Analysis and Estimate of Corn CNCPS Component by Near Infrared Reflectance (NIR) Spectroscopy

The objective of the present study was to investigate the feasibility of predicting the CNCPS (cornell net carbohydrate and protein system) composition of corn by near infrared reflectance spectroscopy (NIRS). Sixty-five corn samples from Heilongjiang province were used. The partial least square (PLS) regression method, second derivative and Norris derivative filter were applied in the NIRS prediction of CNCPS. For dry matter, crude protein, ash, fat, starch, neutral-detergent fiber and acid-detergent fiber, the determination coefficients were 0. 974 3, 0. 968 3, 0. 947 8, 0. 909 8, 0. 977 7, 0. 935 4 and 0. 926 9, and the SD/RMSEP values for them were 3. 96, 4. 78, 3. 75, 4. 25, 4. 13, 3. 88 and 3. 12 9 respectively. The determination coefficient and SD/RMSEP value were 0. 857 5 and 3. 06 for soluble protein, but low determination coefficients of 0. 531 9 and 0. 683 3 with SD/RMSEP values of 5. 50 and 2. 85 were observed for acid-detergent insoluble protein and neutral-detergent insoluble protein. If the SD/RMSEP value <5 and >39 then the effect of model is ideal, and if the SD/RMSEP value >5 or <3, the effect of model is not ideal 9 and at this time, the degree of accuracy of model needs further to be improved. The results of this study indicated that corn nutritive values could be fast and accurately predicted by NIRS. This model was significant in practice for enriching the rapid quantitative methods of determining animal feed materials.