Combining Machine Learning & Reasoning for Biodiversity Data Intelligence

The current crisis in global natural resource management makes it imperative that we better leverage the vast data sources associated with taxonomic entities (such as recognized species of plants and animals), which are known collectively as biodiversity data. However, these data pose considerable challenges for artificial intelligence: while growing rapidly in volume, they remain highly incomplete for many taxonomic groups, often show conflicting signals from different sources, and are multi-modal and therefore constantly changing in structure. In this paper, we motivate, describe, and present a novel workflow combining machine learning and automated reasoning, to discover patterns of taxonomic identity and change – i.e. “taxonomic intelligence” – leading to scalable and broadly impactful AI solutions within the bio-

[1]  Bertram Ludäscher,et al.  Two Influential Primate Classifications Logically Aligned , 2016, Systematic biology.

[2]  Bertram Ludäscher,et al.  Reasoning about taxonomies in first-order logic , 2007, Ecol. Informatics.

[3]  Roberta E. Martin,et al.  Quantifying Tropical Plant Diversity Requires an Integrated Technological Approach. , 2020, Trends in ecology & evolution.

[4]  En Zhu,et al.  Deep Clustering with Convolutional Autoencoders , 2017, ICONIP.

[5]  Vincent S. Smith,et al.  No specimen left behind: industrial scale digitization of natural history collections , 2012, ZooKeys.

[6]  Y. Hu,et al.  Clinical features of patients infected with 2019 novel coronavirus in Wuhan, China , 2020, The Lancet.

[7]  R. Guralnick,et al.  The tempo and mode of the taxonomic correction process: How taxonomists have corrected and recorrected North American bird species over the last 127 years , 2018, PloS one.

[8]  Alena Bartonova,et al.  A global database for metacommunity ecology, integrating species, traits, environment and space , 2020, Scientific Data.

[9]  Gerald F Guala,et al.  The Importance of Species Name Synonyms in Literature Searches , 2016, PloS one.

[10]  Brett R. Scheffers,et al.  Global wildlife trade across the tree of life , 2019, Science.

[11]  Naeem Ramzan,et al.  Taxonomy Matching Using Background Knowledge , 2017, Springer International Publishing.

[12]  Pamela S Soltis,et al.  Old Plants, New Tricks: Phenological Research Using Herbarium Specimens. , 2017, Trends in ecology & evolution.

[13]  V. Nijman,et al.  Disappearing in the Night: An Overview on Trade and Legislation of Night Monkeys in South and Central America , 2017, Folia Primatologica.

[14]  Rachel L. White,et al.  Insights from social media into the illegal trade of wild raptors in Thailand , 2020 .

[15]  David Remsen,et al.  The use and limits of scientific names in biological informatics , 2016, ZooKeys.

[16]  J. Ratcliffe,et al.  Phylogeny matters: revisiting ‘a comparison of bats and rodents as reservoirs of zoonotic viruses’ , 2019, Royal Society Open Science.

[17]  Patrick Mäder,et al.  Machine learning for image based species identification , 2018, Methods in Ecology and Evolution.

[18]  N. Maxted,et al.  Spatial analyses of occurrence data of crop wild relatives (CWR) taxa as tools for selection of sites for conservation of priority CWR in Zambia , 2019, Plant Genetic Resources: Characterization and Utilization.

[19]  Connor J. Burgin,et al.  How many species of mammals are there? , 2018, Journal of Mammalogy.

[20]  Eyal Amir,et al.  Compact Propositional Encodings of First-Order Theories , 2005, IJCAI.

[21]  S. Ellis,et al.  The history and impact of digitization and digital data mobilization on biodiversity research , 2018, Philosophical Transactions of the Royal Society B.

[22]  V. Nijman,et al.  Wildlife trade shifts from brick-and-mortar markets to virtual marketplaces: A case study of birds of prey trade in Thailand , 2020, Journal of Asia-Pacific Biodiversity.

[23]  Jorge Soberón,et al.  A global perspective on decadal challenges and priorities in biodiversity informatics , 2015, BMC Ecology.

[24]  S. Marsden,et al.  Spatio-temporal dynamics of consumer demand driving the Asian Songbird Crisis , 2020 .

[25]  A. H. Malik,et al.  Impediment to Taxonomy and Its Impact on Biodiversity Science: An Indian Perspective , 2012, Proceedings of the National Academy of Sciences, India Section B: Biological Sciences.

[26]  Nico M. Franz,et al.  To increase trust, change the social design behind aggregated biodiversity data , 2017, bioRxiv.

[27]  E.J. Milner-Gulland,et al.  Illegal Wildlife Trade: Scale, Processes, and Governance , 2019, Annual Review of Environment and Resources.

[28]  R. Peet,et al.  Perspectives: Towards a language for mapping relationships among taxonomic concepts , 2009 .

[29]  C. Rondinini,et al.  Geographic distribution ranges of terrestrial mammal species in the 1970s. , 2019, Ecology.

[30]  R. Jacobs,et al.  The species dilemma and its potential impact on enforcing wildlife trade laws , 2018, Evolutionary anthropology.

[31]  Anne Bowser,et al.  The Bari Manifesto: An interoperability framework for essential biodiversity variables , 2019, Ecol. Informatics.

[32]  Bertram Ludäscher,et al.  Verbalizing phylogenomic conflict: Representation of node congruence across competing reconstructions of the neoavian explosion , 2017, bioRxiv.

[33]  Bertram Ludäscher,et al.  Euler/X: A Toolkit for Logic-based Taxonomy Integration , 2013, WFLP 2013.

[34]  Harald Ganzinger,et al.  Set constraints are the monadic class , 1993, [1993] Proceedings Eighth Annual IEEE Symposium on Logic in Computer Science.

[35]  Robert Mesibov,et al.  An audit of some processing effects in aggregated occurrence records , 2018, ZooKeys.

[36]  Le Prestre,et al.  Governing Global Biodiversity : The Evolution and Implementation of the Convention on Biological Diversity , 2002 .

[37]  Leopold Löwenheim.  Über Möglichkeiten im Relativkalkül , 1915 .

[38]  Anthony G. Cohn,et al.  Qualitative Spatial Representation and Reasoning , 2008, Handbook of Knowledge Representation.

[39]  Christoph Fink,et al.  A framework for investigating illegal wildlife trade on social media with machine learning , 2018, Conservation biology : the journal of the Society for Conservation Biology.

[40]  P. Curtis,et al.  Herbarium specimens reveal the footprint of climate change on flowering trends across north-central North America , 2013, Ecology letters.

[41]  Georgina M Mace,et al.  The role of taxonomy in species conservation. , 2004, Philosophical transactions of the Royal Society of London. Series B, Biological sciences.

[42]  Beckett W. Sterner,et al.  Coordinating dissent as an alternative to consensus classification: insights from systematics for bio-ontologies , 2020, History and Philosophy of the Life Sciences.

[43]  James P. Balhoff,et al.  Matching arthropod anatomy ontologies to the Hymenoptera Anatomy Ontology: results from a manual alignment , 2013, Database J. Biol. Databases Curation.

[44]  Nico M. Franz,et al.  Taxonomy for Humans or Computers? Cognitive Pragmatics for Big Data , 2017 .

[45]  Konstantin Olschofsky,et al.  Rapid field identification of cites timber species by deep learning , 2020 .

[46]  V. Nijman,et al.  Illegal pet trade on social media as an emerging impediment to the conservation of Asian otters species , 2018, Journal of Asia-Pacific Biodiversity.

[47]  J. Hawkins,et al.  Comparison of Herbarium Label Data and Published Medicinal Use: Herbaria as an Underutilized Source of Ethnobotanical Information , 2017, Economic Botany.

[48]  Staffan Müller-Wille,et al.  Natural history and information overload: The case of Linnaeus , 2012, Studies in history and philosophy of biological and biomedical sciences.

[49]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[50]  The Gene Ontology Consortium.  Expansion of the Gene Ontology knowledgebase and resources , 2016, Nucleic Acids Res..

[51]  Cesare Tinelli,et al.  Quantifier Instantiation Techniques for Finite Model Finding in SMT , 2013, CADE.

[52]  Priscilla H. C. Crawford,et al.  Can herbarium records be used to map alien species invasion and native species expansion over the past 100 years? , 2009 .

[53]  Robert Mesibov,et al.  A specialist’s audit of aggregated occurrence records , 2013, ZooKeys.