This interdisciplinary project demands a blend of knowledge and expertise in wireless communications, signal processing, microwave/RF imaging, and applied ML. The SoilX Project aims to develop a technology that facilitates efficient megafarm irrigation. It redesigns a radar integrates it with drones and equips it with Artificial intelligence (AI) for soil root-zone moisture classification. Farm irrigation designers will use the classification to optimally allocate irrigation equipment and water resources to different portions of the megafarm. The technology will create a high-speed 3D soil moisture map. The radar signal waveform design, processing, and AI algorithms will be investigated via our developed radar and in-situ lab-based measurements. More information about this project can be found on the SoilX project page.
My responsibilities:
Led a team of 6 PhD and 5 undergraduate students, defining research projects, managing their tasks, and tracking progress.
Collaborated on the prototype implementation of an Intelligent Ground Penetrating Radar (GPR).
Authored data science-related Grant Proposals focusing on 3D Non-Invasive Subsurface Imaging.
Led the design and implementation of machine learning-based signal feature extraction for GPR.
Mentored team members on GPR Data Analysis and end-to-end software development processes.
Directed the GPR/moisture probe data measurement campaign.
Coordinated the drafting of a review paper with multiple collaborators.
Managed the process of purchasing equipment and supplies, including Moisture Probe, Radar Components, Drone, and EMC absorbers.
Supported the establishment of the SoilX Lab, including setting up indoor and outdoor components.