WildWID: An open‐source active RFID system for wildlife research

Rafiq, Kasim; Appleby, Robert G.; Edgar, Jason P.; Radford, Cameron; Smith, Bradley; Jordan, Neil R.; Dexter, Catherine; Jones, Darryl; Blacker, Amy R. F.; Cochrane, Matthew

doi:10.1111/2041-210x.13651

Cited by 14 publications

(12 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…we also aim with RFIDeep to foster low-impact monitoring of sensitive species by reducing human presence and intervention in wild habitats (Hughes et al, 2021;Rafiq et al, 2021;Harrison & Kelly, 2022). We are convinced that combining automatic data collection and real-time data analysis and storage will help secure key ecological information over time necessary to continuously monitor the health of wild populations and their ecosystems.…”

Section: Discussionmentioning

confidence: 99%

RFIDeep: Unfolding the Potential of Deep Learning for Radio-Frequency Identification

Bardon

Cristofari

Winterl

et al. 2023

Preprint

View full text Add to dashboard Cite

Automatic monitoring of wildlife is becoming a critical tool in the field of ecology. In particular, Radio-Frequency IDentification (RFID) is now a widespread technology to assess the phenology, breeding, and survival of many species. While RFID produces massive datasets, no established fast and accurate methods are yet available for this type of data processing. Deep learning approaches have been used to overcome similar problems in other scientific fields and hence might hold the potential to overcome these analytical challenges and unlock the full potential of RFID studies. We present a deep learning workflow, coined "RFIDeep", to derive ecological features, such as breeding status and outcome, from RFID mark-recapture data. To demonstrate the performance of RFIDeep with complex datasets, we used a long-term automatic monitoring of a long-lived seabird that breeds in densely packed colonies, hence with many daily entries and exits. To determine individual breeding status and phenology and for each breeding season, we first developed a one-dimensional convolution neural network (1D-CNN) architecture. Second, to account for variance in breeding phenology and technical limitations of field data acquisition, we built a new data augmentation step mimicking a shift in breeding dates and missing RFID detections, a common issue with RFIDs. Third, to identify the segments of the breeding activity used during classification, we also included a visualisation tool, which allows users to understand what is usually considered a "black box" step of deep learning. With these three steps, we achieved a high accuracy for all breeding parameters: breeding status accuracy = 96.3%; phenological accuracy = 86.9%; breeding success accuracy = 97.3%. RFIDeep has unfolded the potential of artificial intelligence for tracking changes in animal populations, multiplying the benefit of automated mark-recapture monitoring of undisturbed wildlife populations. RFIDeep is an open source code to facilitate the use, adaptation, or enhancement of RFID data in a wide variety of species. In addition to a tremendous time saving for analyzing these large datasets, our study shows the capacities of CNN models to autonomously detect ecologically meaningful patterns in data through visualisation techniques, which are seldom used in ecology.

show abstract

Section: Discussionmentioning

confidence: 99%

RFIDeep: Unfolding the Potential of Deep Learning for Radio-Frequency Identification

Bardon

Cristofari

Winterl

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

“…While other remote playback recording devices exist that are triggered by animal‐borne devices or cues generated by specific taxa (e.g. triggered by RFID detectors: Lendvai et al., 2015; Rafiq et al., 2021, VHF transmitters: Gottwald et al., 2021, ultrasonic bat calls: Gottwald et al., 2021)—which represent key advantages under specific circumstances—another significant benefit of CT‐playback integration is that multiple individuals and species can be studied during a single deployment without needing to invasively capture and tag animals. We note, however, that the same limitations that exist for CTs exist for the BoomBox (e.g.…”

Section: Discussionmentioning

confidence: 99%

BoomBox: An Automated Behavioural Response (ABR) camera trap module for wildlife playback experiments

Palmer

Wang²,

Plucinski³

et al. 2022

Methods Ecol Evol

View full text Add to dashboard Cite

Camera traps (CTs) are a valuable tool in ecological research, amassing large quantities of information on the behaviour of diverse wildlife communities. CTs are predominantly used as passive data loggers to gather observational data for correlational analyses. Integrating CTs into experimental studies, however, can enable rigorous testing of key hypotheses in animal behaviour and conservation biology that are otherwise difficult or impossible to evaluate. We developed the 'BoomBox', an open‐source Arduino‐compatible board that attaches to commercially available CTs to form an Automated Behavioural Response (ABR) system. The modular unit connects directly to the CT’s passive infrared (PIR) motion sensor, playing audio files over external speakers when the sensor is triggered. This creates a remote playback system that captures animal responses to specific cues, combining the benefits of camera trapping (e.g. continuous monitoring in remote locations, lack of human observers, large data volume) with the power of experimental manipulations (e.g. controlled perturbations for strong mechanistic inference). Our system builds on previous ABR designs to provide a cheap (~100USD) and customizable field tool. We provide a practical guide detailing how to build and operate the BoomBox ABR system with suggestions for potential experimental designs that address a variety of questions in wildlife ecology. As proof‐of‐concept, we successfully field tested the BoomBox in two distinct field settings to study species interactions (predator–prey and predator–predator) and wildlife responses to conservation interventions. This new tool allows researchers to conduct a unique suite of manipulative experiments on free‐living species in complex environments, enhancing the ability to identify mechanistic drivers of species' behaviours and interactions in natural systems.

show abstract

“…We suggest two main future study avenues to be explored at the Sakaerat Biosphere Reserve. First, a monitoring study should be designed to evaluate the true use of unintentional wildlife crossing structures, as presented in this study, either via strategic and coordinated camera traps, or via more advanced systems, such as PIT‐tag readers (Bateman et al, 2017), or radio‐frequency identification system (RFID; Rafiq et al, 2021). Second, research is needed to evaluate whether guidance fencing combined with a Before After Control Impact (BACI) along the Highway 304 structures could aid in limiting road mortalities for both King Cobras and other terrestrial species.…”

Section: Discussionmentioning

confidence: 99%

How do King Cobras move across a major highway? Unintentional wildlife crossing structures may facilitate movement

Jones

Marshall

Smith

et al. 2022

Ecology and Evolution

View full text Add to dashboard Cite

Global road networks continue to expand, and the wildlife responses to these landscape‐level changes need to be understood to advise long‐term management decisions. Roads have high mortality risk to snakes because snakes typically move slowly and can be intentionally targeted by drivers. We investigated how radio‐tracked King Cobras (Ophiophagus hannah) traverse a major highway in northeast Thailand, and if reproductive cycles were associated with road hazards. We surveyed a 15.3 km stretch of Highway 304 to determine if there were any locations where snakes could safely move across the road (e.g., culverts and bridges). We used recurse analyses to detect possible road‐crossing events, and used dynamic Brownian Bridge Movement Models (dBBMMs) to show movement pathways association with possible unintentional crossing structures. We further used Integrated Step Selection Functions (ISSF) to assess seasonal differences in avoidance of major roads for adult King Cobras in relation to reproductive state. We discovered 32 unintentional wildlife crossing locations capable of facilitating King Cobra movement across the highway. While our dBBMMs broadly revealed underpasses as possible crossing points, they failed to identify specific underpasses used by telemetered individuals; however, the tracking locations pre‐ and post‐crossing and photographs provided strong evidence of underpass use. Our ISSF suggested a lower avoidance of roads during the breeding season, although the results were inconclusive. With the high volume of traffic, large size of King Cobras, and a 98.8% success rate of crossing the road in our study (nine individuals: 84 crossing attempts with one fatality), we strongly suspect that individuals are using the unintentional crossing structures to safely traverse the road. Further research is needed to determine the extent of wildlife underpass use at our study site. We propose that more consistent integration of drainage culverts and bridges could help mitigate the impacts of roads on some terrestrial wildlife.

show abstract

WildWID: An open‐source active RFID system for wildlife research

Cited by 14 publications

References 29 publications

RFIDeep: Unfolding the Potential of Deep Learning for Radio-Frequency Identification

RFIDeep: Unfolding the Potential of Deep Learning for Radio-Frequency Identification

BoomBox: An Automated Behavioural Response (ABR) camera trap module for wildlife playback experiments

How do King Cobras move across a major highway? Unintentional wildlife crossing structures may facilitate movement

Contact Info

Product

Resources

About