{"id":16197,"date":"2025-04-16T04:54:35","date_gmt":"2025-04-16T08:54:35","guid":{"rendered":"https:\/\/www.bu.edu\/cds-faculty\/?p=16197"},"modified":"2025-09-09T03:37:59","modified_gmt":"2025-09-09T07:37:59","slug":"cds-freshman-publishes-research-machine-learning-conservation","status":"publish","type":"post","link":"https:\/\/www.bu.edu\/cds-faculty\/2025\/04\/16\/cds-freshman-publishes-research-machine-learning-conservation\/","title":{"rendered":"From Frogs to Frontiers: CDS Freshman Publishes Research on Machine Learning and Conservation"},"content":{"rendered":"

While still in high school in Irvine, California, Nemai Anand set out to solve a surprisingly complex problem: how to identify frog species based on their calls despite having access to only sparse, noisy data. Driven by persistence and resourcefulness, he developed a machine learning solution on his home computer, working alongside his father, Anand Sampath. The result? A published research paper in the Journal of Emerging Investigators<\/a> <\/em>(March 2025) and the beginning of his academic journey at Boston University<\/a>\u2019s Faculty of Computing & Data Sciences<\/a> (CDS), where he is now a freshman.<\/p>\n

\u201cIt\u2019s incredibly rare to see a student enter their undergraduate studies with a published research paper already under their belt\u2014especially one that tackles a real-world challenge with such ingenuity,\u201d noted CDS Associate Provost Azer Bestavros<\/a>. \u201cNemai\u2019s work reflects not only technical skill but also a curiosity and drive that embody the spirit of CDS. We\u2019re excited to support his continued journey and look forward to the contributions he\u2019ll make in the years ahead.\u201d<\/p>\n

\"Photo
Boston University Freshman Nemai Anand (CDS’28)<\/figcaption><\/figure>\n

Classifying the Unheard<\/h2>\n

Anand’s research centers on building a machine learning classifier capable of identifying frog species in the Western Ghats\u2014a mountain range in India known as a biodiversity hotspot and known for its large number of endemic amphibians. \u201cBecause so many species in this region have very few recorded calls, there\u2019s a real challenge in training accurate models,\u201d Nemai explains. \u201cWe wanted to test how well a classifier could perform under data-scarce conditions.\u201d Because many frog species in the region are under-recorded, researchers lack the kind of robust datasets that are ideal for training machine learning models.<\/p>\n

\u201cI was interested in computer science because solving problems in coding was like a fun puzzle,\u201d Nemai said.\u00a0 His father, Anand Sampath, suggested the idea of building a frog call classifier. They chose to focus on the mountain range along the southwest coast of India, known for its dense biodiversity and high concentration of endemic amphibians.<\/p>\n

Anand\u2019s challenge was to build a system that could learn to recognize these species anyway. With only limited data available, Anand tested four data augmentation techniques: pitch shifting, time stretching, noise injection, and spectral augmentation. These methods were applied to expand the training set artificially. While spectral augmentation worked best individually, the real gains came from combining methods. \u201cEach technique perturbs the data differently,\u201d Anand explained. \u201cCombining them made the dataset more diverse, and the model learned better from it.\u201d<\/p>\n

Why Frogs?<\/h3>\n

Frogs are often described as biological alarms. Their sensitivity to environmental changes makes them ideal indicators of ecosystem health. But monitoring them in dense, remote regions like the Western Ghats is labor-intensive and inefficient. Anand\u2019s classifier could serve as the backbone of a lightweight, automated tool for researchers in the field: a way to detect species presence without intrusive surveys or costly equipment.<\/p>\n

\u201cThe Western Ghats are home to many endemic species, but there\u2019s little data on each one,\u201d Nemai noted. \u201cOur goal was to see whether we could still build something useful with what little we had.\u201d<\/p>\n

Listen to the recording of a Kemphole Night Frog.<\/span><\/em><\/p>\n\n\/cds-faculty\/files\/2025\/04\/Mudigere-27-Kemphole-Night-Frog.wav<\/a><\/audio>\n

Building Without Blueprints<\/h3>\n

What stands out most about the project is how independently it came together. With no formal advisor, lab access, or institutional resources, Anand built the entire study from the ground up, relying on self-teaching, experimentation, and occasional input from people he reached out to online. The final study was published in The Journal of Emerging Investigators, a peer-reviewed journal for high school researchers. Since its release, the work has drawn interest for its interdisciplinary approach and its promise as a model for low-cost, tech-enabled conservation tools.<\/p>\n

……..<\/h4>\n

\u201cI want to keep exploring how data science can be used across disciplines\u2014from conservation biology to infectious disease…and I\u2019m just getting started,\u201d Nemai Anand (CDS’28)<\/span><\/em><\/h4>\n

……..<\/h4>\n

From Amphibians to Antibodies<\/h3>\n

Now at BU, Nemai (CDS\u201928) continues pursuing his interests in machine learning and bioinformatics.<\/a> He plans to conduct research at the National Emerging Infectious Disease Laboratories (NEIDL) under Dr. John Misasi<\/a>, where he\u2019ll apply machine learning techniques to questions in immunology and bioinformatics. His transition from ecological data to biomedical research reflects his interest in using computation to uncover patterns across disciplines.<\/p>\n

For Anand, the next phase is about leveraging the flexibility of data science to pursue questions that matter, whether in a rainforest or a research lab. \u201cI want to keep exploring how data science can be used across disciplines\u2014from conservation biology to infectious disease,\u201d he says. \u201cThere\u2019s so much potential, and I\u2019m just getting started.\u201d<\/p>\n

Neeza Singh, CDS Research Communications Intern; Maureen McCarthy, Contributor<\/p>\n","protected":false},"excerpt":{"rendered":"

As a high schooler, Nemai Anand built a frog call classifier using machine learning\u2014work that led to a published paper and a future at Boston University CDS.<\/p>\n","protected":false},"author":18026,"featured_media":16200,"comment_status":"closed","ping_status":"open","sticky":false,"template":"","format":"standard","meta":[],"categories":[245,244],"tags":[27,785,26,477,803,784],"_links":{"self":[{"href":"https:\/\/www.bu.edu\/cds-faculty\/wp-json\/wp\/v2\/posts\/16197"}],"collection":[{"href":"https:\/\/www.bu.edu\/cds-faculty\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.bu.edu\/cds-faculty\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.bu.edu\/cds-faculty\/wp-json\/wp\/v2\/users\/18026"}],"replies":[{"embeddable":true,"href":"https:\/\/www.bu.edu\/cds-faculty\/wp-json\/wp\/v2\/comments?post=16197"}],"version-history":[{"count":15,"href":"https:\/\/www.bu.edu\/cds-faculty\/wp-json\/wp\/v2\/posts\/16197\/revisions"}],"predecessor-version":[{"id":16231,"href":"https:\/\/www.bu.edu\/cds-faculty\/wp-json\/wp\/v2\/posts\/16197\/revisions\/16231"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.bu.edu\/cds-faculty\/wp-json\/wp\/v2\/media\/16200"}],"wp:attachment":[{"href":"https:\/\/www.bu.edu\/cds-faculty\/wp-json\/wp\/v2\/media?parent=16197"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.bu.edu\/cds-faculty\/wp-json\/wp\/v2\/categories?post=16197"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.bu.edu\/cds-faculty\/wp-json\/wp\/v2\/tags?post=16197"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}