Automated monitoring of honey bees with barcodes and artificial intelligence reveals two distinct social networks from a single affiliative behavior

Abstract

Barcode-based tracking of individuals is revolutionizing animal behavior studies, but further progress hinges on whether in addition to determining an individual’s location, specific behaviors can be identified and monitored. We achieve this goal using information from the barcodes to identify tightly bounded image regions that potentially show the behavior of interest. These image regions are then analyzed with convolutional neural networks to verify that the behavior occurred. When applied to a challenging test case, detecting social liquid transfer (trophallaxis) in the honey bee hive, this approach yielded a 67% higher sensitivity and an 11% lower error rate than the best detector for honey bee trophallaxis so far. We were furthermore able to automatically detect whether a bee donates or receives liquid, which previously required manual observations. By applying our trophallaxis detector to recordings from three honey bee colonies and performing simulations, we discovered that liquid exchanges among bees generate two distinct social networks with different transmission capabilities. Finally, we demonstrate that our approach generalizes to detecting other specific behaviors. We envision that its broad application will enable automatic, high-resolution behavioral studies that address a broad range of previously intractable questions in evolutionary biology, ethology, neuroscience, and molecular biology.

Methods for assessing bee foraging preferences: a short review and a new automated apparatus

“…It is important to note that these open-air platforms may unintentionally introduce artificial factors, which could potentially bias the observations. Furthermore, although comprehensive, video recordings provide behavioral data that may necessitate substantial manual time and effort for subsequent data processing and analysis, thus rendering them less ideal for large-scale investigations (Gernat et al, 2023). For smaller-scale investigations, infrared (IR) sensors provide precise bee passage and visitation rate data, but their cost and complexity can pose challenges that may limit their widespread use (Pešović et al, 2017).…”

Ant social network structure is highly conserved across species

“…For example, we now know that increased group size and genetic heterogeneity can confer fitness benefits by enhancing division of labour [2,13] (though do not always seem to [14]), how fundamental aspects of insect biology map onto colony social networks [15,16] and how social network structure is influenced by both pathogens [17,18] and symbionts [19]. We also know more about the dynamics of individual-level behavioural change [9,20,21], foraging and food dissemination [22,23], cooperative transport [24] and other aspects of self-organization [12,[25][26][27], all of which are important topics for scientists investigating biological and artificial collective systems, and optimization algorithms [28][29][30].…”