Deep learning workflow to support in-flight processing of digital aerial imagery for wildlife population surveys

Deep learning shows promise for automating detection and classification of wildlife from digital aerial imagery to support cost-efficient remote sensing solutions for wildlife population monitoring. To support in-flight orthorectification and machine learning processing to detect and classify wildlife from imagery in near real-time, we evaluated deep learning methods that address hardware limitations and the need for processing efficiencies to support the envisioned in-flight workflow. We developed an annotated dataset for a suite of marine birds from high-resolution digital aerial imagery collected over open water environments to train the models. The proposed 3-stage workflow for automated, in-flight data processing includes: 1) image filtering based on the probability of any bird occurrence, 2) bird instance detection, and 3) bird instance classification. For image filtering, we compared the performance of a binary classifier with Mask Region-based Convolutional Neural Network (Mask R-CNN) as a means of sub-setting large volumes of imagery based on the probability of at least one bird occurrence in an image. On both the validation and test datasets, the binary classifier achieved higher performance than Mask R-CNN for predicting bird occurrence at the image-level. We recommend the binary classifier over Mask R-CNN for workflow first-stage filtering. For bird instance detection, we leveraged Mask R-CNN as our detection framework and proposed an iterative refinement method to bootstrap our predicted detections from loose ground-truth annotations. We also discuss future work to address the taxonomic classification phase of the envisioned workflow.

Using the R package popharvest to assess the sustainability of offtake in birds

The R package popharvest was designed to help assess the sustainability of offtake in birds when only limited demographic information is available. In this article, we describe some basics of harvest theory and then discuss several considerations when using the different approaches in popharvest to assess whether observed harvests are unsustainable. Throughout, we emphasize the importance of distinguishing between the scientific and policy aspects of managing offtake. The principal product of popharvest is a sustainable harvest index (SHI), which can indicate whether the harvest is unsustainable but not the converse. SHI is estimated based on a simple, scalar model of logistic population growth, whose parameters may be estimated using limited knowledge of demography. Uncertainty in demography leads to a distribution of SHI values and it is the purview of the decision-maker to determine what amounts to an acceptable risk when failing to reject the null hypothesis of sustainability. The attitude toward risk, in turn, will likely depend on the decision-maker's objective(s) in managing offtake. The management objective as specified in popharvest is a social construct, informed by biology, but ultimately it is an expression of social values that usually vary among stakeholders. We therefore suggest that any standardization of criteria for management objectives in popharvest will necessarily be subjective and, thus, hard to defend in diverse decision-making situations. Because of its ease of use, diverse functionalities, and a minimal requirement of demographic information, we expect the use of popharvest to become widespread. Nonetheless, we suggest that while popharvest provides a useful platform for rapid assessments of sustainability, it cannot substitute for sufficient expertise and experience in harvest theory and management.

Evaluation of harvest and information needs for North American sea ducks

Wildlife managers routinely seek to establish sustainable limits of sport harvest or other regulated forms of take while confronted with considerable uncertainty. A growing body of ecological research focuses on methods to describe and account for uncertainty in management decision-making and to prioritize research and monitoring investments to reduce the most influential uncertainties. We used simulation methods incorporating measures of demographic uncertainty to evaluate risk of overharvest and prioritize information needs for North American sea ducks (Tribe Mergini). Sea ducks are popular game birds in North America, yet they are poorly monitored and their population dynamics are poorly understood relative to other North American waterfowl. There have been few attempts to assess the sustainability of harvest of North American sea ducks, and no formal harvest strategy exists in the U.S. or Canada to guide management. The popularity of sea duck hunting, extended hunting opportunity for some populations (i.e., special seasons and/or bag limits), and population declines have led to concern about potential overharvest. We used Monte Carlo simulation to contrast estimates of allowable harvest and observed harvest and assess risk of overharvest for 7 populations of North American sea ducks: the American subspecies of common eider (Somateria mollissima dresseri), eastern and western populations of black scoter (Melanitta americana) and surf scoter (M. perspicillata), and continental populations of white-winged scoter (M. fusca) and long-tailed duck (Clangula hyemalis). We combined information from empirical studies and the opinions of experts through formal elicitation to create probability distributions reflecting uncertainty in the individual demographic parameters used in this assessment. Estimates of maximum growth (r_max), and therefore of allowable harvest, were highly uncertain for all populations. Long-tailed duck and American common eider appeared to be at high risk of overharvest (i.e., observed harvest < allowable harvest in 5–7% and 19–26% of simulations, respectively depending on the functional form of density dependence), whereas the other populations appeared to be at moderate risk to low risk (observed harvest < allowable harvest in 22–68% of simulations, again conditional on the form of density dependence). We also evaluated the sensitivity of the difference between allowable and observed harvest estimates to uncertainty in individual demographic parameters to prioritize information needs. We found that uncertainty in overall fecundity had more influence on comparisons of allowable and observed harvest than adult survival or observed harvest for all species except long-tailed duck. Although adult survival was characterized by less uncertainty than individual components of fecundity, it was identified as a high priority information need given the sensitivity of growth rate and allowable harvest to this parameter. Uncertainty about population size was influential in the comparison of observed and allowable harvest for 5 of the 6 populations where it factored into the assessment. While this assessment highlights a high degree of uncertainty in allowable harvest, it provides a framework for integration of improved data from future research and monitoring. It could also serve as the basis for harvest strategy development as management objectives and regulatory alternatives are specified by the management community.

Spatial modeling of wetland condition in the U.S. Prairie Pothole Region

We propose a spatial modeling framework for wetland data produced from a remote-sensing-based waterfowl habitat survey conducted in the U.S. Prairie Pothole Region (PPR). The data produced from this survey consist of the area containing water on many thousands of wetland basins (i.e., prairie potholes). We propose a two-state model containing wet and dry states. This model provides a concise description of wet probability, i.e., the probability that a basin contains water, and the amount of water contained in wet basins. The two model components are spatially linked through a common latent effect, which is assumed to be spatially correlated. Model fitting and prediction is carried out using Markov chain Monte Carlo methods. The model primarily facilitates mapping of habitat conditions, which is useful in varied monitoring and assessment capacities. More importantly, the predictive capability of the model provides a rigorous statistical framework for directing management and conservation activities by enabling characterization of habitat structure at any point on the landscape.