Precipitation is a critical input for hydrologic simulation and prediction, and is widely used for agriculture, water resources management, and prediction of flood and drought, among other activities. Traditional precipitation prediction researches often established one or more probability models of historical data based on the statistical prediction methods and machine learning techniques. However, few studies have been attempted deep learning methods such as the state-of-the-art for Recurrent Neural Networks (RNNs) networks in meteorological sequence time series predictions. We deployed Long Short-Term Memory (LSTM) network models for predicting the precipitation based on meteorological data from 2008 to 2018 in Jingdezhen City. After identifying the correlation between meteorological variables and the precipitation, nine significant input variables were selected to construct the LSTM model. Then, the selected meteorological variables were refined by the relative importance of input variables to reconstruct the LSTM model. Finally, the LSTM model with final selected input variables is used to predict the precipitation and the performance is compared with other classical statistical algorithms and the machine learning algorithms. The experimental results show that the LSTM is suitable for precipitation prediction. The RNN models, combined with meteorological variables, could predict the precipitation accurately in Jingdezhen City and provide sufficient time to prepare strategies against potential related disasters.

This study investigated the influence of five El Niño–Southern Oscillation (ENSO) types on rainy-season precipitation in China: central Pacific warming (CPW), eastern Pacific cooling (EPC), eastern Pacific warming (EPW), conventional ENSO and ENSO Modoki. The multi-scale moving t test was applied to determine the onset and withdrawal of rainy season. Results showed that the precipitation anomaly can reach up to 30 % above average precipitation during decaying CPW and EPW phases. Developing EPW could cause decreasing precipitation over large areas in China with 10–30 % lower than average precipitation in most areas. Conventional El Niño in the developing phase had the largest influence on ENSO-related precipitation among developing ENSO and ENSO Modoki regimes. Decaying ENSO also showed a larger effect on precipitation anomalies, compared to decaying ENSO Modoki. The difference between rainy-season precipitation under various ENSO regimes may be attributed to the combined influence of anti-cyclone in the western North Pacific and the Indian monsoon. Stronger monsoon and anti-cyclone are associated with enhanced rainy-season precipitation. The results suggest a certain predictability of rainy-season precipitation related to ENSO regimes.

Extreme events such as rainstorms and floods are likely to increase in frequency due to the influence of global warming, which is expected to put considerable pressure on water resources. This paper presents a regional frequency analysis of precipitation extremes and its spatio-temporal pattern characteristics based on well-known index-flood L-moments methods and the application of advanced statistical tests and spatial analysis techniques. The results indicate the following conclusions. First, during the period between 1969 and 2015, the annual precipitation extremes at Fengjie station show a decreasing trend, but the Wuhan station shows an increasing trend, and the other 24 stations have no significant trend at a 5% confidence level. Secondly, the Hanjiang River Basin can be categorized into three homogenous regions by hierarchical clustering analysis with the consideration of topography and mean precipitation in these areas. The GEV, GNO, GPA and P III distributions fit better for most of the basin and MARE values range from 3.19% to 6.41% demonstrating that the best-fit distributions for each homogenous region is adequate in predicting the quantiles estimates. Thirdly, quantile estimates are reliable enough when the return period is less than 100 years, however estimates for a higher return period (e.g., 1000 years) become unreliable. Further, the uncertainty of quantiles estimations is growing with the growing return periods and the estimates based on R95P series have a smaller uncertainty to describe the extreme precipitation in the Hanjiang river basin (HJRB). Furthermore, In the HJRB, most of the extreme precipitation events (more than 90%) occur during the rainy season between May and October, and more than 30% of these extreme events concentrate in July, which is mainly impacted by the sub-tropical monsoon climate. Finally, precipitation extremes are mainly concentrated in the areas of Du River, South River and Daba Mountain in region I and Tianmen, Wuhan and Zhongxiang stations in region III, located in the upstream of Danjiangkou Reservoir and Jianghan Plain respectively. There areas provide sufficient climate conditions (e.g., humidity and precipitation) responsible for the occurring floods and will increase the risk of natural hazards to these areas.

Understanding the spatiotemporal variability of seasonal extreme precipitation and its linkage with climate patterns is of great importance for water resource management over the Yangtze River Basin. Hence, this study examined the spatiotemporal variability of seasonal extreme precipitation through the archetypal analysis (AA), by which observations were decomposed and characterized as several extreme modes. Six archetypes were identified and can obviously exhibit the features of events with above average or below average precipitation. Summer precipitation is the most variable compared to the winter, spring, and autumn precipitation through the trend analysis. It ranged from extremely dry (A6) to normal (A1 and A2) to extremely wet (A4). Climate teleconnections to the four archetypes for summer precipitation and relative importance of climate patterns were thus investigated. Results show that El Niño Southern Oscillation index is the strongest determinant of the ensuing archetypes representing the events with above average precipitation, while the Atlantic Multi-decadal Oscillation (AMO) contributes most to the events with below-average precipitation. A warm phase of the Pacific Decadal Oscillation (PDO) is significantly correlated with the above-average precipitation.

In terms of climate change and precipitation, there is large interest in how large-scale climatic features affect regional rainfall amount and rainfall occurrence. Large-scale climate elements need to be downscaled to the regional level for hydrologic applications. Here, a new Nonhomogeneous Hidden Markov Model (NHMM) called the Bayesian-NHMM is presented for downscaling and predicting of multisite daily rainfall during rainy season over the Huaihe River Basin (HRB). The Bayesian-NHMM provides a Bayesian method for parameters estimation. The model avoids the risk to have no solutions for parameter estimation, which often occurs in the traditional NHMM that uses point estimates of parameters. The Bayesian-NHMM accurately captures seasonality and interannual variability of rainfall amount and wet days during the rainy season. The model establishes a link between large-scale meteorological characteristics and local precipitation patterns. It also provides a more stable and efficient method to estimate parameters in the model. These results suggest that prediction of daily precipitation could be improved by the suggested new Bayesian-NHMM method, which can be helpful for water resources management and research on climate change.

The paper explores the impact of El Niño-Southern Oscillation (ENSO) on rainy season precipitation properties over the Yangtze River Basin. The multi-scale moving t-test was used to determine the onset and withdrawal of the rainy season. Results showed the following: (1) Onset and withdrawal of the averaged rainy season over the Yangtze River Basin showed a similar distribution and both progressed northwards and westwards. There is a trend for delayed onset of rainy season precipitation over the Yangtze River Basin. A similar trend in the withdrawal of rainy season precipitation was not found. (2) The decaying Central and Eastern Pacific Warming are indicative of wet signals in the Yangtze River Basin, with precipitation anomalies up to 25% above normal. The decaying Eastern Pacific Cooling and developing Eastern Pacific Warming are indicative of dry signals over the Yangtze River Basin, with 5–20% lower than average precipitation (3) ENSO Modoki in the developing phase is more important than the developing ENSO when it comes to present wetter or drier signals. Conversely, the decaying ENSO shows more prominent wet or dry signals than the decaying ENSO Modoki.