Rice, as an important staple crop, takes yield as the fundamental indicator and plays a vital role in ensuring food security and promoting agricultural development. However, traditional methods for measuring individual rice plant yield rely on destructive harvesting, which is time-consuming, labor-intensive, and unable to predict in real-time.

Hence, we developed an intelligent web tool for predicting individual rice yield per plant by deep convolutional neural networks. The training data for the prediction model was WGSR, a dataset containing 93 rice. It offers valuable insights to agricultural researchers, aiding their understanding of rice growth patterns and optimizing cultivation management.