Modeling SAR Observables by Combining a Crop-Growth Model With Machine Learning

Nikaein, T.; Lopez Dekker, F.J.; Steele-Dunne, S.C.; Kumar, V.; Huber, M.

doi:10.1109/JSTARS.2023.3301124

Modeling SAR Observables by Combining a Crop-Growth Model With Machine Learning

Title

Modeling SAR Observables by Combining a Crop-Growth Model With Machine Learning

Author

Nikaein, T. (TU Delft Mathematical Geodesy and Positioning)
Lopez Dekker, F.J. (TU Delft Mathematical Geodesy and Positioning)
Steele-Dunne, S.C. (TU Delft Mathematical Geodesy and Positioning)
Kumar, V. (TU Delft Mathematical Geodesy and Positioning)
Huber, M. (European Space Agency (ESA))

Date

2023

Abstract

In this article, our aim is to estimate synthetic aperture radar (SAR) observables, such as backscatter in VV and VH polarizations, as well as the VH/VV ratio, cross ratio, and interferometric coherence in VV, from agricultural fields. In this study, we use the decision support system for agrotechnology transfer (DSSAT) crop-growth simulation model to simulate parcel-level phenological and growth parameters for over 1500 parcels of silage maize in the Netherlands. The crop model was calibrated using field data, including silage maize phenological phases, leaf area index, and above-ground dry biomass (AGB). The simulations incorporate fine-resolution gridded precipitation data and soil parameters to model the interaction between soil-plant-atmosphere and genotype in DSSAT. The crop variables produced by DSSAT are then used as inputs to a support vector regression model. This model is trained to simulate SAR observables in 2017, 2018, and 2019, and its performance is evaluated using independent fields in each of these years. The results show a close fit between modeled and observed SAR C-band observables. The importance of vegetation variables in the estimation of SAR observables is assessed. The AGB showed significant importance in the estimation of backscatter. This study demonstrates the potential value of combining crop-growth simulation models and machine learning to simulate SAR observables. For example, the SVR model developed here could be used as an observation operator in an assimilation context to constrain vegetation and soil water dynamics in a crop-growth model.

Subject

Biological system modeling
Crop
Crops
Data models
Decision support systems
DSSAT
forward-model
SAR
Sentinel-1
silage maize
simulation
Soil
Synthetic aperture radar
Vegetation mapping