Abstract In this study, hyperspectral imagery was used to develop models for predicting onion yields in two years (2017 and 2018). First, the bands for the full width half maximum (FWHM) measurement of 5 nm in the canopied areas were merged as FWHM 10, 25, and 50 nm. This was based on a commercialized band-pass filter that considered the development of the compact multispectral image sensors. Then, band rationing was performed to correct the unstable reflectance through incomplete radiating normalization. Stepwise and variable importance in projection in partial least squares (PLS_VIP) approaches were applied to select the optimal FWHM by evaluating both models’ performance and the number of overlapped band ratios. The optimal FWHM measurement was 10 nm, with both high model performances and the highest number of overlapped band ratios. The overlapped ratios of 440/450, and 730/760 in variable importance in projection (VIP) 1 were fixed in the onion-yield prediction model. Conversely, the non-fixed, non-overlapped ratios of 420/430, 490/500, 500/510, 590/600, 620/630, 660/670, 670/680, 710/720, 810/820, and 870/880 were reduced one by one; this was dependent on their removal ranking in descending order of the mean ratio of reduction (MROR) based on the RMSE value, using the leave-one-out method. These combinations in both the fixed and non-fixed band ratios were used to develop prediction models with and without effective accumulated temperature (EAT) values. In all combinations, the models’ performance developed with EAT were increased by preventing slight or sharp decrease in performance, compared to those without EAT. The models, in each year, developed by seven band ratios (420/430, 440/450, 500/510, 590/600, 620/630, 670/680, and 730/760) among the combinations were maintained. The prediction models with EAT were cross-validated (by predicting the 2017 yields using the 2018 model and the 2018 yields using the 2017 model) to evaluate the reproducibility in other years. The reproducibility of the model developed by the seven band ratios was optimal with errors of RMSE = 172 g/m2, RE = 30.3% in 2017 using the 2018 model and RMSE = 215 g/m2 and RE = 33.2% in 2018 using the 2017 model. Consequently, the key band ratios for predicting the onion yields were identified as the seven band ratios with EAT at 420/430, 440/450, 500/510, 590/600, 620/630, 670/680, and 730/760. Ultimately, these findings will provide compact multispectral image sensors specialized in onion-yield prediction that can monitor wide agriculture fields mounted on various platforms.

中文翻译：

---

使用窄带高光谱图像和有效累积温度中的关键变量对洋葱 (Allium cepa L.) 进行产量预测和验证

摘要 在本研究中，高光谱图像用于开发预测两年（2017 年和 2018 年）洋葱产量的模型。首先，将顶篷区域中 5 nm 的半高全宽 (FWHM) 测量波段合并为 FWHM 10、25 和 50 nm。这是基于考虑开发紧凑型多光谱图像传感器的商业化带通滤波器。然后，通过不完全辐射归一化进行波段配给以校正不稳定的反射率。通过评估两种模型的性能和重叠带比的数量，应用偏最小二乘法 (PLS_VIP) 投影中的逐步和可变重要性来选择最佳 FWHM。最佳 FWHM 测量值为 10 nm，具有较高的模型性能和最高数量的重叠带比。在洋葱产量预测模型中，投影 (VIP) 1 中可变重要性的重叠比率 440/450 和 730/760 是固定的。相反，非固定、非重叠比率 420/430、490/500、500/510、590/600、620/630、660/670、670/680、710/720、810/870 /880 一一减少；这取决于基于 RMSE 值的平均减少率 (MROR) 降序排列，使用留一法。这些固定和非固定带比的组合用于开发具有和不具有有效积温 (EAT) 值的预测模型。在所有组合中，与未使用 EAT 的模型相比，使用 EAT 开发的模型的性能通过防止性能轻微或急剧下降而得到提高。模型，在每年，保持了组合之间由七个带比（420/430、440/450、500/510、590/600、620/630、670/680和730/760）开发。使用 EAT 的预测模型进行了交叉验证（通过使用 2018 模型预测 2017 年产量和使用 2017 模型预测 2018 年产量）以评估其他年份的可重复性。由七个波段比率开发的模型的再现性是最佳的，误差为 RMSE = 172 g/m2，使用 2018 模型的 2017 年误差为 30.3%，使用 2017 年模型的 2018 年误差为 RMSE = 215 g/m2 和 RE = 33.2%模型。因此，预测洋葱产量的关键波段比率被确定为 EAT 为 420/430、440/450、500/510、590/600、620/630、670/680 和 730/760 的七个波段比率。最终，