Accurate early season predictions of crop yield at the within-field scale can be used to address a range of crop production, management, and precision agricultural challenges. While the remote sensing of within-field insights has been a research goal for many years, it is only recently that observations with the required spatio-temporal resolutions, together with efficient assimilation methods to integrate these into modeling frameworks, have become available to advance yield prediction efforts. Here we explore a yield prediction approach that combines daily high-resolution CubeSat imagery with the APSIM crop model. The approach employs APSIM to train a linear regression that relates simulated yield to simulated leaf area index (LAI). That relationship is then used to identify the optimal regression date at which the LAI provides the best prediction of yield: in this case, approximately 14 weeks prior to harvest. Instead of applying the regression on satellite imagery that is coincident, or closest to, the regression date, our method implements a particle filter that integrates CubeSat-based LAI into APSIM to provide end-of-season high-resolution (3 m) yield maps weeks before the optimal regression date. The approach is demonstrated on a rainfed maize field located in Nebraska, USA, where suitable collections of both imagery and in-situ data were available for assessment. The procedure does not require in-field data to calibrate the regression model, with results showing that even with a single assimilation step, it is possible to provide yield estimates with good accuracy up to 21 days before the optimal regression date. Yield spatial variability was reproduced reasonably well, with a strong correlation to independently collected measurements (R² = 0.73 and rRMSE = 12%). When the field averaged yield was compared, our approach reduced yield prediction error from 1 Mg/ha (control case based on a calibrated APSIM model), to 0.5 Mg/ha (using satellite imagery alone), and then to 0.2 Mg/ha (results with assimilation up to three weeks prior to the optimal regression date). Such a capacity to provide spatially explicit yield predictions early in the season has considerable potential to enhance digital agricultural goals and improve end-of-season yield predictions.

在田间范围内对作物产量的准确早期预测可用于解决一系列作物生产、管理和精准农业挑战。多年来，实地洞察的遥感一直是一个研究目标，但直到最近，具有所需时空分辨率的观测以及将它们整合到建模框架中的有效同化方法才可用于提高产量预测努力。在这里，我们探索了一种将每日高分辨率 CubeSat 图像与 APSIM 作物模型相结合的产量预测方法。该方法使用 APSIM 来训练将模拟产量与模拟叶面积指数 (LAI) 相关联的线性回归。然后使用该关系来确定 LAI 提供最佳产量预测的最佳回归日期：在这种情况下，大约在收获前 14 周。我们的方法不是对与回归日期重合或最接近的卫星图像应用回归，而是实现了一个粒子滤波器，将基于 CubeSat 的 LAI 集成到 APSIM 中，以提供季末高分辨率 (3 m) 产量图最佳回归日期前几周。该方法在位于美国内布拉斯加州的雨养玉米田中得到了演示，那里收集了合适的图像和原位数据用于评估。该程序不需要现场数据来校准回归模型，结果表明，即使采用单个同化步骤，可以在最佳回归日期前 21 天提供具有良好准确度的产量估计值。产量空间变异性得到了相当好的再现，与独立收集的测量值（R²  = 0.73 且 rRMSE = 12%）。当比较田间平均产量时，我们的方法将产量预测误差从 1 毫克/公顷（基于校准的 APSIM 模型的控制案例）降低到 0.5 毫克/公顷（仅使用卫星图像），然后降低到 0.2 毫克/公顷（最佳回归日期前三周同化的结果）。这种在季节早期提供空间明确的产量预测的能力在加强数字农业目标和改善季末产量预测方面具有相当大的潜力。