Geology topics

Laurence A. Clarfeld

Publications and source records attributed to Laurence A. Clarfeld.

5 recordsLinked to original sources

USGS2025

Observations of tear-drinking by lepidopterans on moose ( Alces alces americana ) in northeastern North America

Lepidoptera have long been known to feed on the tears of vertebrates as a presumed source of minerals or nutrients. While this unusual behavior has been observed in a variety of species, only a single previous record has been documented outside of the tropics. Here, we present the first documentation of moths visiting the eyes of a bull moose ( Alces americanus americanus ), captured via trail camera in Green Mountain National Forest, Vermont, United States. We discuss the biogeography of this behavior, how it may differ between tropical and temperate climates, and its potential impact on moose health.

Vermont↗

USGS2025

DeepFaune New England: A species classification model for trail camera images in northeastern North America

The DeepFaune New England model classifies wildlife species in trail camera images, identifying 24 taxa from northeastern North America with high (97%) accuracy. The model was adapted from the DeepFaune model for identifying European wildlife, demonstrating the practicality of transfer learning across continents. The majority of training data is openly licensed, and the model itself is open source, enabling easy integration into camera trapping workflows. The open source software is available at ( https://code.usgs.gov/vtcfwru/deepfaune-new-england ), and has been further integrated into the PyTorch-Wildlife framework.

New England↗

USGS2025

Two-stage models improve machine learning classifiers in wildlife research: A case study in identifying false positive detections of Ruffed Grouse

Autonomous recording units are increasingly being used to monitor wildlife on large geographic and temporal scales, paired with machine learning (ML) to automate detection of wildlife. However, false positive detections from ML classifiers can result in erroneous ecological models that can lead to misguided management and conservation actions. We used a two-stage general approach to understand and reduce false positive detections, a technique in which outputs of the primary classification model are passed to a secondary classification model to yield the probability that a detection from the primary model is a true positive detection. This approach is demonstrated on two open-source models that detect Ruffed Grouse ( Bonasa umbellus ). We analyzed over 9500 h of acoustic data collected in 2022–2023 from the Green Mountain National Forest in Vermont, USA, and found the two models detected different types of acoustic signals associated with differing life history traits. The first model yielded 4106 detections (71.5 % true positives) while the second model yielded 524 detections (17.0 % true positives). Secondary logistic regression models separated true positives and false positives with high accuracy (84.5 % and 89.8 % respectively). Our findings go beyond improving Ruffed Grouse monitoring and conservation efforts to, more broadly, illustrate how two-stage ML approaches can improve the use of model-derived detections in wildlife research.

Vermont↗

USGS2024

Accounting for missing ticks: Use (or lack thereof) of hierarchical models in tick ecology studies

Ixodid (hard) ticks play important ecosystem roles and have significant impacts on animal and human health via tick-borne diseases and physiological stress from parasitism. Tick occurrence, abundance, activity, and key life-history traits are highly influenced by host availability, weather, microclimate, and landscape features. As such, changes in the environment can have profound impacts on ticks, their hosts, and the spread of diseases. Researchers recognize that spatial and temporal factors influence activity and abundance and attempt to account for both by conducting replicate sampling bouts spread over the tick questing period. However, common field methods notoriously underestimate abundance, and it is unclear how (or if) tick studies model the confounding effects of factors influencing activity and abundance. This step is critical as unaccounted variance in detection can lead to biased estimates of occurrence and abundance. We performed a descriptive review to evaluate the extent to which studies account for the detection process while modeling tick data. We also categorized the types of analyses that are commonly used to model tick data. We used hierarchical models (HMs) that account for imperfect detection to analyze simulated and empirical tick data, demonstrating that inference is muddled when detection probability is not accounted for in the modeling process. Our review indicates that only 5 of 412 (1 %) papers explicitly accounted for imperfect detection while modeling ticks. By comparing HMs with the most common approaches used for modeling tick data (e.g., ANOVA), we show that population estimates are biased low for simulated and empirical data when using non-HMs, and that confounding occurs due to not explicitly modeling factors that influenced both detection and abundance. Our review and analysis of simulated and empirical data shows that it is important to account for our ability to detect ticks using field methods with imperfect detection. Not doing so leads to biased estimates of occurrence and abundance which could complicate our understanding of parasite-host relationships and the spread of tick-borne diseases. We highlight the resources available for learning HM approaches and applying them to analyzing tick data.

Maine↗

USGS2023

Evaluating a tandem human-machine approach to labelling of wildlife in remote camera monitoring

Remote cameras (“trail cameras”) are a popular tool for non-invasive, continuous wildlife monitoring, and as they become more prevalent in wildlife research, machine learning (ML) is increasingly used to automate or accelerate the labor-intensive process of labelling (i.e., tagging) photos. Human-machine hybrid tagging approaches have been shown to greatly increase tagging efficiency (i.e., time to tag a single image). However, those potential increases hinge on the extent to which an ML model makes correct vs. incorrect predictions. We performed an experiment using a ML model that produces bounding boxes around animals, people, and vehicles in remote camera imagery (MegaDetector) to consider the impact of a ML model’s performance on its ability to accelerate human labeling. Six participants tagged trail camera images collected from 12 sites in Vermont and Maine, USA (January–September 2022) using three tagging methods (one with ML bounding box assistance and two without assistance). We used a generalized linear mixed model to examine the influence of ML model performance and tagging method on tagging efficiency. We found that ML bounding boxes offer significant improvement in tagging efficiency when labelling data compared to unassisted tagging. Additionally, the time taken to label with bounding boxes was not statistically different from an unassisted tagging approach. However, we found that gains in efficiency are contingent on the ML algorithm’s performance and that incorrect ML predictions, particularly the 4.2% false positive and 3.6% false negative predictions, can slow the tagging process compared to a non-hybrid approach. These findings indicate that although practitioners usually forgo the production of bounding boxes when selecting a data labelling process due to the increased effort, ML bounding box-assisted tagging can offer an efficient method for labeling. More broadly, ML-assisted data labelling offers an opportunity to accelerate the analysis of trail camera imagery, but an assessment of the ML model’s performance can illuminate whether the hybrid-tagging approach is ultimately a help or hinderance.

Maine, Vermont↗