Prediction of the Nutrient Content in Dairy Manure Using Artificial Neural Network Modeling

Abstract

Nutrients in animal manure are valuable inputs in agronomic crop production. Timely and reliable information on animal manure nutrient content will facilitate the utilization of manure as organic fertilizer and reduce any associated potential environmental problems. The objective of this study was to investigate the feasibility of using multiple linear regression (MLR), polynomial regression, and artificial neural network (ANN) models to determine nutrient content in dairy manure. Fresh manure samples (n = 86) from Holstein dairy cattle were collected from 34 dairy farms located in Beijing city, China. All samples were analyzed for nutrient content (ammonium nitrogen, total potassium, total nitrogen, and total phosphorus) by standard laboratory methods. The physicochemical properties (specific gravity, electrical conductivity, and pH) of dairy manure samples were measured. Relationships between nutrient content and physicochemical properties were explored by MLR, polynomial regression, and ANN models. Several parameters (R(2), modeling efficiency statistic, mean squared error of prediction, mean bias, linear bias, and maximum bias) were calculated to evaluate model performance. The residual analysis results indicated that all MLR models for the testing data set had significant mean and linear bias. When compared with MLR and polynomial regression models, the ANN model for all nutrient contents had better performance with higher R(2) and modeling efficiency statistics and lower mean squared error of prediction, mean bias, linear bias, and maximum bias. These findings demonstrated that the ANN model may be an appropriate tool to predict dairy manure nutrient content.

Rapid estimation of nutrients in chicken manure during plant-field composting using physicochemical properties

“…Livestock manure is complex material and affected by many factors (Westerman et al, 2006), and therefore more complex relationships between manure nutrient and physicochemical properties deserve further investigation. As an example, those with higher accuracy of prediction using artificial neural networks reported by Chen et al (2008). In addition, according to the suggestions by Moral et al (2008), there are few studies on physicochemical models for salinity and heavy metals in comparison with fruitful studies on nutrient content in animal manure.…”

Technical aspects concerning the detection of animal waste nutrient content via its electrical characteristics

“…The proposed correlation laws are linear in the majority of studies, but other reported relationships are polynomial and multi-parametric (Parera i Pous et al, 2010b;Suresh and Choi, 2011;Yagüe et al, 2012). One publication proposes the use of artificial neural network models to determine the nutrient content of dairy cattle manure (Chen et al, 2008).…”

Supplementary Feeding on the Nutrient Balance of Lactating Dairy Cow at Contrasting Temperature Regimes: Assessment Using Cornell Net Carbohydrate and Protein System (Cncps) Model

“…Nennich et al (2005) showed a linear relationship between crude protein intake and N excretion, which support the argument. Chen et al (2008) also used N feed content to predict manure N content using artificial neural network approach, beside the psychochemical properties of the manure, and the findings demonstrated that the predictors (N feed content and psychochemical properties) and the model were appropriate to predict dairy manure N content. Regarding the partitioning of productive N or manure N to total N, treatment of P. purpureum without supplementation (R1) was the most productive with value of 53%.…”