CubeSat Enabled Sensor Fusion Approach for Daily Mapping of In-field Leaf Area Index

Abstract:

The recent emergence of new observational paradigms combined with advances in conventional spaceborne sensing has resulted in a proliferation of satellite sensor data. This geospatial information revolution constitutes a game changer in the ability to derive time-critical and location-specific insights into dynamic land surface processes. However, sensor interoperability issues and cross-calibration challenges present obstacles in realizing the full potential of these rich geospatial datasets.

At Planet, we have implemented a methodology--the CubeSat-Enabled Spatio-Temporal Enhancement Method (CESTEM)--to enhance, harmonize, inter-calibrate, and fuse cross-sensor data streams leveraging rigorously calibrated ‘gold standard’ satellites (i.e., Sentinel, Landsat, MODIS) in synergy with superior resolution CubeSats from Planet. The result is next generation analysis ready data (L3H), delivering clean (i.e. free from clouds and shadows), gap-filled (i.e., daily, 3 m), temporally consistent, and radiometrically robust surface reflectance (SR) feeds featuring and synergizing inputs from both public and private sensor sources.

In this work, L3H SR data are used to derive higher-level biophysical properties in order to deliver quantitative insights that are directly usable and actionable. Leaf area index (LAI) is retrieved using a novel hybrid inversion method that combines non-parametric machine-learning and state-of-the-art physically-based understanding. The adopted approach leverages 1) the enhanced spectral capability of Sentinel-2 sensor data to establish robust spectral-to-plant trait relationships, and 2) CubeSat data to enable significant enhancements both spatially and temporally. The developed technology (L3H-BIO) facilitates high resolution (daily, 3 m) insights into crop growth dynamics, developing plant stress, and crop disturbances to allow for needed improvements in the management and sustainable development of the agri-business sector. The repeatable in-field information on crop conditions to be provided by L3H-BIO has significant potential for powering smarter, more efficient, and productive farming at broad scales.