Jian Ding
Yale University
jian.ding@yale.edu
Bio
Jian Ding is a Ph.D. candidate in the Computer Science Department at Yale University, advised by Prof. Leandros Tassiulas. She holds an M.S. in Electrical and Computer Engineering from Rice University and a B.S. in Optical Engineering from Zhejiang University. Her research focuses on building wireless systems for next-generation communications and agricultural sensing. Her work has been recognized at ACM MobiCom (Best Paper Honorable Mention, 2019; Best Poster Runner-up, 2024) and by the community through the 2025 MobiSys Rising Star Award. She is also a recipient of the Yale Roberts Innovation Fund (2025), the Yale Planetary Solutions Acceleration Grant (2025), and is one of the inaugural Yale Engineering Innovation Fellows (2024).
Areas of Research
- Communications and Networking
Democratizing Future Agriculture: From Soil Sensors to RAN Infrastructure
Sustainable agriculture increasingly relies on intelligent, low-cost systems that can monitor environmental conditions, transmit data reliably, and support real-time decision-making. However, the adoption of such technologies remains limited by the high cost and complexity of specialized sensing and communication hardware. My research addresses this challenge by developing scalable, machine learning-driven systems that leverage commodity hardware and software-defined wireless platforms to enable precision agriculture. On the sensing side, I design algorithms that transform everyday devices, such as Wi-Fi radios and smartphone cameras, into multi-modal soil sensors. By combining signal processing with machine learning, these systems estimate soil properties like moisture, electrical conductivity, and carbon content without the need for custom hardware. The solutions are low-cost and have been tested across a range of real-world soil types. In parallel, I develop software-defined wireless systems that provide high-performance, low-latency connectivity using general-purpose CPUs. I show that massive MIMO baseband processing can be executed entirely in software, removing the need for expensive FPGAs or ASICs and enabling flexible, open wireless infrastructure for agricultural automation. By unifying sensing, communication, and machine learning through accessible hardware and scalable architectures, my research aims to democratize intelligent infrastructure for agriculture and other environmental and infrastructure systems.