Dr Chandrama Sarker

Find Chandrama Sarker on


Chandrama has a background in remote sensing image analysis and water resources with a Bachelor in Geography and a Master of Geoinformation Science and Earth Observation with a specialization in Water Resources in the Netherlands. She did a Master of Engineering from the University of New South Wales.

Before joining the Centre she worked as a Research Associate in a project of the Indian Council of Agricultural Research, titled, “Development of Spectral Reflectance Methods and Low-Cost Sensors for Real-Time Application of Variable Rate inputs in Precision Farming”. After joining the Center, she completed her Ph.D. in automated flood mapping using advanced machine learning techniques supervised by Associate Professor Dr. Luis Mejias and Senior Lecturer Dr. Frederic Maire.

Chandrama’s research topic is “Automated Detection of Flooded Areas Using Machine Learning Methods.”

She’s involved in research that includes generating adaptive classification algorithms that are able to automatically detect flooded areas from multi-temporal, multi-spectral, and multi-sensor remote sensing images.

The objective of her research is to develop classification models utilizing deep feed-forward artificial neural networks that are able to differentiate permanent water bodies from flooded areas in real-time remote sensing images acquired by aerial or space-borne sensors.

Chandrama’s has joined the Company Downer Defence System as the Subject Matter Expert in Geospatial Data Science. Her roles there to help in doing the geospatial related data analysis in various projects the team involved and also to assist in prototyping various geo-spatial capabilities for future involvements.

Key Publications
1. Flood Mapping with Convolutional Neural Networks Using Spatio-Contextual Pixel Information.
URL: https://doi.org/10.3390/rs11192331

2. Integrating Recursive Bayesian Estimation with Support Vector Machine to Map Probability of Flooding from Multispectral Landsat Data
URL: http://ieeexplore.ieee.org/document/7797054/

3. Evaluation of the impact of image spatial resolution in designing a context-based fully convolution neural networks for flood mapping.
URL: http://dx.doi.org/10.1109/dicta47822.2019.8945888


Key Links:

ResearchGate: https://www.researchgate.net/profile/Chandrama_Sarker
Google Scholar: https://scholar.google.co.in/citations?hl=en&pli=1&user=shD4oqoAAAAJ
Spatial Informatics Lab: https://spatialinformatics.wordpress.com/mrs-chandrama-sarker/