Global weather forecast models are vital tools with numerous applications, including public safety, agriculture, and transportation. Recent advancements in artificial intelligence (AI) and deep learning (DL) have shown the potential to enhance weather forecasting accuracy and speed. In this study, we developed a short‐term hourly weather forecast framework with a wavelet transform function for data preprocessing and a spatiotemporal DL model, PredRNN, for predicting five surface atmospheric variables, including wind speed and direction, mean sea level pressure (MSLP), temperature, and precipitation. The framework demonstrated promising results. It produces global forecasts at 0.25° (∼25 km) with a 1‐day lead time RMSE of 1.8 m/s for wind components, 180 Pa for MSLP, and 1.8 K for temperature. Although our model does not surpass state‐of‐the‐art AI weather forecast models across all metrics, it outperforms these models in precipitation forecasting and wind prediction at short lead times and achieves comparable accuracy for MSLP. Its native hourly forecasting capability, together with training on widely accessible GPU hardware, contributes meaningfully to the advancement of accessible DL weather forecasting methods. Our work highlights the importance of integrating temporal components and data transformation techniques to improve the predictability and accuracy of weather forecasts.
Hoang Tran, Hao Li, Vinh Ngoc Tran et al.· Journal of Geophysical Resea...· 0 citations
Drought has intensified across the Mekong River Basin (MRB) due to climate variability and increasing human interventions, creating substantial risks for water resources and agriculture. This study applied the SWAT model to simulate hydrological processes and evaluate meteorological, agricultural, and hydrological droughts using the SPI, SSWI, and SRI indices. Model calibration (1982–2001) and validation (2002–2019) at seven hydrological stations produced satisfactory to very good performance, with R2 values ranging from 0.80 to 0.89 and 0.52 to 0.69, respectively. The model effectively captured seasonal flow dynamics, although uncertainties increased toward downstream regions influenced by reservoir operations and land-use change. Analysis of precipitation and soil moisture revealed strong spatial contrasts among sub-basins: upstream areas exhibited limited infiltration and rapid drainage. At the same time, midstream and downstream regions retained soil moisture longer due to favorable topography and soil characteristics. Multi-decadal drought evaluation reveals several prominent drought periods from 1970 to 2000, consistent with major large-scale climate anomalies. Correlation analysis shows stronger linkages among drought indices at longer accumulation periods, indicating tighter coupling of drought processes under prolonged dry conditions. Overall, integrating SWAT simulations with multi-index drought diagnostics provides a robust framework for characterizing meteorological, agricultural, and hydrological drought dynamics, supporting improved drought monitoring and water resource management in the MRB.
Anh Nguyen Quoc, Thi-Thu-Ha Nguyen, Phong Nguyen Thanh et al.· Vietnam Journal of Earth Sci...· 0 citations