The article "Farm typologies for understanding farm systems and improving agricultural policy" by Robert Huber et al. explores the role of farm typologies in identifying patterns and heterogeneity across various farm systems, and their potential to support agricultural policy design. The authors review 13 studies on farm typologies to develop a framework that connects the purposes of farm typologies with different stages of the policy process. They identify multiple purposes for farm typologies, including understanding farm characteristics, heterogeneity, and development, as well as policy-making. The framework suggests that connecting these purposes can enhance the validity, transferability, and relevance of farm typologies for agricultural policy. The authors also highlight the importance of cooperation between typology developers and users, and the use of new data and methods like machine learning to improve typologies. They conclude that future research should build on existing work while addressing specific challenges in the policy process, such as perceived fairness and legitimacy, to increase the effectiveness and efficiency of agricultural policies.The article "Farm typologies for understanding farm systems and improving agricultural policy" by Robert Huber et al. explores the role of farm typologies in identifying patterns and heterogeneity across various farm systems, and their potential to support agricultural policy design. The authors review 13 studies on farm typologies to develop a framework that connects the purposes of farm typologies with different stages of the policy process. They identify multiple purposes for farm typologies, including understanding farm characteristics, heterogeneity, and development, as well as policy-making. The framework suggests that connecting these purposes can enhance the validity, transferability, and relevance of farm typologies for agricultural policy. The authors also highlight the importance of cooperation between typology developers and users, and the use of new data and methods like machine learning to improve typologies. They conclude that future research should build on existing work while addressing specific challenges in the policy process, such as perceived fairness and legitimacy, to increase the effectiveness and efficiency of agricultural policies.