Remote sensing images captured by satellites play a critical role in Earth observation (EO). With the advancement of satellite technology, the number and variety of remote sensing satellites have increased, which provide abundant data for precise environmental monitoring and effective resource management. However, existing satellite imagery often faces a trade-off between spatial and temporal resolutions. It is challenging for a single satellite to simultaneously capture images with high spatial and temporal resolutions. Consequently, spatiotemporal fusion techniques, which integrate images from different sensors, have garnered significant attention. Over the past decade, research on spatiotemporal fusion has achieved remarkable progress. Nevertheless, traditional fusion methods often encounter difficulties when dealing with complicated fusion scenarios. With the development of computer science, deep learning models, such as convolutional neural networks (CNNs), generative adversarial networks (GANs), Transformers, and diffusion models, have recently been introduced into the field of spatiotemporal fusion, resulting in efficient and accurate algorithms. These algorithms exhibit various strengths and limitations, which require further analysis and comparison. Therefore, this paper reviews the literature on deep learning-based spatiotemporal fusion methods, analyzes and compares existing deep learning-based fusion algorithms, summarizes current challenges in this field, and proposes possible directions for future studies.

In physical model inversion of leaf area index (LAI) over complex vegetation canopies, variations in canopy structure, background moisture, and background brightness can cause spectrally similar lookup table (LUT) candidates to represent different combinations of canopy and background parameters, reducing retrieval stability. This study proposes a PROSAIL lookup table inversion method for GaoFen-5A (GF-5A) hyperspectral imagery based on physically informed parameter range refinement. A small set of key GF-5A feature bands was selected to preserve information sensitive to canopy structure and background conditions while reducing spectral redundancy. Vegetation type information was used to determine the LIDFa range, while the normalized difference infrared index (NDII) and brightness index (BI) were used to guide the refinement of psoil and rsoil ranges according to moisture related and brightness related spectral responses, respectively. Combining compact spectral inputs with refined PROSAIL parameter ranges improved LUT candidate selection under variable canopy and background conditions. Validation using 62 field LAI values aggregated at the GF-5A pixel scale yielded a coefficient of determination (R²) of 0.6000, a root mean square error (RMSE) of 1.1461, a mean absolute error (MAE) of 0.8712, and a Bias of −0.0092, outperforming the comparison schemes. These results indicate improved physical consistency and stability in LAI inversion under complex canopy and background conditions.