Prediction Of Summer Precipitation Research Articles

Ensemble tree model prediction of summer precipitation in north china based on predictor selection strategy

Ensemble tree model prediction of summer precipitation in north china based on predictor selection strategy

Subseasonal Predictability of Early and Late Summer Rainfall over East Asia

Abstract Considering the significant differences in the rainfall characteristics over East Asia between the early [May–June (MJ)] and late [July–August (JA)] summer, this study investigates the subseasonal predictability of the rainfall over East Asia in early and late summer, respectively. Distinctions are obvious for both the spatial distribution of the prediction skill and the most predictable patterns, that is, the leading pattern of the average predictable time (APT1) between the MJ and JA rainfall. Further analysis found that the distinct APT1s of MJ and JA rainfall are attributable to their different predictability sources. The predictability of the MJ rainfall APT1 is mainly from the boreal intraseasonal oscillation signal, whereas that of the JA rainfall APT1 is provided by the Pacific–Japan teleconnection pattern. This study sheds light on the temporal variation of predictability sources of summer precipitation over East Asia, offering a possibility to improve the summer precipitation prediction skill over East Asia through separate predictions for early and late summer, respectively.

Decadal Variations in the Summer Precipitation Over Eastern China Associated With Spring Arctic Sea Ice

AbstractThis study investigated the contribution of Arctic sea ice concentration (SIC) on decadal variations of the dominant mode of summer precipitation over eastern China during 1981–2020. The spatial pattern of leading empirical orthogonal function mode has changed from a dipole pattern with negative anomalies over Jianghuai Valley and positive anomalies over southern China during 1981–2001 to the Yangtze River Valley (YRV) pattern during 2002–2020. Spring SIC over Kara Sea was significantly related to the dipole pattern, through influencing Eurasian snow depth. The associated anomalous temperature gradient and atmospheric circulation affected the meridional displacement of the East Asian subtropical jet, which favored the dipole pattern of summer precipitation. For the YRV pattern, spring SIC over Greenland Sea has an impact on the sea surface temperature anomalies in the western Pacific by triggering a wave train that influenced the precipitation through the establishment of the Pacific–Japan pattern. The results of this study may provide reference value for the prediction of summer precipitation over eastern China.

Prediction of Summer Precipitation in North China: Role of the Evolution of Sea Surface Temperature Anomalies from Boreal Winter to Spring

Abstract Prediction of summer precipitation in north China (NCP) has long been a challenge partly because its low correlation with previous sea surface temperature (SST) anomalies (SSTA) limits the application of SST in NCP prediction. This study aims to extract optimal predictors of NCP from the SST field using an objective method—empirically optimal screening (EOS). It finds that the optimal precursory signal of NCP lies in the change of SSTA from winter to spring rather than the SSTA itself. This study identifies two optimal precursory signs predicting a positive (negative) NCP anomaly: the anomalous SST cooling (warming) from winter to spring in the coastal area of Somalia and Peru. Interestingly, these two presummer conditions have considerable independence, but they lead to a similar summer development of La Niña (El Niño). In summer, the tropical precipitation anomaly pattern associated with La Niña (El Niño) development excites a meridional wave train over the western Pacific and the circumglobal teleconnection in the Northern Hemisphere. Both of the anomalous wave trains show abnormal high (low) pressure over northeast Asia, which induces the south (north) wind anomalies over north China and produces abundant (deficient) precipitation there. These results highlight the importance of the SST evolution from winter to spring, break through the limitation of SST application in NCP prediction, and thus bring a prospect of improving NCP forecast skills. Significance Statement Sea surface temperature (SST) anomalies are most used as predictors in climate prediction. However, the forecast of summer precipitation in north China is limited by its low correlation with prior SST anomalies. In this paper, we find that the optimal precursory signal of north China precipitation (NCP) is not the SST anomaly itself, but the changes of SST anomalies from winter to spring in the coastal area of Somalia and Peru. These two precursory signals are almost independent yet indicate similar summer situations leading to NCP anomaly. These results highlight the importance of the dynamic evolution of sea surface temperature in improving the forecast skill of NCP.

Improving Seasonal Prediction of Summer Precipitation in the Middle–Lower Reaches of the Yangtze River Using a TU-Net Deep Learning Approach

Abstract The two-step U-Net model (TU-Net) contains a western North Pacific subtropical high (WNPSH) prediction model and a precipitation prediction model fed by the WNPSH predictions, oceanic heat content, and surface temperature. The data-driven forecast model provides improved 4-month lead predictions of the WNPSH and precipitation in the middle and lower reaches of the Yangtze River (MLYR), which has important implications for water resources management and precipitation-related disaster prevention in China. When compared with five state-of-the-art dynamical climate models including the Climate Forecast System of Nanjing University of Information Science and Technology (NUIST-CFS1.0) and four models participating in the North American Multi-Model Ensemble (NMME) project, the TU-Net produces comparable skills in forecasting 4-month lead geopotential height and winds at the 500- and 850-hPa levels. For the 4-month lead prediction of precipitation over the MLYR region, the TU-Net has the best correlation scores and mean latitude-weighted RMSE in each summer month and in boreal summer [June–August (JJA)], and pattern correlation coefficient scores are slightly lower than the dynamical models only in June and JJA. In addition, the results show that the constructed TU-Net is also superior to most of the dynamical models in predicting 2-m air temperature in the MLYR region at a 4-month lead. Thus, the deep learning-based TU-Net model can provide a rapid and inexpensive way to improve the seasonal prediction of summer precipitation and 2-m air temperature over the MLYR region. Significance Statement The purpose of this study is to examine the seasonal predictive skill of the western North Pacific subtropical high anomalies and summer rainfall anomalies over the middle and lower reaches of the Yangtze River region by means of deep learning methods. Our deep learning model provides a rapid and inexpensive way to improve the seasonal prediction of summer precipitation as well as 2-m air temperature. The work has important implications for water resources management and precipitation-related disaster prevention in China and can be extended in the future to predict other climate variables as well.

Two deep learning-based bias-correction pathways improve summer precipitation prediction over China

As most global climate models (GCM) suffer from large biases in simulating/predicting summer precipitation over China, it is of great importance to develop suitable bias-correction methods. This study proposes two pathways of bias-correction with deep learning (DL) models incorporated. One is the deterministic pathway (DP), in which the bias correction is directly applied to the precipitation forecasts. The other one, namely the probability pathway (PP), corrects the forecasted precipitation anomalies using a conditional probability method before being added to the observational climatology. These two pathways have been applied to correct the precipitation forecasts based on a GCM prediction system Nanjing University of Information Science and Technology Climate Forecast System version 1.0 (NUIST-CFS1.0). The applications of DL models in the both pathways yield higher resolution of corrected predictions than the uncorrected ones. Both pathways improve summer precipitation predictions at 4-month lead. Moreover, the DP correction shows a better performance in predicting extreme precipitation, while the PP is proficient in correcting the spatial pattern of precipitation anomalies over China. The present results highlight the importance of the application of appropriate correction strategy for different prediction purposes.

Seasonal‐Interannual Predictions of Summer Precipitation Over the Tibetan Plateau in North American Multimodel Ensemble

AbstractVariations of precipitation over the Tibetan Plateau (TP) have great hydrometeorological impacts on local and surrounding areas. Focusing on the TP precipitation in the boreal summer, this study investigates the seasonal‐interannual predictions of eight dynamical models from the North‐American Multi‐Model Ensemble (NMME) using different observational data sets for verification. Results show dynamical prediction skill of the TP precipitation is regionally dependent with significantly high skills in the southwestern TP up to about three‐season ahead. Prediction skill of precipitation anomalies over the southwestern TP is significantly reliant on the models' ability in reproducing the observed relationship between the anomalous southwest‐TP precipitation and Pacific Sea surface temperature (SST). Using the different gridded observational data sets as verifications can lead to variations in prediction skills, and the multi‐observation mean tends to obtain the highest skills over the southwestern TP. These results provide a deeper understanding of dynamical seasonal‐interannual predictability of summer precipitation in TP.

Multi-Model Ensemble Prediction of Summer Precipitation in China Based on Machine Learning Algorithms

The development of machine learning (ML) provides new means and methods for accurate climate analysis and prediction. This study focuses on summer precipitation prediction using ML algorithms. Based on BCC CSM1.1, ECMWF SEAS5, NCEP CFSv2, and JMA CPS2 model data, we conducted a multi-model ensemble (MME) prediction experiment using three tree-based ML algorithms: the decision tree (DT), random forest (RF), and adaptive boosting (AB) algorithms. On this basis, we explored the applicability of ML algorithms for ensemble prediction of seasonal precipitation in China, as well as the impact of different hyperparameters on prediction accuracy. Then, MME predictions based on optimal hyperparameters were constructed for different regions of China. The results showed that all three ML algorithms had an optimal maximum depth less than 2, which means that, based on the current amount of data, the three algorithms could only predict positive or negative precipitation anomalies, and extreme precipitation was hard to predict. The importance of each model in the ML-based MME was quantitatively evaluated. The results showed that NCEP CFSv2 and JMA CPS2 had a higher importance in MME for the eastern part of China. Finally, summer precipitation in China was predicted and tested from 2019 to 2021. According to the results, the method provided a more accurate prediction of the main rainband of summer precipitation in China. ML-based MME had a mean ACC of 0.3, an improvement of 0.09 over the weighted average MME of 0.21 for 2019–2021, exhibiting a significant improvement over the other methods. This shows that ML methods have great potential for improving short-term climate prediction.

Summer precipitation prediction in eastern China based on machine learning

Summer precipitation prediction in eastern China based on machine learning

An Algorithm for Precipitation Correction in Flood Season Based on Dendritic Neural Network.

In recent years, the National Climate Center has developed a dynamic downscaling prediction technology based on the Climate-Weather Research and Forecasting (CWRF) regional climate model and used it for summer precipitation prediction, but there are certain deviations, and it is difficult to predict more accurately. The CWRF model simulates the summer precipitation forecast data from 1996 to 2019 and uses a combination of dendrite net (DD) and artificial neural networks (ANNs) to conduct a comparative analysis of summer precipitation correction techniques. While summarizing the characteristics and current situation of summer precipitation in the whole country, the meteorological elements related to precipitation are analyzed. CWRF is used to simulate summer precipitation and actual observation precipitation data to establish a model to correct the precipitation. By comparing with the measured data of the ground station after quality control, the relevant evaluation index analysis is used to determine the best revised model. The results show that the correction effect based on the dendritic neural network algorithm is better than the CWRF historical return, in which, the anomaly correlation coefficient (ACC) and the temporal correlation coefficient (TCC) both increased by 0.1, the mean square error (MSE) dropped by about 26%, and the overall trend anomaly (Ps) test score was also improved, showing that the machine learning algorithms can correct the summer precipitation in the CWRF regional climate model to a certain extent and improve the accuracy of weather forecasts.

Seasonal Prediction of Summer Precipitation over East Africa Using NUIST-CFS1.0

Seasonal Prediction of Summer Precipitation over East Africa Using NUIST-CFS1.0

Seasonal Prediction of Summer Precipitation in the Middle and Lower Reaches of the Yangtze River Valley: Comparison of Machine Learning and Climate Model Predictions

The middle and lower reaches of the Yangtze River valley (YRV), which are among the most densely populated regions in China, are subject to frequent flooding. In this study, the predictor importance analysis model was used to sort and select predictors, and five methods (multiple linear regression (MLR), decision tree (DT), random forest (RF), backpropagation neural network (BPNN), and convolutional neural network (CNN)) were used to predict the interannual variation of summer precipitation over the middle and lower reaches of the YRV. Predictions from eight climate models were used for comparison. Of the five tested methods, RF demonstrated the best predictive skill. Starting the RF prediction in December, when its prediction skill was highest, the 70-year correlation coefficient from cross validation of average predictions was 0.473. Using the same five predictors in December 2019, the RF model successfully predicted the YRV wet anomaly in summer 2020, although it had weaker amplitude. It was found that the enhanced warm pool area in the Indian Ocean was the most important causal factor. The BPNN and CNN methods demonstrated the poorest performance. The RF, DT, and climate models all showed higher prediction skills when the predictions start in winter than in early spring, and the RF, DT, and MLR methods all showed better prediction skills than the numerical climate models. Lack of training data was a factor that limited the performance of the machine learning methods. Future studies should use deep learning methods to take full advantage of the potential of ocean, land, sea ice, and other factors for more accurate climate predictions.

Improving China’s summer precipitation prediction in 2020 by observational constrained bias correction

Improving China’s summer precipitation prediction in 2020 by observational constrained bias correction

Improvement in the Prediction of Summer Precipitation in the North China−Hetao Region Using the Tropospheric Temperature Over the Tibetan Plateau in Spring

We investigated the relationship between the spring tropospheric temperature over the Tibetan Plateau (TPT) and summer precipitation in eastern China on an interannual timescale using the monthly mean ERA-Interim reanalysis dataset, the HadISST dataset and the daily mean precipitation dataset for China. We found that there is a significant positive correlation between the spring TPT and summer precipitation in the North China−Hetao region. The relationship is manifested in the context of the East Asia–Pacific pattern teleconnection. In the high spring TPT index years, the geopotential height anomalies over East Asia and the western North Pacific present a negative phase of the East Asia–Pacific pattern teleconnection in the subsequent summer. This circulation pattern is beneficial for the water vapor transport from the western Pacific to inland, which further transport to the North China−Hetao region from the Yangtze River–Yellow rivers region. Anomalous upward motion occurs in the North China–Hetao region, which increases precipitation. The East Asian subtropical westerly jet shifts further north and the South Asian high weakens and shrinks westward. These conditions all favor an increase in precipitation over the North China–Hetao region. The spring TPT plays an important part in the prediction of summer precipitation in the North China−Hetao region. The improvement in the use of the spring TPT to predict summer precipitation in the North China–Hetao region is examined by comparing the prediction equations with and without the prediction factor of the spring TPT on the basis of the sea surface temperatures in key regions. After considering the impact of the spring TPT, the explanatory variance of the prediction equation for precipitation in the North China–Hetao region increases by 17.3%.

An effective downscaling model for operational prediction of summer precipitation over China

A hybrid downscaling model for operational prediction of summer precipitation at 160 stations over China is proposed in this paper. The prediction model is conducted in February, and six predictors extending from the tropics to high latitudes with specific mechanisms are involved. Simultaneous sea level pressure over pan-East Asia and spring sea surface temperature (SST) over the tropical Atlantic Ocean are from the Climate Forecast System version 2 (CFSv2). The others are observational predictors including winter SST over the tropical Indian Ocean, sea ice concentration (SIC) over the Hudson Bay–Baffin Bay–Davis Strait in winter and the Barents–Kara Sea in autumn, and winter outgoing longwave radiation over the tropics. Different predictors impact the summer precipitation of different regions in China. Validations for schemes based on individual predictors (IP-schemes) and all predictors (HD-scheme) indicate that downscaling schemes outperform CFSv2 in predicting summer precipitation over China, especially the HD-scheme. The temporal and spatial anomaly correlation coefficient, root-mean-square errors, and ratio of the same sign (RSS) are estimated. For RSS (Anomalous RSS), the results are improved from 27.8% (23.8%) for CFSv2 to 77.8% (61.9%) for HD-scheme. Notably, the RSSs of IP-schemes based on SIC are equivalent to that of HD-scheme. This partly emphasizes the importance of preceding Arctic sea ice to summer rainfall in China. Moreover, two cases from hindcasts and two from the operational application are chosen for further validation of the prediction skill of HD-scheme. The case studies confirm that the hybrid downscaling model proposed in this paper not only outperforms CFSv2 but can also be applied well to real-time forecasting of summer precipitation over China.

Important role of North Atlantic air–sea coupling in the interannual predictability of summer precipitation over the eastern Tibetan Plateau

Tibetan Plateau (TP) summer precipitation, whose first leading mode presents a dipole oscillation between the northeastern and southeastern TP, plays important roles in the water cycle and atmospheric circulation. Using a weakly coupled data assimilation (WCDA) system to constrain the atmospheric component in a coupled model with a global atmospheric reanalysis product, this study demonstrates significant improvements in predicting the interannual variation of summer precipitation over the eastern TP, capturing the strong reversal mode between the northeastern and southeastern TP. These improvements are mainly attributed to the strong air–sea coupling over the North Atlantic (NA) and its remote impacts on the TP precipitation. This coupling allows observation-constrained atmosphere to significantly influence initial conditions (ICs) of sea surface temperature (SST) in the NA area and then obviously affect predictions of both NA SST and summer North Atlantic Oscillation (SNAO), which affects the downstream TP atmospheric circulation through the wave train of Eliassen-Palm (EP) stationary wave flux. This study highlights the importance of NA air–sea coupling in the interannual predictability of TP precipitation and suggests a new source of interannual predictability of TP precipitation.

Dryness over the U.S. Southwest, a Springboard for Cold Season Pacific SST to Influence Warm Season Drought over the U.S. Great Plains

AbstractAlthough the influence of sea surface temperature (SST) forcing and large-scale teleconnection on summer droughts over the U.S. Great Plains has been suggested for decades, the underlying mechanisms are still not fully understood. Here we show a significant correlation between low-level moisture condition over the U.S. Southwest in spring and rainfall variability over the Great Plains in summer. Such a connection is due to the strong influence of the Southwest dryness on the zonal moisture advection to the Great Plains from spring to summer. This advection is an important contributor for the moisture deficit during spring to early summer, and so can initiate warm season drought over the Great Plains. In other words, the well-documented influence of cold season Pacific SST on the Southwest rainfall in spring, and the influence of the latter on the zonal moisture advection to the Great Plains from spring to summer, allows the Pacific climate variability in winter and spring to explain over 35% of the variance of the summer precipitation over the Great Plains, more than that can be explained by the previous documented west Pacific–North America (WPNA) teleconnection forced by tropical Pacific SST in early summer. Thus, this remote land surface feedback due to the Southwest dryness can potentially improve the predictability of summer precipitation and drought onsets over the Great Plains.

The Application of a Decision Tree and Stochastic Forest Model in Summer Precipitation Prediction in Chongqing

Meteorological disasters are the result of the interaction of multiple factors and multiple systems. In order to improve the accuracy of prediction, it is necessary not only to consider the characteristics and cycles of each subsystem, but also to study the interaction of all systems. Based on the summer precipitation data and 130 circulation indexes of 34 national meteorological observation stations in Chongqing from 1961 to 2010, the prediction model of Chongqing summer precipitation was established based on the decision tree and the stochastic forest algorithm based on machine learning, and the prediction test of 2011–2018 was carried out independently by the model. Compared with the results of the single-factor prediction model, the trend consistency rate increased by 37.5% and 12.5% respectively. In addition, when using the random forest model to predict summer precipitation in Chongqing from 2014 to 2018, the 5-year average Ps, Cc and PC scores were 84.6, 0.27 and 67.1, respectively, which were significantly improved compared with 72.4, −0.12 and 52.9 of the current climate forecasting methods, and the forecast quality of the random forest was relatively stable. The multi-system collaborative impact model based on decision tree and random forest algorithm can achieve high accuracy and stability. Thus, this method can not only be an effective means for the diagnosis and prediction of climate causes, but also has a good theoretical and practical value for the prediction of extreme disasters.

Neuro-fuzzy modeling and prediction of summer precipitation with application to different meteorological stations

Research community has a growing interest in neural networks because of their practical applications in many fields for accurate modeling and prediction of the complex behavior of systems arising from engineering, economics, business, financial and metrological fields. Artificial neural networks (ANN) are very flexible function approximations tool used as universal modeling based on the separating of the past dynamics into clusters, in which we construct local models to capture the potential growth of the series depends on the previously known values. In this study, rain data of five major cities of Sindh province of Pakistan is considered, and summer rainfall of these five synoptic stations are statistically evaluated for prediction. The nonlinear autoregressive network with exogenous inputs (NARX) model for a time series is analyzed to evaluate the pattern of precipitation. We train a highly nonlinear NARX network model from randomly generated initial weights that converged to the best solution with the help of the Levenberg-Marquardt algorithm. A multi-step ahead NARX response time predictor is developed for rain forecasting. The performance of the NARX model is viable to capture nonlinear behavior with a high value of correlation coefficient R ranging from 0.70 to 0.99 for different synoptic stations. The results calculated using the proposed NARX neural network time series approach are accurate and reliable based on the coefficient of correlation and mean square error indices for rainfall forecasting.

Relationship between Tropical Indian Ocean SSTA in Spring and Precipitation of Northeast China in Late Summer

Sea surface temperature anomaly (SSTA) is a major signal for prediction of summer precipitation in East Asia. The relationship between SSTA in the tropical oceans and summer precipitation in East Asia has been documented in many studies. However, the relationship between SSTA and late summer (July-August) precipitation (JAP) over Northeast China (NEC) on the interannual timescale has received little attention. In this study, we examine the relationship between Indian Ocean Basin warming (IOBW) anomalies in spring and the JAP in NEC since the early 1960s. A significant positive correlation is found between the spring IOBW index and JAP over NEC. The positive spring IOBW anomaly is followed by an anomalous anticyclone from Northwest Pacific to the Korean Peninsula. This anomalous anticyclone favors a significantly strong and northward western Pacific subtropical high (WPSH), which facilitates anomalous southerly winds over NEC and the transport of more water vapor into this region. Further analysis indicates that the spring IOBW anomalies have important impacts on the vertical air motion in the tropics and subtropics during the summer. Significant anomalous upward (downward) motion covering Indonesia (Northwest Pacific to the southern Korean Peninsula) occurs when the IOBW is in its positive phase, which favors the northward movement of the WPSH in late summer and more precipitation over NEC in July-August. Modulation of the atmospheric circulation by this mechanism further influences the JAP over NEC.