Nitrogen Loss Risk Spatial Analysis

Problem

Nitrogen surplus from agricultural fields contributes to groundwater contamination and eutrophication. Identifying high-risk areas requires spatial analysis that accounts for geographic clustering and local conditions.

Approach

Applied spatial autocorrelation analysis (Moran's I) and local indicators of spatial association (LISA) using PySAL. Data reprojected to EPSG:3857 for metric distance calculations. Kriging interpolation for continuous risk surface estimation.

Data

Regional nitrogen balance data with farm-level surplus calculations and geographic coordinates.

Validation

Cross-validation of kriging predictions. Sensitivity analysis for distance thresholds and neighborhood definitions.

Results

Identified spatial clusters of high nitrogen loss risk. Maps highlight priority areas for mitigation interventions.

My Role

Analyst. Performed spatial statistics, created visualizations, interpreted results.

Next Steps

Integrate with soil type and hydrology data; predictive modeling for future scenarios; policy recommendation synthesis.

Key Outcomes

• Spatial risk mapping
• Cluster identification
• Policy-relevant visualizations