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

Table 8

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

Fertilization model	Mean square error	Maximum absolute error	Minimum absolute error	Mean absolute error	Correlation
Traditional BP neural network	10.377	19.4	0.561	8.243	0.9939
BP neural network optimized by PSO algorithm	4.6287	12.1	0.006	2.481	0.9989
BP neural network optimized by GRA-PSO algorithm	1.2870	2.9	0.01	0.794	0.9999