A Dataset on Corn Silage in China Used to Establish a Prediction Model Showing Variation in Nutrient Composition

It is important to assess the nutritional concentrations of forage before it can be used for tremendous improvements in the dairy industry. This improvement requires a rapid, accurate, and portable method for detecting nutrient values, instead of traditional laboratory analysis. Fourier-transform in...

Full description

Saved in:
Bibliographic Details
Main Authors: Shu Zhang, Jian Hao, Donghai Wang, Chenglong Luo, Na Lu, Xiaocen Guo, Yanfang Liu, Zixiao Zhang, Shengli Li
Format: Article
Language:English
Published: Wiley 2023-01-01
Series:Journal of Spectroscopy
Online Access:http://dx.doi.org/10.1155/2023/7860822
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849699046264930304
author Shu Zhang
Jian Hao
Donghai Wang
Chenglong Luo
Na Lu
Xiaocen Guo
Yanfang Liu
Zixiao Zhang
Shengli Li
author_facet Shu Zhang
Jian Hao
Donghai Wang
Chenglong Luo
Na Lu
Xiaocen Guo
Yanfang Liu
Zixiao Zhang
Shengli Li
author_sort Shu Zhang
collection DOAJ
description It is important to assess the nutritional concentrations of forage before it can be used for tremendous improvements in the dairy industry. This improvement requires a rapid, accurate, and portable method for detecting nutrient values, instead of traditional laboratory analysis. Fourier-transform infrared (ATR-FTIR) spectroscopy technology was applied, and partial least squares regression (PLSR) and backpropagation artificial neural network (BP-ANN) algorithms were used in the current study. The objective of this study was to estimate the discrepancy in nutritional content and rumen degradation in WPCS grown in various regions and to propose a novel analytical method for predicting the nutrient content of whole plant corn silage (WPCS). The Zhengdan 958 cultivar of WPCS was selected from eight different sites to compare the discrepancies in nutrients and rumen degradation. A total of 974 WPCS samples from 235 dairy farms scattered across five Chinese regions were collected, and nutritional indicators were modeled. As a result, substantial discrepancies in nutritional concentrations and rumen degradation of WPCS were found when they were cultivated in different growing regions. The WPCS in Wuxi showed 1.14% higher dry matter (DM) content than that in Jinan. Lanzhou had 11.57% and 8.25% lower neutral detergent fiber (NDF) and acid detergent fiber (ADF) concentrations than Jinan, respectively. The DM degradability of WPCS planted in Bayannur was considerably higher than that in Jinan (6 h degradability: Bayannur vs. Jinan = 49.85% vs. 33.96%), and the starch of WPCS from Bayannur (71.79%) was also the highest after 6 h in the rumen. The results indicated that the contents of NDF, ADF, and starch were estimated precisely based on ATR-FTIR combined with PLSR or the BP-ANN algorithm (R2 ≥ 0.91). This was followed by crude protein (CP), DM (0.82 ≤ R2 ≤ 0.90), ether extract (EE), and ash (0.66 ≤ R2 ≤ 0.81). The BP-ANN algorithm had a higher prediction performance than PLSR (R2PLSR ≤ R2BP-ANN; RMSEPLSR ≥ RMSEBP-ANN). The same WPCS cultivar grown in different regions had various nutrient concentrations and rumen degradation. ATR-FTIR technology combined with the BP-ANN algorithm could effectively evaluate the CP, NDF, ADF, and starch contents of WPCS.
format Article
id doaj-art-32c0d7b52a4d48dd8b3323f6ff5f21ba
institution DOAJ
issn 2314-4939
language English
publishDate 2023-01-01
publisher Wiley
record_format Article
series Journal of Spectroscopy
spelling doaj-art-32c0d7b52a4d48dd8b3323f6ff5f21ba2025-08-20T03:18:44ZengWileyJournal of Spectroscopy2314-49392023-01-01202310.1155/2023/7860822A Dataset on Corn Silage in China Used to Establish a Prediction Model Showing Variation in Nutrient CompositionShu Zhang0Jian Hao1Donghai Wang2Chenglong Luo3Na Lu4Xiaocen Guo5Yanfang Liu6Zixiao Zhang7Shengli Li8College of Animal ScienceInner Mongolia Yili Industrial Group Co.,Ltd.College of Animal ScienceState Key Laboratory of Animal NutritionBeijing Jingwa Agricultural Science & Technology Innovation CenterBeijing Jingwa Agricultural Science & Technology Innovation CenterBeijing Sino Agricultural Aiko Testing Technology Co.,Ltd.Beijing Jingwa Agricultural Science & Technology Innovation CenterState Key Laboratory of Animal NutritionIt is important to assess the nutritional concentrations of forage before it can be used for tremendous improvements in the dairy industry. This improvement requires a rapid, accurate, and portable method for detecting nutrient values, instead of traditional laboratory analysis. Fourier-transform infrared (ATR-FTIR) spectroscopy technology was applied, and partial least squares regression (PLSR) and backpropagation artificial neural network (BP-ANN) algorithms were used in the current study. The objective of this study was to estimate the discrepancy in nutritional content and rumen degradation in WPCS grown in various regions and to propose a novel analytical method for predicting the nutrient content of whole plant corn silage (WPCS). The Zhengdan 958 cultivar of WPCS was selected from eight different sites to compare the discrepancies in nutrients and rumen degradation. A total of 974 WPCS samples from 235 dairy farms scattered across five Chinese regions were collected, and nutritional indicators were modeled. As a result, substantial discrepancies in nutritional concentrations and rumen degradation of WPCS were found when they were cultivated in different growing regions. The WPCS in Wuxi showed 1.14% higher dry matter (DM) content than that in Jinan. Lanzhou had 11.57% and 8.25% lower neutral detergent fiber (NDF) and acid detergent fiber (ADF) concentrations than Jinan, respectively. The DM degradability of WPCS planted in Bayannur was considerably higher than that in Jinan (6 h degradability: Bayannur vs. Jinan = 49.85% vs. 33.96%), and the starch of WPCS from Bayannur (71.79%) was also the highest after 6 h in the rumen. The results indicated that the contents of NDF, ADF, and starch were estimated precisely based on ATR-FTIR combined with PLSR or the BP-ANN algorithm (R2 ≥ 0.91). This was followed by crude protein (CP), DM (0.82 ≤ R2 ≤ 0.90), ether extract (EE), and ash (0.66 ≤ R2 ≤ 0.81). The BP-ANN algorithm had a higher prediction performance than PLSR (R2PLSR ≤ R2BP-ANN; RMSEPLSR ≥ RMSEBP-ANN). The same WPCS cultivar grown in different regions had various nutrient concentrations and rumen degradation. ATR-FTIR technology combined with the BP-ANN algorithm could effectively evaluate the CP, NDF, ADF, and starch contents of WPCS.http://dx.doi.org/10.1155/2023/7860822
spellingShingle Shu Zhang
Jian Hao
Donghai Wang
Chenglong Luo
Na Lu
Xiaocen Guo
Yanfang Liu
Zixiao Zhang
Shengli Li
A Dataset on Corn Silage in China Used to Establish a Prediction Model Showing Variation in Nutrient Composition
Journal of Spectroscopy
title A Dataset on Corn Silage in China Used to Establish a Prediction Model Showing Variation in Nutrient Composition
title_full A Dataset on Corn Silage in China Used to Establish a Prediction Model Showing Variation in Nutrient Composition
title_fullStr A Dataset on Corn Silage in China Used to Establish a Prediction Model Showing Variation in Nutrient Composition
title_full_unstemmed A Dataset on Corn Silage in China Used to Establish a Prediction Model Showing Variation in Nutrient Composition
title_short A Dataset on Corn Silage in China Used to Establish a Prediction Model Showing Variation in Nutrient Composition
title_sort dataset on corn silage in china used to establish a prediction model showing variation in nutrient composition
url http://dx.doi.org/10.1155/2023/7860822
work_keys_str_mv AT shuzhang adatasetoncornsilageinchinausedtoestablishapredictionmodelshowingvariationinnutrientcomposition
AT jianhao adatasetoncornsilageinchinausedtoestablishapredictionmodelshowingvariationinnutrientcomposition
AT donghaiwang adatasetoncornsilageinchinausedtoestablishapredictionmodelshowingvariationinnutrientcomposition
AT chenglongluo adatasetoncornsilageinchinausedtoestablishapredictionmodelshowingvariationinnutrientcomposition
AT nalu adatasetoncornsilageinchinausedtoestablishapredictionmodelshowingvariationinnutrientcomposition
AT xiaocenguo adatasetoncornsilageinchinausedtoestablishapredictionmodelshowingvariationinnutrientcomposition
AT yanfangliu adatasetoncornsilageinchinausedtoestablishapredictionmodelshowingvariationinnutrientcomposition
AT zixiaozhang adatasetoncornsilageinchinausedtoestablishapredictionmodelshowingvariationinnutrientcomposition
AT shenglili adatasetoncornsilageinchinausedtoestablishapredictionmodelshowingvariationinnutrientcomposition
AT shuzhang datasetoncornsilageinchinausedtoestablishapredictionmodelshowingvariationinnutrientcomposition
AT jianhao datasetoncornsilageinchinausedtoestablishapredictionmodelshowingvariationinnutrientcomposition
AT donghaiwang datasetoncornsilageinchinausedtoestablishapredictionmodelshowingvariationinnutrientcomposition
AT chenglongluo datasetoncornsilageinchinausedtoestablishapredictionmodelshowingvariationinnutrientcomposition
AT nalu datasetoncornsilageinchinausedtoestablishapredictionmodelshowingvariationinnutrientcomposition
AT xiaocenguo datasetoncornsilageinchinausedtoestablishapredictionmodelshowingvariationinnutrientcomposition
AT yanfangliu datasetoncornsilageinchinausedtoestablishapredictionmodelshowingvariationinnutrientcomposition
AT zixiaozhang datasetoncornsilageinchinausedtoestablishapredictionmodelshowingvariationinnutrientcomposition
AT shenglili datasetoncornsilageinchinausedtoestablishapredictionmodelshowingvariationinnutrientcomposition