Extracting Interactions between Flying Bat Pairs Using Model-Free Methods

Abstract

Social animals exhibit collective behavior whereby they negotiate to reach an agreement, such as the coordination of group motion. Bats are unique among most social animals, since they use active sensory echolocation by emitting ultrasonic waves and sensing echoes to navigate. Bats’ use of active sensing may result in acoustic interference from peers, driving different behavior when they fly together rather than alone. The present study explores quantitative methods that can be used to understand whether bats flying in pairs move independently of each other or interact. The study used field data from bats in flight and is based on the assumption that interactions between two bats are evidenced in their flight patterns. To quantify pairwise interaction, we defined the strength of coupling using model-free methods from dynamical systems and information theory. We used a control condition to eliminate similarities in flight path due to environmental geometry. Our research question is whether these data-driven methods identify directed coupling between bats from their flight paths and, if so, whether the results are consistent between methods. Results demonstrate evidence of information exchange between flying bat pairs, and, in particular, we find significant evidence of rear-to-front coupling in bats’ turning behavior when they fly in the absence of obstacles.

Transfer Entropy Analysis of Interactions between Bats Using Position and Echolocation Data

“…Overall, the results from this study are consistent with the result found in a previous study [ 19 ], showing that there is evidence of leadership by the rear bat in the curvature of the trajectories. The addition of data from the echolocation calls also supports this finding.…”

“…In this Begin subset, there is information transfer from the rear bat to the front bat, but no information flow from the front bat to the rear bat. This indicates leadership of the rear bats, which is consistent with the findings in [ 19 ]. Including data about calls increases the statistical significance of the information transfer.…”

“…This could give more information on how distance affects the interaction between in a pair of bats. The previous study [ 19 ] also looked at how obstacles affected interaction, and this could be studied in further detail by adding data from the echolocation calls made by the bats.…”

“…Specifically, transfer entropy, an extension of Shannon’s concept of entropy to measure information flow between time series, has been used to study the interaction of animal groups such as fish [ 16 ], meerkats (Suricat suricatta) [ 17 ], and insects [ 18 ]. It has also previously been used to determine leader–follower interactions in meerkats [ 17 ], bats [ 19 , 20 ], and in fish–robot interactions [ 21 ].…”

“…Previous studies have used information theory to model the interaction between bats flying in pairs [ 19 , 20 ]. Using 3D trajectories extracted from videos of wild bats in flight, these studies used transfer entropy and convergent cross mapping to identify interaction between bats.…”