ASN-ASAS SYMPOSIUM: FUTURE OF DATA ANALYTICS IN NUTRITION: Mathematical modeling in ruminant nutrition: approaches and paradigms, extant models, and thoughts for upcoming predictive analytics1,2

Abstract

This paper outlines typical terminology for modeling and highlights key historical and forthcoming aspects of mathematical modeling. Mathematical models ( MM ) are mental conceptualizations, enclosed in a virtual domain, whose purpose is to translate real-life situations into mathematical formulations to describe existing patterns or forecast future behaviors in real-life situations. The appropriateness of the virtual representation of real-life situations through MM depends on the modeler’s ability to synthesize essential concepts and associate their interrelationships with measured data. The development of MM paralleled the evolution of digital computing. The scientific community has only slightly accepted and used MM, in part because scientists are trained in experimental research and not systems thinking. The scientific advancements in ruminant production have been tangible but incipient because we are still learning how to connect experimental research data and concepts through MM, a process that is still obscure to many scientists. Our inability to ask the right questions and to define the boundaries of our problem when developing models might have limited the breadth and depth of MM in agriculture. Artificial intelligence ( AI ) has been developed in tandem with the need to analyze big data using high-performance computing. However, the emergence of AI, a computational technology that is data-intensive and requires less systems thinking of how things are interrelated, may further reduce the interest in mechanistic, conceptual MM. Artificial intelligence might provide, however, a paradigm shift in MM, including nutrition modeling, by creating novel opportunities to understand the underlying mechanisms when integrating large amounts of quantifiable data. Associating AI with mechanistic models may eventually lead to the development of hybrid mechanistic machine-learning modeling. Modelers must learn how to integrate powerful data-driven tools and knowledge-driven approaches into functional models that are sustainable and resilient. The successful future of MM might rely on the development of redesigned models that can integrate existing technological advancements in data analytics to take advantage of accumulated scientific knowledge. However, the next evolution may require the creation of novel technologies for data gathering and analyses and the rethinking of innovative MM concepts rather than spending resources in collecting futile data or amending old technologies.

Methane emissions of extensive grazing breeding herds in relation to the weaning and yearling stages in the Eastern Plains of Colombia

“…As suggested above, reaching valuable global markets increasingly require quality products supported by documented, low carbon foot printing (McAulifee et al 2018). This is consistent with Godde et al (2019) and Tedeschi et al (2002Tedeschi et al ( , 2019, who argued that in the face of climate variability it is critical to use modelling approaches to capture short and long, simple and complex environmental livestock representations of earlier or current real-life farming systems in tropical Australian rangelands or elsewhere. Therefore, baseline data and scenarios for various environmental burdens from savanna-beef based production systems in Colombia are desirable to integrate local deep knowledge-sharing and data-driven modelling.…”

Proceedings of the 9th Workshop on Modelling Nutrient Digestion and Utilization in Farm Animals (MODNUT)

“…Our simulation suggests that AI methods have not been designed for precision, but accuracy, and requires larger dataset to perform adequately as well as the human element for judgment (i.e., knowledge and wisdom; Tedeschi, 2019). It seems that ML can accurately predict methane emission, but lacks precision compared to MLR.…”

“…Since then, substantial progress in mathematical modeling has been absent, almost reaching to a halt. Artificial intelligence (AI) might incentivize an avant-garde technological wave in predictive analytics (Tedeschi, 2019), but the scientific community has a long way to go. The objective of this study was to compare AI methods with least-squares regression to predict methane emission.…”

Review: Synergy between mechanistic modelling and data-driven models for modern animal production systems in the era of big data

“…Some have suggested that such problems are rooted in communication and training as opposed to user-friendliness (Cartwright et al, 2016), and protocols to improve the user experience, such as customer journey mapping, are recommended (Vasilieva, 2018). Tedeschi (2019) reflected that innovation in MM for ruminant nutrition had gone stagnant since 2010 and proposed several reasons why, including (1) the field had reached a certain level of maturity or that (2) students are not being properly introduced to the required 'systems thinking' approach. We further suggest that the 'lag' observed by Tedeschi (2019) could have an additional origin related to reaching a level of success with nutritional models beyond which we need to integrate with other disciplinesgenetics, epigenetics, health, animal management, environment, whole farm modelling and life cycle assessmentbefore further knowledge (and then wisdom) can be extracted from the generated models.…”

“…The use of models in animal agriculture Models of all types (Figure 1) have a strong history of application in animal production, where their objectives have typically revolved around optimally feeding and growing livestock. For an excellent review of the historical evolution of model development and use, for example, in ruminant nutrition, see Tedeschi (2019). Such a development path has largely been paralleled in swine and poultry (Dumas et al, 2008;Sakomura et al, 2015).…”