Scholarlink

The rising population necessitates meeting the demand for maximum crop yield to ensure a stable life. However, traditional farming methods may not be suitable for every crop, especially in challenging conditions such as low water availability and soil infertility. This makes it imperative to explore alternative approaches to address these agricultural challenges. Traditional farming gives less yield as it mostly depends on natural resources like soil and water, however technology can help to increase quality of soil by providing precise fertilizer leading to healthy crop condition. Artificial Intelligence (AI) plays crucial role for making smart decision approach to increase the crop yield. AI can enhance soil quality through precise fertilizer application, promoting optimal crop conditions. Additionally, deciding which crops to cultivate involves considering various factors. The crop yield prediction model utilizes Bayesian Ridge Regression, K-Nearest Neighbours (KNN), Support Vector Machine (SVM), Decision Tree, Random Forest, Gradient Boosting Machine (GBM), Extreme Gradient Boosting (XGBoost), Light Gradient Boosting Machine (Light GBM), and Artificial Neural Network (ANN). XGBoost and Light GBM outperformed with an R-Square of 99.2631% and 99.9963% respectively by reducing overfit. In crop price forecasting models, gated recurrent units (GRU) outperform over Long Short-Term Memory (LSTM) and Autoregressive Integrated Moving Average (ARIMA).

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 Yield Prediction and Price Forecasting Using Machine Learning

  • 会议论文

  • 发表日期：

    2025年

查看全文
  • Nihar Ranjan Swain,
  • Vaishali Choudhary,
  • Shivam Silswal,
  • Apoorva S. Shastri,
  • Sotirios Spanogiannopoulos

摘要

The rising population necessitates meeting the demand for maximum crop yield to ensure a stable life. However, traditional farming methods may not be suitable for every crop, especially in challenging conditions such as low water availability and soil infertility. This makes it imperative to explore alternative approaches to address these agricultural challenges. Traditional farming gives less yield as it mostly depends on natural resources like soil and water, however technology can help to increase quality of soil by providing precise fertilizer leading to healthy crop condition. Artificial Intelligence (AI) plays crucial role for making smart decision approach to increase the crop yield. AI can enhance soil quality through precise fertilizer application, promoting optimal crop conditions. Additionally, deciding which crops to cultivate involves considering various factors. The crop yield prediction model utilizes Bayesian Ridge Regression, K-Nearest Neighbours (KNN), Support Vector Machine (SVM), Decision Tree, Random Forest, Gradient Boosting Machine (GBM), Extreme Gradient Boosting (XGBoost), Light Gradient Boosting Machine (Light GBM), and Artificial Neural Network (ANN). XGBoost and Light GBM outperformed with an R-Square of 99.2631% and 99.9963% respectively by reducing overfit. In crop price forecasting models, gated recurrent units (GRU) outperform over Long Short-Term Memory (LSTM) and Autoregressive Integrated Moving Average (ARIMA).