■配备可见光和多光谱相机的无人机(UAV)为远程作物监测和稻田地上生物量(AGB)估算提供了可靠而有效的方法。然而,现有的研究主要集中在基于冠层光谱特征或通过将植物高度(PH)作为参数的AGB估计上。在这些研究中,对水稻的空间结构和物候阶段的考虑不足。在这项研究中,提出了一种充分考虑水稻三维生长动态的新方法,集成两个水平(雨篷罩,CC)和冠层发育的垂直(PH)方面,并计算水稻的生长天数。
■为了研究组合光谱的协同效应,空间和时间参数,在江苏省进行了小规模小区试验和大规模田间试验,中国从2021年到2022年。二十种植被指数(VIs)被用作光谱特征,PH和CC作为空间参数,和移植后天数(DAT)作为时间参数。用五种回归方法(MSR,ENet,PLSR,RF和SVR),使用来自六个特征组合(VI,PH+CC,PH+CC+DAT,VIs+PH+CC,VIs+DAT,VIs+PH+CC+DAT)。
■结果表明,提取的PH与地面测量的PH之间存在很强的相关性(R2=0.89,RMSE=5.08cm)。此外,VIs,在分till中期至开花期,PH和CC与AGB表现出很强的相关性。在分till中期至开花期的最佳AGB估计结果来自PLSR模型,以VI和DAT为输入(R2=0.88,RMSE=1111kg/ha,NRMSE=9.76%),而对于VIs,PH,CC,和DAT都作为输入(R2=0.88,RMSE=1131千克/公顷,NRMSE=9.94%)。对于字段采样数据,结合不同特征输入的ENet模型具有最佳的估计结果(%误差=0.6%-13.5%),展示了卓越的实际适用性。
■模型评估和特征重要性排名表明,使用时间和空间参数增强VI显着提高了AGB估计精度。总之,光谱和时空特征的融合增强了AGB估算模型的实际物理意义,并显示出在主要物候阶段准确估算水稻AGB的巨大潜力。
UNASSIGNED: Unmanned aerial vehicles (UAVs) equipped with visible and multispectral cameras provide reliable and efficient methods for remote crop monitoring and above-ground biomass (AGB) estimation in rice fields. However, existing research predominantly focuses on AGB estimation based on canopy spectral features or by incorporating plant height (PH) as a parameter. Insufficient consideration has been given to the spatial structure and the phenological stages of rice in these studies. In this study, a novel method was introduced by fully considering the three-dimensional growth dynamics of rice, integrating both horizontal (canopy cover, CC) and vertical (PH) aspects of canopy development, and accounting for the growing days of rice.
UNASSIGNED: To investigate the synergistic effects of combining spectral, spatial and temporal parameters, both small-scale plot experiments and large-scale field testing were conducted in Jiangsu Province, China from 2021 to 2022. Twenty vegetation indices (VIs) were used as spectral features, PH and CC as spatial parameters, and days after transplanting (DAT) as a temporal parameter. AGB estimation models were built with five regression methods (MSR, ENet, PLSR, RF and SVR), using the derived data from six feature combinations (VIs, PH+CC, PH+CC+DAT, VIs+PH +CC, VIs+DAT, VIs+PH+CC+DAT).
UNASSIGNED: The results showed a strong correlation between extracted and ground-measured PH (R2 = 0.89, RMSE=5.08 cm). Furthermore, VIs, PH and CC exhibit strong correlations with AGB during the mid-tillering to flowering stages. The optimal AGB estimation results during the mid-tillering to flowering stages on plot data were from the PLSR model with VIs and DAT as inputs (R 2 = 0.88, RMSE=1111kg/ha, NRMSE=9.76%), and with VIs, PH, CC, and DAT all as inputs (R 2 = 0.88, RMSE=1131 kg/ha, NRMSE=9.94%). For the field sampling data, the ENet model combined with different feature inputs had the best estimation results (%error=0.6%-13.5%), demonstrating excellent practical applicability.
UNASSIGNED: Model evaluation and feature importance ranking demonstrated that augmenting VIs with temporal and spatial parameters significantly enhanced the AGB estimation accuracy. In summary, the fusion of spectral and spatio-temporal features enhanced the actual physical significance of the AGB estimation models and showed great potential for accurate rice AGB estimation during the main phenological stages.