USGS Science⌕ Search

Geology topics

Maitreyi Sur

Publications and source records attributed to Maitreyi Sur.

6 recordsLinked to original sources
USGS2023

Supervised versus unsupervised approaches to classification of accelerometry data

Sophisticated animal-borne sensor systems are increasingly providing novel insight into how animals behave and move. Despite their widespread use in ecology, the diversity and expanding quality and quantity of data they produce have created a need for robust analytical methods for biological interpretation. Machine learning tools are often used to meet this need. However, their relative effectiveness is not well known and, in the case of unsupervised tools, given that they do not use validation data, their accuracy can be difficult to assess. We evaluated the effectiveness of supervised ( n = 6), semi-supervised ( n = 1), and unsupervised ( n = 2) approaches to analyzing accelerometry data collected from critically endangered California condors ( Gymnogyps californianus ). Unsupervised K-means and EM (expectation–maximization) clustering approaches performed poorly, with adequate classification accuracies of <0.8 but very low values for kappa statistics (range: −0.02 to 0.06). The semi-supervised nearest mean classifier was moderately effective at classification, with an overall classification accuracy of 0.61 but effective classification only of two of the four behavioral classes. Supervised random forest (RF) and k-nearest neighbor (kNN) machine learning models were most effective at classification across all behavior types, with overall accuracies >0.81. Kappa statistics were also highest for RF and kNN, in most cases substantially greater than for other modeling approaches. Unsupervised modeling, which is commonly used for the classification of a priori-defined behaviors in telemetry data, can provide useful information but likely is instead better suited to post hoc definition of generalized behavioral states. This work also shows the potential for substantial variation in classification accuracy among different machine learning approaches and among different metrics of accuracy. As such, when analyzing biotelemetry data, best practices appear to call for the evaluation of several machine learning techniques and several measures of accuracy for each dataset under consideration.

Ecology and Evolution↗
USGS2021

Linking behavioral states to landscape features for improved conservation management

A central theme for conservation is understanding how animals differentially use, and are affected by change in, the landscapes they inhabit. However, it has been challenging to develop conservation schemes for habitat-specific behaviors. Here we use behavioral change point analysis to identify behavioral states of golden eagles ( Aquila chrysaetos ) in the Sonoran and Mojave Deserts of the southwestern United States, and we identify, for each behavioral state, conservation-relevant habitat associations. We modeled behavior using 186,859 GPS points from 48 eagles and identified 2,851 distinct segments comprising four behavioral states. Altitude above ground level (AGL) best differentiated behavioral states, with two clusters of short-distance movement behaviors characterized by low AGL (state 1 AGL = 14 m (median); state 2 AGL = 11 m) and two associated with longer-distance movement behaviors and characterized by higher AGL (state 3 AGL = 108 m; state 4 AGL = 450 m). Behaviors such as perching and low-altitude hunting were associated with short-distance movements in updraft-poor environments, at higher elevations, and over steeper and more north-facing terrain. In contrast, medium-distance movements such as hunting and transiting were over gentle and south-facing slopes. Long-distance transiting occurred over the desert habitats that generate the best updraft. This information can guide management of this species, and our approach provides a template for behavior-specific habitat associations for other species of management concern.

California↗
USGS2019

Relevance of individual and environmental drivers of movement of Golden Eagles

An animal's movement is expected to be governed by an interplay between goals determined by its internal state and energetic costs associated with navigating through the external environment. Understanding this ecological process is challenging when an animal moves in two dimensions and even more difficult for birds that move in a third dimension. To understand the dynamic interaction between the internal state of an animal and the variable external environment, we evaluated hypotheses explaining association of different covariates of movement and the trade‐offs birds face as they make behavioural decisions in a fluctuating landscape. We used ~870 000 GPS telemetry data points collected from 68 Golden Eagles Aquila chrysaetos to test demographic, diel, topographic and meteorological hypotheses to determine (1) the probability that these birds would be in motion and (2), once in motion, their flight speed. A complex and sometimes interacting set of potential internal and external factors determined movement behaviour. There was good evidence that reproductive state, manifested as age, sex and seasonal effects, had a significant influence on the probability of being in motion and, to a lesser extent, on speed of motion. Likewise, movement responses to the external environment were often unexpectedly strong. These responses, to northness of slope, strength of orographic updraft and intensity of solar radiation, were regionally and temporally variable. In contrast to previous work showing the role of a single environmental factor in determining movement decisions, our analyses support the hypothesis that multiple factors simultaneously interact to influence animal movement. In particular they highlighted how movement is influenced by the interaction between the individual's internal reproductive state and the external environment, and that, of the environmental factors, topographic influences are often more relevant than meteorological influences in determining patterns of flight behaviour. Further disentangling of how these internal and externals states jointly affect movement will provide additional insights into the energetic costs of movement and benefits associated with achieving process‐driven goals.

California↗
USGS2018

The utility of point count surveys to predict wildlife interactions with wind energy facilities: An example focused on golden eagles

Wind energy development is rapidly expanding in North America, often accompanied by requirements to survey potential facility locations for existing wildlife. Within the USA, golden eagles ( Aquila chrysaetos ) are among the most high-profile species of birds that are at risk from wind turbines. To m inimize golden eagle fatalities in areas proposed for wind development, modified point count surveys are usually conducted to estimate use by these birds. However, it is not always clear what drives variation in the relationship between on-site point count data and actual use by eagles of a wind energy project footprint. We used existing GPS-GSM telemetry data, collected at 15 min intervals from 13 golden eagles in 2012 and 2013, to explore the relationship between point count data and eagle use of an entire project footprint. To do this, we overlaid the telemetry data on hypothetical project footprints and simulated a variety of point count sampling strategies for those footprints. We compared the time an eagle was found in the sample plots with the time it was found in the project footprint using a metric we called “error due to sampling”. Error due to sampling for individual eagles appeared to be influenced by interactions between the size of the project footprint (20, 40, 90 or 180 km 2 ) and the sampling type (random, systematic or stratified) and was greatest on 90 km 2 plots. However, use of random sampling resulted in lowest error due to sampling within intermediate sized plots. In addition sampling intensity and sampling frequency both influenced the effectiveness of point count sampling. Although our work focuses on individual eagles (not the eagle populations typically surveyed in the field), our analysis shows both the utility of simulations to identify specific influences on error and also potential improvements to sampling that consider the context-specific manner that point counts are laid out on the landscape.

California↗
USGS2017

Improved supervised classification of accelerometry data to distinguish behaviors of soaring birds

Soaring birds can balance the energetic costs of movement by switching between flapping, soaring and gliding flight. Accelerometers can allow quantification of flight behavior and thus a context to interpret these energetic costs. However, models to interpret accelerometry data are still being developed, rarely trained with supervised datasets, and difficult to apply. We collected accelerometry data at 140Hz from a trained golden eagle ( Aquila chrysaetos ) whose flight we recorded with video that we used to characterize behavior. We applied two forms of supervised classifications, random forest (RF) models and K-nearest neighbor (KNN) models. The KNN model was substantially easier to implement than the RF approach but both were highly accurate in classifying basic behaviors such as flapping (85.5% and 83.6% accurate, respectively), soaring (92.8% and 87.6%) and sitting (84.1% and 88.9%) with overall accuracies of 86.6% and 92.3% respectively. More detailed classification schemes, with specific behaviors such as banking and straight flights were well classified only by the KNN model (91.24% accurate; RF = 61.64% accurate). The RF model maintained its accuracy of classifying basic behavior classification accuracy of basic behaviors at sampling frequencies as low as 10Hz, the KNN at sampling frequencies as low as 20Hz. Classification of accelerometer data collected from free ranging birds demonstrated a strong dependence of predicted behavior on the type of classification model used. Our analyses demonstrate the consequence of different approaches to classification of accelerometry data, the potential to optimize classification algorithms with validated flight behaviors to improve classification accuracy, ideal sampling frequencies for different classification algorithms, and a number of ways to improve commonly used analytical techniques and best practices for classification of accelerometry data.

PLoS ONE↗