GeoPard Tutorials | Precision Ag Software
  • Introduction to GeoPard
    • GeoPard Platform: Frequently Asked Questions (FAQ)
  • 🖥️Product Tour - Web App
    • Getting Started
      • Create a new farm
      • Draw a new field
      • Upload a field boundary
      • Edit a boundary
      • Edit a field name
      • Add a label
    • 🛰️Satellite Monitoring
      • Order Planet Scope (3m daily) imagery
      • Indices for Crops and Soils
      • 📈Crop Development Index Graph
    • 📊Zones Maps and Analytics
      • Assign Variable Rates in the Zones (Ag inputs Rates Distribution Tool)
      • Creating Zones Map using Satellite Imagery
      • Creating Zones Map using Soil/Yield/As Applied Data
      • Creating Zones Map using Topography
      • Creating Zones Map using a Template
      • Draw Zones Manually, Clone from an existing layer
      • Usage of Data Classification
      • Edit Zones Map: Merge & Split
      • Multi-Year Zones
      • Multi-Layer Analytics
      • Compare layers
      • Heterogeneity factor
      • Relative variation factor
    • 📊Equation-based Analytics
      • Batch Equation analytics
      • Catalog of Predefined Agronomic Equations
      • Catalog of Custom Functions
    • ⛰️Topography
    • ⛰️3D Maps
    • Import
      • Field Boundary
      • Soil Data
      • Yield Data
      • As Applied/As Planted Data
      • Machinery Proprietary Formats
      • Import from MyJohnDeere
    • Export / Download
      • Field Boundary Export
      • Batch Export of Boundaries, Zones and Scouting Pins
      • Zones Map Export as shapefile
      • Satellite Imagery Export as geotiff or geojson
      • Export Scouting Notes as shapefile
      • Export VRA map In ISOXML Format
      • Export to MyJohnDeere
    • 🤖API
    • Operations Log - Track errors/Imports and Analytics
    • Organizations and Roles
    • Farms Sharing between Accounts & Organizations
    • Managing Crop Season information with tags(labels)
      • Case: Managing fields for several clients
      • Case: Season details including crop and year
      • Case: Field operation details
    • ⚙️User Settings
      • Subscriptions, Account limits & Plans
      • Restoring password
      • Order the package
      • Changing preferences
    • 🚜John Deere Operations Center Integration
      • 🚜John Deere Operations Center Integration
        • 1. Create Free Trial Account with you John Deere Account
        • 2. Connect to JohnDeere Operations Center
        • 3. Connect to John Deere Organizations
        • 4. Import into GeoPard from John Deere Operations Center
        • 5. Configure Automated Data Sync
        • 6. Export Rx Maps to John Deere Operations Center as Files
        • 7. Export Field Boundaries into John Deere Operations Center
          • 7a. Organization configuration of export boundary to John Deere Operations Center as File
        • 8. Export Rx Maps to John Deere Operations Center as Work Plans
        • 9. Export Soil, Topography, Satellite or Analytics as Map Layers
      • 🚜John Deere Operations Center Data Sharing
        • 1. "Staff Member" sharing
        • 2. Problem-solving of "Staff Member" sharing
        • 3. "Partner Organization" sharing
        • 4. Problem-solving of "Partner Organization" sharing
        • 5. Problem-solving of import from John Deere to GeoPard
        • 6. Problem-solving of Work Plan creation
        • 7. Sharing Fields/Boundaries Between Partner Organizations in John Deere Ops Center, DataSync config
  • 🚀Changelog & Product Releases
    • Release Notes
      • Release Web May 2025 (Rates Distribution, improved Legends)
      • Release Web March 2025 (Improved Zones, WorkPlans updates, Yield data enhancements)
      • Release Web January 2025 (Free Trial, Usage-based Pricing Plan, USDA Yield Cleaning protocol, Export of calibrated Yield data to John Deere Ops Center, Import of kml)
      • Release Web August 2024 (Data Layer Previews, Spatially localized Zones; Use zones and Equations in new Equations)
      • Release Web July 2024 (Equation Map creation, Spatially localized zones, Seeding and Application Work Plans)
      • Release Web May 2024 (Raw view for Satellite Images, export of Zone Maps as WorkPlan to the John Deere Operations Center, redesign of Batch Analytics)
      • Release Web April 2024 (Batch Equation Maps and enhanced layer transparency)
      • Release Web February 2024 (Per area pricing, units)
      • Release Web January 2024 (many UI improvements)
      • Release Web November 2023 (Clone Polygons, Subscription management)
      • Release Web October 2023 (Yield Calibration, Equation Maps as ISOXML, PDF Export and John Deere Integration)
      • Release Web September 2023 (Cleaning & Calibrating Yield Datasets, more languages support)
      • Release Mobile August 2023 (Mobile app impovements)
      • Release Web July 2023 (Operations Log page, Sum in datasets)
      • Release Web June 2023 (Improved Equations, Operations log v1)
      • Release Mobile May 2023 (Social Login)
      • Release Web May 2023 (John Deere integration improvements)
      • Release Web January 2023 (huge amount of small improvements)
      • Release Web October 2022 (Integration with AgGateway protocols, Isoxml support and more)
      • Release Web April 2022 (3D maps and Zoning Tools)
  • 👨‍🌾Agronomy
    • Precision Agronomy Use Cases & Best Practices Overview
    • Field Management Zones (Productivity Zones) Creation Process
    • Variable Rate Seeding (Planting) Maps
    • Yield Calibration & Cleaning
    • Synthetic Yield Map
    • Create Soil Sampling Zones, Points, Route, export as KML, and execute
    • Evaluate Accuracy of Seeding Application
    • Evaluate Accuracy of Fertilizer Application
    • Field Trial Analytics
    • Nitrogen Use Efficiency & Uptake
    • Comparing Yield Datasets
    • Compare Soil Scanner Data between Years
    • Flood Detection / Insurance report
    • Profit Maps (COMING)
    • VRA/Rx/Prescription Fertilizer Maps (COMING)
    • VRA/Rx/Prescription Nitrogen Maps (COMING)
    • VRA/Rx/Prescription Spraying Maps (COMING)
    • Multi-Layer Field Potential Maps (COMING)
    • VR Lime Application Based on Soil Scanner pH Data (COMING)
    • Merging Yield Datasets Belonging to the Same Field (COMING)
  • 📱Product Tour - Mobile App
    • Installation
    • Logging in
    • Viewing satellite images
    • Viewing zones maps
    • Viewing soil data
    • Viewing yield data
    • Viewing topography maps
    • Viewing as applied datasets
    • Working in the field/Scouting zones maps
    • Working offline
    • Filters
    • Options
    • Settings
  • 🤖API Docs
    • GeoPard API Overview
    • Getting Started
    • Authorization: ApiKey, Credentials or OAuth 2.0
    • Diagrams with Basic Flows
      • 1. Field Registration
      • 2. GraphQL Subscription
      • 3. Grep Satellite Imagery
      • 4. Upload Soil | AsApplied | Yield Datasets
      • 5. Execute Equations
      • 6. Generate ZonesMap
      • 7. Download Gridded Data
      • 8. Download Original Data
    • Data Schema
    • Requests Overview
      • 1. Subscription: Get Events
      • 2. Query: Get "Fields"
      • 3. Query: Get "SatelliteImages"
      • 4. Query: Get defined "SatelliteImage"
      • 5. Query: Get "RasterMaps"
      • 6. Query: Get "ZonesMaps"
      • 7. Mutation: Generate "ZonesMap"
      • 8. Mutation: Generate "RasterMap"
      • 9. Mutation: Generate "ZonesMap" asynchronously
      • 10. Mutation: Generate "RasterMap" asynchronously
      • 11. Mutation: Generate Yield based "ZonesMap" asynchronously
      • 12. Mutation: Generate Soil based "ZonesMap" asynchronously
      • 13. Mutation: Create "Farm"
      • 14. Mutation: Create a "Field" or edit the boundary of the existing field (with optional labels)
      • 15. Query: Get "TopographyMap"
      • 16. Query: Get "YieldDatasets"
      • 17. Query: Get "SoilDatasets"
      • 18. Mutation: Generate zip archive with "ZonesMap" and "Field"
      • 19. Mutation: Delete "Field"
      • 20. Mutation: Delete "Farm"
      • 21. Mutation: Delete "ZonesMap"
      • 22. Mutation: Delete "RasterAnalytisMap"
      • 23. Mutation: Delete "SoilDataset"
      • 24. Mutation: Delete "YieldDataset"
      • Notes (Pins)
        • 25. Mutation: Save "Note" attached to "Field"
        • 26. Mutation: Save "Note" attached to "ZonesMap"
        • 27. Mutation: Save "Note" attached to "SoilDataset"
        • 28. Mutation: Save multiple "Notes", Batch operation
        • 29. Mutation: Delete "Note"
        • 30. Mutation: Delete multiple "Notes"
        • 31. Query: Get all "Notes" related to "Field"
        • 32. Query: Get "Notes" related to "ZonesMap" and type
        • 33. Query: Get "Notes" related to "SoilDataset" and type
        • 34. Query: Get a selected "Note" with all "Comments"
        • 35. Mutation: Add "Comment" to the selected "Note"
        • 36. Mutation: Add multiple "Comments" to the selected "Notes"
      • 37. Query: Get "SatelliteImages" in the defined interval
      • 38. Query: Get "UserData"
      • 39. Mutation: Set custom color schemas to selected "GeoMaps"
      • 40. Query: Get "Labels" on the account level
      • 41. Mutation: Save "Labels" on the account level
      • 42. Mutation: Delete "Label" on the account level
      • 43. Query Get "Fields"
      • 44. Mutation: Set Field Labels
      • 45. Mutation: Save User Data
      • 46. Mutation: Generate multi-layer "ZonesMap" asynchronously
      • 47. Query: Get "ZonesMaps"
      • 48. Query: Get Gridded Data from "TopographyMap"
      • 49. Query: Get Gridded Data from "FieldSatelliteImage"
      • 50. Query: Get Gridded Data from "VectorAnalysisMap"
      • 51. Query: Get Gridded Data from "YieldDataset"
      • 52. Query: Get Gridded Data from "SoilDataset"
      • 53. Query: Get Gridded Data from "AsAppliedDataset"
      • 54. Query: Get Vector Data from "SoilDataset"
      • 55. Upload zip files (over 6 MB)
      • 56. Upload photos
      • 57. Query: Get "Photos" attached to the selected "Note"
      • 58. Query: Get "Photos" attached to "Comments"
      • 59. Query: Get "AsAppliedDatasets"
      • 60. Mutation: Generate As-Applied-based "ZonesMap" asynchronously
      • 61. Mutation: Delete "AsAppliedDataset"
      • 62. Mutation: Share Farms
      • 63. Mutation: Save Organization
      • 64. Mutation: Add Users to Organization
      • 65. Mutation: Delete Users from Organization
      • 66. Mutation: Save Field
      • 67. Mutation: Save Farm
      • 68. Mutation: Refresh "VectorAnalysisMap" Statistics
      • 69. Mutation: Delete "Photo"
      • 70. Mutation: Delete multiple "Photos"
      • 71. Mutation: Generate a zip archive with "Notes"
      • 72. Query: Get Gridded Data as GeoJSON or GeoTIFF
      • 73. Query: Get Gridded Data with the Selected Buffer
      • 74. Mutation: Verify "Equation"
      • 75. Mutation: Generate "EquationMap" asynchronously
      • 76. Query: Get "EquationMap"
      • 77. Mutation: Delete "EquationMap"
      • 78. Query: Find "Fields" by "externalKey"
      • 79. Query: Find "Farms" by "externalKey"
      • 80. Query: Get Original Data
      • 81. Query: Get GeoJSON of "EquationMap"
      • 82. Query: Restore Subscription Events
      • 83. Query: Collect Platform Context
      • 84. Mutation: Calibrate and Clean YieldDataset
      • 85. Mutation: Assign Rates to VectorAnalysisMap (ZonesMap)
      • 86. Query: Get "Farms"
      • 87. Mutation: Save Custom VectorAnalysisMap (ZonesMap)
      • 88. Mutation: Export ZonesMap as Zipped Shapefile
      • 89. Mutation: Export ZonesMap as Zipped ISOXML
    • Geo Endpoints
      • WMS - Get Raster Pictures of Spatial Data Layers
        • 1. LAI
        • 2. RGB
        • 3. Field: boundary
        • 4. Field: thumbnail
        • 5. ZonesMap
        • 6. ZonesMap: custom color schema
        • 7. ZonesMap: thumbnail
        • 8. RasterMap
        • 9. RasterMap: custom color schema
        • 10. RasterMap: thumbnail
        • 11. TopographyMap: elevation in absolute numbers
        • 12. YieldDatasetsMap
        • 13. SoilDatasetsMap
        • 14. SoilDatasetsMap: custom color schema
        • 15. AsAppliedDatasetsMap
        • 16. Satellite Image: cropped by Field boundary
        • 17. Satellite Image: cropped by Field boundary and custom color schema
        • 18. YieldDatasetsMap: custom color schema
        • 19. Satellite Image: 10 colors visualization
      • WFS - Get Spatial Data Layers in Vector format (shp, geojson)
        • 1. Get the Field Boundary as Geojson
        • 2. Get the Zones map as Geojson
        • 3. Get Zones Attributes as JSON
        • 4. Get Soil data as Geojson
        • 5. Get Yield data as Geojson
    • Uploading Files
    • API FAQ
  • 🛣️Platform Roadmap
    • Roadmap
  • GIS quick Hints
    • QGIS: Change String to Number values in the shapefile
    • QGIS: Yield Data Manipulations
    • QGIS: Split Boundaries Into Subfields
    • QGIS: Merge Vector Layers
    • QGIS: Merge Selected Features from Vector Files
    • QGIS: Calculate NDVI for the Drone Geotiff File
    • QGIS: Split Multi-field Shapefiles
    • QGIS: Convert CSV to SHP
    • QGIS: Reproject Shapefile
  • Policies
    • Your Data Stays Yours, Securely Managed By GeoPard
    • Terms & Conditions
    • Privacy Policy
Powered by GitBook

Start Working with GeoPard

  • Go to GeoPard Website
  • Demo Request
  • LinkedIn

This Portal Sections

  • Introduction
  • Product Tour - Web App (incl. video)
  • Product Tour - Mobile App (incl. video)
  • Precision Agronomy Use Cases

Powered by GeoPard Agriculture - Automated precisionAg platform

On this page
  • Understanding Deviation in Soil Scanner Data
  • Choosing the Right Deviation Method
  • Direct Difference Calculation
  • Relative Difference Calculation
  • Normalized Difference Calculation
  • Relative Deviation per Pixel
  • Mean Absolute Error (MAE) per Pixel
  • Conclusion

Was this helpful?

  1. Agronomy

Compare Soil Scanner Data between Years

This article outlines various mathematical methods to quantify differences between soil scanner datasets and enhance decision-making for researchers and agronomists.

PreviousComparing Yield DatasetsNextFlood Detection / Insurance report

Last updated 1 month ago

Was this helpful?

Soil scanners are essential tools for precision agriculture, enabling the collection of high-resolution data on soil properties such as moisture, organic matter, and nutrient levels. Comparing two soil scanner datasets is crucial for understanding changes over time, validating different scanning methods, or calibrating new devices. This article explores various mathematical approaches to measure deviation between two soil scanner datasets, providing actionable insights for researchers and agronomists.

Understanding Deviation in Soil Scanner Data

The deviation between two soil scanner datasets refers to the differences in measured values at the same locations, which may arise due to variations in measurement conditions, sensor calibration, or soil dynamics. The most common types of deviations include:

  • Absolute Differences: Direct subtraction of values between datasets.

  • Relative Differences: Comparison based on the magnitude of measurements.

  • Error Metrics: Statistical measures like Mean Absolute Error (MAE) and Normalized Difference.

Two soil scanner datasets with potassium for 2024 and 2025 were chosen.

Choosing the Right Deviation Method

Method
Best for

Direct Difference

Simple visualization of positive/negative changes

Relative Difference

Comparing datasets with different scales

Normalized Difference

Standardized analysis across different datasets

Relative Deviation

Proportional differences, useful for trend analysis

Mean Absolute Error (MAE) per Pixel

Identifying areas with large absolute differences

Direct Difference Calculation

This Direct Difference method simply subtracts one dataset from the other to visualize the changes in soil attributes directly.

Pros:

  • Clearly shows positive and negative changes.

  • Easy to interpret and visualize.

Cons:

  • The difference values may be hard to compare if datasets have different scales.

  • High variation can dominate interpretation.

Relative Difference Calculation

The Relative Difference method calculates the percentage change between the datasets based on the second dataset, offering another perspective on deviation.

Pros:

  • Good for understanding how much one dataset has changed in proportion to another.

  • Normalizes differences across varying magnitudes.

Cons:

  • Can become unstable when values in the second dataset are close to zero.

  • Less intuitive when absolute differences are important.

Normalized Difference Calculation

The Normalized Difference method normalizes the datasets by their global maximum value before computing differences, ensuring that variations are comparable across different scales.

Pros:

  • Effective for datasets with different dynamic ranges.

  • Reduces the impact of extreme values.

Cons:

  • Small variations may appear exaggerated if not scaled properly.

Relative Deviation per Pixel

The Relative Deviation method calculates the deviation as a percentage relative to the first dataset. It helps in understanding proportional differences rather than absolute differences.

Pros:

  • Useful when comparing datasets with different scales.

  • Expresses deviation in an interpretable percentage format.

Cons:

  • Can be misleading if the original values are very small.

Mean Absolute Error (MAE) per Pixel

The Mean Absolute Error (MAE) method measures the absolute differences between corresponding values in two datasets. It provides a clear view of where the highest discrepancies occur.

Pros:

  • Simple and intuitive.

  • Highlights large differences clearly.

  • Works well for datasets with similar scales.

Cons:

  • Doesn't show the direction of the difference (i.e., positive or negative change).

  • Sensitive to outliers.

Conclusion

Comparing soil scanner datasets requires a variety of mathematical approaches to extract meaningful differences. Whether using absolute metrics like MAE, relative deviations, or normalized comparisons, selecting the right method depends on the use case. By leveraging these techniques, agronomists and researchers can improve soil analysis, detect field variations, and enhance precision agriculture workflows.

The usage of geopard.calculate_difference(dataset_1, dataset_2) with parameters explanation is documented .

The usage of geopard.calculate_relative_difference(dataset_1, dataset_2) with parameters explanation is documented .

The usage of geopard.calculate_normalized_difference(dataset_1, dataset_2) with parameters explanation is documented .

The usage of geopard.calculate_per_pixel_relative_deviation(dataset_1, dataset_2) with parameters explanation is documented .

The usage of geopard.calculate_per_pixel_mae(dataset_1, dataset_2) with parameters explanation is documented .

👨‍🌾
Initial soil scanner datasets
Direct Difference Calculation
Relative Difference Calculation
Normalized Difference Calculation
Relative Deviation per Pixel
Mean Absolute Error (MAE) per Pixel
here
here
here
here
here