Geology topics

Zhicheng Tang

Publications and source records attributed to Zhicheng Tang.

2 recordsLinked to original sources

USGS2024

Detection probability and bias in machine-learning-based unoccupied aerial system non-breeding waterfowl surveys

Unoccupied aerial systems (UASs) may provide cheaper, safer, and more accurate and precise alternatives to traditional waterfowl survey techniques while also reducing disturbance to waterfowl. We evaluated availability and perception bias based on machine-learning-based non-breeding waterfowl count estimates derived from aerial imagery collected using a DJI Mavic Pro 2 on Missouri Department of Conservation intensively managed wetland Conservation Areas. UASs imagery was collected using a proprietary software for automated flight path planning in a back-and-forth transect flight pattern at ground sampling distances (GSDs) of 0.38–2.29 cm/pixel (15–90 m in altitude). The waterfowl in the images were labeled by trained labelers and simultaneously analyzed using a modified YOLONAS image object detection algorithm developed to detect waterfowl in aerial images. We used three generalized linear mixed models with Bernoulli distributions to model availability and perception (correct detection and false-positive) detection probabilities. The variation in waterfowl availability was best explained by the interaction of vegetation cover type, sky condition, and GSD, with more complex and taller vegetation cover types reducing availability at lower GSDs. The probability of the algorithm correctly detecting available birds showed no pattern in terms of vegetation cover type, GSD, or sky condition; however, the probability of the algorithm generating incorrect false-positive detections was best explained by vegetation cover types with features similar in size and shape to the birds. We used a modified Horvitz–Thompson estimator to account for availability and perception biases (including false positives), resulting in a corrected count error of 5.59 percent. Our results indicate that vegetation cover type, sky condition, and GSD influence the availability and detection of waterfowl in UAS surveys; however, using well-trained algorithms may produce accurate counts per image under a variety of conditions.

Missouri↗

USGS2024

Nonbreeding waterfowl behavioral response to crewed and uncrewed aerial surveys on conservation areas in Missouri

Monitoring waterfowl populations provides the basis for improving habitat quantity and quality, establishing harvest regulations, and ensuring sustainable waterfowl populations through appropriate management. Waterfowl biologists currently use a variety of population and habitat monitoring methods ranging from informal ground observations to low-level occupied aircraft surveys. Although unoccupied aerial systems (UAS) may provide safer and more precise alternatives to traditional aerial survey techniques that are less disturbing to waterfowl, there is limited information on how waterfowl in winter respond to UAS. We compared the behavioral responses of waterfowl to helicopters and UAS on Missouri Department of Conservation wetland conservation areas October – February 2021-2022. Helicopter surveys were flown using an Airbus H125 helicopter at heights of 100 – 350 m, with UAS surveys flown using a DJI Mavic 2 Pro UAS at 15 – 90 m. Waterfowl behavior was categorized as alert, swim, fly, or abandonment using flock-scan surveys recorded for 10-minute periods before, during, and after the surveys. The percentage of time flocks spent in each behavior during- or post-survey were compared to time spent in those behaviors pre-survey. Waterfowl increased time spent swimming, flying, and abandonment in response to helicopter flights, whereas UAS flights did not influence overall waterfowl behavior. Additionally, waterfowl did not change behavior in response to UAS flights regardless of waterfowl guild (mallard, other duck, or goose) or hunting season (open or closed). Waterfowl did increase flight behavior during UAS flights at 30 m, however, there was no change in behavior at all other UAS survey altitudes. UAS may be a good alternative to traditional waterfowl survey methods and are not likely to affect waterfowl distributions or energy expenditures during the survey periods.

Missouri↗