Abstract: High-resolution LAI data can provide more detailed information for remote sensing applications. However, for deep learning-based LAI retrieval methods, a training dataset composed of sensor data with a moderate or low spatial resolution cannot be directly applied to derive LAI from high-spatial-resolution sensor data due to distribution discrepancies between different sensor data. Following in this insight, we proposed a multi-task adversarial transfer learning framework, named DANN_MT. This framework leverages an adaptive adversarial training strategy to extract domain-invariant features between MODIS and Landsat surface reflectance data, enabling the retrieval of high-resolution LAI. To address the incomplete consistency between tasks of generating corresponding moderate-resolution LAI and high-resolution LAI, the DANN_MT model is designed with multi-task learning. Comparison results suggest that the retrieved high-resolution LAI exhibit reasonable spatial distribution and seasonality. Direct validation demonstrates that the retrieved high-resolution LAI (RMSE for the GBOV sites: 0.86, RMSE for the IMAGINES sites: 0.82) have a higher accuracy than the SNAP LAI (RMSE for the GBOV sites: 0.93, RMSE for the IMAGINES sites: 0.95). These conclusions reveal that the knowledge learned from the moderate-spatial-resolution dataset is successfully transferred to produce the high-spatial-resolution LAI from Landsat surface reflectance using the proposed DANN_MT model.

Citation: Li Juan, Xiao Zhiqiang, Sun Rui, Song Jinglin, and Shi Chenhui. 2025.“Retrieval of Leaf Area Index from the Landsat Surface Reflectance Using Multi-Task Adversarial Transfer Learning.”International Journal of Digital Earth, 18(1). doi:10.1080/17538947.2025.2520002.

论文链接: https://doi.org/10.1080/17538947.2025.2520002