Institute of Information Science, Academia Sinica



Press Ctrl+P to print from browser

TIGP (BIO)—Using Deep Learning to Understand the Evolution of Animal Morphology


TIGP (BIO)—Using Deep Learning to Understand the Evolution of Animal Morphology

  • LecturerDr. Sheng-Feng Shen (Biodiversity Research Center, Academia Sinica)
    Host: TIGP (BIO)
  • Time2022-03-24 (Thu.) 14:00 – 16:00
  • LocationAuditorium 101 at IIS New Building

How the seemingly infinite number of living forms on Earth evolved is a question that has interested biologists since Darwin's time and is considered to be one of the keys to understanding the evolution of life. However, how to objectively quantify and analyze a large number of biological forms has always been a difficult problem to solve. Recent breakthroughs in artificial intelligence and computer vision have provided possible solutions. Therefore, in this research project, we plan to apply deep learning methods to quantify the morphological diversity of major taxa of moths, sharks, and birds worldwide. We will use YOLOv4 to automatically detect, locate, and acquire biological images in photographs for analysis, train Convolutional Neural Network (CNN) to extract and quantify species feature patterns and use Variational Auto-Encoder (VAE) to generate explainable corresponding images of quantified features. We will use these objective computer vision methods to perform large-scale morphological analyses of animals to understand how evolutionary history and environmental pressures have shaped the evolution of these taxa' s morphological diversity. We believe that our research will revolutionize past studies that require subjective human definitions of animal characteristics.


As an evolutionary ecologist, I have used an integrative approach that includes behavioral observations, experimental manipulations, meta-analysis and evolutionary theoretical modeling, to study the (1) ecological and social determinants of social evolution, (2) the ecological consequences of sociality, (3) species range size and (4) population and species vulnerability to climate change. The model organisms I study mainly include cooperatively breeding birds, Taiwan yuhina Yuhina brunneiceps, social burying beetles Nicrophorus nepalensis Hope, 1831 and moths. My research contributes to the understanding of macroecology, such as species range size and range limits, using both evolutionary theory and experimental methods. I also use macroecological perspective to study the evolution of sociality, such as the influence of cooperative behavior of social organisms on their distribution ranges and abundance. Please visit my website to learn more about my research at 【Shen’s Lab】.