Utilizing Collocated Crop Growth Model Simulations to Train Agronomic Satellite Retrieval Algorithms

Abstract

Due to its worldwide coverage and high revisit time, satellite-based remote sensing provides the ability to monitor in-season crop state variables and yields globally. In this study, we presented a novel approach to training agronomic satellite retrieval algorithms by utilizing collocated crop growth model simulations and solar-reflective satellite measurements. Specifically, we showed that bidirectional long short-term memory networks (BLSTMs) can be trained to predict the in-season state variables and yields of Agricultural Production Systems sIMulator (APSIM) maize crop growth model simulations from collocated Moderate Resolution Imaging Spectroradiometer (MODIS) 500-m satellite measurements over the United States Corn Belt at a regional scale. We evaluated the performance of the BLSTMs through both k-fold cross validation and comparison to regional scale ground-truth yields and phenology. Using k-fold cross validation, we showed that three distinct in-season maize state variables (leaf area index, aboveground biomass, and specific leaf area) can be retrieved with cross-validated R2 values ranging from 0.4 to 0.8 for significant portions of the season. Several other plant, soil, and phenological in-season state variables were also evaluated in the study for their retrievability via k-fold cross validation. In addition, by comparing to survey-based United State Department of Agriculture (USDA) ground truth data, we showed that the BLSTMs are able to predict actual county-level yields with R2 values between 0.45 and 0.6 and actual state-level phenological dates (emergence, silking, and maturity) with R2 values between 0.75 and 0.85. We believe that a potential application of this methodology is to develop satellite products to monitor in-season field-scale crop growth on a global scale by reproducing the methodology with field-scale crop growth model simulations (utilizing farmer-recorded field-scale agromanagement data) and collocated high-resolution satellite data (fused with moderate-resolution satellite data).

Evaluation of the Uncertainty in Satellite-Based Crop State Variable Retrievals Due to Site and Growth Stage Specific Factors and Their Potential in Coupling with Crop Growth Models

“…The analysis used in this study relied on strong crop growth model simulation performance to expand the dataset of ground-truth LAI values to daily resolution. The strong performance of the HM simulations at the Mead, Nebraska sites, seen in [90] and Figures 1 and 2, provides a potential path [67] for future research to expand the development of testing agronomic satellite retrievals to a wide variety of G x E x M factors with farmer-provided agromanagement data. The results in Table 6 show that using HM simulation data from Mead, Nebraska to train LAI retrievals can provide nearly identical performance to using actual ground-truth LAI measurements from Mead, while Table 7 shows there are some relatively significant biases in using modeled LUECanopy to perform the training.…”

“…Thus, it can be used to provide validation of the temporal analysis performed on crop growth model simulations of LAI. In addition, it should be noted that, as in [67], the methods in this paper can be applied to crop growth model simulated variables whose time series are more difficult to measure than LAI and GPP, providing a basis to analyze performance over a wide range of crop state variables.…”

“…The crop model’s stronger performance at field-scale in predicting both the yield and individual within-season process can be attributed to the availability of significantly more accurate agromanagement information, and to a lesser extent to more accurate soil and weather data, at this scale [66]. Thus, incorporating field-scale crop growth modeling of secondary parameters in training and testing agricultural satellite retrieval algorithms [67] can potentially provide for significant advances in addressing the uncertainty caused by site and growth stage specific secondary factors.…”

“…The availability of collocated crop growth model simulations allows us to (a) analyze the sensitivity of the genotype x management (G × M) factors retrieval by the satellite to variability in the relationship of satellite measurments and crop state variables and (b) use time-series analysis to analyze the uncertainty caused by this variability. Furthermore, the collocated crop growth model simulations are used to demonstrate the possibility of training and testing agricultural remote sensing algorithms with farmer-collected agromanagement data across a wide range of spatiotemporal variability, following the concept we introduced in [67] at the regional scale. Specifically, as in [67], the crop growth model simulations based on the provided data can be used to train and test remote sensing retrieval algorithms and, with sufficient farmer participation, a large swath of the spatiotemporal variability of the secondary factors affecting the retrievals can be covered.…”

“…Furthermore, the collocated crop growth model simulations are used to demonstrate the possibility of training and testing agricultural remote sensing algorithms with farmer-collected agromanagement data across a wide range of spatiotemporal variability, following the concept we introduced in [67] at the regional scale. Specifically, as in [67], the crop growth model simulations based on the provided data can be used to train and test remote sensing retrieval algorithms and, with sufficient farmer participation, a large swath of the spatiotemporal variability of the secondary factors affecting the retrievals can be covered. This dataset would allow further research to find methods to optimally use available weather, soil, and remote sensing data to create algorithms to map the regional-scale variability in G × E × M. As a result, by using crop growth model simulations at a fixed number of sites where the G × M parameters are known, a remote sensing retrieval algorithm could be trained to map G × M parameters where they are unknown and where no high quality collocated crop growth model simulations are available.…”