Assistant Professor · Gauhati University
Nairit Barkataki
Ground penetrating radar, from the antenna to the neural network: building radar hardware and the AI that interprets what it sees underground.
About
Nairit Barkataki is an Assistant Professor in the Department of Instrumentation & USIC at Gauhati University. He has been working on the analysis and interpretation of ground penetrating radar (GPR) data using artificial intelligence since 2016.
He and his team have developed neural network models that detect buried objects and estimate their size, shape and material, and that estimate soil properties such as moisture and soil type from GPR data. The team is also building a prototype GPR system for research: it generates and transmits custom waveforms, works with a range of antennas and frequencies, and processes the data on an FPGA platform in real time using AI models developed in-house.
Research areas
Ground Penetrating Radar
Signal processing and hardware design
From an FPGA-based prototype radar to the algorithms that read its echoes: the size, shape and material of buried objects, and the moisture and type of the soil around them.
7 publications · Explore →
Electromagnetics
EM characterisation and antenna design
Designing, simulating and measuring antennas for GPR, where the antenna's centre frequency sets the balance between how deep the radar sees and how small a target it can resolve.
2 publications · Explore →
Artificial Intelligence
Deep learning on FPGAs and GPUs
Neural networks that turn raw radar data into measurements, trained on simulated and experimental GPR data, with the aim of running them in real time next to the radar.
6 publications · Explore →
Ground Penetrating Radar — Photo: CTBTO Preparatory Commission, CC BY 2.0, via Wikimedia Commons (cropped)
Latest papers
All papers →
Size estimation of underground targets from GPR frequency spectra: A deep learning approach
21 min read
Estimation of soil moisture from GPR data using Artificial Neural Networks
10 min read
A CNN model for predicting size of buried objects from GPR B-Scans
26 min read
Classification of Soil Types from GPR B-Scans using Deep Learning Techniques
12 min read
Recent publications
All publications →Efficient Hyperbola Detection and Fitting using Image Processing Techniques and Column-Connection Clustering
2023 Second International Conference on Advances in Computational Intelligence and Communication (ICACIC)
A Deep Neural Network with Electronic Nose for Water Stress Prediction in Khasi Mandarin Orange Plants
Measurement Science and Technology, vol. 34, 125152
Size estimation of underground targets from GPR frequency spectra: A deep learning approach
Journal of Applied Geophysics, vol. 213, 105009
Automatic Material Classification of Targets from GPR Data using Artificial Neural Networks
2022 IEEE Silchar Subsection Conference (SILCON)
A CNN model for predicting size of buried objects from GPR B-Scans
Journal of Applied Geophysics, vol. 200, 104620
Estimation of soil moisture from GPR data using artificial neural networks
2021 IEEE International Conference on Technology, Research, and Innovation for Betterment of Society (TRIBES)
Get in touch
For collaborations, student projects or questions about the research.