Our flower prediction models are based on cutting-edge research in remote sensing, phenology detection, and agricultural monitoring. These peer-reviewed publications form the scientific foundation of our prediction algorithms.
Remote sensing approach for predicting forest flowering patterns using satellite data
Multi-temporal analysis of flowering detection using Sentinel satellite imagery
Climate change impacts on flowering timing patterns in multiple species
Development of improved indices for flower detection and quantification
UAV-based approach for counting and analyzing pear blossom clusters
Automated detection and quantification of apple tree flowering using drone technology
Quantitative analysis of flowering coverage using UAV remote sensing
Species-specific flowering analysis using unmanned aerial systems
Combined UAV and satellite approach for invasive species flowering detection
Spectral analysis techniques for large-scale flowering pattern mapping
These publications represent state-of-the-art research in flowering phenology detection using various remote sensing platforms including satellites, UAVs, and ground-based sensors. Our algorithms incorporate techniques from:
© 2025 FlorCast Team. Built for NASA Space Apps Challenge 2025.
All referenced papers are the property of their respective authors and publishers.