Scholarship & Research
Permanent URI for this communityhttps://scholarworks.montana.edu/handle/1/1
Browse
2 results
Search Results
Item Smart wildlife monitoring: evaluating a camera trap enabled with artificial intelligence(Montana State University - Bozeman, College of Agriculture, 2024) Kaltenbach, Taylor Louise Gregory; Chairperson, Graduate Committee: Jared T. Beaver; Jeffrey C. Mosley (co-chair)Wildlife-livestock conflicts, including depredation, disease transmission, and resource competition, present significant challenges to both the ecological and economic aspects of ranching operations. These conflicts can undermine the sustainability of ranching operations as well as the conservation of wildlife in working landscapes. Leveraging timely and precise data on wildlife activity, distribution, and their interactions with livestock are crucial for enhancing ongoing conflict mitigation efforts and to help sustain wildlife on working landscapes. I evaluated the potential of an artificial intelligence (AI)-enabled camera trap to limit false positive images and provide real-time monitoring of wildlife presence while reducing data overload. In Study 1, I compared the performance of a prototype, edge AI-enabled camera trap (Grizzly Systems) with 2 traditional, non-AI camera traps (Browning and Reconyx) at 8 sites across 3 ranches in south-central Montana, USA, from mid-June through mid-September 2023. I also evaluated the influence of site-specific environmental conditions, including air temperature, wind speed, cloud cover, and vegetation type on camera trap performance. The Grizzly Systems camera trap captured fewer false positive images but exhibited a higher rate of missed detections compared to the Browning and Reconyx camera trap models. Across all 3 camera trap models, the probability of positive detections declined with warmer air temperatures and greater wind speeds. In addition, warmer air temperatures positively influenced missed detections by Reconyx and Grizzly Systems camera trap models, but warmer air temperatures negatively influenced missed detections by Browning camera traps. In Study 2, I compared the performance of a cellular-connected AI-enabled Grizzly Systems camera trap, equipped with an automated image processing and notification reduction workflow, to a traditional, non-AI, cellular-connected Reconyx camera trap at 2 sites in south-central Montana, USA from mid-April to mid-June 2023. The AI-enabled, cellular-connected Grizzly Systems camera trap successfully sent real-time notifications of wildlife presence and transmitted significantly fewer false positive images than the cellular-connected Reconyx camera trap. However, the Grizzly Systems camera trap sent substantially fewer notifications of positive detections than the Reconyx camera trap, which are likely attributed to missed detections by the Grizzly Systems camera trap.Item Permeability of three-strand electric fences by black bears and grizzly bears(Montana State University - Bozeman, College of Agriculture, 2018) Johnson, Brittani Justine; Chairperson, Graduate Committee: Lance McNewElectric fencing has been used to deter bears in North America for several decades. Producers have turned to a design of a minimum of five-wire electric fence as their primary solution to reduce livestock depredation and to reduce raids of chicken houses and beeyards. However, these designs are expensive and reducing the number of wires used in a design to three wires would be beneficial. Scientific evaluations of the efficacy of three-wire electric fencing at deterring bears is lacking. In 2015 and 2016, I conducted a study in the Blackfoot Valley of Montana to evaluate the efficacy of rapid-deployment electric fencing designs in deterring bears from baited enclosures. Baited enclosures of two fencing configurations were established at 20 sites in the study area. Each enclosure was systematically energized and unenergized for 3-day periods; and passage into the enclosure was monitored with trail cameras to provide information on effectiveness and permeability. I recorded 134 visits by bears to fenced enclosures during the study seasons of 2015 and 2016. Of these visits, 78 occurred in 2015 and included 57 black bears and 21 grizzly bears. Fifty-six visits occurred in 2016, including 34 black bears and 22 grizzly bears. Black bears and grizzly bears were successful at passing the short fence 48% (95% CI: 32.0 -- 63.6) and 23% (5.0 -- 53.8) of the time, respectively, when it was not energized. When the short fence was energized, black bears were 7% (0.2 -- 33.9) successful in passing, whereas grizzly bears were successful in 25% (5.5 -- 57.2) of attempts. When not energized, both species successfully passed the tall fence design in 58% (95% CI: 27.7 -- 84.8) of attempts. Black bears and grizzly bears successfully entered energized enclosures with tall fences in 30% (95% CI: 13.2 -- 52.9) and 0% (95% CI: 0.0 -- 45.9) of attempts, respectively. Both fence types deterred bears from entering baited enclosures and all fences allowed less than perfect access when unenergized, suggesting that even minimalistic configurations of electric fences may act as barriers to black and grizzly bears. Further study evaluating the effects of rapidly increasing construction of electric fencing is needed to assess landscape level effects on bear movement and habitat selection.