T Dashevskiy

Consulting project for FarmLogs: Temporal analysis of satellite imagery to determine crop type

Transcript

1. Temporal analysis of satellite imagery to determine crop type Tatiana Dashevskiy
2. 1 out of 3 farms use FarmLogs services
3. Fertilizer Match Services for Specific Fields
4. Fertilizer Crops only detected at the END of season Match Services for Specific Fields
5. How to Detect Crops Early in the Season Temporal analysis of satellite images
6. Deliverable: Model in Python and Crop Detector Application https://youtu.be/EPtDwFKibOI
7. Features: - Time Series Data - RGB - Near-infrared - vegetation index - Crop Type: - 60% corn - 40% 6 other crops Image Data May July August 8,000 Images for 900 Fields
8. Feature Engineering May July August Slope of Average pixel value over time per Field
9. Feature Engineering May July August Slope of Average pixel value over time per Field
10. Feature Engineering May July August Slope of Average pixel value over time per Field Soybean Corn
11. Images only RGB, near infrared, vegetation index 24% Error Random Forest Crops detectable early in the season!
12. Images only RGB, near infrared, vegetation index 24% Error Weather 19% Error Lasso regression analysis + SMOTE to balance data sets Random Forest Crops detectable early in the season! min & max temp, precipitation, etc.
13. Images only RGB, near infrared, vegetation index 24% Error Weather 19% Error Lasso regression analysis + SMOTE to balance data sets Random Forest Crops detectable early in the season! min & max temp, precipitation, etc. 21% Improvement!
14. Tatiana Dashevskiy PhD in Physics, Applied dynamical systems in neuroscience Post Doc Seattle Children’s Research Institute