Attribute Selection Impact on Linear and Nonlinear Regression Models for Crop Yield Prediction

Table 6

RRSE, 𝑅, and RMAE measures using all the potential attributes.

Crop dataset	RRSE (%)			𝑅			RMAE (%)
	MLR	M5′	ANN	MLR	M5′	ANN	MLR	M5′	ANN
PJ01	85.36	48.83	65.51	0.89	0.9	0.92	14.21	6.99	9.28
CBP02	99.85	99.85	124.23	0.63	0.63	0.64	10.25	10.25	13.21
CBA03	136.96	156.29	86.07	0.76	0.77	0.59	14.99	15.33	7.83
CBM04	470.62	262.08	350.32	−0.66	−0.66	−0.68	11.2	6.54	8.05
CP05	102.68	362.5	123.61	0.36	0.08	0.54	10.12	32.25	11.75
PA06	98.02	102.87	110.24	0.07	0.15	0.19	26.02	27.56	27.93
PA07	110.86	165.41	113.18	−0.03	−0.13	−0.18	20.67	37.07	24.23
TS08	166.86	100.56	146.6	0.45	0.28	0.09	32.83	19.95	43.57
Average (RRSE < 100)	94.41	74.34	75.79	0.53	0.77	0.76	16.83	8.62	8.55
Count (<100)	3	2	2				3	2	2
Average (all)	158.9	162.3	139.97	0.31	0.25	0.26	17.54	19.49	18.23