Scholarlink

<p>India’s food production is primarily reliant on cereal crops, such as wheat, rice, and different pulses. A stable climate is crucial for maintaining and managing variability in cropping systems. Seasonal climate changes, especially droughts, can hinder productivity. Enhanced forecasting methods for agricultural yields under different climate scenarios would enable farmers and stakeholders to make better decisions regarding crop management and selection. Existing crop yield prediction methods suffer from high computational time complexity and low prediction accuracy. Therefore, an automated crop prediction system is essential to help farmers make better judgments before planting. As a result, to overcome the above-mentioned challenges we use a Deep Learning Model with a Whale Optimization Algorithm for Crop Yield Prediction Based on Climate Changes (DLMWOA-CYPBCC). Initially, this work collects the data from the Indian Datasets. Then, perform data cleaning and normalization via the min-max normalization technique on the collected data. After that, select the essential features by eliminating unnecessary features using the Red Fox Optimization Algorithm (RFOA) to reduce the time complexity. Finally, WOA with a hybrid RNN-LSTM technique is employed to predict the crop yield in precision agriculture, in which the suggested work’s uniqueness is demonstrated by the application of the WOA algorithm to the hybrid DL model hyperparameter selection, which enhances overall performance. We simulate and evaluate the performance on the Python platform and analyze the effectiveness through Root Mean Squared Error (RMSE), Mean Absolute Error (MSE), and Correlation Coefficient (R2) metrics to calculate the outcomes of the DL crop yield prediction.</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

Deep learning models for crop yield prediction in South India based on climate change

  • 期刊论文

  • 发表日期：

    2025年9月3日

查看全文
  • Munugapati Bhavana,
  • Koppula Srinivas Rao

摘要

India’s food production is primarily reliant on cereal crops, such as wheat, rice, and different pulses. A stable climate is crucial for maintaining and managing variability in cropping systems. Seasonal climate changes, especially droughts, can hinder productivity. Enhanced forecasting methods for agricultural yields under different climate scenarios would enable farmers and stakeholders to make better decisions regarding crop management and selection. Existing crop yield prediction methods suffer from high computational time complexity and low prediction accuracy. Therefore, an automated crop prediction system is essential to help farmers make better judgments before planting. As a result, to overcome the above-mentioned challenges we use a Deep Learning Model with a Whale Optimization Algorithm for Crop Yield Prediction Based on Climate Changes (DLMWOA-CYPBCC). Initially, this work collects the data from the Indian Datasets. Then, perform data cleaning and normalization via the min-max normalization technique on the collected data. After that, select the essential features by eliminating unnecessary features using the Red Fox Optimization Algorithm (RFOA) to reduce the time complexity. Finally, WOA with a hybrid RNN-LSTM technique is employed to predict the crop yield in precision agriculture, in which the suggested work’s uniqueness is demonstrated by the application of the WOA algorithm to the hybrid DL model hyperparameter selection, which enhances overall performance. We simulate and evaluate the performance on the Python platform and analyze the effectiveness through Root Mean Squared Error (RMSE), Mean Absolute Error (MSE), and Correlation Coefficient (R2) metrics to calculate the outcomes of the DL crop yield prediction.