Wang Taojun, Crawford Melba M, Tuinstra Mitchell R
School of Electrical and Computer Engineering, Purdue University, West Lafayette, IN, United States.
Lyles School of Civil Engineering, Purdue University, West Lafayette, IN, United States.
Front Plant Sci. 2023 Apr 11;14:1138479. doi: 10.3389/fpls.2023.1138479. eCollection 2023.
Yield for biofuel crops is measured in terms of biomass, so measurements throughout the growing season are crucial in breeding programs, yet traditionally time- and labor-consuming since they involve destructive sampling. Modern remote sensing platforms, such as unmanned aerial vehicles (UAVs), can carry multiple sensors and collect numerous phenotypic traits with efficient, non-invasive field surveys. However, modeling the complex relationships between the observed phenotypic traits and biomass remains a challenging task, as the ground reference data are very limited for each genotype in the breeding experiment. In this study, a Long Short-Term Memory (LSTM) based Recurrent Neural Network (RNN) model is proposed for sorghum biomass prediction. The architecture is designed to exploit the time series remote sensing and weather data, as well as static genotypic information. As a large number of features have been derived from the remote sensing data, feature importance analysis is conducted to identify and remove redundant features. A strategy to extract representative information from high-dimensional genetic markers is proposed. To enhance generalization and minimize the need for ground reference data, transfer learning strategies are proposed for selecting the most informative training samples from the target domain. Consequently, a pre-trained model can be refined with limited training samples. Field experiments were conducted over a sorghum breeding trial planted in multiple years with more than 600 testcross hybrids. The results show that the proposed LSTM-based RNN model can achieve high accuracies for single year prediction. Further, with the proposed transfer learning strategies, a pre-trained model can be refined with limited training samples from the target domain and predict biomass with an accuracy comparable to that from a trained-from-scratch model for both multiple experiments within a given year and across multiple years.
生物燃料作物的产量是以生物量来衡量的，因此在整个生长季节进行测量对于育种计划至关重要，但传统方法既耗时又费力，因为它们涉及破坏性采样。现代遥感平台，如无人机（UAV），可以搭载多个传感器，并通过高效、非侵入性的田间调查收集众多表型性状。然而，对观测到的表型性状和生物量之间的复杂关系进行建模仍然是一项具有挑战性的任务，因为育种实验中每个基因型的地面参考数据非常有限。在本研究中，提出了一种基于长短期记忆（LSTM）的递归神经网络（RNN）模型用于高粱生物量预测。该架构旨在利用时间序列遥感和气象数据以及静态基因型信息。由于从遥感数据中导出了大量特征，因此进行了特征重要性分析以识别和去除冗余特征。提出了一种从高维遗传标记中提取代表性信息的策略。为了增强泛化能力并尽量减少对地面参考数据的需求，提出了迁移学习策略，用于从目标域中选择信息最丰富的训练样本。因此，可以用有限的训练样本对预训练模型进行优化。在一个种植了多年、包含600多个测交杂种的高粱育种试验中进行了田间试验。结果表明，所提出的基于LSTM的RNN模型在单年预测中可以实现高精度。此外，通过所提出的迁移学习策略，可以用来自目标域的有限训练样本对预训练模型进行优化，并且对于给定年份内的多个实验以及跨多年的实验，预测生物量的准确性与从头训练的模型相当。
