Scholarlink

<p>Accurate yield prediction is crucial for both farmers and the agriculture industry. By providing advance insights, it aids in effective planning and informed decision-making about agricultural imports and exports, which significantly impact farmers’ incomes. Leveraging machine learning algorithms can significantly enhance yield prediction accuracy, benefiting both individual farmers and the broader agricultural sector. This study presents a machine learning-based model to predict groundnut production one month in advance for five districts in Gujarat: Junagadh, Jamnagar, Amreli, Bhavnagar, and Rajkot. The environmental parameters used to train machine learning models include the Normalized Difference Vegetation Index (NDVI), Enhanced Vegetation Index (EVI), Leaf Area Index (LAI), Fraction of Photosynthetically Active Radiation (FPAR), and Gross Primary Product (GPP), along with weather parameters such as Rainfall, Land Surface Temperature (LST), and Soil Moisture Index (SMI). These parameters were obtained from the Moderate Resolution Imaging Spectroradiometer (MODIS) and the Climate Hazards Group InfraRed Precipitation with Station data (CHIRPS). The training data was utilized across eight different machine learning models: Linear Regression, Random Forest Regression, Decision Tree Regression, XGBoost Regressor, Gradient Boosting Regression, Lasso Regressor, Ridge Regressor, and Support Vector Regressor (SVR). The models were then evaluated using the R² score, Root Mean Square and Agreement Index, with the XGBoost Regressor emerging as the top performer among all algorithms. The study offers valuable insights into the application of machine learning models for predicting crop yield.</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

District-Level Groundnut Yield Prediction in Gujarat State Using Machine Learning and Remote Sensing Data

  • 期刊论文

  • 发表日期：

    2026年1月27日

查看全文
  • Drashti Nayakpara,
  • Divya Prajapati,
  • Kamal Pandey,
  • N. R. Patel

摘要

Accurate yield prediction is crucial for both farmers and the agriculture industry. By providing advance insights, it aids in effective planning and informed decision-making about agricultural imports and exports, which significantly impact farmers’ incomes. Leveraging machine learning algorithms can significantly enhance yield prediction accuracy, benefiting both individual farmers and the broader agricultural sector. This study presents a machine learning-based model to predict groundnut production one month in advance for five districts in Gujarat: Junagadh, Jamnagar, Amreli, Bhavnagar, and Rajkot. The environmental parameters used to train machine learning models include the Normalized Difference Vegetation Index (NDVI), Enhanced Vegetation Index (EVI), Leaf Area Index (LAI), Fraction of Photosynthetically Active Radiation (FPAR), and Gross Primary Product (GPP), along with weather parameters such as Rainfall, Land Surface Temperature (LST), and Soil Moisture Index (SMI). These parameters were obtained from the Moderate Resolution Imaging Spectroradiometer (MODIS) and the Climate Hazards Group InfraRed Precipitation with Station data (CHIRPS). The training data was utilized across eight different machine learning models: Linear Regression, Random Forest Regression, Decision Tree Regression, XGBoost Regressor, Gradient Boosting Regression, Lasso Regressor, Ridge Regressor, and Support Vector Regressor (SVR). The models were then evaluated using the R² score, Root Mean Square and Agreement Index, with the XGBoost Regressor emerging as the top performer among all algorithms. The study offers valuable insights into the application of machine learning models for predicting crop yield.