A satellite‐based mobile warning system to reduce interactions with an endangered species

Breece, Matthew W.; Oliver, Matthew J.; Fox, Dewayne A.; Hale, Edward A.; Haulsee, Danielle E.; Shatley, Matthew; Bograd, Steven J.; Hazen, Elliott L.; Welch, Heather

doi:10.1002/eap.2358

Cited by 10 publications

(4 citation statements)

References 39 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Dynamic management tools provide information on species distributions in space and time, environmental conditions, and activities of interest, to help guide such management (Lewison et al, 2015). The development of these tools for protected species has included whales (WhaleWatch; Hazen et al, 2017), fish (Atlantic Sturgeon Risk of Encounter; Breece et al, 2021), and turtles (TurtleWatch; Howell et al, 2015). In this study, we have improved on our earlier dynamic SDMs for Eastern Leatherback turtles (Degenford et al, 2021; Hoover et al, 2019) by combining different types of data to provide a more holistic estimate of their occurrence based on the environmental conditions to help inform and improve protection for this critically endangered population.…”

Section: Discussionmentioning

confidence: 99%

Integrating telemetry and point observations to inform management and conservation of migratory marine species

Liang

Bailey

Hoover³

et al. 2023

Ecosphere

View full text Add to dashboard Cite

Species distribution models have been widely used in both terrestrial and marine systems, and applications have included invasive species management, evaluating potential effects of climate change, and conservation. Generally, only a single type of data can be accommodated within the model structures used, which may lead to higher uncertainty in the predictions when the data are sparse. In this case, it can be beneficial to pool data from multiple sources and data types, such as fishery observations and telemetry data. An integrated

show abstract

Section: Discussionmentioning

confidence: 99%

Integrating telemetry and point observations to inform management and conservation of migratory marine species

Liang

Bailey

Hoover³

et al. 2023

Ecosphere

View full text Add to dashboard Cite

show abstract

“…Near-term environmental forecasts aid water resource managers in meeting both human and ecological needs. For example, forecasts of lake water quality enable better informed decisions about in situ management to meet safe drinking water criteria (Thomas et al, 2020), broad-scale flood forecasts alert the public and emergency responders to potentially harmful water inundation (Nevo et al, 2022), and forecasts of the distribution of endangered aquatic species (e.g., Atlantic sturgeon [Acipenser oxyrinchus]) allow commercial fishers to steer clear of potentially harmful interactions (Breece et al, 2021). Similarly, managers can use water temperature forecasts and monitoring to mitigate fish stress during warm periods through short-term interventions such as temporary fishing restrictions and closures (Boyd et al, 2010;Gale et al, 2013;Jeanson et al, 2021) or timed cool-water releases from reservoirs (Jager and Smith, 2008;Olden and Naiman, 2010;Zwart et al, 2022).…”

Section: Introductionmentioning

confidence: 99%

Evaluating deep learning architecture and data assimilation for improving water temperature forecasts at unmonitored locations

Zwart,

Diaz,

Hamshaw

et al. 2023

Front. Water

View full text Add to dashboard Cite

Deep learning (DL) models are increasingly used to forecast water quality variables for use in decision making. Ingesting recent observations of the forecasted variable has been shown to greatly increase model performance at monitored locations; however, observations are not collected at all locations, and methods are not yet well developed for DL models for optimally ingesting recent observations from other sites to inform focal sites. In this paper, we evaluate two different DL model structures, a long short-term memory neural network (LSTM) and a recurrent graph convolutional neural network (RGCN), both with and without data assimilation for forecasting daily maximum stream temperature 7 days into the future at monitored and unmonitored locations in a 70-segment stream network. All our DL models performed well when forecasting stream temperature as the root mean squared error (RMSE) across all models ranged from 2.03 to 2.11°C for 1-day lead times in the validation period, with substantially better performance at gaged locations (RMSE = 1.45–1.52°C) compared to ungaged locations (RMSE = 3.18–3.27°C). Forecast uncertainty characterization was near-perfect for gaged locations but all DL models were overconfident (i.e., uncertainty bounds too narrow) for ungaged locations. Our results show that the RGCN with data assimilation performed best for ungaged locations and especially at higher temperatures (>18°C) which is important for management decisions in our study location. This indicates that the networked model structure and data assimilation techniques may help borrow information from nearby monitored sites to improve forecasts at unmonitored locations. Results from this study can help guide DL modeling decisions when forecasting other important environmental variables.

show abstract

“…The former is based on using mechanistic or process‐based models to project an ecological system forward in time, whereas the latter is based on using the established statistical models together with forecasts of their key environmental predictors. For instance, correlative species distributions project future animal distributions according to forecasts of their environmental drivers (e.g., Barlow & Torres, 2021; Breece et al, 2021). This type of model is being used increasingly for managing human–wildlife conflicts in real time for the purpose of limiting the probability of encounter.…”

Section: Introductionmentioning

confidence: 99%

A real‐time data assimilative forecasting system for animal tracking

Randon

Dowd

Joy

2022

Ecology

View full text Add to dashboard Cite

Monitoring technologies now provide real-time animal location information, which opens up the possibility of developing forecasting systems to fuse these data with movement models to predict future trajectories. State-space modeling approaches are well established for retrospective location estimation and behavioral inference through state and parameter estimation. Here we use a statespace model within a comprehensive data assimilative framework for probabilistic animal movement forecasting. Real-time location information is combined with stochastic movement model predictions to provide forecasts of future animal locations and trajectories, as well as estimates of key behavioral parameters. Implementation uses ensemble-based sequential Monte Carlo methods (a particle filter). We first apply the framework to an idealized case using a nondimensional animal movement model based on a continuous-time random walk process. A set of numerical forecasting experiments demonstrates the workflow

show abstract

A satellite‐based mobile warning system to reduce interactions with an endangered species

Cited by 10 publications

References 39 publications

Integrating telemetry and point observations to inform management and conservation of migratory marine species

Integrating telemetry and point observations to inform management and conservation of migratory marine species

Evaluating deep learning architecture and data assimilation for improving water temperature forecasts at unmonitored locations

A real‐time data assimilative forecasting system for animal tracking

Contact Info

Product

Resources

About