Learning to fly: integrating spatial ecology with unmanned aerial vehicle surveys

Baxter, Peter; Hamilton, Grant

doi:10.1002/ecs2.2194

Cited by 36 publications

(23 citation statements)

References 48 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The two key motivators for drone‐based automated methods are reducing (on‐ground) human observer bias and reducing cost (Baxter & Hamilton, ; Chabot & Bird, ; Hodgson et al., ; Hollings et al., ). For large and complex wildlife aggregations, such as our waterbird colonies, it is rarely possible to perform comprehensive on‐ground counts and so drone‐use provides an attractive option, and coupled with semi‐automated methods, presents significant time savings too.…”

Section: Discussionmentioning

confidence: 99%

“…Despite the interest in automated methods for counting aggregations of birds, their use by ecologists and managers for monitoring complex wildlife aggregations remains limited (Chabot & Francis, ), with manual approaches still dominating (Buckland et al., ; Drever et al., ). There are three key reasons that have been highlighted for the disconnect between new methods and their ecological application: (a) most methods have only been demonstrated at small spatial scales relative to real‐world applications (even if the number of individuals is very large) and in homogenous areas with little environmental complexity (Hollings et al., ); (b) ecological complexity and outcomes are not appropriately considered with respect to the mobility of individuals and variation in the types of target features of interest (Baxter & Hamilton, ); and (c) there is a high technical threshold for implementing most methods (Chabot & Francis, ).…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Monitoring large and complex wildlife aggregations with drones

et al. 2019

View full text Add to dashboard Cite

Recent advances in drone technology have rapidly led to their use for monitoring and managing wildlife populations but a broad and generalised framework for their application to complex wildlife aggregations is still lacking. We present a generalised semi‐automated approach where machine learning can map targets of interest in drone imagery, supported by predictive modelling for estimating wildlife aggregation populations. We demonstrated this application on four large spatially complex breeding waterbird colonies on floodplains, ranging from c. 20,000 to c. 250,000 birds, providing estimates of bird nests. Our mapping and modelling approach was applicable to all four colonies, without any modification, effectively dealing with variation in nest size, shape, colour and density and considerable background variation (vegetation, water, sand, soil, etc.). Our semi‐automated approach was between three and eight times faster than manually counting nests from imagery at the same level of accuracy. This approach is a significant improvement for monitoring large and complex aggregations of wildlife, offering an innovative solution where ground counts are costly, difficult or not possible. Our framework requires minimal technical ability, is open‐source (Google Earth Engine and R), and easy to apply to other surveys.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Monitoring large and complex wildlife aggregations with drones

et al. 2019

View full text Add to dashboard Cite

show abstract

“…The two key motivators for drone-based automated methods are reducing (on-ground) human observer bias and reducing cost Baxter & Hamilton 2018;Hodgson et al 2018;Hollings et al 2018). For large and complex wildlife aggregations, such as our waterbird colonies, it is rarely possible to perform comprehensive on-ground counts and so drone-use provides an attractive option, and coupled with semi-automated methods, presents significant time savings too.…”

Section: Cost-benefit Of the Semi-automated Approachmentioning

confidence: 99%

“…Drones should be viewed as a tool to complement ecological and environmental monitoring practitioners, rather than a replacement option. We suggest development of semi-automated approaches should focus on adaptability to deliver key monitoring indicators (Baxter & Hamilton 2018), and that detection methods themselves should aim for three main properties: 1) use predictor data that is easily derived from common drone-based (or airborne) imagery; 2) minimal parametrisation among environments, ensuring any parametrisation should be accessible to non-expert users; and 3) implementation on widely available platforms, not requiring significant local computing resources but able to manage large volumes of image data.…”

Section: Recommendationsmentioning

confidence: 99%

“…Despite the interest in automated methods for counting aggregations of birds, their use by ecologists and managers for monitoring complex wildlife aggregations remains limited (Chabot & Francis 2016), with manual approaches still dominating (Buckland et al 2012;Drever et al 2015). There are three key reasons that have been highlighted for the disconnect between new methods and their ecological application: 1) most methods have only been demonstrated at small spatial scales relative to real-world applications (even if the number of individuals is very large) and in homogenous areas with little environmental complexity (Hollings et al 2018); 2) ecological complexity and outcomes are not appropriately considered with respect to the mobility of individuals and variation in the types of target features of interest (Baxter & Hamilton 2018); and 3) there is a high technical threshold for implementing most methods (Chabot & Francis 2016).…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Monitoring large and complex wildlife aggregations with drones

Lyons¹,

Brandis²,

Murray³

et al. 2019

Preprint

View full text Add to dashboard Cite

•Recent advances in drone technology have rapidly led to their use for monitoring and managing wildlife populations but a broad and generalised framework for their application to complex wildlife aggregations is still lacking•We present a generalised semi-automated approach where machine learning can map targets of interest in drone imagery, supported by predictive modelling for estimating wildlife aggregation populations. We demonstrated this application on four large spatially complex breeding waterbird colonies on floodplains, ranging from ~20,000 to ~250,000 birds, providing estimates of bird nests•Our mapping and modelling approach was applicable to all four colonies, without any modification, effectively dealing with variation in nest size, shape, colour and density and considerable background variation (vegetation, water, sand, soil etc.). Our semi-automated approach was between 3 to 8 times faster than manually counting nests from imagery at the same level of accuracy•This approach is a significant improvement for monitoring large and complex aggregations of wildlife, offering an innovative solution for monitoring large and complex aggregations where ground counts are costly, difficult or not possible. Our framework requires minimal technical ability, is open-source (e.g., Google Earth Engine and R), and generalisable to other surveys

show abstract

Predicting the spatial expansion of an animal population with presence‐only data

Barton,

Healey,

Cordes

et al. 2023

Ecology and Evolution

View full text Add to dashboard Cite

Predictive models can improve the efficiency of wildlife management by guiding actions at the local, landscape and regional scales. In recent decades, a vast range of modelling techniques have been developed to predict species distributions and patterns of population spread. However, data limitations often constrain the precision and biological realism of models, which make them less useful for supporting decision‐making. Complex models can also be challenging to evaluate, and the results are often difficult to interpret for wildlife management practitioners. There is therefore a need to develop techniques that are appropriately robust, but also accessible to a range of end users. We developed a hybrid species distribution model that utilises commonly available presence‐only distribution data and minimal demographic information to predict the spread of roe deer (Capreolus caprelous) in Great Britain. We take a novel approach to representing the environment in the model by constraining the size of habitat patches to the home‐range area of an individual. Population dynamics are then simplified to a set of generic rules describing patch occupancy. The model is constructed and evaluated using data from a populated region (England and Scotland) and applied to predict regional‐scale patterns of spread in a novel region (Wales). It is used to forecast the relative timing of colonisation events and identify important areas for targeted surveillance and management. The study demonstrates the utility of presence‐only data for predicting the spread of animal species and describes a method of reducing model complexity while retaining important environmental detail and biological realism. Our modelling approach provides a much‐needed opportunity for users without specialist expertise in computer coding to leverage limited data and make robust, easily interpretable predictions of spread to inform proactive population management.

show abstract

Learning to fly: integrating spatial ecology with unmanned aerial vehicle surveys

Abstract: Citation: Baxter, P. W. J., and G. Hamilton. 2018. Learning to fly: integrating spatial ecology with unmanned aerial vehicle surveys. Ecosphere 9(4):Abstract. Despite the increasing importance of new survey tools such as unmanned aerial vehicles

Cited by 36 publications

References 48 publications

Monitoring large and complex wildlife aggregations with drones

Monitoring large and complex wildlife aggregations with drones

Monitoring large and complex wildlife aggregations with drones

Predicting the spatial expansion of an animal population with presence‐only data

Contact Info

Product

Resources

About