# Geospatial

Tutorials for satellite imagery, remote sensing, and earth and atmospheric modeling workloads.

### [GPU-accelerated climate modeling](https://www.union.ai/docs/v2/union/tutorials/geospatial/climate-modeling/page.md)

Run ensemble atmospheric simulations on H200 GPUs with multi-source data ingestion and real-time extreme event detection.

### [Satellite image classification](https://www.union.ai/docs/v2/union/tutorials/geospatial/satellite_image_classification/page.md)

Build a production-grade EfficientNet pipeline for land-use classification with caching, experiment tracking, and reporting.

## Subpages

- [GPU-accelerated climate modeling](https://www.union.ai/docs/v2/union/tutorials/geospatial/climate-modeling/page.md)
  - Overview
  - Implementation
  - Dependencies and container image
  - Simulation parameters and data structures
  - Task environments
  - Data ingestion: multiple sources in parallel
  - Preprocessing with Dask
  - GPU-accelerated atmospheric simulation
  - Distributing across multiple GPUs
  - The main workflow
  - Running the pipeline
  - Key concepts
  - Ensemble forecasting
  - Adaptive mesh refinement
  - Real-time event detection
  - Where to go next
- [Satellite image classification](https://www.union.ai/docs/v2/union/tutorials/geospatial/satellite_image_classification/page.md)
  - Background
  - Dataset
  - Model
  - Two-Phase Training
  - Pipeline
  - Task 1: Data Download (`dataset_env`)
  - Task 2: GPU Training (`training_env`)
  - Task 3: Report Generation (`report_env`)
  - Task 4: Orchestration (`pipeline_env`)
  - Running the Pipeline
  - What You Get

---
**Source**: https://github.com/unionai/unionai-docs/blob/main/content/tutorials/geospatial/_index.md
**HTML**: https://www.union.ai/docs/v2/union/tutorials/geospatial/