Table 1.
Summary of modelling approaches.
Table 2.
Identified data sources and their description of these variables.
Fig 1.
BNM configuration for Nankeen Kestrel, Straw-necked Ibis, and Cattle Egret.
(a) BNM design for Nankeen Kestrel, (b) BNM design for Straw-necked Ibis, (c) BNM design for Cattle Egret.
Fig 2.
Hazard species—abundance (vertical axis) against solar day (seasonality) (horizontal axis).
Blue markers indicate abundance on a particular day, orange markers shows days where at least one individual of the relevant hazard species was involved in a strike occurrence, and grey markers give the expected abundance on any day. (a) Cattle Egret abundance, seasonality, and expected abundance, (b) Nankeen Kestrel abundance, seasonality and expected abundance, (c) Straw-necked Ibis abundance, seasonality, and expected abundance.
Table 3.
Logistic regression modelling results for each of the three hazard species showing model quality (accuracy and F Score), attribute with highest feature importance in the model, and threshold value that maximises strike likelihood prediction accuracy.
Fig 3.
The receiver-operating characteristic (ROC) curve of the BNM.
(a) Nankeen Kestrel data set, (b) Straw-necked Ibis data set, (c) Cattle Egret data set.
Fig 4.
BNM configuration for Cattle Egret including conditional probabilities and indicative variables for high and low collision likelihood.
Node influence strength is given by the width of connecting arcs.
Fig 5.
BNM configuration for Nankeen Kestrel including conditional probabilities and indicative variables for high and low collision likelihood.
Node influence strength is given by the width of connecting arcs.
Fig 6.
BNM configuration for Straw-necked Ibis including conditional probabilities and indicative variables for high and low collision likelihood.
Node influence strength is given by the width of connecting arcs.
Table 4.
Cluster validation measures by hazard species.
Fig 7.
2-dimensional cluster plots for Cattle Egret, Straw-necked Ibis, and Nankeen Kestrel.
The axes for these plots are the principal components of the multi-dimensional vectors used as input to the K-means algorithm. (a) Cluster results for Cattle Egret where k = 2. Cluster 1 includes 187 days, cluster 2 includes 574 days. (b) Cluster results for Straw-necked Ibis where k = 2. Cluster 1 includes 191 days, cluster 2 includes 570 days. (c) Cluster results for Nankeen Kestrel where k = 2. Cluster 1 includes 130 days, cluster 2 includes 631 days.
Fig 8.
Silhouette plot of Cattle Egret where k = 2.
Fig 9.
Silhouette plot of Straw-necked Ibis where k = 2.
Fig 10.
Silhouette plot of Nankeen Kestrel where k = 2.
Table 5.
Clusters, collision probability, and 95% confidence interval by hazard species.
Fig 11.
Hazard species—Principal Component Analysis, PC1 and PC2 for Cattle Egret, Straw-necked Ibis, and Nankeen Kestrel.
For any variable, its contribution to overall variance is given by the distance from the origin (vector length) and is colour-coded (blue indicates a lower contribution, and red the highest). (a) Plot of contribution of variables to PC1 and PC2 for Cattle Egret. (b) Plot of contribution of variables to PC1 and PC2 for Straw-necked Ibis. (c) Plot of contribution of variables to PC1 and PC2 for Nankeen Kestrel.