Key Strengths

Extensive experience in geospatial data processing and analysis, including DEM super-resolution, void filling, and rainfall data extraction.
Proficiency in deep learning frameworks for geospatial applications (e.g., CRPAG for DEM void filling, ensemble learning for drought prediction).
Strong background in handling various geospatial data formats (NetCDF, GRIB) and cloud-optimized formats (Zarr).
Demonstrated ability to develop end-to-end pipelines for geospatial predictions, from data input to visualization (Plotly/Streamlit).
Experience with spatial statistics and sampling techniques for addressing class imbalance in geospatial datasets.

Cultural & Operational Fit

Cultural Fit Analysis

The candidate's projects are highly aligned with the 'Geospatial Data Scientist' target role, demonstrating a deep interest and practical experience in the field. The diversity of projects, ranging from computer vision for DEMs to climate data analysis and flood prediction, indicates a broad understanding of geospatial challenges. However, all listed projects are personal, and there is only one current professional experience entry with a future start date, which limits the assessment of collaborative work environments or broader organizational fit. The lack of diverse technologies beyond Jupyter Notebook and Python might indicate a narrower toolset, potentially impacting adaptability to different team tech stacks.

Soft Skills & Operational Fit

The candidate's project descriptions indicate a strong focus on problem-solving within the geospatial domain. The nature of the projects suggests an ability to work independently on complex technical challenges. However, without direct assessment data, specific soft skills like teamwork, leadership, or stress handling cannot be definitively evaluated.

AI is analyzing your overall score…

Identifying your key strengths…

Evaluating your skill match against the job requirements…

Sayantan Mandal

Geospatial Data Scientist

https://www.opentalent.in/sayantan-mandal

Geospatial Data Scientist, Remote Sensing & GIS consultant, Deep Learning, ML, AI prompt Engineering PhD, Research Scholar, University of Delhi

Delhi School of Economics, University of Delhi

New DelhiMember since June 12, 2026

https://www.opentalent.in/sayantan-mandal

Top Skills

Jupyter NotebookPython

Skills

Jupyter NotebookPython

Experience

Delhi School of Economics, University of Delhi

Geospatial Data Scientist

June 12, 2026 – Present

Projects

apis_Agent_1_CV_Phraser

February 10, 2026 – Present

apis_Agent_1_CV_Phraser — GitHub repository

View Project

DSHAT-Code-of-Computer-Vision-for-DEM-Super-resolution

October 21, 2025 – October 21, 2025

The DS-HAT framework is dedicated to the Super-Resolution (SR) stage of the pipeline, which effectively enhances the spatial resolution of globally available low-resolution DEMs.

View Project

CRPAG-Code-of-Computer-Vision-for-DEM-void-filling

September 25, 2025 – September 25, 2025

The Conditional Residual Pyramid Attentional Generator (CRPAG) is a specialized deep learning framework designed to reconstruct voids in Digital Elevation Models (DEMs) with high accuracy and terrain fidelity. Unlike conventional methods (e.g., interpolation, U-Nets, CNNs), CRPAG leverages multi-modal fusion, to deliver state-of-the-art performance

View Project

NASA-IMERG-Data-Extraction-Pipeline-and-Cloudburst-Detection

August 24, 2025 – August 24, 2025

Detailed Tutorial with complete visualization of how hourly NASA IMERG rainfall (NetCDF format) was extracted for a local area, analyzed at the grid-cell level, flagged for cloudbursts (≥ 100 mm/day), and published as an interactive Plotly/Streamlit dashboard.

View Project

Deep-Ensemble-Learning-model-for-Drought-Prediction

July 3, 2025 – July 3, 2025

Ensemble Deep Learning is a highly efficient method in ML and Deep Learning (DL) that leverages this combined knowledge of multiple DL models to enhance the accuracy of predictions. It combines several classifiers to address biases, limit overfitting, and improve robustness.

View Project

ERA5_data_extraction_and_post_processing

June 12, 2025 – June 12, 2025

This repository provides a comprehensive Python script for extracting, processing, and analyzing ERA5 hourly reanalysis data and how to load GRIB files, filter specific meteorological variables, perform necessary unit conversions, merge datasets, visualize time series, and efficiently save the processed data into the cloud-optimized Zarr format.

View Project

Flood-Prediction-using-Random-Forest-Algorithm

June 8, 2025 – June 8, 2025

This code demonstrates a streamlined workflow for building and deploying machine learning models for geospatial predictions, moving seamlessly from vector data input to raster output.

View Project

Geospatial-Data-Balancing-for-Machine-Learning-A-Spatially-Stratified-Sampling-Approach

June 7, 2025 – June 7, 2025

This repository presents a novel and scientifically robust methodology for addressing class imbalance in geospatial machine learning datasets, particularly those where rare events (minority class) are significantly outnumbered by non-events (majority class). The approach integrates spatial buffering and K-Means clustering.if

View Project

-9999-GIS-Data-Cleaner

May 18, 2025 – May 18, 2025

A GIS data cleaning tool for replacing -9999 values and visualizing missing data.

View Project

GEOAI-Driven-Rainfall-Time-Series-Extraction-and-Zarr-Based-Geospatial-Stacking

April 30, 2025 – June 5, 2025

Step by step GIS execution through Python

View Project

Key Strengths

Extensive experience in geospatial data processing and analysis, including DEM super-resolution, void filling, and rainfall data extraction.
Proficiency in deep learning frameworks for geospatial applications (e.g., CRPAG for DEM void filling, ensemble learning for drought prediction).
Strong background in handling various geospatial data formats (NetCDF, GRIB) and cloud-optimized formats (Zarr).
Demonstrated ability to develop end-to-end pipelines for geospatial predictions, from data input to visualization (Plotly/Streamlit).
Experience with spatial statistics and sampling techniques for addressing class imbalance in geospatial datasets.

Cultural & Operational Fit

Cultural Fit Analysis

Soft Skills & Operational Fit