Institute for Environmental Solutions, Forest Owners’ Consulting Centre and Latvian State Forest Research Institute "Silava" with support from European Regional Development Fund, develop novel ICT-based (data-driven) wild animal (ungulate) census methodology to support decision making on sustainable wildlife management and conflict resolution among landowners, hunters and society.
Wild ungulates are a valuable natural resource with annual contribution of above 394 million EUR to the European Union’s (EU) economy through game meat production. Additionally, wild ungulate expansion is connected to damages exceeding 100 million EUR to agricultural crops and forests.
Despite the importance of abundance estimates, none of several ungulate monitoring methods used in Europe is satisfying in terms of cost-effectiveness and accuracy. The most commonly used ground-based counting techniques – snow tracking and drive counts – can lead to biased and/or imprecise results and are very labour intensive. Thus, there is a clear need for new, efficient, cost-effective, and reliable methods to estimate ungulate densities.
Currently, ungulate population management planning in Latvia is based on estimates without a regular census while also leaving out important indices, such as sex-age structure of the population, compliance of population density with the territorial capacity, scope of damage to other branches of economy. Total population size is calculated as arithmetic sum of all estimates reported from the game management units.
Sustainable adaptive wildlife management is a potential solution for loss reduction but requires reliable information on wildlife census for evidence-based decision making. Information communication technologies (ICT) based solutions should be considered as efficient, cost-effective, and reliable option.
During this project researchers will develop novel, automatic (with a low labour intensity) ICT-based wild animal census methodology by focusing on four dominant even-toed ungulates species in Latvia – red deer (Cervus elaphus), roe deer (Capreolus capreolus), elk (Alces alces) and wild boar (Sus scrofa). It is planned to test effective and remote data acquisition techniques with minimal human involvement – unmanned aerial vehicles equipped with thermal and visible light cameras, movement-activated camera traps, passive acoustic sensor networks and GPS tracking of animals.
Development of automatic data processing workflows will be based on advanced machine learning techniques and obtained target animal detection and classification data products will be linked to assessment of animal population and living space capacity in a fixed territory resulting in the methodology for wild animal census for sustainable wildlife management.
Project “ICT-based wild animal census approach for sustainable wildlife management” (No. 184.108.40.206/18/A/146) is part of European Regional Development Fund, 1.1.1 "Improve research and innovation capacity and the ability of Latvian research institutions to attract external funding, by investing in human capital and infrastructure" 220.127.116.11. measure “Support for applied research”.
Find more about this project here.