Use of near-infrared spectroscopy and multivariate approach for estimating silage fermentation quality from freshly harvested maize

Abstract

The study aimed to evaluate the most predictive traits of fresh maize and the most appropriate multivariate approach for estimating silage fermentation quality. The use of near infrared (NIRs) instruments allowed rapid, accurate and cheap analysis. Samples of fresh maize plant (n ¼ 822) from hybrids (Class Cultivar) of early and late classes, were harvested at three maturity stages: early, medium and late, in three areas (level input field) of 'low', 'medium' and 'high' soil fertility, along three consecutive years. Several algorithms of feature selection, regression, classification and machine learning, were tested. Maize silage fermentative quality was summarised through a Fermentative Quality Index (FQI). We found the most predictive traits as dry matter (DM), starch, and acid detergent lignin (ADL), with negative coefficients, or water-soluble carbohydrates (WSC) with a positive coefficient. FQI was significantly (p < 0.0001) affected by year (negatively for 2018), level input field (positively for high level) and maturity stage (negatively for the late harvest). The most satisfying results were attained using a stepwise regression algorithm (R 2 ¼ 0.48), improved by the introduction of fixed effects (R 2 ¼ 0.55) and partial least square discriminant analysis (PLS-DA), which was assessed through the Mattew Correlation Coefficient (MCC) in validation (MCC ¼ 0.57). Concluding, among the tested approaches, the use of linear regression after stepwise algorithm or the use of PLS could be of practical help for the farmers to the effective management of the ensiling process of maize plants, even though environmental conditions should be considered to improve the predictions. HIGHLIGHTSThe prediction of FQ at harvest would allow the farmer to tune up the ensiling process The prediction of FQ through the use of portable NIRs instruments was successful DM, starch and ADL were negatively related to FQ index ARTICLE HISTORY

Short Communication: Prognostic Values of a Multiparametric Risk Score in Maize Silage Undergoing Different Ensiling Conditions

“…Consistently with the MFA, the quantitative variables grouped for DM, EE and starch, and in the opposite, grouped for ash, CP, ADF, and lignin (sa), while WSC stands alone (Figure 2B). This finding confirms the positive relation between DM and starch [32], and data from the previous study, except WSC, where the spatial distribution of quantitative variables was studied with a Principal Component Analysis [15]. In the current study, we found an anomalous trend for the ratio starch/WSC during the three experimental years.…”

“…These data can be used by farmers and maize growers to make better processing choices at the time of harvest and when processing the whole maize plant into the silos [11,12]. Due to big data availability, the use of Machine Learning (ML) techniques has become more common in agricultural research in establishing knowledge-based farming systems [13,14] and particularly for estimating silage fermentation quality from freshly harvested maize [15]. Maize is the most studied crop using ML because of its versatile usage and wide world diffusion, and even for its quality evaluation via the use of spectrometers [14].…”

Effect of Inoculants and Sealing Delay on the Fermentation Quality of Early Harvested Wheat Forage

“…To simplify the quality evaluation, various indexes have been considered to summarize the overall fermentative quality of silage, such as the Flieg-Zimmer score (FZs) [11], the Vanbelle and Bertin score [12,13], the German agricultural society (DLG) score [14,15], the homolactic index [16,17], the standardised quality score (SQS) [18], and the fermentative quality index (FQI) score [19]. The composition of the fresh ensiled plant, including the DM, crude protein (CP), fibre, N-free extract and water-soluble carbohydrates (WSC) content, affects the final quality of the silage [10,20,21]. Additionally, various factors can decrease the aerobic stability of silages, providing a chance for opportunistic microorganisms such as yeast (Saccharomyces, Candida, Cryptococcus, and Pichia), moulds, bacilli, and acetic acid bacteria to become active and generate heat while consuming nutrients from the silage, which can cause spoilage [11,22,23].…”

“…The pre-ensiled composition can be assessed to compute a prognostic risk score for the aerobic stability of maize silage [30,31]. Additionally, research has shown that post-silage quality can be partially linked to fresh maize's pre-silage characteristics, even using machine learning techniques under different harvesting and ensiling conditions [20]. Furthermore, using portable Near-Infrared Spectroscopy (NIRS) instruments permits onfarm rapid, ecologic and cheap analysis of forages [32][33][34].…”

Assessment of Maize Silage Quality under Different Pre-Ensiling Conditions

“…Evaluate the effectiveness of a multivariate approach and multiple linear regression in predicting the potential of freshly harvested maize (FHM) to ensure silage fermentation quality based on the chemical composition of the harvested whole-plant maize [17].…”