Worldwide, our collective research and policy institutions, including the American Society of Animal Science (ASAS), are calling for more systems-based research and analysis of society’s most pressing and complex problems. However, the use of systems analysis within animal science remains limited and researchers may not have the tools to answer this call. This review thus introduces important concepts in systems thinking methodology, such as policy resistance, feedback processes, and dynamic complexity. An overall rationale for systems thinking and analysis is presented, along with examples of the application of these concepts in current animal science research. In order to contrast systems approaches to more frequently employed event-oriented research frameworks, both frameworks are then applied to the ASAS’ identified “Grand Challenge” problem of antimicrobial resistance (AMR) in order to compare these two kinds of analyses. Systems thinking stresses the importance of underlying system structures that lead to persistent problem behaviors vs a focus on unidirectional cause-and-effect relationships. A potential systems framework for animal production decisions to use antimicrobials is shown that more explicitly accounts for AMR in a way that can lead to different animal production decisions than the event-oriented framework. Acknowledging and accounting for fundamental system structures that can explain persistent AMR will lead to different potential solutions to this problem than would be suggested from more linear approaches. The challenges and benefits of incorporating systems methods into animal science research are then discussed.

Accurate agricultural commodity price models enable efficient allocation of limited natural resources, leading to improved sustainability in agriculture. Because of climate change, price volatility and uncertainty in the sector are expected to increase in the future, increasing the need for improved price modeling. With the emergence of machine learning (ML) algorithms, novel tools are now available to enhance the modeling of agricultural commodity prices. This research explores both univariate and multivariate ML techniques to perform probabilistic price prediction modeling for the Canadian beef industry, taking into account beef production, commodity markets, and international trade features to enhance accuracy. We model Alberta fed steer prices using three multivariate ML algorithms (support vector regression (SVR), random forest (RF), and Adaboost (AB)) and three univariate ML algorithms (autoregressive integrated moving average (ARIMA), seasonal ARIMA (SARIMA), and the seasonal autoregressive integrated moving average with exogenous factors (SARIMAX)). We apply these models to monthly fed steer price data between January 2005 and September 2023 and compare predicted prices with observed prices using several validation metrics. The outcomes indicate that both random forest (RF) and Adaboost (AB) show superior overall performance in accurately predicting Alberta fed steer prices in comparison to other algorithms. To better account for the variance of the best model performance, we subsequently adopted a probabilistic approach by considering uncertainty in our best-selected ML model. The beef industry can use these improved price models to minimize resource waste and inefficiency in the sector and improve the long-term sustainability prospects for beef producers in Canada.

There is a growing body of literature highlighting the need for increased focus on gender dynamics and inequality within agri-food systems, and in the design of policies that improve food and nutrition security while addressing climate change. Application of analytical tools that both (a) increase understanding of distinct gendered outcomes and constraints in these settings and (b) facilitate the development of policies that are gender-responsive and effective at mitigating climate change impacts is needed. Yet, identification of policies that improve or harm gendered outcomes is limited within many current analytical approaches by significant knowledge gaps about gender-specific realities, and by the lack of a systems perspective. We summarize these challenges in the context of agri-food supply chains under climate change and recommend Participatory Systems Modeling (PSM) as a method to address barriers to capturing “the gender variable” effectively and improving gender-responsive policy design. We discuss the methodology behind PSM and present examples of its usage in understanding agri-food supply chains as an integral component of global agri-food systems and determinant of food and nutrition security outcomes, where gender dynamics and climate change are important overarching system features and drivers. We recommend how PSM can be best utilized to improve the gender sensitivity of policy design for key agri-food system components like agri-food supply chains, and discuss ways that PSM itself can become more gender-responsive as a research and policy design tool.