algorithms’ primary goal is to minimise waste and maximise agricultural yield by assisting in the making of well-informed decisions about crop planting, irrigation, and harvesting. The paper highlights the use of various supervised learning algorithms to address key challenges in agricultural management. Random Forest is employed for crop recommendation, while a combination of SVM and Random Forest tackles fertilizer recommendation. Our supervised learning models achieved high accuracy: Random Forest for crop recommendation (98.90%), SVM and Random Forest for fertilizer recommendation (97.89%).Top performers were SVM and Gradient Boosting, both achieving a result of 0.995 across all metrics through Orange Data Mining Tool. This paper contributes to the growing body of research exploring the applications of machine learning in agriculture. Specifically, it examines the effectiveness of different algorithms in tackling pest management challenges for various crops, offering a pathway towards cost-effective modernization of farming practices.