Signals of local bioclimate-driven ecomorphological changes in wild birds

Abstract

Across disciplines—biological, ecological, evolutionary, or environmental—researchers increasingly recognize the importance and the need for cost-effective, non-invasive techniques for in-situ morphological measurements of organisms in diverse research contexts. By applying a non-invasive technique using digital images taken under field conditions, we successfully measured the body sizes of wild Painted Storks (Mycteria leucocephala) in two different biogeographic regions of India, spatially separated by 20° of latitude. We have used the wild Painted Storks as model species for measuring their morphometrics using a non-invasive technique that could easily be applied to similar species, rare, endemic, colonial, aquatic, and even those with cultural taboos. Our results satisfactorily classify and predict the sexes of the species and their biogeographic origin based on independent morphological variables using Machine Learning algorithms. The BayesNet yielded the correct classification instances (Receiver Operating Characteristic (ROC) = 0.985), outperforming all the other tested classifying algorithms. A strong relationship was observed between the local bioclimatic conditions and the morphological variations in wild Painted Storks reflecting clear eco-geographic patterns. Without this non-invasive technique, it would be almost impossible to collect morphological measurements at a large scale from live birds under field conditions. Our study is a testimony to the effectual use of the non-invasive digital method for in-situ measurements from free-living wild species in the field, assuming significance, especially from climate change perspectives, biology, ecology, and conservation.

Challenges and opportunities in applying AI to evolutionary morphology

“…The end goal of many studies using this approach is to assign an ecomorphological characterisation to phenotypic traits and to parse their ecological signal (Barr, 2018). AI has been implemented in this field through the use of algorithms that infer present and past ecomorphologies by reducing the dimensionality of ecomorphological data through ML pipelines such as Random Forest analyses (Mahendiran et al, 2022;Rabinovich, 2021;Sosiak and Barden, 2021;Spradley et al, 2019). Similarly, ML procedures have been used to discriminate and sort phenotypes (especially morphology) based on their belonging to specific ecomorphs or ecological guilds (MacLeod et al, 2022).…”

Ecological Role and Ecosystem Services of Birds: A Review

“…In natural ecosystems, birds are important dispersers of plant seeds, promoting and maintaining biodiversity and community structure [35]. Birds are one of the most important seed dispersers of about 80,000 species of angiosperms, of which about 25,000 are trees, shrubs, and herbaceous plants [36]. In addition, birds contribute to reforestation in deforested areas by helping in dispersing and germinating seeds, thereby reducing the cost of reforestation [37].…”