Ungulate Detection and Species Classification from Camera Trap Images Using RetinaNet and Faster R-CNN.

Changes in the ungulate population density in the wild has impacts on both the wildlife and human society. In order to control the ungulate population movement, monitoring systems such as camera trap networks have been implemented in a non-invasive setup. However, such systems produce a large number of images as the output, hence making it very resource consuming to manually detect the animals. In this paper, we present a new dataset of wild ungulates which was collected in Latvia. Moreover, we demonstrate two methods, which use RetinaNet and Faster R-CNN as backbones, respectively, to detect the animals in the images. We discuss the optimization of training and impact of data augmentation on the performance. Finally, we show the result of aforementioned tune networks over the real world data collected in Latvia.

Bite Me: Bark Stripping Showed Negligible Effect on Volume Growth of Norway Spruce in Latvia.

Over the past few decades, increasing populations of cervid species in the Baltic region have reduced the quality and vitality of cultivated Norway spruce (Picea abies (L.) Karst.) stands. This study evaluated the effect of bark stripping on the volume growth of spruce trees in Latvia. Data collection took place in two forest stands. In each stand, 20 Norway spruce trees were sampled, 10 with visible bark damage scars and 10 control trees. Stem discs were collected from control trees at specified heights (0 m, 0.5 m, 1 m, 1.3 m, and 2 m, and then at one-metre intervals up to the top) and from damaged trees at additional specific points relative to the damage. Each disc was sanded and scanned; tree ring widths were measured in 16 radial directions using WinDendro 2012a software. Annual volume growth reconstruction was performed for each tree. Changes in relative volume growth were analysed in interaction with scar parameters, tree type (damaged/control), and pre-damage volume using linear regression models. The significance of parameter interactions was assessed using analysis of variance (ANOVA). Pairwise comparisons of estimated marginal means (EMMs) were conducted using Tukey's HSD post hoc test. No significant effect of bark stripping on the total stem volume increment was detected. However, the length of bark stripping scars had a significant impact on relative volume growth in the lower parts of the stems. These findings underscore the importance of further research examining a broader spectrum of cervid damage intensity and the effects of repeated damage on tree survival and growth.

Genetic Monitoring of Grey Wolves in Latvia Shows Adverse Reproductive and Social Consequences of Hunting.

Nowadays, genetic research methods play an important role in animal population studies. Since 2009, genetic material from Latvian wolf specimens obtained through hunting has been systematically gathered. This study, spanning until 2021, scrutinizes the consequences of regulated wolf hunting on population genetic metrics, kinship dynamics, and social organization. We employed 16 autosomal microsatellites to investigate relationships between full siblings and parent-offspring pairs. Our analysis encompassed expected and observed heterozygosity, inbreeding coefficients, allelic diversity, genetic distance and differentiation, mean pairwise relatedness, and the number of migrants per generation. The Latvian wolf population demonstrated robust genetic diversity with minimal inbreeding, maintaining stable allelic diversity and high heterozygosity over time and it is not fragmented. Our findings reveal the persistence of conventional wolf pack structures and enduring kinship groups. However, the study also underscores the adverse effects of intensified hunting pressure, leading to breeder loss, pack disruption, territorial displacement, and the premature dispersal of juvenile wolves.