Scholarlink

Crop yield forecasting plays an important role in managing resources, aversions of risks, and the food security in India where more than 700 million people depend on agriculture. This research responds to prediction problems with techniques in ML and DL on a dataset obtained from the Ministry of Jal Shakti and Ministry of Agriculture containing variables such as rainfall, temperature, type, and quality of soils. Existing models fail to predict data variability and are unable to deal with nonlinearity. There are models utilized in our system including XGBoost, Random Forest, and Regression Models which are escalated through EDA to guarantee higher precision and reliability. Gains made in accuracy by this approach lead to betterment in planning and decision making of the farmers. This work aims to promote development in the agricultural industry through the improvement of actionable information accuracy and classification performance.

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

Crop and Yield Prediction Using Data Analysis and Machine Learning Algorithms

  • 会议论文

  • 发表日期：

    2026年

查看全文
  • S. Subbulakshmi,
  • P. C. Vasudev,
  • Anandhu S. Nair,
  • Aditya Anil Deyal,
  • G. Arjun

摘要

Crop yield forecasting plays an important role in managing resources, aversions of risks, and the food security in India where more than 700 million people depend on agriculture. This research responds to prediction problems with techniques in ML and DL on a dataset obtained from the Ministry of Jal Shakti and Ministry of Agriculture containing variables such as rainfall, temperature, type, and quality of soils. Existing models fail to predict data variability and are unable to deal with nonlinearity. There are models utilized in our system including XGBoost, Random Forest, and Regression Models which are escalated through EDA to guarantee higher precision and reliability. Gains made in accuracy by this approach lead to betterment in planning and decision making of the farmers. This work aims to promote development in the agricultural industry through the improvement of actionable information accuracy and classification performance.