Developments in non-invasive techniques for identifying, assessing, and monitoring of wildlife populations (e.g., genetic analyses, camera traps) have advanced our ability to sample rare species without directly capturing and handling an animal, which could result in injury or death. Yet, when surveying a large and fragmented geographical area, these methods can be costly and difficult to employ. Subsequently, small populations, or rare species, may go unmonitored, or even undetected, and much needed management or conservation strategies may be employed too late, or not at all.
In our investigation, we seek to improve on methods for deploying and analyzing large-scale non-invasive methods of wildlife population data collection and analyses. We will utilize advanced technologies, such as wireless sensor networks and machine learning analyses, to develop more cost effective sampling methods and data analyses to detect, assess, and monitor species and populations over a large geographical area. These advanced technologies may be used in sample design, implementation, and sample and data analysis phases of the project. More cost-effective and efficient methods for detecting and monitoring of rare species will improve landscape-scale wildlife management and conservation efforts.
The findings of this project could be used to pursue external funding sources that allow us to continue, and to expand, our investigation.