Toqi Tahamid Sarker

I study computer vision and deep learning for animal science, ecology, and agriculture, with a particular focus on small, efficient models and on predictions that report how far they can be trusted. My work spans three areas: optical gas imaging of methane emissions from cattle, distance estimation with prediction intervals for trail-camera wildlife surveys, and weed segmentation and growth stage classification. My current work develops grounded vision-language models that segment gas plumes and estimate their concentration.

I'm a PhD candidate at Southern Illinois University Carbondale, advised by Dr. Khaled R. Ahmed at the BASE Lab, and I will complete my PhD in May 2027. I also enjoy building software, from research tools for annotating and measuring images to full-stack web platforms. Before SIU, I was a Graduate Research Assistant at Georgia State University's Panacea Lab, where I worked on solar event tracking, and a co-founder and software engineer at Penguin Ecommerce in Dhaka, Bangladesh.

I have served as a teaching assistant for deep learning for computer vision, co-taught workshops on AI in animal science, and co-mentored three master's students. I'm on the 2026–27 academic and industry job market.