UGUlhas Gondhali

Ulhas Gondhali

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


Ulhas Gondhali has a total of 17 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Wildlife management and conservation implications for Blackbuck corresponding with Tal Chhapar Wildlife Sanctuary, Rajasthan, India

    by Ulhas Gondhali, Yogendra Singh Rathore, Sandeep Kumar Gupta, Kanti Prakash Sharma

    Blackbuck Antilope cervicapra are native to the Indian subcontinent. Pressures from anthropogenic activities, including hunting, agriculture, urbanization, and deforestation, have led to the encroachment, and destruction of natural Blackbuck habitats. As a result, this species, once abundant, and often found close to human settlements, declined drastically in the 20th century. It almost became extinct in Bangladesh, Nepal, and Pakistan, leading to the Blackbuck being added to the IUCN Red List of Species. Nevertheless, many Blackbuck populations are still at risk owing to habitat loss, poaching, and threats from invasive species. This study addressed the issues related to Blackbuck conservation and management by examining conservation challenges in Tal Chhapar Wildlife Sanctuary as a case study. We describe protective measures and approaches for stakeholders in habitat management, and the mitigation of other conservation issues.

  • Open Access

    Descriptive Analysis of Online Wildlife Products Using Vision Language Models

    by Kinshuk Sharma, Juliana Silva Barbosa, Spencer Roberts, Ulhas Gondhali, Gohar Petrossian, Jennifer Jacquet, Juliana Freire, Sunandan Chakraborty


  • Open Access

    A Cost-Effective LLM-based Approach to Identify Wildlife Trafficking in Online Marketplaces

    by Juliana Silva Barbosa, Ulhas Gondhali, Gohar Petrossian, Kinshuk Sharma, Sunandan Chakraborty, Jennifer Jacquet, Juliana Freire

    Wildlife trafficking remains a critical global issue, significantly impacting biodiversity, ecological stability, and public health. Despite efforts to combat this illicit trade, the rise of e-commerce platforms has made it easier to sell wildlife products, putting new pressure on wild populations of endangered and threatened species. The use of these platforms also opens a new opportunity: as criminals sell wildlife products online, they leave digital traces of their activity that can provide insights into trafficking activities as well as how they can be disrupted. The challenge lies in finding these traces. Online marketplaces publish ads for a plethora of products, and identifying ads for wildlife-related products is like finding a needle in a haystack. Learning classifiers can automate ad identification, but creating them requires costly, time-consuming data labeling that hinders support for diverse ads and research questions. This paper addresses a critical challenge in the data science pipeline for wildlife trafficking analytics: generating quality labeled data for classifiers that select relevant data. While large language models (LLMs) can directly label advertisements, doing so at scale is prohibitively expensive. We propose a cost-effective strategy that leverages LLMs to generate pseudo labels for a small sample of the data and uses these labels to create specialized classification models. Our novel method automatically gathers diverse and representative samples to be labeled while minimizing the labeling costs. Our experimental evaluation shows that our classifiers achieve up to 95% F1 score, outperforming LLMs at a lower cost. We present real use cases that demonstrate the effectiveness of our approach in enabling analyses of different aspects of wildlife trafficking.


  • Open Access

    Crime script analysis of the illegal sales of spiny-tailed lizards on YouTube

    by Ulhas Gondhali, Antonia Merzon, Thanaphon Nunphong, Tzu-Ying Lo, Yu-Hsuan Liu, Gohar A. Petrossian

    The oil derived from the spiny-tailed lizards (STLs) is illegally sold as an alternative medicinal aphrodisiac that is claimed to cure male sexual dysfunction in addition to other bodily ailments. The high demand generated from this illegal trade is rapidly depleting the species from its natural habitat. The goal of this research is to uncover the process of cyber-enabled illegal trade in STLs. To achieve this goal, this research uses data from a total of 127 videos and 4608 comments associated with these videos and the crime script analysis technique to outline and detail the steps taken to poach, prepare, and sell oil derived from spiny-tailed lizards (STL) and other protected wild animals on YouTube. The results indicate that sellers, operating primarily from Pakistan, employ a variety of techniques to attract buyers, such as preparing the oil by dissecting alive STL while being captured in the video to show the authenticity of the product. In addition to YouTube, sellers use other social media platforms, including WhatsApp, Facebook, Instagram, and Twitter/X, to communicate with potential buyers and to advertise their products. These products are shipped around the world using international courier services, such as DHL and TCS, with primary markets in South Asia and the Middle East. The sellers accept money transactions from Western Union, MoneyGram, and PayPal. They also seem to operate without any major restrictions from local authorities or host social media platforms. Based on these findings, this research proposed various recommendations for policy and practice.


  • Open Access

    Estimating the Genetic Polymorphisms of Gujarat Population using 17 Y Chromosomal STR loci

    by Aditi Mishra, Ulhas Gondhali, Sumit Choudhary

    The present study aims to report genetic variations in unrelated male (n = 118) of the Gujarat population with the help of seventeen Y-STR markers (DYS456, DYS389I, DYS390, DYS389II, DYS458, DYS19, DYS385a/b, DYS393, DYS391, DYS439, DYS635, DYS392, Y GATA H4, DYS437, DYS438 and DYS448). Allele frequencies and forensic parameters were calculated. A total of 96 distinct alleles were reported with their corresponding allele frequency values ranging from 0.008 to 0.644. A higher value of discrimination capacity (0.9830) and haplotype diversity (0.9997) was observed in the studied population. A total of 116 haplotypes were observed among which 114 haplotypes were unique. The genetic diversity for 17 Y-STR ranged from 0.526 (DYS437) to 0.837 (DYS385b). The locus DYS385b showed the highest polymorphism (0.809). Genetic relationship and their corresponding p-value were also studied among the studied population and other Indian populations. Apart from this, the obtained results were evidenced by constructing a phylogenetic tree and were also shown using Multidimensional Scaling (MDS) plot. The higher value of haplotype diversity and discrimination capacity indicates greater potential in distinguishing male individuals from the studied population. Hence, it is assumed that generated population data are highly valuable for forensic caseworks and population genetics.