Accurate estimation of the fraction of absorbed photosynthetically active radiation (fPAR) is important for maize growth and yield estimations. Light detection and ranging (LiDAR)-derived canopy vertical structural and hyperspectral image-derived vegetation spectral information are complementary for vegetation fPAR estimation. This study explores the potential of artificial neural networks (ANNs) with two types of data to estimate maize fPAR. First, 45 metrics were derived from LiDAR data and 13 from a hyperspectral image. Then, the ANNs and stepwise multiple linear regression (SMLR) methods were used to estimate the fPAR. Finally, model validity was assessed using in-situ data. Results showed that the ANNs performed better in fPAR inversion (R ² = 0.910, adj. R ² = 0.921, RMSE = 0.046, RRMSE = 0.056, where R ² is the coefficient of determination, adj. R ² the adjusted coefficient of determination, RMSE the root mean squared error, and RRMSE the relative root mean squared error) than SMLR (R ² = 0.638, adj. R ² = 0.609, RMSE = 0.077, RRMSE = 0.092) and SMLR with the natural logarithm of data (R ² = 0.855, adj. R ² = 0.825, RMSE = 0.067, RRMSE = 0.081). This study is helpful for guiding the accurate estimation of maize fPAR using remote sensing techniques.

准确估算吸收的光合有效辐射（fPAR）的比例对于玉米生长和产量估算很重要。源自光检测和测距（LiDAR）的冠层垂直结构和源自高光谱图像的植被光谱信息是植被fPAR估计的补充。这项研究探索了利用两种数据来估计玉米fPAR的人工神经网络（ANN）的潜力。首先，从LiDAR数据得出45个度量，从高光谱图像得出13个。然后，使用ANN和逐步多元线性回归（SMLR）方法估计fPAR。最后，使用原位数据评估模型的有效性。结果表明，人工神经网络在fPAR反演中表现更好（R ²  = 0.910，调整后R ² = 0.921，RMSE = 0.046，RRMSE = 0.056，其中R ²是确定系数adj。R ²的校正后测定系数，RMSE均方根误差和RRMSE相对均方根误差）比SMLR（R ²  = 0.638，调整后R ²  = 0.609，RMSE = 0.077，RRMSE = 0.092）和SMLR数据的自然对数（R ²  = 0.855，调整后R ²  = 0.825，RMSE = 0.067，RRMSE = 0.081）。这项研究有助于指导使用遥感技术对玉米fPAR的准确估算。