一种榆黄菇的生长预测模型训练方法、装置及设备
By combining a bidirectional long short-term memory network and a graph convolutional network to create a growth prediction model, the problem of insufficient prediction accuracy for the growth status of *Pleurotus ostreatus* was solved, enabling accurate prediction of the growth pattern of *Pleurotus ostreatus* and improving the application efficiency of smart agriculture.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- BEIJING ACADEMY OF AGRICULTURE & FORESTRY SCIENCES
- Filing Date
- 2025-05-13
- Publication Date
- 2026-07-17
AI Technical Summary
Existing technologies lack sufficient accuracy in predicting the growth status of *Pleurotus ostreatus*, making it difficult to meet the precision requirements of smart agriculture. Single models fail to fully extract various types of information during the growth process.
A growth prediction model combining bidirectional long short-term memory network and graph convolutional network was adopted. By collecting morphological data, image data and growth environment data of elm yellow mushroom, a multimodal dataset was constructed. Spatial features were extracted by graph convolutional network and temporal features were processed by bidirectional long short-term memory network. Attention fusion layer and extreme gradient boosting regression model were used for training to achieve deep fusion and dynamic modeling of multimodal data.
It improves the accuracy of predicting the growth status of elm mushrooms, enables comprehensive analysis and precise prediction of the growth patterns of elm mushrooms, and supports the efficient application of smart agriculture.
Smart Images
Figure CN120670838B_ABST