MeitY Sponsored Multilevel Capacity Building and Skilling in Industry-Aligned Emerging Technologies
Sponsored by: Ministry of Electronics and Information Technology (MeitY), Govt. of India
Course Name: Introduction to Spatial Computiing
Venue: Hybrid
Course Fee: Free
Duration: Starting from Oct 17, 2026 (Saturday)
Instructor: Prof. Gaurav Arora
Email: saksham.tech@iiitd.ac.in
Website: https://mcbs.iiitd.edu.in
Course Brief: Spatial Computing is rapidly transforming agriculture, climate science, environmental management, smart cities, autonomous systems, public health, and economic policy. This intensive boot camp introduces students to a comprehensive computational workflow for extracting information from spatial datasets; managing, manipulating and analyzing it; and developing spatially-aware analytical systems. Unlike traditional Geographic Information Systems (GIS) courses with a primary focus on mapping, this boot camp emphasizes using computational skills to ‘think’ and ‘plan’ with spatial data by integrating GIS, remote sensing, spatial statistics, spatial databases, causal inference and machine learning to solve real-world problems. Participants will build an end-to-end spatial computing pipeline using open-source software and publicly available datasets.
Motivation: Modern government and non-government agencies generate enormous volumes of spatial data from satellites, drones, mobile devices, IoT sensors, transportation systems, and administrative databases. Meaningful decision systems can be built with these data upon upskilling with GIS for visualization purposes and state-of-the-art computational apparatus for modelling, prediction, optimization, and decision-making frameworks. Overall, this course introduces the principles and tools needed to transform raw spatial data into actionable intelligence.
Course outcomes: At the end of this course, students will be able to
1. Understand spatial data structures and computational representations.
2. Process raster, vector, point cloud, and network datasets.
3. Develop reproducible spatial analysis workflows.
4. Build spatial statistical and econometric models.
5. Apply machine learning to geospatial datasets.
6. Integrate remote sensing products with socioeconomic databases.
7. Develop decision-support applications using spatial computing.
Eligibility: Students of physical, computation and social sciences (3rd year UG or above) who are interested in characterizing, comprehending and modeling the spatial dimension in modern datasets and conduct statistical inference for real-world applications
Pre-requisites: Students should have the knowledge of basic probability and statistics, linear algebra and differential calculus. In addition, basic programming skills will really help. No GIS experience is required.
Software Platforms: ArcGIS; R and Python
Course Schedule: [Format: 2 Hour Lecture + 4- Hour Lab Session]
Day 1:
Lecture: Introduction to spatial data, spatial random processes; spatial data generating processes; and spatial models. Geostatistical data, Lattice data, Point data
Lab: Spatial database management: public repositories, acquisition and visualization (Arc GIS-1)
Day 2:
Lecture: Spatial pattern recognition; exploratory spatial data analysis (ESDA); spatial stationarity; spatial autocorrelation: concept and measurement
Lab: Spatial data engineering: manipulation and analysis; ESDA with a real-world dataset (Arc GIS-2)
Day 3:
Lecture: Spatial statistical devices and their properties: Variogram, Semivariogram, Correlogram and Covariogram. Empirical variogram, directional variogram and variogram model fitting.
Lab: Variogram model fitting, estimation and cross-validation using a real-world dataset (R and Arc GIS)
Day 4:
Lecture: Spatial prediction: concept and application. Minimum variance unbiased estimators: Ordinary Kriging, Kriging with spatial covariance.
Lab: Kriging with real-world datasets (R); Kriging as a policy device: the case of groundwater governance.
Day 5:
Lecture: Spatial Econometrics and Regional science: Moving from characterizing spatial patterns to “explaining” them. Spatial autocorrelation structures: spatial weights matrix and spatial lag operators.
Lab: Preliminaries of regression analysis using R. Constructing spatial weights matrices using Arc GIS and R.
Day 6:
Lecture: Measuring spatial externalities using spatial weights matrix and spatial lag operators. Spatial Regression Analysis: alternative models (SAR, SEM, SDM and so on) and hypothesis testing (likelihood ratio test and langrage multiplier test)
Lab: Spatial regression analysis using R.
Day 7:
Lecture: Spatial regression analysis with machine learning approaches. Resource management and regional planning with a Statistical-Econometric Approach
Lab: Resource management and regional planning application: Spatial dependence and groundwater governance using U.P Groundwater Department datasets.
Day 8:
Lecture: Space-time processes; spatial-temporal statistics; spatio-temporal variogram estimation; spatio-temporal Kriging
Lab: Spatio-temporal prediction using R.
Days 9-10: Students will on a pre-defined project outlining a computational workflow pipeline to implement spatial computing tools for resource management and policy implementation. Students will present their findings. Dedicated doubt sessions will be scheduled.
Assessment: Students shall get the certification on the basis of the project and attendance in the course.