| Cite this article: | 刘勇,何淑林,刘慧敏,等.基于神经网络算法的果树需水预测研究[J].灌溉排水学报,0,():-. |
| LIU Yong,HE Shu-lin,LIU Hui-min,et al.基于神经网络算法的果树需水预测研究[J].灌溉排水学报,0,():-. |
|
| |
|
|
| This article has been：Browse 2390Times Download 0Times |
|
|
|
| DOI： |
|
| Study on Water Demand Prediction of Fruit Trees Based on Neural Network Algorithm |
|
LIU Yong1, HE Shu-lin1, LIU Hui-min1, JIN Li-qiang2
|
|
1.Heilongjiang University;2.Heilongjiang East Water Saving Equipment Co,Ltd
|
| Abstract: |
| 【Objective】In order to realize efficient and intelligent irrigation of orchard, transpiration prediction model was established in this paper.【Method】Some experiment were conducted. Firstly, Principal Component Analysis was used to analyze the collected orchard environmental data, and the key influencing factors were screened out. Then, a prediction model based on Long Short-Term Memory Networks was established to predict the transpiration of fruit trees. In order to improve the accuracy of prediction, Attention Mechanism is added to the LSTM neural network to form the attention-LSTM prediction model.【Result】By comparing the prediction accuracy of the model proposed in this paper with other models, the simulation experiment proves that the prediction model proposed in this paper has high prediction accuracy.【Conclusion】The prediction model proposed in this paper can achieve precision irrigation of orchard and improve fruit yield, which has a certain practical significance. |
| Key words: Prediction of transpiration; LSTM neural network; PCA; Attention mechanism |
|
|
|
|
|
|
