Saurabh Kaushik

Saurabh Kaushik

Postdoctoral Researcher, Geospatial Data Science, Machine Learning, Computer Vision, Geo-foundational Models, Transfomers, Data Fusion

Sitemap

A list of all the posts and pages found on the site. For you robots out there, there is an XML version available for digesting as well.

Pages

Posts

A Step-by-Step Guide to Acquiring Multisource Remote Sensing Data Using Python

less than 1 minute read

Published:

Read full blog here guide The intersection of computer vision, remote sensing, and earth observation has proven to be highly effective in monitoring and predicting Earth surface processes. These tasks often require combining multisource remote sensing data to provide complementary information to deep learning models. Since these models are data-intensive, performing large-scale analyses necessitates a sophisticated pipeline for downloading and processing multisource remote sensing data efficiently.

datasets

Glacial Lake-Bench

Global multi-sensor dataset for glacial lake mapping (S1 VV/VH, S2 bands, NDWI, DEM, slope).

Debris-Cover Glacier Training Dataset

Multisource Remote Sensing Dataset for training and evluating deep learning models for Debris-Covered Glacier Mapping (Global Supraglacial Debris Dataset GSDD)

portfolio

publications

Climate change drives glacier retreat in Bhaga basin located in Himachal Pradesh, India

Published in Geocarto International, 2018

Landslide Susceptibility Assessment
Figure: Features of some major glaciers with snout visible in 2017 satellite data. ACC-Z, accumulationzone; ABL-Z, ablation-zone; TSL-Z, transition zone; MM; medieval moraine; SGD, supraglacial debris;DGV, de-glaciated valley.

Recommended citation: Kaushik, S.*, Dharpure, J.K., Joshi, P.K., Ramanathan, A.L., & Singh, T. (2018). Climate change drives glacier retreat in Bhaga basin located in Himachal Pradesh, India. Geocarto International.
Download Paper

Development of glacier mapping in Indian Himalaya: a review of approaches

Published in International Journal of Remote Sensing, 2019

Recommended citation: Kaushik, S.*, Joshi, P. K., & Singh, T. (2019). Development of glacier mapping in Indian Himalaya: a review of approaches. International Journal of Remote Sensing.
Download Paper

Examining the Glacial Lake dynamics in a warming climate and GLOF modelling in parts of Chandra basin, Himachal Pradesh, India

Published in Science of the Total Environment, 2020

Landslide Susceptibility Assessment
Figure: The study reports applicability of Lake Detection Algorithm (LDA), glacial lake expansion in warming climate and GLOF modelling in parts of Western Himalaya.

Recommended citation: Kaushik, S.*, Rafiq, M., Joshi, P. K., & Singh, T. (2020). Examining the Glacial Lake dynamics in a warming climate and GLOF modelling in parts of Chandra basin, Himachal Pradesh, India. Science of the Total Environment.
Download Paper

Automated mapping of glacial lakes using multisource remote sensing data and deep convolutional neural network

Published in International Journal of Applied Earth Observation and Geoinformation, 2022

AEO3 AEO1
Proposed deep learning model (GLNet) and example of precise glacial lake mapping using GLNet.

Recommended citation: Kaushik, S.*, Singh, T., Joshi, P.K., & Dietz, A.J. (2022). Automated mapping of glacial lakes using multisource remote sensing data and deep convolutional neural network. International Journal of Applied Earth Observation and Geoinformation.
Download Paper

Landslide susceptibility assessment at the landscape level using multivariate analysis coupled with statistical algorithms: An insight from India’s Kailash Sacred Landscape, Western Himalaya

Published in Geomatics Natural Hazards and Risk, 2023

Landslide Susceptibility Assessment
Figure: Landslide susceptibility assessment at the landscape level using multivariate analysis coupled with statistical algorithms – An insight from India’s Kailash Sacred Landscape, Western Himalaya.

Recommended citation: Pandey, A., Sarkar, S.M., Palni, S., Parashar, D., Singh, G., Kaushik, S., Chandra, N., Costache, R., Singh, P.A., Mishra, P.A., Almohamad, H., Al-Mutiry, M., & Ghassan, A.H. (2023). Landslide susceptibility assessment at the landscape level using multivariate analysis coupled with statistical algorithms: An insight from India’s Kailash Sacred Landscape, Western Himalaya. Geomatics Natural Hazards and Risk.
Download Paper

Increasing risk of glacial lake outburst flood in Sikkim, Eastern Himalaya under climate warming

Published in Remote Sensing Applications: Society and Environment, 2024

Landslide Susceptibility Assessment
Figure: Identification of potentially dangerous glacial lakes in Sikkim Himalaya.

Recommended citation: Kaushik, S.*, Rafiq, M., Dharpure, J., Joshi, P. K., Singh, T., Howat, I., Moortgat, J., & Dietz, A.J. (2024). Glacial Lake outburst flood risk assessment and dam break modeling in Sikkim Himalaya. Remote Sensing Applications: Society and Environment.
Download Paper

Automatic extraction of glacial lakes from Landsat imagery using deep learning across the Third Pole

Published in Remote Sensing of Environment, 2024

Landslide Susceptibility Assessment
Figure: Glacial lakes in the TPR in 2020. a–p) The elevation distribution of glacial lakes for various sub-regions and the entire TPR, q) the distribution of glacial lake number and area (km2) on a 1o × 1o grid, where the circle sizes represent number, and the colors are area.

Recommended citation: Tang, Q., Zhang, G., Yao, T., Wieland, M., Liu, L., & Kaushik, S. (2024). Automatic extraction of glacial lakes from Landsat imagery using deep learning across the Third Pole. Remote Sensing of Environment.
Download Paper

Combining machine learning algorithms for bridging gaps in GRACE and GRACE Follow-On missions using ERA5-Land reanalysis

Published in Science of Remote Sensing, 2025

Landslide Susceptibility Assessment
Figure: Monthly multi-model Leader predictions of TWSA during the GRACE and GRACE-FO data gap (July 2017 to May 2018). Black boxes and circles highlight extreme events (drought and flood), while light green and light blue circles indicate strong seasonal variations in predicted TWSA.

Recommended citation: Dharpure, J.K., Howat, I.M., & Kaushik, S. (2024). Declining Groundwater Storage in the Indus Basin Revealed Using GRACE and GRACE-FO Data. Water Resources Research.
Download Paper

Assessing Geo-Foundational Models for Flood Inundation Mapping: Benchmarking models for Sentinel-1, Sentinel-2, and Planetscope

Published in Under-Review, 2025

Landslide Susceptibility Assessment
Figure: A visual analysis of model performance showing Clay, Prithvi, DOFA GFMs outperform traditional CNN models and vision transformers (TransNorm). Yellow boxes show examples of false positive classification by models.
Landslide Susceptibility Assessment
Figure: Fine-tuning Clay Geo-Foundation Model for flood inundation mapping.

Abstract

Geo-Foundational Models (GFMs) enable fast and reliable extraction of spatiotemporal information from satellite imagery, improving flood inundation mapping by leveraging location and time embeddings. Despite their potential, it remains unclear whether GFMs outperform traditional models like U-Net. A systematic comparison across sensors and data availability scenarios is still lacking, which is an essential step to guide end-users in model selection. To address this, we evaluate three GFMs, Prithvi 2.0, Clay V1.5, DOFA, and UViT (a Prithvi variant), against TransNorm, U-Net, and Attention U-Net using PlanetScope, Sentinel-1, and Sentinel-2. We observe competitive performance among all GFMs, with only 2-5% variation between the best and worst models across sensors. Clay outperforms others on PlanetScope (0.79 mIoU) and Sentinel-2 (0.70), while Prithvi leads on Sentinel-1 (0.57). In leave-one-region-out cross-validation across five regions, Clay shows slightly better performance across all sensors (mIoU: 0.72(0.04), 0.66(0.07), 0.51(0.08)) compared to Prithvi (0.70(0.05), 0.64(0.09), 0.49(0.13)) and DOFA (0.67(0.07), 0.64(0.04), 0.49(0.09)) for PlanetScope, Sentinel-2, and Sentinel-1, respectively. Across all 19 sites, leave-one-region-out cross-validation reveals a 4% improvement by Clay compared to U-Net. Visual inspection highlights Clay's superior ability to retain fine details. Few-shot experiments show Clay achieves 0.64 mIoU on PlanetScope with just five training images, outperforming Prithvi (0.24) and DOFA (0.35). In terms of computational time, Clay is a better choice due to its smaller model size (26M parameters), making it ~3x faster than Prithvi (650M) and 2x faster than DOFA (410M). Contrary to previous findings, our results suggest GFMs offer small to moderate improvements in flood mapping accuracy at lower computational cost and labeling effort compared to traditional U-Net.

Recommended citation: Kaushik, S., Maurya, L., Tellman, B., Zhang, Z., & Dharpure, J.K. (2025). Assessing the value of Geo-Foundational Models for Flood Inundation Mapping: Benchmarking models for Sentinel-1, Sentinel-2, and Planetscope for end-users. (Under-Review)
Download Paper

GLACIA: Instance-Aware Positional Reasoning for Glacial Lake Segmentation via Multimodal Large Language Model

Published in WACV (GeoCV-Workshop), 2026

Landslide Susceptibility Assessment
Figure: Conceptual shift from traditional segmentation (a) and VQA-based reasoning (b) to our reasoning-driven paradigm (c), which unifies accurate instance-specific masks with interpretable positional reasoning.

Recommended citation: Maurya Lalit, Kaushik Saurabh, Tellman Beth (2026). GLACIA: Instance-Aware Positional Reasoning for Glacial Lake Segmentation via Multimodal Large Language Model WACV (GeoCV-Workshop)
Download Paper

talks

teaching

Teaching philosophy

, , 1900

Teaching is one of the most direct ways a scientist can impact the world and make it a better place. It provides an opportunity to engage with and shape the lives of students who are preparing to be the leaders and citizens of the next generation. I see teaching and mentoring as an opportunity to create transformative change, one person at a time. Having worked with numerous professors during my PhD and postdoctoral positions, I was fortunate to observe the best elements of their various teaching styles. I will incorporate these elements into my own teaching philosophy, which centers on three main objectives: (i) inspiring students’ curiosity to develop questions about environmental change, (ii) using empirical data—both qualitative and quantitative—to explore these questions, and (iii) fostering an understanding that conceptualizing trade-offs is often more valuable than finding the “right” answer. Underlying my teaching philosophy is a commitment to diversity and inclusion, encompassing gender, racial, class, sexual, ability, religious, and other identities. My interdisciplinary background allows me to teach a variety of courses. I can teach methods courses at both the undergraduate and graduate levels, including Geographical Information Systems (in ArcGIS, QGIS, or Python), Digital Image Processing, Fundamentals of Remote Sensing , Remote Sensing Applications, and Earth Observation using Machine Learning and satellite data.

tools