A multi-sensor platform built for rangeland and conservation data.
Hyperspectral UAV surveys, satellite data integration, handheld NIR, and custom ML models — combined into scalable workflows for mapping, analysis, and program documentation.
The sensing stack
Multiple platforms, calibrated to work together.
Hyperspectral UAV Sensors
- Airborne sensors collecting tens to hundreds of spectral bands
- Centimeter-to-meter resolution over large coverage areas
- Plant species, biomass, and stress mapping from the air
Satellite Data
- Sentinel-2, Landsat, and Planet for landscape-scale coverage
- Time-series analysis for change detection and phenology
- Coarser resolution complemented by UAV ground truth
Handheld NIR
- Close-range scanning for bale, forage, and direct plant confirmation
- Calibrated models for species identity and chemistry (crude protein, ADF/NDF)
- Smartphone-based workflow for fast field use
ML model pipeline
From raw spectra to calibrated, validated outputs.
Spectral preprocessing and feature engineering
- Baseline correction, derivative transforms, dimensionality reduction
- Controlled for geometry, moisture, and sensor drift
- Preprocessing tailored to sensor type and target medium
Model types and validation
- PLS, PLS-DA, SVM, and lightweight neural networks
- Performance targets set per engagement with documented failure modes
- Validated against held-out samples and real field conditions
Data delivery
Outputs designed for the programs and workflows clients actually use.
GIS-compatible mapping outputs
Shapefiles, GeoTIFFs, and KMZ files ready for program submissions, management planning, and agency review.
Program-formatted reports
Documentation designed to support EQIP applications, Defend the Core submissions, and internal management records.
Screening reports with confidence scores
Per-scan or per-lot outputs with pass/warn/flag results, chemistry estimates, and documented performance bounds.
The science behind it
NIR spectroscopy and machine learning make fast, field-ready plant identification and chemistry analysis possible.
NIR spectroscopy and plant chemistry
Near-infrared light measures overtone and combination bands tied to O-H, C-H, and N-H bonds. Differences in water, cellulose, lignin, protein, and mineral content create repeatable spectral fingerprints across plant species.
ML detection in mixed media
We use preprocessing and models like PLS-DA, SVM, and lightweight neural networks to isolate species signatures. Training across diverse mixtures enables detection even when targets are diluted in other materials.
Integrated platform, not just sensors
Zubr's differentiation is the combination of sensor calibration, domain-specific ML models, and conservation program knowledge. Off-the-shelf hardware is the starting point, not the product.
How a typical engagement works
From scoping call to delivered data products.
Scope the data need
Define species targets, geography, program requirements, delivery formats, and timeline.
Collect and calibrate
UAV flights, satellite data pulls, or field NIR scanning — per the agreed plan and sampling design.
Process and model
Spectral preprocessing, model training or application, and output QA against documented performance targets.
Deliver and document
GIS files, analysis reports, and program-ready documentation — with support for any submission or review process.
Need a custom technology approach?
Tell us your target species, geography, and program requirements.
Request a consultation