Name of the A brief description about the topic, and specific

faculty PhD topic requirements, if any

The project will deal with developing novel self-supervised
Biplab Self-supervised learning in the context of remote learning techniques for remote sensing image classification
Banerjee sensing image analysis under limited or sparse supervision
This interdisciplinary approach harnesses the combined
strengths of optical and radar remote sensing datasets to provide
comprehensive insights for urban applications. By fusing data
from both modalities, it enables a deeper understanding of urban
Avik Synergistic Integration of Optical and Radar Remote dynamics, facilitating more accurate mapping, monitoring, and
Bhattacharya Sensing Datasets for Urban Applications analysis of urban environments.
Compositional data analysis (Coda) approach to
Alok Porwal geochemical data for mineral exploration Good background of geology, geochemistry and geostatistics
Semi-supervised machine learning for delineating
geophysical/geochemical anomalies for targeting Good understanding of machine learning algorithms and good
Alok Porwal mineral deposits. coding skills

Good understanding of machine learning algorithms and good

Alok Porwal Text mining of geological reports coding skills
Climate change has a multitude of effects in terms of increase in
temperature, vapor pressure deficit, and frequency of dry
extreme events such as droughts and heatwaves. It is important
to understand how terrestrial ecosystems are responding to
these extremes since their sustenance is important in the context
of carbon sequestration and other benefits. This project deals
with studying the terrestrial ecosystem response using a variety
of remote sensing and reanalysis datasets. The focus will be on
soil-plant-atmosphere interactions. Candidates will have the
Karthikeyan Global terrestrial ecosystem response to dry extreme freedom to study both past and future responses using GCM
Lanka events simulations.
Soil moisture is an important variable that is present at the land-
atmosphere interface, which is responsible for the partitioning of
Karthikeyan Hyper resolution land surface modelling towards land surface fluxes into evapotranspiration, runoff, and
Lanka generating farm scale soil moisture profile simulations subsurface contributions. Accurate soil moisture information is
 critical for agriculture water management, monitoring of floods
and droughts, and land surface feedback mechanisms. This
project deals with setting up a hyper-resolution land surface
model, which has the ability to produce surface and rootzone soil
moisture at an unprecedented scale of 30 meters resolution and
subsequently ingest satellite data in a data assimilation algorithm
to simulate soil moisture fluxes at hyper-resolution scales in an
Indian catchment. The outcomes of the project can contribute to
the agriculture, hydrology, and climate communities of India.
Soil moisture has a significant role in influencing the feedback
from the land surface. There is a growing literature that depicts
its influence on the evolution of dry extreme events. This project
deals with a thorough examination of soil moisture feedback
using numerical weather model Weather Research and
Forecasting (WRF) model simulations. Specifically, we would be
interested to study the role of land using water and heat tracking
schemes when extreme dry events and compound extremes get
Karthikeyan Land-atmosphere interactions during dry extreme triggered. It is desirable for the candidates to have experience
Lanka events [with Prof. Vishal Dixit, IDPCS] running the WRF model.
Sub-seasonal to seasonal predictions are now the frontline
research to ensure adequate time for planning and adaptation.
There is limited effort that is made to carry out predictions at S2S
scales (1-3 months ahead) in India. This work deals with
developing models using machine learning or dynamical models
to predict various aspects of droughts at S2S scales. Candidates
Karthikeyan Sub-seasonal to seasonal agricultural drought with a good understanding of atmosphere processes and
Lanka prediction programming background are desirable for this project.
Prof. Surya Development of geospatial knowledge representation framework
Durbha Geospatial Knowledge Representation for Disasters
Prof. Surya
Durbha Geospatial Generative AI Understanding Generative AI for Geographic problems.
Deepak Understanding planetary evolution using Moon and Crater distribution and characteristics are similar and different in
Singh Mars caters distribution with Machine Learning many ways between Mars and Moon. This work will explore the
 planetary evolution using crater's distribution/characteristics with
Machine learning techniques.

The work will be done using current modeling techniques and

Deepak Characteristics and dynamics of Venus atmosphere latest observations of Venus. Some modeling/coding background
Singh and it's interaction with the surface is desired. MATLAB and fortran knowledge is a plus
Cryovolcanism process significantly alter the icy surface of icy
moons such as Europa, Enceladus etc. over a period of time.
This study will utilize state of the art modeling techniques along
with remote sensing observation to study the surface ice and it's
Deepak Surface characteristics and cryovolcanism evolution of evolution for icy moons of our solar system. Prior knowledge with
Singh solar system icy moons modeling and MATLAB is desired.
The PhD scholar will work towards developing an indigenous
software for monitoring deformation activities using Similar Time-
series Interferometric Pixels (STIP) based Multi-temporal SAR
Interferometry (MT-InSAR), which will utilize the information
available in the phase time series of highly coherent PS as well
as moderately coherent DS. The software will later be evaluated
Groundwater subsidence monitoring using distributed in monitoring groundwater changes and integrating it well level
Ashutosh scatterers in multi-temporal InSAR data acquired from groundwater monitoring wells.
Tiwari