Land Surface

Land surface research focuses on understanding and modeling the complex interactions between the Earth's surface and the atmosphere, primarily concerning energy, water, and carbon fluxes. Current research heavily utilizes machine learning, particularly recurrent neural networks (RNNs) and convolutional neural networks (CNNs), alongside traditional physics-based models, to improve the accuracy and efficiency of land surface predictions, including streamflow routing and greenhouse gas emissions. These advancements are crucial for improving weather forecasting, climate change modeling, and resource management, offering more accurate predictions of crucial variables like land surface temperature and vegetation indices. The integration of diverse data sources, such as satellite imagery and in-situ measurements, is key to enhancing model performance and addressing uncertainties.