An Improved Crop Yield Prediction Using CNN-BiLSTM Model with Attention Mechanism

Highlights A yield prediction model based on the CNN-BiLSTM fusion attention mechanism is constructed. The superiority of BiLSTM over the traditional LSTM model in the field of yield prediction is verified. The yield prediction effect of the proposed model is better than that of the existing yield prediction research. Abstract. Food is an important source of nutrients for people, and food production is an important basis for food reserves. In this study, a convolutional neural network-bidirectional long short-term memory (CNN-BiLSTM) model combined with an attention mechanism is proposed to predict crop yield. Firstly, the maximum temperature, minimum temperature, and rainfall data of 9 states in the rainfed corn belt of the United States are adopted as the original data, which are converted into cumulative climate parameters to reflect the growth process of corn. Then, the cumulative climate parameters are used as the input of the proposed model. The proposed model mainly consists of 4 parts: CNN module, BiLSTM module, attention module, and fully connected layer, which makes full use of the advantages of CNN in feature extraction and BiLSTM in processing time series. In addition, to ensure the relevance of time series data, the attention mechanism is used to allocate weights and calculate the correlation degrees between data. The experimental results show that BiLSTM exhibits better convergence ability than the standard one-way LSTM, and the crop yield prediction results obtained by the proposed model are better than those of the exponentially weighted average method, DeepCropNet, and CNN-RNN comparative algorithm. Keywords: Attention mechanism, Bidirectional long short memory network, Convolutional neural network, Crop yield prediction.