Skip to main content

​
Google Earth Engine Integration

Nika provides native integration with Google Earth Engine (GEE), enabling you to access the world’s largest satellite imagery archive and perform cloud-based geospatial analysis directly within your Nika workspace.

​
Native Earth Engine API Support

​
Seamless Python Integration

Nika supports the official earthengine-api Python library natively, allowing you to run Earth Engine code directly in your Nika workspace without additional setup or configuration. Key Features:
  • Native API Support: Full access to Earth Engine’s Python API
  • Credential Management: Secure handling of GEE credentials
  • Cloud Processing: Leverage Earth Engine’s distributed computing
  • Real-time Results: Instant visualization of analysis outputs
  • Batch Processing: Handle large-scale geospatial operations

​
Why Earth Engine Integration Matters

Google Earth Engine provides access to:
  • Petabytes of satellite imagery from Landsat, Sentinel, and other missions
  • Global-scale datasets for environmental monitoring
  • Cloud-based processing for computationally intensive analysis
  • Time-series analysis capabilities for change detection
  • Machine learning tools for automated feature extraction
Our integration makes this powerful platform accessible within your familiar Nika environment.

​
Getting Started

​
Setting Up Earth Engine Credentials

  1. Create Earth Engine Account: Sign up at earthengine.google.com
  2. Generate Service Account: Create credentials in Google Cloud Console
  3. Upload Credentials: Add your ee-credentials.json to Nika workspace
  4. Verify Connection: Test your Earth Engine access

​
Basic Earth Engine Workflow

# Example: Basic Earth Engine analysis in Nika
import ee
import geemap

# Initialize Earth Engine
ee.Initialize()

# Load a Landsat collection
landsat = ee.ImageCollection('LANDSAT/LC08/C02/T1_L2') \
    .filterBounds(ee.Geometry.Point([-122.2751, 37.8063])) \
    .filterDate('2020-01-01', '2020-12-31') \
    .filter(ee.Filter.lt('CLOUD_COVER', 20))

# Calculate NDVI
def addNDVI(image):
    ndvi = image.normalizedDifference(['SR_B5', 'SR_B4']).rename('NDVI')
    return image.addBands(ndvi)

# Apply NDVI calculation
landsat_ndvi = landsat.map(addNDVI)

# Get the median NDVI
median_ndvi = landsat_ndvi.select('NDVI').median()

# Display in Nika
nika_map = geemap.Map()
nika_map.addLayer(median_ndvi, {'min': -1, 'max': 1, 'palette': ['red', 'yellow', 'green']}, 'NDVI')
nika_map.display()

​
Advanced Integration with geemap

​
Leveraging Dr. Wu Qiusheng’s geemap

Nika fully supports geemap, the powerful Python package created by Dr. Wu Qiusheng (@giswqs) that simplifies Earth Engine data visualization and analysis.

​
Enhanced Visualization Capabilities

# Example: Advanced geemap visualization
import geemap
import ee

# Create an interactive map
Map = geemap.Map(center=[40, -100], zoom=4)

# Load and display multiple datasets
dem = ee.Image('USGS/SRTMGL1_003')
landcover = ee.Image('ESA/WorldCover/v100').select('Map')

# Add layers with custom styling
Map.addLayer(dem, {'min': 0, 'max': 3000, 'palette': ['006633', 'E5FFCC', '662A00', 'D8D8D8', 'F5F5F5']}, 'DEM')
Map.addLayer(landcover, {}, 'Land Cover')

# Add time series analysis
Map.add_landsat_timeseries(
    roi=ee.Geometry.Rectangle([-122.2751, 37.8063, -122.2750, 37.8064]),
    start_year=2020,
    end_year=2023
)

# Display in Nika workspace
Map.to_streamlit()

​
Interactive Analysis Tools

# Example: Interactive Earth Engine analysis
import geemap.foliumap as geemap

# Create interactive map with analysis tools
Map = geemap.Map()

# Add drawing tools for ROI selection
Map.add_draw_control()

# Add Earth Engine datasets
Map.add_ee_layer(ee.Image('USGS/SRTMGL1_003'), {}, 'DEM')

# Add analysis widgets
Map.add_analysis_widgets()

# Export functionality
Map.add_export_control()

​
Use Cases

​
Environmental Monitoring

# Example: Forest cover change analysis
import ee
import geemap

# Define study area
roi = ee.Geometry.Rectangle([-122.5, 37.5, -122.0, 38.0])

# Load Landsat collections for different years
landsat_2015 = ee.ImageCollection('LANDSAT/LC08/C02/T1_L2') \
    .filterBounds(roi) \
    .filterDate('2015-06-01', '2015-08-31') \
    .filter(ee.Filter.lt('CLOUD_COVER', 10))

landsat_2023 = ee.ImageCollection('LANDSAT/LC09/C02/T1_L2') \
    .filterBounds(roi) \
    .filterDate('2023-06-01', '2023-08-31') \
    .filter(ee.Filter.lt('CLOUD_COVER', 10))

# Calculate forest cover change
def calculate_forest_cover(image):
    ndvi = image.normalizedDifference(['SR_B5', 'SR_B4'])
    forest = ndvi.gt(0.3).rename('forest')
    return forest

forest_2015 = landsat_2015.map(calculate_forest_cover).median()
forest_2023 = landsat_2023.map(calculate_forest_cover).median()

# Calculate change
forest_change = forest_2023.subtract(forest_2015)

# Visualize results
Map = geemap.Map()
Map.addLayer(forest_change, {'min': -1, 'max': 1, 'palette': ['red', 'white', 'green']}, 'Forest Change')

​
Agricultural Analysis

# Example: Crop monitoring with Sentinel-2
import ee

# Load Sentinel-2 data
sentinel = ee.ImageCollection('COPERNICUS/S2_SR') \
    .filterBounds(roi) \
    .filterDate('2023-01-01', '2023-12-31') \
    .filter(ee.Filter.lt('CLOUDY_PIXEL_PERCENTAGE', 20))

# Calculate vegetation indices
def add_vegetation_indices(image):
    ndvi = image.normalizedDifference(['B8', 'B4']).rename('NDVI')
    evi = image.expression('2.5 * ((NIR - RED) / (NIR + 6 * RED - 7.5 * BLUE + 1))', {
        'NIR': image.select('B8'),
        'RED': image.select('B4'),
        'BLUE': image.select('B2')
    }).rename('EVI')
    return image.addBands([ndvi, evi])

# Apply indices calculation
sentinel_with_indices = sentinel.map(add_vegetation_indices)

# Create time series
time_series = sentinel_with_indices.select('NDVI')

​
Climate Research

# Example: Temperature analysis with MODIS
import ee

# Load MODIS land surface temperature
modis_lst = ee.ImageCollection('MODIS/006/MOD11A1') \
    .filterBounds(roi) \
    .filterDate('2023-01-01', '2023-12-31')

# Extract temperature data
def extract_temperature(image):
    lst = image.select('LST_Day_1km').multiply(0.02).subtract(273.15)
    return lst.rename('temperature')

# Calculate temperature statistics
temperature_series = modis_lst.map(extract_temperature)
mean_temp = temperature_series.mean()
max_temp = temperature_series.max()
min_temp = temperature_series.min()

​
Best Practices

​
Credential Management

  • Store credentials securely in Nika workspace
  • Use service accounts for production applications
  • Regularly rotate credentials
  • Monitor API usage and quotas

​
Performance Optimization

  • Use appropriate spatial and temporal filters
  • Leverage Earth Engine’s cloud processing
  • Implement efficient data structures
  • Cache frequently accessed datasets

​
Data Quality

  • Validate input data sources
  • Check for cloud cover and data gaps
  • Implement quality control measures
  • Document data processing workflows

​
Advanced Features

​
Custom Earth Engine Functions

# Example: Custom analysis function
def custom_analysis(roi, start_date, end_date):
    """
    Custom Earth Engine analysis function
    """
    # Load data
    collection = ee.ImageCollection('LANDSAT/LC08/C02/T1_L2') \
        .filterBounds(roi) \
        .filterDate(start_date, end_date)
    
    # Custom processing
    def process_image(image):
        # Your custom analysis here
        return image
    
    # Apply processing
    result = collection.map(process_image)
    
    return result

​
Batch Processing

# Example: Batch processing multiple regions
import ee
import pandas as pd

# Define multiple regions
regions = [
    {'name': 'Region 1', 'geometry': ee.Geometry.Rectangle([-122, 37, -121, 38])},
    {'name': 'Region 2', 'geometry': ee.Geometry.Rectangle([-121, 37, -120, 38])},
    # Add more regions...
]

# Process each region
results = []
for region in regions:
    # Perform analysis
    result = custom_analysis(region['geometry'], '2023-01-01', '2023-12-31')
    results.append({
        'region': region['name'],
        'result': result
    })

​
Troubleshooting

​
Common Issues

Authentication Problems
  • Verify Earth Engine account activation
  • Check credential file format and permissions
  • Ensure proper service account setup
  • Validate API quotas and limits
Performance Issues
  • Optimize spatial and temporal filters
  • Use appropriate data collections
  • Implement efficient processing chains
  • Monitor Earth Engine usage quotas
Data Access Issues
  • Verify dataset availability and access permissions
  • Check temporal and spatial coverage
  • Validate data quality and completeness
  • Monitor Earth Engine service status

​
Support Resources

​
Documentation

​
Community

​
Get Expert Help

⌘I