Getting Started

Jupyter &Google Colab

Under Development

Launch ready-to-run Python notebook environments on Google Colab or copy pre-configured scripts for local Jupyter analysis.

Cloud Executable Templates

Google Colab provides a zero-setup, free cloud environment for running interactive python code. By loading our SDK in Google Colab or your local Jupyter installation, you can directly fetch planetary grids and stream them into scientific modeling pipelines.

Notebook Library

Language: Python (earth-engine, numpy, rasterio)

01. Sentinel-2 Imagery and NDVI Calculation

Learn how to query Sentinel-2 multispectral rasters, execute cloud filtering math, and calculate the Normalized Difference Vegetation Index (NDVI) dynamically in Python.

Launch in Colab

Language: Python (geopandas, scikit-learn, scipy)

02. Soil Carbon Benchmarking & Interpolation

Interlink spatial soil core lab results with environmental variables (elevation, temperature) and apply geo-spatial kriging interpolation models.

Launch in Colab

Language: Python (richdem, pysheds, matplotlib)

03. Hydrology Watershed Runoff Modeling

Import digital elevation maps (DEM) from Copernicus archives, calculate slopes/aspects, and model drainage watersheds.

Launch in Colab

Python Quickstart Code

Paste the following cell scripts inside your Jupyter notebook to install and perform an NDVI computation.

cell_install.sh

1	# Install the VELSTROM Python SDK and spatial mapping libraries
2	!pip install velstrom-sdk rasterio geopandas scikit-image --quiet

cell_main.py

1	import velstrom as vel
2	import numpy as np
3	import matplotlib.pyplot as plt
4
5	# Authenticate with credentials
6	session = vel.Session(api_key="vel_live_early_access_key")
7
8	# Pull Sentinel-2 bands for a specified area
9	imagery = session.get_raster(
10	bbox=[-122.68, 45.51, -122.65, 45.53],
11	bands=["B04", "B08"], # Red & NIR
12	date="2026-05-15"
13	)
14
15	# Compute NDVI in memory
16	red = imagery.read_band("B04").astype(float)
17	nir = imagery.read_band("B08").astype(float)
18	ndvi = (nir - red) / (nir + red + 1e-10)
19
20	# Visualize the computed index
21	plt.figure(figsize=(10, 6))
22	plt.imshow(ndvi, cmap="RdYlGn")
23	plt.colorbar(label="NDVI Value")
24	plt.title("Sentinel-2 NDVI Vegetation Map")
25	plt.show()