1. |
- Gauld, Jethro G., et al.
(author)
-
Hotspots in the grid : Avian sensitivity and vulnerability to collision risk from energy infrastructure interactions in Europe and North Africa
- 2022
-
In: Journal of Applied Ecology. - : John Wiley & Sons. - 0021-8901 .- 1365-2664. ; 59:6, s. 1496-1512
-
Journal article (peer-reviewed)abstract
- Wind turbines and power lines can cause bird mortality due to collision or electrocution. The biodiversity impacts of energy infrastructure (EI) can be minimised through effective landscape-scale planning and mitigation. The identification of high-vulnerability areas is urgently needed to assess potential cumulative impacts of EI while supporting the transition to zero carbon energy. We collected GPS location data from 1,454 birds from 27 species susceptible to collision within Europe and North Africa and identified areas where tracked birds are most at risk of colliding with existing EI. Sensitivity to EI development was estimated for wind turbines and power lines by calculating the proportion of GPS flight locations at heights where birds were at risk of collision and accounting for species' specific susceptibility to collision. We mapped the maximum collision sensitivity value obtained across all species, in each 5 x 5 km grid cell, across Europe and North Africa. Vulnerability to collision was obtained by overlaying the sensitivity surfaces with density of wind turbines and transmission power lines. Results: Exposure to risk varied across the 27 species, with some species flying consistently at heights where they risk collision. For areas with sufficient tracking data within Europe and North Africa, 13.6% of the area was classified as high sensitivity to wind turbines and 9.4% was classified as high sensitivity to transmission power lines. Sensitive areas were concentrated within important migratory corridors and along coastlines. Hotspots of vulnerability to collision with wind turbines and transmission power lines (2018 data) were scattered across the study region with highest concentrations occurring in central Europe, near the strait of Gibraltar and the Bosporus in Turkey. Synthesis and applications. We identify the areas of Europe and North Africa that are most sensitive for the specific populations of birds for which sufficient GPS tracking data at high spatial resolution were available. We also map vulnerability hotspots where mitigation at existing EI should be prioritised to reduce collision risks. As tracking data availability improves our method could be applied to more species and areas to help reduce bird-EI conflicts.
|
|
2. |
- Resheff, Yehezkel S., et al.
(author)
-
How to treat mixed behavior segments in supervised machine learning of behavioural modes from inertial measurement data
- 2024
-
In: Movement Ecology. - : BioMed Central (BMC). - 2051-3933. ; 12:1
-
Journal article (peer-reviewed)abstract
- 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 similar to 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.
|
|