In-season crop progress in unsurveyed regions using networks trained on synthetic data

Abstract

Many commodity crops have growth stages during which they are particularly vulnerable to stress-induced yield loss. In-season crop progress information is useful for quantifying crop risk, and satellite remote sensing (RS) can be used to track progress at regional scales. At present, all existing RS-based crop progress estimation (CPE) methods which target crop-specific stages rely on ground truth data for training/calibration. Such data are collected via field trials or surveys. This reliance on ground survey data confines CPE methods to surveyed regions, limiting their utility. In this study, a new method is developed for conducting RS-based in-season CPE in unsurveyed regions by combining data from surveyed regions with synthetic crop progress data generated for an unsurveyed region of interest. Corn-growing zones in Argentina were used as surrogate ‘unsurveyed’ regions. These zones have climates and dual planting systems which differ from the single planting system in the US Midwest – the surveyed region in this study. Existing weather generation, crop growth, and optical radiative transfer models were linked to produce synthetic weather, crop progress, and canopy reflectance data. These data mimic weather, cultivars, and cropping practices in the unsurveyed region. A neural network (NN) method based upon bi-directional Long Short-Term Memory was trained separately on surveyed data, synthetic data, and two different combinations of surveyed and synthetic data. In the absence of real validation data in unsurveyed regions, a stopping criterion was developed which uses the weighted divergence of surveyed and synthetic data validation loss. F1 score was modified to measure CPE accuracy when the NN was trained on each data combination, with scores based on over- and under-estimates of crop progress throughout the season. Including synthetic data during training improved performance in 9 out of 11 corn-growing zones in Argentina. Net F1 scores across all crop progress stages increased by 8.7% when trained on a combination of surveyed region and synthetic data, and overall performance was only 21% lower than when the NN was trained on surveyed data and applied in the US Midwest. Performance gain from synthetic data was greatest in zones with dual planting windows, while the inclusion of surveyed region data from the US Midwest helped mitigate NN sensitivity to noise in NDVI data. Overall results suggest in-season CPE in other unsurveyed regions may be possible with increased quantity and variety of synthetic crop progress data.

Plant phenotyping relevance

作物の生育ステージを衛星リモートセンシングとニューラルネットワークで推定する手法を開発し、合成データによる性能評価も行っており、植物状態の取得・推定が研究の中心である。

Code and data availability

公開状態または取得可能な本文経路を確認できませんでした。

No evidence-backed public reproduction asset is currently recorded.