Search for: All records

According to twenty-first century climate-model projections, greenhouse warming will intensify rainfall variability and extremes across the globe. However, verifying this prediction using observations has remained a substantial challenge owing to large natural rainfall fluctuations at regional scales. Here we show that deep learning successfully detects the emerging climate-change signals in daily precipitation fields during the observed record. We trained a convolutional neural network (CNN) with daily precipitation fields and annual global mean surface air temperature data obtained from an ensemble of present-day and future climate-model simulations. After applying the algorithm to the observational record, we found that the daily precipitation data represented an excellent predictor for the observed planetary warming, as they showed a clear deviation from natural variability since the mid-2010s. Furthermore, we analysed the deep-learning model with an explainable framework and observed that the precipitation variability of the weather timescale (period less than 10 days) over the tropical eastern Pacific and mid-latitude storm-track regions was most sensitive to anthropogenic warming. Our results highlight that, although the long-term shifts in annual mean precipitation remain indiscernible from the natural background variability, the impact of global warming on daily hydrological fluctuations has already emerged. 

Abstract This study investigates why the major convective envelope of the Madden–Julian oscillation (MJO) detours to the south of the Maritime Continent (MC) only during boreal winter [December–March (DJFM)]. To examine processes affecting this MJO detour, the MJO-related variance of precipitation and column-integrated moisture anomalies in DJFM are compared with those in the seasons before [October–November (ON)] and after [April–May (AM)]. While MJO precipitation variance is much higher in the southern MC (SMC) during DJFM than in other seasons, the MJO moisture variance is comparable among the seasons, implying that the seasonal locking of the MJO’s southward detour cannot be explained by the magnitude of moisture anomalies alone. The higher precipitation variance in the SMC region is partly explained by the much higher moisture sensitivity of precipitation in DJFM than in other seasons, resulting in a more efficient conversion of anomalous moisture to anomalous precipitation. DJFM is also distinguishable from the other seasons by stronger positive wind–evaporation feedback onto MJO precipitation anomalies due to the background westerly wind in the lower troposphere. It is found that the seasonal cycle of moisture–precipitation coupling and wind–evaporation feedback in the SMC region closely follows that of the Australian monsoon, which is active exclusively in DJFM. Our results suggest that the MJO’s southward detour in the MC is seasonally locked because it occurs preferentially when the Australian monsoon system produces a background state that is favorable for MJO development in the SMC. 

The diversity in the lightning parameterizations for numerical weather and climate models causes considerable uncertainty in lightning prediction. In this study, we take a data-driven approach to address the lightning parameterization problem, by combining machine learning (ML) techniques with the rich lightning observations from the World Wide Lightning Location Network. Three ML algorithms are trained over the contiguous United States (CONUS) to predict lightning stroke density in a 1° box based on the information about the atmospheric variables in the same grid (local) or over the entire CONUS (nonlocal). The performance of the ML-based lightning schemes is examined and compared with that of a simple, conventional lightning parameterization scheme of Romps et al. We find that all ML-based lightning schemes exhibit a performance that is superior to that of the conventional scheme in the regions and in the seasons with climatologically higher lightning stroke density. To the west of the Rocky Mountains, the nonlocal ML lightning scheme achieves the best overall performance, with lightning stroke density predictions being 70% more accurate than the conventional scheme. Our results suggest that the ML-based approaches have the potential to improve the representation of lightning and other types of extreme weather events in the weather and climate models.