Dr. Kumar Mainali is a senior data scientist with a Ph.D. in ecology, evolution, and behavior, and an MS in statistics from The University of Texas at Austin. His research career spans diverse fields, including conservation biology, ecology, biogeography, climate change, human microbiome, behavior, and remote sensing.

‍

Dr. Mainali applies cutting-edge technology of machine learning and AI to predict complex problems, mathematical tools to solve fundamental questions in ecology and biogeography, and sophisticated statistical tools to understand processes, patterns, and mechanisms in ecology and earth systems. An AI system he co-developed accurately maps wetlands at high-resolution (1-m) using free data.

‍

Dr. Mainali has extensively worked on the models for mapping species distribution, both by applying and developing the methods. His research includes modeling over 700 species at local, national and global levels, contributing to numerous publications in renowned scientific journals.

‍

Notably, he devised a novel metric of biodiversity published in Science Advances, which received extensive global attention (~17,000 downloads in one year, 98th percentile attention score). This metric resolved a well-known, long-standing problem that plagued the traditionally used metrics of cooccurrence analysis.

‍

Moreover, Dr. Mainali performed one of the first sophisticated statistical analyses comparing expert maps of species range to SDM maps, introducing “expert score” metric to quantify their agreement.

‍

Additionally, he contributed to one of the earliest applications of formal causal models in human microbiome analysis. His work has been featured in over 50 media outlets in the U.S. and Australia.

‍

Recently, he served as a guest editor for a special section of the Journal of Biogeography, focusing on emerging technologies, including machine learning.