GeoMaster
Comprehensive geospatial science skill covering GIS, remote sensing, spatial analysis, and ML for Earth observation across 70+ topics with 500+ code examples in 8 programming languages.
Installation
# Core Python stack (conda recommended)
conda install -c conda-forge gdal rasterio fiona shapely pyproj geopandas
# Remote sensing & ML
uv pip install rsgislib torchgeo earthengine-api
uv pip install scikit-learn xgboost torch-geometric
# Network & visualization
uv pip install osmnx networkx folium keplergl
uv pip install cartopy contextily mapclassify
# Big data & cloud
uv pip install xarray rioxarray dask-geopandas
uv pip install pystac-client planetary-computer
# Point clouds
uv pip install laspy pylas open3d pdal
# Databases
conda install -c conda-forge postgis spatialite
Quick Start
NDVI from Sentinel-2
import rasterio
import numpy as np
with rasterio.open('sentinel2.tif') as src:
red = src.read(4).astype(float) # B04
nir = src.read(8).astype(float) # B08
ndvi = (nir - red) / (nir + red + 1e-8)
ndvi = np.nan_to_num(ndvi, nan=0)
profile = src.profile
profile.update(count=1, dtype=rasterio.float32)
with rasterio.open('ndvi.tif', 'w', **profile) as dst:
dst.write(ndvi.astype(rasterio.float32), 1)
Spatial Analysis with GeoPandas
import geopandas as gpd
# Load and ensure same CRS
zones = gpd.read_file('zones.geojson')
points = gpd.read_file('points.geojson')
if zones.crs != points.crs:
points = points.to_crs(zones.crs)
# Spatial join and statistics
joined = gpd.sjoin(points, zones, how='inner', predicate='within')
stats = joined.groupby('zone_id').agg({
'value': ['count', 'mean', 'std', 'min', 'max']
}).round(2)
Google Earth Engine Time Series
import ee
import pandas as pd
ee.Initialize(project='your-project')
roi = ee.Geometry.Point([-122.4, 37.7]).buffer(10000)
s2 = (ee.ImageCollection('COPERNICUS/S2_SR_HARMONIZED')
.filterBounds(roi)
.filterDate('2020-01-01', '2023-12-31')
.filter(ee.Filter.lt('CLOUDY_PIXEL_PERCENTAGE', 20)))
def add_ndvi(img):
return img.addBands(img.normalizedDifference(['B8', 'B4']).rename('NDVI'))
s2_ndvi = s2.map(add_ndvi)
def extract_series(image):
stats = image.reduceRegion(ee.Reducer.mean(), roi.centroid(), scale=10, maxPixels=1e9)
return ee.Feature(None, {'date': image.date().format('YYYY-MM-dd'), 'ndvi': stats.get('NDVI')})
series = s2_ndvi.map(extract_series).getInfo()
df = pd.DataFrame([f['properties'] for f in series['features']])
df['date'] = pd.to_datetime(df['date'])
Core Concepts
Data Types
| Type |
Examples |
Libraries |
| Vector |
Shapefile, GeoJSON, GeoPackage |
GeoPandas, Fiona, GDAL |
| Raster |
GeoTIFF, NetCDF, COG |
Rasterio, Xarray, GDAL |
| Point Cloud |
LAS, LAZ |
Laspy, PDAL, Open3D |
Coordinate Systems
- EPSG:4326 (WGS 84) - Geographic, lat/lon, use for storage
- EPSG:3857 (Web Mercator) - Web maps only (don't use for area/distance!)
- EPSG:326xx/327xx (UTM) - Metric calculations, <1% distortion per zone
- Use
gdf.estimate_utm_crs() for automatic UTM detection
# Always check CRS before operations
assert gdf1.crs == gdf2.crs, "CRS mismatch!"
# For area/distance calculations, use projected CRS
gdf_metric = gdf.to_crs(gdf.estimate_utm_crs())
area_sqm = gdf_metric.geometry.area
OGC Standards
- WMS: Web Map Service - raster maps
- WFS: Web Feature Service - vector data
- WCS: Web Coverage Service - raster coverage
- STAC: Spatiotemporal Asset Catalog - modern metadata
Common Operations
Spectral Indices
def calculate_indices(image_path):
"""NDVI, EVI, SAVI, NDWI from Sentinel-2."""
with rasterio.open(image_path) as src:
B02, B03, B04, B08, B11 = [src.read(i).astype(float) for i in [1,2,3,4,5]]
ndvi = (B08 - B04) / (B08 + B04 + 1e-8)
evi = 2.5 * (B08 - B04) / (B08 + 6*B04 - 7.5*B02 + 1)
savi = ((B08 - B04) / (B08 + B04 + 0.5)) * 1.5
ndwi = (B03 - B08) / (B03 + B08 + 1e-8)
return {'NDVI': ndvi, 'EVI': evi, 'SAVI': savi, 'NDWI': ndwi}
Vector Operations
# Buffer (use projected CRS!)
gdf_proj = gdf.to_crs(gdf.estimate_utm_crs())
gdf['buffer_1km'] = gdf_proj.geometry.buffer(1000)
# Spatial relationships
intersects = gdf[gdf.geometry.intersects(other_geometry)]
contains = gdf[gdf.geometry.contains(point_geometry)]
# Geometric operations
gdf['centroid'] = gdf.geometry.centroid
gdf['simplified'] = gdf.geometry.simplify(tolerance=0.001)
# Overlay operations
intersection = gpd.overlay(gdf1, gdf2, how='intersection')
union = gpd.overlay(gdf1, gdf2, how='union')
Terrain Analysis
def terrain_metrics(dem_path):
"""Calculate slope, aspect, hillshade from DEM."""
with rasterio.open(dem_path) as src:
dem = src.read(1)
dy, dx = np.gradient(dem)
slope = np.arctan(np.sqrt(dx**2 + dy**2)) * 180 / np.pi
aspect = (90 - np.arctan2(-dy, dx) * 180 / np.pi) % 360
# Hillshade
az_rad, alt_rad = np.radians(315), np.radians(45)
hillshade = (np.sin(alt_rad) * np.sin(np.radians(slope)) +
np.cos(alt_rad) * np.cos(np.radians(slope)) *
np.cos(np.radians(aspect) - az_rad))
return slope, aspect, hillshade
Network Analysis
import osmnx as ox
import networkx as nx
# Download and analyze street network
G = ox.graph_from_place('San Francisco, CA', network_type='drive')
G = ox.add_edge_speeds(G).add_edge_travel_times(G)
# Shortest path
orig = ox.distance.nearest_nodes(G, -122.4, 37.7)
dest = ox.distance.nearest_nodes(G, -122.3, 37.8)
route = nx.shortest_path(G, orig, dest, weight='travel_time')
Image Classification
from sklearn.ensemble import RandomForestClassifier
import rasterio
from rasterio.features import rasterize
def classify_imagery(raster_path, training_gdf, output_path):
"""Train RF and classify imagery."""
with rasterio.open(raster_path) as src:
image = src.read()
profile = src.profile
transform = src.transform
# Extract training data
X_train, y_train = [], []
for _, row in training_gdf.iterrows():
mask = rasterize([(row.geometry, 1)],
out_shape=(profile['height'], profile['width']),
transform=transform, fill=0, dtype=np.uint8)
pixels = image[:, mask > 0].T
X_train.extend(pixels)
y_train.extend([row['class_id']] * len(pixels))
# Train and predict
rf = RandomForestClassifier(n_estimators=100, max_depth=20, n_jobs=-1)
rf.fit(X_train, y_train)
prediction = rf.predict(image.reshape(image.shape[0], -1).T)
prediction = prediction.reshape(profile['height'], profile['width'])
profile.update(dtype=rasterio.uint8, count=1)
with rasterio.open(output_path, 'w', **profile) as dst:
dst.write(prediction.astype(rasterio.uint8), 1)
return rf
Modern Cloud-Native Workflows
STAC + Planetary Computer
import pystac_client
import planetary_computer
import odc.stac
# Search Sentinel-2 via STAC
catalog = pystac_client.Client.open(
"https://planetarycomputer.microsoft.com/api/stac/v1",
modifier=planetary_computer.sign_inplace,
)
search = catalog.search(
collections=["sentinel-2-l2a"],
bbox=[-122.5, 37.7, -122.3, 37.9],
datetime="2023-01-01/2023-12-31",
query={"eo:cloud_cover": {"lt": 20}},
)
# Load as xarray (cloud-native!)
data = odc.stac.load(
list(search.get_items())[:5],
bands=["B02", "B03", "B04", "B08"],
crs="EPSG:32610",
resolution=10,
)
# Calculate NDVI on xarray
ndvi = (data.B08 - data.B04) / (data.B08 + data.B04)
Cloud-Optimized GeoTIFF (COG)
import rasterio
from rasterio.session import AWSSession
# Read COG directly from cloud (partial reads)
session = AWSSession(aws_access_key_id=..., aws_secret_access_key=...)
with rasterio.open('s3://bucket/path.tif', session=session) as src:
# Read only window of interest
window = ((1000, 2000), (1000, 2000))
subset = src.read(1, window=window)
# Write COG
with rasterio.open('output.tif', 'w', **profile,
tiled=True, blockxsize=256, blockysize=256,
compress='DEFLATE', predictor=2) as dst:
dst.write(data)
# Validate COG
from rio_cogeo.cogeo import cog_validate
cog_validate('output.tif')
Performance Tips
# 1. Spatial indexing (10-100x faster queries)
gdf.sindex # Auto-created by GeoPandas
# 2. Chunk large rasters
with rasterio.open('large.tif') as src:
for i, window in src.block_windows(1):
block = src.read(1, window=window)
# 3. Dask for big data
import dask.array as da
dask_array = da.from_rasterio('large.tif', chunks=(1, 1024, 1024))
# 4. Use Arrow for I/O
gdf.to_file('output.gpkg', use_arrow=True)
# 5. GDAL caching
from osgeo import gdal
gdal.SetCacheMax(2**30) # 1GB cache
# 6. Parallel processing
rf = RandomForestClassifier(n_jobs=-1) # All cores
Best Practices
- Always check CRS before spatial operations
- Use projected CRS for area/distance calculations
- Validate geometries:
gdf = gdf[gdf.is_valid]
- Handle missing data:
gdf['geometry'] = gdf['geometry'].fillna(None)
- Use efficient formats: GeoPackage > Shapefile, Parquet for large data
- Apply cloud masking to optical imagery
- Preserve lineage for reproducible research
- Use appropriate resolution for your analysis scale
Detailed Documentation
- Coordinate Systems - CRS fundamentals, UTM, transformations
- Core Libraries - GDAL, Rasterio, GeoPandas, Shapely
- Remote Sensing - Satellite missions, spectral indices, SAR
- Machine Learning - Deep learning, CNNs, GNNs for RS
- GIS Software - QGIS, ArcGIS, GRASS integration
- Scientific Domains - Marine, hydrology, agriculture, forestry
- Advanced GIS - 3D GIS, spatiotemporal, topology
- Big Data - Distributed processing, GPU acceleration
- Industry Applications - Urban planning, disaster management
- Programming Languages - Python, R, Julia, JS, C++, Java, Go, Rust
- Data Sources - Satellite catalogs, APIs
- Troubleshooting - Common issues, debugging, error reference
- Code Examples - 500+ examples
GeoMaster covers everything from basic GIS operations to advanced remote sensing and machine learning.
1---2name: geomaster3description: Comprehensive geospatial science skill covering remote sensing, GIS, spatial analysis, machine learning for earth observation, and 30+ scientific domains. Supports satellite imagery processing (Sentinel, Landsat, MODIS, SAR, hyperspectral), vector and raster data operations, spatial statistics, point cloud processing, network analysis, cloud-native workflows (STAC, COG, Planetary Computer), and 8 programming languages (Python, R, Julia, JavaScript, C++, Java, Go, Rust) with 500+ code examples. Use for remote sensing workflows, GIS analysis, spatial ML, Earth observation data processing, terrain analysis, hydrological modeling, marine spatial analysis, atmospheric science, and any geospatial computation task.4license: MIT License5metadata:6 source: https://skillmd.com/skills/k-dense-ai/geomaster7 version: "1.0"8 skill-author: K-Dense Inc.9---1011# GeoMaster1213Comprehensive geospatial science skill covering GIS, remote sensing, spatial analysis, and ML for Earth observation across 70+ topics with 500+ code examples in 8 programming languages.1415## Installation1617```bash18# Core Python stack (conda recommended)19conda install -c conda-forge gdal rasterio fiona shapely pyproj geopandas2021# Remote sensing & ML22uv pip install rsgislib torchgeo earthengine-api23uv pip install scikit-learn xgboost torch-geometric2425# Network & visualization26uv pip install osmnx networkx folium keplergl27uv pip install cartopy contextily mapclassify2829# Big data & cloud30uv pip install xarray rioxarray dask-geopandas31uv pip install pystac-client planetary-computer3233# Point clouds34uv pip install laspy pylas open3d pdal3536# Databases37conda install -c conda-forge postgis spatialite38```3940## Quick Start4142### NDVI from Sentinel-24344```python45import rasterio46import numpy as np4748with rasterio.open('sentinel2.tif') as src:49 red = src.read(4).astype(float) # B0450 nir = src.read(8).astype(float) # B0851 ndvi = (nir - red) / (nir + red + 1e-8)52 ndvi = np.nan_to_num(ndvi, nan=0)5354 profile = src.profile55 profile.update(count=1, dtype=rasterio.float32)5657 with rasterio.open('ndvi.tif', 'w', **profile) as dst:58 dst.write(ndvi.astype(rasterio.float32), 1)59```6061### Spatial Analysis with GeoPandas6263```python64import geopandas as gpd6566# Load and ensure same CRS67zones = gpd.read_file('zones.geojson')68points = gpd.read_file('points.geojson')6970if zones.crs != points.crs:71 points = points.to_crs(zones.crs)7273# Spatial join and statistics74joined = gpd.sjoin(points, zones, how='inner', predicate='within')75stats = joined.groupby('zone_id').agg({76 'value': ['count', 'mean', 'std', 'min', 'max']77}).round(2)78```7980### Google Earth Engine Time Series8182```python83import ee84import pandas as pd8586ee.Initialize(project='your-project')87roi = ee.Geometry.Point([-122.4, 37.7]).buffer(10000)8889s2 = (ee.ImageCollection('COPERNICUS/S2_SR_HARMONIZED')90 .filterBounds(roi)91 .filterDate('2020-01-01', '2023-12-31')92 .filter(ee.Filter.lt('CLOUDY_PIXEL_PERCENTAGE', 20)))9394def add_ndvi(img):95 return img.addBands(img.normalizedDifference(['B8', 'B4']).rename('NDVI'))9697s2_ndvi = s2.map(add_ndvi)9899def extract_series(image):100 stats = image.reduceRegion(ee.Reducer.mean(), roi.centroid(), scale=10, maxPixels=1e9)101 return ee.Feature(None, {'date': image.date().format('YYYY-MM-dd'), 'ndvi': stats.get('NDVI')})102103series = s2_ndvi.map(extract_series).getInfo()104df = pd.DataFrame([f['properties'] for f in series['features']])105df['date'] = pd.to_datetime(df['date'])106```107108## Core Concepts109110### Data Types111112| Type | Examples | Libraries |113|------|----------|-----------|114| Vector | Shapefile, GeoJSON, GeoPackage | GeoPandas, Fiona, GDAL |115| Raster | GeoTIFF, NetCDF, COG | Rasterio, Xarray, GDAL |116| Point Cloud | LAS, LAZ | Laspy, PDAL, Open3D |117118### Coordinate Systems119120- **EPSG:4326** (WGS 84) - Geographic, lat/lon, use for storage121- **EPSG:3857** (Web Mercator) - Web maps only (don't use for area/distance!)122- **EPSG:326xx/327xx** (UTM) - Metric calculations, <1% distortion per zone123- Use `gdf.estimate_utm_crs()` for automatic UTM detection124125```python126# Always check CRS before operations127assert gdf1.crs == gdf2.crs, "CRS mismatch!"128129# For area/distance calculations, use projected CRS130gdf_metric = gdf.to_crs(gdf.estimate_utm_crs())131area_sqm = gdf_metric.geometry.area132```133134### OGC Standards135136- **WMS**: Web Map Service - raster maps137- **WFS**: Web Feature Service - vector data138- **WCS**: Web Coverage Service - raster coverage139- **STAC**: Spatiotemporal Asset Catalog - modern metadata140141## Common Operations142143### Spectral Indices144145```python146def calculate_indices(image_path):147 """NDVI, EVI, SAVI, NDWI from Sentinel-2."""148 with rasterio.open(image_path) as src:149 B02, B03, B04, B08, B11 = [src.read(i).astype(float) for i in [1,2,3,4,5]]150151 ndvi = (B08 - B04) / (B08 + B04 + 1e-8)152 evi = 2.5 * (B08 - B04) / (B08 + 6*B04 - 7.5*B02 + 1)153 savi = ((B08 - B04) / (B08 + B04 + 0.5)) * 1.5154 ndwi = (B03 - B08) / (B03 + B08 + 1e-8)155156 return {'NDVI': ndvi, 'EVI': evi, 'SAVI': savi, 'NDWI': ndwi}157```158159### Vector Operations160161```python162# Buffer (use projected CRS!)163gdf_proj = gdf.to_crs(gdf.estimate_utm_crs())164gdf['buffer_1km'] = gdf_proj.geometry.buffer(1000)165166# Spatial relationships167intersects = gdf[gdf.geometry.intersects(other_geometry)]168contains = gdf[gdf.geometry.contains(point_geometry)]169170# Geometric operations171gdf['centroid'] = gdf.geometry.centroid172gdf['simplified'] = gdf.geometry.simplify(tolerance=0.001)173174# Overlay operations175intersection = gpd.overlay(gdf1, gdf2, how='intersection')176union = gpd.overlay(gdf1, gdf2, how='union')177```178179### Terrain Analysis180181```python182def terrain_metrics(dem_path):183 """Calculate slope, aspect, hillshade from DEM."""184 with rasterio.open(dem_path) as src:185 dem = src.read(1)186187 dy, dx = np.gradient(dem)188 slope = np.arctan(np.sqrt(dx**2 + dy**2)) * 180 / np.pi189 aspect = (90 - np.arctan2(-dy, dx) * 180 / np.pi) % 360190191 # Hillshade192 az_rad, alt_rad = np.radians(315), np.radians(45)193 hillshade = (np.sin(alt_rad) * np.sin(np.radians(slope)) +194 np.cos(alt_rad) * np.cos(np.radians(slope)) *195 np.cos(np.radians(aspect) - az_rad))196197 return slope, aspect, hillshade198```199200### Network Analysis201202```python203import osmnx as ox204import networkx as nx205206# Download and analyze street network207G = ox.graph_from_place('San Francisco, CA', network_type='drive')208G = ox.add_edge_speeds(G).add_edge_travel_times(G)209210# Shortest path211orig = ox.distance.nearest_nodes(G, -122.4, 37.7)212dest = ox.distance.nearest_nodes(G, -122.3, 37.8)213route = nx.shortest_path(G, orig, dest, weight='travel_time')214```215216## Image Classification217218```python219from sklearn.ensemble import RandomForestClassifier220import rasterio221from rasterio.features import rasterize222223def classify_imagery(raster_path, training_gdf, output_path):224 """Train RF and classify imagery."""225 with rasterio.open(raster_path) as src:226 image = src.read()227 profile = src.profile228 transform = src.transform229230 # Extract training data231 X_train, y_train = [], []232 for _, row in training_gdf.iterrows():233 mask = rasterize([(row.geometry, 1)],234 out_shape=(profile['height'], profile['width']),235 transform=transform, fill=0, dtype=np.uint8)236 pixels = image[:, mask > 0].T237 X_train.extend(pixels)238 y_train.extend([row['class_id']] * len(pixels))239240 # Train and predict241 rf = RandomForestClassifier(n_estimators=100, max_depth=20, n_jobs=-1)242 rf.fit(X_train, y_train)243244 prediction = rf.predict(image.reshape(image.shape[0], -1).T)245 prediction = prediction.reshape(profile['height'], profile['width'])246247 profile.update(dtype=rasterio.uint8, count=1)248 with rasterio.open(output_path, 'w', **profile) as dst:249 dst.write(prediction.astype(rasterio.uint8), 1)250251 return rf252```253254## Modern Cloud-Native Workflows255256### STAC + Planetary Computer257258```python259import pystac_client260import planetary_computer261import odc.stac262263# Search Sentinel-2 via STAC264catalog = pystac_client.Client.open(265 "https://planetarycomputer.microsoft.com/api/stac/v1",266 modifier=planetary_computer.sign_inplace,267)268269search = catalog.search(270 collections=["sentinel-2-l2a"],271 bbox=[-122.5, 37.7, -122.3, 37.9],272 datetime="2023-01-01/2023-12-31",273 query={"eo:cloud_cover": {"lt": 20}},274)275276# Load as xarray (cloud-native!)277data = odc.stac.load(278 list(search.get_items())[:5],279 bands=["B02", "B03", "B04", "B08"],280 crs="EPSG:32610",281 resolution=10,282)283284# Calculate NDVI on xarray285ndvi = (data.B08 - data.B04) / (data.B08 + data.B04)286```287288### Cloud-Optimized GeoTIFF (COG)289290```python291import rasterio292from rasterio.session import AWSSession293294# Read COG directly from cloud (partial reads)295session = AWSSession(aws_access_key_id=..., aws_secret_access_key=...)296with rasterio.open('s3://bucket/path.tif', session=session) as src:297 # Read only window of interest298 window = ((1000, 2000), (1000, 2000))299 subset = src.read(1, window=window)300301# Write COG302with rasterio.open('output.tif', 'w', **profile,303 tiled=True, blockxsize=256, blockysize=256,304 compress='DEFLATE', predictor=2) as dst:305 dst.write(data)306307# Validate COG308from rio_cogeo.cogeo import cog_validate309cog_validate('output.tif')310```311312## Performance Tips313314```python315# 1. Spatial indexing (10-100x faster queries)316gdf.sindex # Auto-created by GeoPandas317318# 2. Chunk large rasters319with rasterio.open('large.tif') as src:320 for i, window in src.block_windows(1):321 block = src.read(1, window=window)322323# 3. Dask for big data324import dask.array as da325dask_array = da.from_rasterio('large.tif', chunks=(1, 1024, 1024))326327# 4. Use Arrow for I/O328gdf.to_file('output.gpkg', use_arrow=True)329330# 5. GDAL caching331from osgeo import gdal332gdal.SetCacheMax(2**30) # 1GB cache333334# 6. Parallel processing335rf = RandomForestClassifier(n_jobs=-1) # All cores336```337338## Best Practices3393401. **Always check CRS** before spatial operations3412. **Use projected CRS** for area/distance calculations3423. **Validate geometries**: `gdf = gdf[gdf.is_valid]`3434. **Handle missing data**: `gdf['geometry'] = gdf['geometry'].fillna(None)`3445. **Use efficient formats**: GeoPackage > Shapefile, Parquet for large data3456. **Apply cloud masking** to optical imagery3467. **Preserve lineage** for reproducible research3478. **Use appropriate resolution** for your analysis scale348349## Detailed Documentation350351- **[Coordinate Systems](references/coordinate-systems.md)** - CRS fundamentals, UTM, transformations352- **[Core Libraries](references/core-libraries.md)** - GDAL, Rasterio, GeoPandas, Shapely353- **[Remote Sensing](references/remote-sensing.md)** - Satellite missions, spectral indices, SAR354- **[Machine Learning](references/machine-learning.md)** - Deep learning, CNNs, GNNs for RS355- **[GIS Software](references/gis-software.md)** - QGIS, ArcGIS, GRASS integration356- **[Scientific Domains](references/scientific-domains.md)** - Marine, hydrology, agriculture, forestry357- **[Advanced GIS](references/advanced-gis.md)** - 3D GIS, spatiotemporal, topology358- **[Big Data](references/big-data.md)** - Distributed processing, GPU acceleration359- **[Industry Applications](references/industry-applications.md)** - Urban planning, disaster management360- **[Programming Languages](references/programming-languages.md)** - Python, R, Julia, JS, C++, Java, Go, Rust361- **[Data Sources](references/data-sources.md)** - Satellite catalogs, APIs362- **[Troubleshooting](references/troubleshooting.md)** - Common issues, debugging, error reference363- **[Code Examples](references/code-examples.md)** - 500+ examples364365---366367**GeoMaster covers everything from basic GIS operations to advanced remote sensing and machine learning.**