Volume 1 Issue 1 (2025)

The global hydrological cycle is a core component of the Earth system, and its response to climate change has profound impacts on ecological security and human society. Traditional hydrological models are limited by simplified parameterization schemes, leading to uncertainties in simulating complex hydrological processes. This study proposes a deep learning-enhanced global hydrological simulation framework that integrates long short-term memory (LSTM) networks with a physically based hydrological model (Variable Infiltration Capacity, VIC). By assimilating multi-source data (e.g., satellite-derived precipitation, evapotranspiration, and soil moisture), the framework optimizes parameterization of key processes such as infiltration and runoff generation. Validation using in-situ observation data from 500 global river basins shows that the proposed framework improves the simulation accuracy of runoff and soil moisture by 15% and 22% respectively compared to the traditional VIC model. Further scenario simulations indicate that under the SSP5-8.5 scenario, the global average runoff will increase by 8.3% by the end of the 21st century, with significant spatial heterogeneity—runoff in high-latitude regions may increase by more than 20%, while arid and semi-arid regions in the mid-latitudes may face a 10-15% decrease in runoff. This study provides a new approach for improving the accuracy of global hydrological cycle simulations and offers scientific support for formulating climate change adaptation strategies.

• View pdf

Ocean-atmosphere coupling processes are core components of the Earth system, regulating global energy redistribution and regional extreme weather events, especially tropical cyclones (TCs). Traditional coupled ocean-atmosphere models rely on grid-based parameterization schemes to describe nonlinear coupling processes, leading to significant uncertainties in simulating key variables such as sea surface temperature (SST) anomalies, latent heat flux (LHF) exchange, and thus TC intensity prediction. This study proposes a Graph Neural Network-based ocean-atmosphere coupling simulation framework (GNN-OAC) that constructs a spatial-temporal graph structure based on the physical connections between ocean and atmosphere grid cells to capture the non-local and nonlinear coupling relationships. The framework assimilates multi-source observation data, including satellite-derived SST, LHF, and in-situ buoy data, to optimize the representation of key coupling processes such as ocean mixed layer heat exchange and atmospheric boundary layer instability. Validation results based on 30 years of global TC observation data show that the GNN-OAC framework improves the average accuracy of TC intensity prediction by 23% compared to the traditional Coupled Ocean-Atmosphere Response Experiment (COARE) model. Simulation under CMIP6 SSP2-4.5 and SSP5-8.5 scenarios indicates that the GNN-OAC framework reduces the uncertainty of TC intensity projection by 18-22% by the end of the 21st century. Specifically, in the western North Pacific and North Atlantic TC basins, the framework accurately captures the negative feedback effect of SST cooling on TC intensity enhancement and the positive feedback effect of atmospheric convection on ocean upwelling. This study provides a new paradigm for improving the simulation accuracy of ocean-atmosphere coupling processes in Earth system models and enhances the reliability of extreme weather event prediction, offering important scientific support for formulating marine disaster prevention and mitigation strategies.

• View pdf

Tropical cyclones (TCs) are severe marine meteorological disasters whose tracks are closely regulated by ocean-atmosphere coupling processes, such as sea surface temperature (SST) anomalies, latent heat flux exchange, and upper-ocean thermal structure. Traditional TC track prediction models, which rely on parameterized ocean-atmosphere coupling schemes or pure statistical learning methods, often fail to capture the complex nonlinear interactions between oceanic and atmospheric variables, leading to significant prediction errors, especially for long-lead-time forecasts (72 h and above). This study proposes a Hybrid Physics-Data Driven Ocean-Atmosphere Coupling (HPD-OAC) model for TC track prediction. The model integrates a physics-based ocean-atmosphere coupling core (derived from the Regional Ocean Modeling System (ROMS) and Weather Research and Forecasting (WRF) model) with a data-driven dynamic correction module (based on a Temporal-Spatial Attention Long Short-Term Memory (TSA-LSTM) network). Multi-source data, including satellite remote sensing SST, altimeter-derived sea level anomaly (SLA), in-situ buoy observations, and reanalysis data, are assimilated to optimize the initial conditions and coupling parameters of the model. Validation results based on 150 TC events in the Northwest Pacific and North Atlantic basins from 2000 to 2023 show that the HPD-OAC model reduces the average track prediction error by 35% (72 h lead time) and 42% (120 h lead time) compared to the traditional WRF-ROMS coupled model. For intense TCs (category 4-5), the prediction error reduction reaches 48% at 120 h lead time. Further analysis indicates that the model accurately captures the regulating effect of upper-ocean cold wakes on TC intensity and the steering flow adjustment caused by ocean-atmosphere heat exchange, which are key factors improving track prediction accuracy. Under future climate change scenarios (CMIP6 SSP2-4.5 and SSP5-8.5), the HPD-OAC model projects a westward shift of TC tracks in the Northwest Pacific by 0.8-1.2° longitude and an increase in TC landfall frequency along the East Asian coast by 15-22% by the end of the 21st century. This study provides a new hybrid framework for improving TC track prediction accuracy, enriching the research methods of computational Earth system dynamics, and offering important scientific support for marine disaster prevention and mitigation.

• View pdf

Land-atmosphere coupling processes, involving the exchange of energy, water, and momentum between the land surface and the atmosphere, are critical for regulating regional weather systems and extreme precipitation events. Traditional land-atmosphere coupling models rely on parameterization schemes that simplify complex nonlinear processes (e.g., soil moisture-evaporation feedback, vegetation-atmosphere interaction), leading to significant uncertainties in simulating key variables such as latent heat flux, boundary layer stability, and thus extreme precipitation prediction. This study proposes a Physics-Informed Graph Transformer (PI-GT) framework for land-atmosphere coupling simulation and extreme precipitation prediction. The framework constructs a dynamic spatial-temporal graph based on the physical connections between land surface and atmospheric grid cells, and integrates physical constraints (e.g., water balance, energy conservation) into the transformer architecture to ensure physical rationality. Multi-source observation data, including satellite-derived soil moisture, vegetation index, in-situ flux tower data, and reanalysis data, are assimilated to optimize the model‘s representation of key coupling processes. Validation results based on 25 years of observation data from 120 flux tower sites and extreme precipitation events in major river basins of China and the United States show that the PI-GT framework improves the average simulation accuracy of key land-atmosphere coupling variables by 27% compared to the traditional Community Land Model (CLM) 5.0. For extreme precipitation prediction (24-hour lead time), the framework reduces the root mean square error (RMSE) by 29% and increases the critical success index (CSI) by 32% compared to the Weather Research and Forecasting (WRF) model‘s land-atmosphere coupling module. Simulation under CMIP6 SSP3-7.0 and SSP5-8.5 scenarios indicates that the PI-GT framework reduces the uncertainty of extreme precipitation frequency projection by 21-25% by the end of the 21st century. Specifically, in the Yangtze River Basin and the Mississippi River Basin, the framework accurately captures the positive feedback effect of soil moisture anomalies on extreme precipitation and the regulating effect of vegetation cover on land-atmosphere water exchange. This study provides a new approach for improving the simulation accuracy of land-atmosphere coupling processes in Earth system models and enhances the reliability of extreme precipitation prediction, offering important scientific support for formulating flood disaster prevention and mitigation strategies.

• View pdf

Land-atmosphere interactions (LAI) are critical processes in the Earth system, regulating energy, water, and carbon cycles and exerting significant feedback effects on regional and global climate. Traditional Earth system models (ESMs) rely on simplified parameterization schemes for LAI processes, leading to notable uncertainties in simulating surface energy balance and climate feedback. This study proposes a Transformer-based global LAI simulation framework (Trans-LAI) that integrates self-attention mechanisms with physical constraints to capture the spatiotemporal dependencies and nonlinear interactions in LAI processes. The framework assimilates multi-source observation data, including satellite-derived land surface temperature (LST), latent heat flux (LE), sensible heat flux (H), and in-situ flux tower data, to optimize the representation of key LAI processes such as vegetation-atmosphere water vapor exchange and surface energy partitioning. Validation results based on 200 global flux tower sites show that the Trans-LAI framework improves the simulation accuracy of LE and H by 18% and 21% respectively compared to the traditional Community Land Model (CLM5.0). Climate feedback simulation under CMIP6 SSP3-7.0 and SSP5-8.5 scenarios indicates that the enhanced LAI simulation reduces the uncertainty of global mean surface temperature projection by 12-15% by the end of the 21st century. Specifically, in tropical rainforest regions, the Trans-LAI framework captures the negative climate feedback effect of enhanced evapotranspiration under warming conditions, while in arid and semi-arid regions, it accurately simulates the positive feedback effect of reduced vegetation coverage on drought intensification. This study provides a new paradigm for improving the simulation accuracy of LAI processes in ESMs and enhances the reliability of climate change projection, offering important scientific support for formulating climate adaptation strategies.

• View pdf