Search

The application of supervised machine learning methods to identify behavioural modes from inertial measurements of bio-loggers has become a standard tool in behavioural ecology. Several design choices can affect the accuracy of identifying the behavioural modes. One such choice is the inclusion or exclusion of segments consisting of more than a single behaviour (mixed segments) in the machine learning model training data. Currently, the common practice is to ignore such segments during model training. In this paper we tested the hypothesis that including mixed segments in model training will improve accuracy, as the model would perform better in identifying them in the test data. We test this hypothesis using a series of data simulations on four datasets of accelerometer data coupled with behaviour observations, obtained from four study species (Damaraland mole-rats, meerkats, olive baboons, polar bears). Results show that when a substantial proportion of the test data are mixed behaviour segments (above ~ 10%), including mixed segments in machine learning model training improves the accuracy of classification. These results were consistent across the four study species, and robust to changes in segment length, sample size, and degree of mixture within the mixed segments. However, we also find that in some cases (particularly in baboons) models trained with mixed segments show reduced accuracy in classifying test data containing only single behaviour (pure) segments, compared to models trained without mixed segments. Based on these results, we recommend that when the classification model is expected to deal with a substantial proportion of mixed behaviour segments (> 10%), it is beneficial to include them in model training, otherwise, it is unnecessary but also not harmful. The exception is when there is a basis to assume that the training data contains a higher rate of mixed segments than the actual (unobserved) data to be classified—such a situation may occur particularly when training data are collected in captivity and used to classify data from the wild. In this case, excess inclusion of mixed segments in training data should probably be avoided. [ABSTRACT FROM AUTHOR]

Rivers support some of Earth's richest biodiversity.sup.1 and provide essential ecosystem services to society.sup.2, but they are often fragmented by barriers to free flow.sup.3. In Europe, attempts to quantify river connectivity have been hampered by the absence of a harmonized barrier database. Here we show that there are at least 1.2 million instream barriers in 36 European countries (with a mean density of 0.74 barriers per kilometre), 68 per cent of which are structures less than two metres in height that are often overlooked. Standardized walkover surveys along 2,715 kilometres of stream length for 147 rivers indicate that existing records underestimate barrier numbers by about 61 per cent. The highest barrier densities occur in the heavily modified rivers of central Europe and the lowest barrier densities occur in the most remote, sparsely populated alpine areas. Across Europe, the main predictors of barrier density are agricultural pressure, density of river-road crossings, extent of surface water and elevation. Relatively unfragmented rivers are still found in the Balkans, the Baltic states and parts of Scandinavia and southern Europe, but these require urgent protection from proposed dam developments. Our findings could inform the implementation of the EU Biodiversity Strategy, which aims to reconnect 25,000 kilometres of Europe's rivers by 2030, but achieving this will require a paradigm shift in river restoration that recognizes the widespread impacts caused by small barriers. Validated barrier inventories and modelling indicate that Europe's rivers are fragmented by more than one million barriers, such as dams, weirs and fords, causing major impacts on biodiversity., Author(s): Barbara Belletti [sup.1] [sup.29] , Carlos Garcia de Leaniz [sup.2] , Joshua Jones [sup.2] , Simone Bizzi [sup.1] [sup.30] , Luca Börger [sup.2] , Gilles Segura [sup.3] [sup.4] , [...]

Many animals return to their home areas (i.e., ‘homing’) after translocation to sites further away. Such translocations have traditionally been used in behavioral ecology to understand the orientation and migration behavior of animals. The movement itself can then be followed by marking and recapturing animals or by tracking, for example, using GPS systems. Most detailed studies investigating this behavior have been conducted in smaller vertebrates (e.g., birds, amphibians, and mice), whereas information on larger mammals, such as red deer, is sparse. We conducted GPS-assisted translocation experiments with red deer at two sites in the Czech Republic. Individuals were translocated over a distance of approximately 11 km and their home journey was tracked. Circular statistics were used to test for significant homeward orientation at distances of 100, 500, 1000, and 5000 m from the release site. In addition, we applied Lavielle trajectory segmentation to identify the different phases of homing behavior. Thirty-one out of 35 translocations resulted in successful homing, with a median time of 4.75 days (range 1.23–100 days). Animals were significantly oriented towards home immediately after release and again when they came closer to home; however, they did not show a significant orientation at the distances in between. We were able to identify three homing phases, an initial ‘exploratory phase’, followed by a ‘homing phase’ which sometimes was again followed by an ‘arrival phase’. The ‘homing phase’ was characterized by the straightest paths and fastest movements. However, the variation between translocation events was considerable. We showed good homing abilities of red deer after translocation. Our results demonstrate the feasibility of conducting experiments with environmental manipulations (e.g., to impede the use of sensory cues) close to the release site. The homing behavior of red deer is comparable to that of other species, and might represent general homing behavior patterns in animals. Follow-up studies should further dissect and investigate the drivers of the individual variations observed and try to identify the sensory cues used during homing. [ABSTRACT FROM AUTHOR]