Scholarlink

Reasonable agribusiness is turning out to be progressively basic as worldwide food request ascends while regular assets stay restricted. Estimating crop yields is imperative for arranging and enhancing agricultural creation, and machine learning (ML) calculations have arisen as amazing assets for this reason. This exploration paper investigates the use of different ML calculations to anticipate crop yields precisely and productively. By dissecting various elements, including soil quality, weather conditions, and authentic yield information, ML models can give bits of knowledge into future agricultural result. This paper means to feature the capability of ML in progressing economical farming practices by upgrading yield expectation precision. It audits the difficulties related to carrying out these advancements, like information accessibility, model overfitting, and the requirement for area explicit transformations. Besides, it assesses the presentation of various calculations and talks about the ramifications of their application in true cultivating situations. The discoveries of this exploration accentuate the significance of proceeding with advancement and improvement in ML-based rural estimating to advance supportability in the area.

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

Moving Toward Sustainable Agriculture by Forecasting Crop Yield Using ML Algorithms

  • 会议论文

  • 发表日期：

    2025年

查看全文
  • Valliappan Raju,
  • Biswajit Brahma,
  • Yogita Thareja,
  • Abhilash Maroju,
  • Rachit Garg,
  • Samarth Gupta

摘要

Reasonable agribusiness is turning out to be progressively basic as worldwide food request ascends while regular assets stay restricted. Estimating crop yields is imperative for arranging and enhancing agricultural creation, and machine learning (ML) calculations have arisen as amazing assets for this reason. This exploration paper investigates the use of different ML calculations to anticipate crop yields precisely and productively. By dissecting various elements, including soil quality, weather conditions, and authentic yield information, ML models can give bits of knowledge into future agricultural result. This paper means to feature the capability of ML in progressing economical farming practices by upgrading yield expectation precision. It audits the difficulties related to carrying out these advancements, like information accessibility, model overfitting, and the requirement for area explicit transformations. Besides, it assesses the presentation of various calculations and talks about the ramifications of their application in true cultivating situations. The discoveries of this exploration accentuate the significance of proceeding with advancement and improvement in ML-based rural estimating to advance supportability in the area.