Spatial Intelligence Platform

SPATIAL
MIND

|

Building intelligent systems that fuse satellite imagery, sensor data, and AI to understand infrastructure, movement, environment, and spatial behaviour — from India to the world.

IIT Roorkee GeoAI Remote Sensing GNSS Earth Systems
Scroll
0Research Projects
0Years in Geospatial
0Publications
0Satellite Datasets

Flagship Framework · Raipur, Chhattisgarh

Geospatial Urban Nexus
Intelligence Framework

GUNIF is a five-stage modular GeoAI pipeline that integrates multi-temporal LULC, biophysical remote sensing indices (NDVI, NDWI, NDBI), land surface temperature, SUHI mapping, road networks, and CPCB air quality data into a single spatial intelligence architecture — producing the Urban Stress Index (USI) for evidence-based urban planning.

USI Urban Stress Index
=
UI Urbanization Index
NDBI · Road · PoI · BU∆
+
ESI Environmental Stress
LST Anomaly · PM₂.₅
EBI Ecological Buffer
NDVI · NDWI · Green Connectivity

Five-Stage Modular Pipeline

Stage 01
📥
Data Ingestion

ESRI LULC 10m, Landsat 8, OSM networks, WorldPop, CPCB — exclusively open datasets for global transferability.

Stage 02
🛰️
Biophysical Analysis

NDVI, NDBI, NDWI, LST retrieval, SUHI zoning, PM₂.₅ IDW interpolation across 512 harmonized 1 km grid cells.

Stage 03
📊
Spatial Statistics

Getis-Ord Gi* hotspots, Global Moran's I, LISA clustering, OLS diagnostics, and GWR with adaptive bi-square kernel.

Stage 04
🧮
Index Construction

PCA-weighted UI, equal-weight ESI, MSPA-derived EBI — all min-max normalized and synthesized into the composite USI.

Stage 05
🗺️
GeoAI Intelligence

Risk & vulnerability mapping, double-burden zone identification, actionable planning intelligence for Tier-2 cities globally.

Key Findings · Raipur Urban Agglomeration

+31.7%
Built-up expansion
2017–2025
~38%
Urban population in
high-to-critical stress
7.6%
Study area in
critical stress zones
2.3×
Faster growth within
2 km of highways
GeoAI Urban Stress Index GWR · OLS Land Surface Temperature SUHI Mapping Tier-2 Cities Raipur · Chhattisgarh Open Data

Live Intelligence Feed

What's New

Space science dispatches, live Earth events, and geospatial discoveries — curated in real-time from NASA, USGS, and global space newsrooms.

Core Domains

Research Capabilities

🛰️
Remote Sensing

Multi-temporal satellite imagery analysis, SAR processing, and spectral decomposition for land-cover mapping and change detection.

🧠
Geo-AI

Deep learning pipelines for spatial feature extraction, object detection in aerial imagery, and geospatial foundation models.

🗺️
Spatial Analytics

Advanced geostatistics, spatial econometrics, and scalable vector/raster workflows with GeoPandas, GDAL, and PostGIS.

🚗
Intelligent Mobility

GPS trajectory mining, urban mobility modelling, transport network analysis, and traffic pattern forecasting at city scale.

🌍
Earth Systems

Climate & environmental data pipelines from ERA5, MODIS, Sentinel — fused with ML for environmental intelligence.

📡
GNSS & Positioning

Precise point positioning, multi-GNSS processing, and real-time kinematic workflows for centimetre-level accuracy.

Peer-Reviewed Work

Selected Publications

IEEE Trans. ITS2023

Real-Time IoT-Based Connected Vehicle Infrastructure for Intelligent Transportation Safety

  • YOLO v4 on GPU: 0.9777 mAP at 74.26 fps — vehicle, pedestrian & animal detection
  • Geospatial hotspot zones relayed via cloud; dual-tier IoT alert (display + audio) on zone entry
  • IEEE Member publication — IIT Roorkee Geomatics Engineering Group
EXPLORE INSIGHTS →
ASCE J. Transp. Eng.2023

Advanced Transportation Safety Using Real-Time GIS-Based Alarming System for Animal-Prone Zones and Pothole Areas

  • YOLO v3 + GIS buffer-zone pipeline: 0.976 mAP; real-time driver alert before entering hazard buffer
  • ~3,500 pothole fatalities in India (2020) — hotspot mapping targets the highest-risk corridors
  • Foundation for autonomous vehicle safety integration in Indian road conditions
EXPLORE INSIGHTS →
Systems Engineering2021

Cost Reduction for Advanced Driver Assistance Systems Through Hardware Downscaling and Deep Learning

  • YOLO v3 on NVIDIA GTX 1060: 0.9618 precision, 74.36 fps at democratised cost
  • Comparative GPU benchmark for Indian automotive context; 421,104 accidental deaths cited (India 2019)
  • Framework for real-time congestion estimation and accident detection via affordable ADAS
EXPLORE INSIGHTS →
Geomatica2024

SMARTS: Sustainable Management and Agriculture Resource Technology System Using Remote Sensing Descriptors and IoT

  • Sentinel-2 vegetation-moisture indices over 10 years (2015–2024) to map moisture-deficit zones
  • IoT soil moisture sensors achieved 97.24% precision in real-time irrigation alerts
  • SMARTS architecture is location-agnostic and scalable for any agricultural geography
EXPLORE INSIGHTS →
Electrica2024

Hazardous Zone Identification by Spectral Analysis of Ground Penetrating Radar Response

  • 1 GHz ground-coupled GPR + Discrete Fourier Transform features; SVM classifier on IIT Roorkee campus data
  • Detects clay + water pockets beneath pavement — mechanism behind rainy-season road subsidence
  • Non-destructive evaluation tool for pre-monsoon infrastructure auditing
EXPLORE INSIGHTS →
J. Geography & Cartography2024

Adaptive Fuzzy Logic for Gap Filling in UAV Orthomosaics: A Methodology for Accurate Geospatial Mapping

  • Adaptive fuzzy logic + edge-detection correction of information loss in UAV orthomosaic stitching
  • Generates corrected orthomosaics, DSMs and DTMs with improved sub-metre spatial fidelity
  • Framework spans engineering, construction monitoring, and environmental management
EXPLORE INSIGHTS →
J. Geography & Cartography2025

Spatial Analysis and Classification of Land Use Patterns in Lucknow District Using GIS and Random Forest

  • Random Forest on Landsat: ~90% overall accuracy; built-up +484.59 km², wetlands −674.52 km²
  • Forest area −75.44 km²; wastelands converted to urban/agricultural use
  • Reliable LULC monitoring framework for heterogeneous Indian urban landscapes
EXPLORE INSIGHTS →
Discover Cities2025

Predictive Modeling of Land Cover Changes in Round-1 Smart Cities of India Using Cellular Automata and GIS

  • 20-year LULC (2001–2021) for Ahmedabad, Chennai, Jaipur & Surat; CA model projects to 2031
  • Ahmedabad: 183→252 km², Jaipur: 133→222 km² built-up over two decades
  • Thematic layers (slope, CBD distance, population density) drive CA spatial prediction
EXPLORE INSIGHTS →
J. Env. Eng. & Science2026

Satellite-Driven Assessment of Urban Pollution Susceptibility in West Bengal, India

  • Sentinel-5P (UV aerosol, CO, NO₂, HCHO) fused via weight-of-evidence modelling
  • Urban +44.9%, vegetation −8.06% (2017–2023); Kolkata & industrial districts highest susceptibility
  • Directly informs SDG-11 — emission control zones, sustainable urban planning, monitoring
EXPLORE INSIGHTS →

About

Where Space
Meets Intelligence

Spatial Mind is a research-driven platform at the intersection of geospatial science, machine learning, and Earth observation. Rooted at IIT Roorkee — India's foremost civil engineering and spatial technology institution — we build tools and knowledge that matter at scale.

Our work spans precision positioning, satellite analytics, mobility intelligence, and AI-driven terrain understanding. We collaborate globally while staying anchored in India's rich geospatial landscape.

Location
Roorkee, India
Affiliation
IIT Roorkee
Focus
GeoAI & Remote Sensing

Get In Touch

Let's Build Something
That Matters

Open to collaborations in GeoAI, remote sensing research, spatial data consultancy, and intelligent mobility systems.