Geo-Spatial Analysis using Google Earth Engine for Remote Sensing and Agriculture
This workshop aims to introduce participants to Google Earth Engine (GEE)—a cloud-based geospatial analysis platform—for applications in remote sensing, environmental monitoring, and agricultural intelligence. Attendees will gain foundational and practical experience in handling Earth observation datasets on the GEE platform. The workshop will also expose participants to Agri-Tech research using GEE, sharing insights from our recent works combining satellite data with deep learning for crop monitoring and analysis.
Dr. Kumar Rajamani
(Associate Director, CropIn Pvt Ltd)
Bio: Dr. Kumar Rajamani is Associate Director at Cropin Technologies Pvt. Ltd., with prior experience at KLA Tencor, Philips Research, GE GRC, and Robert Bosch. He holds a Ph.D. from the University of Bern and completed his postdoc at the University of Luebeck, focusing on medical deep learning. His interests span Deep Learning, AgriTech, Remote Sensing, and Medical Imaging, and he holds nine patents.
Dr. Praveen Pankajakshan
(Chief AI Scientist, UrbanKisaan Pvt. Ltd.)
Bio: Dr. Praveen Pankajakshan is currently a Visiting Researcher at Harvard University. With a Ph.D. (Summa cum Laude) in Signal and Image Processing from INRIA-CNRS-UNS, his work spans AI, remote sensing, agriculture, and biomedical signal processing. He has held research and leadership roles at Shell, Samsung SAIT, and the Pasteur Institute, and holds several patents and international publications.
Sai Kulvanth S
(AI Product Engineer, UrbanKisaan Pvt. Ltd.)
Bio: Sai Kulvanth is an AI engineer specializing in geospatial AI and precision agriculture. At UrbanKisaan, he builds scalable AI products that integrate satellite data for actionable insights in sustainable farming. His interests lie in remote sensing, time-series analysis, and explainable AI for agritech solutions.
Sai Shravan Gade
(AI/ML Engineer, imPAC Labs)
Bio: Sai Shravan is a currently working as AI/ML Engineer. He has an experience over the past 1 year in Data Science with Geospatial data on crop type classification and monitoring using Earth observation data.
Ashrith S
(Computer Vision Engineer, Kshema Pvt Ltd)
Bio: Ashrith is currently a CV engineer with a focus on satellite imagery interpretation, anomaly detection, and edge deployment of AI models. His recent projects involve data extraction, crop type classification using GEE and Deep Learning.
Vidyasager K
(Computer Vision Engineer, Kshema Pvt Ltd)
Bio: Vidyasager brings in hands-on with Land-Use Land-Cover (LUCL) classification using GEE. Currently working as a Computer Vision Engineer at Kshema Pvt Ltd.
- Primary Audience: Researchers, students, data scientists, environmental engineers, policy analysts, and practitioners in remote sensing
- Expected Participation: 40–60 attendees
- Prerequisites: Basic programming knowledge (JavaScript/Python preferred); familiarity with geospatial data is helpful but not mandatory
|
Time
|
Segment
|
Details
|
|
0–20 min
|
Introduction & Slide
Presentation to GeoSpatial AI
|
GEE overview, platform
capabilities, collection types
|
|
20-30 min
|
Setting up the server
|
Initializing project and getting started with GEE APIs.
|
|
30–60 min
|
Guided Hands-on Session I
|
Accessing image collections (Satellite, Weather, Radar) and filtering imagery
|
|
60– 90 min
|
Guided Hands-on Session II
|
Computing and Visualizing indices and trends
|
|
90–120 min
|
Use Case Demos
|
Crop monitoring, drought mapping, flood alerts
|
|
120–170 min
|
Recent Works
|
Our recent works in Argi-Tech using geo-spatial AI
|
|
170–180 min
|
Q&A + Resource sharing
|
Open Q&A, sharing scripts, notebooks, and GEE resources
|
- Participants will leave with practical experience in using GEE for real-world remote sensing tasks
- Ability to process and infer from Image Collections in Google Earth Engine
- Enhanced adoption of cloud geospatial tools among early researchers and institutions
- Potential for future collaborations in AI + Remote Sensing research and publishing research papers in the domain of Agri-Tech using GEE
