A Prediction Model of Forest Preliminary Precision Fertilization Based on Improved GRA-PSO-BP Neural Network

Table 7

Correlation and error value of three models for predicting phosphorus fertilizer.

Fertilization model	Mean square error	Maximum absolute error	Minimum absolute error	Mean absolute error	Correlation
Traditional BP neural network	2.1253	3.54	0.097	1.732	0.9986
BP neural network optimized by PSO algorithm	0.1590	0.36	0.023	0.121	0.9999
BP neural network optimized by GRA-PSO algorithm	0.1699	0.3	0.002	0.119	0.9999