Prediction of Grain Yield in Henan Province Based on Grey BP Neural Network Model

Table 3

Evaluation index of the precision grade of grain yield prediction model.

Predicted models	Coefficient of determination	Probability of small error	Posterior difference ratio	Level
SR	0.43	0.24	2.15	Unqualified
GM (1, N)	0.65	0.60	0.32	Barely qualified
BPNN	0.80	0.87	0.23	Barely qualified
LSTM	0.86	0.90	0.17	Qualified
CNN	0.88	0.91	0.08	Qualified
GR-BPNN	0.93	1.00	0.05	Good

SR: stepwise regression; GM (1, N): grey GM (1, N) model; BP: backpropagation neural network; LSTM: long short-term memory; CNN: convolutional neural network; GR-BPNN: grey relational-back propagation neural network.