Venkata Ratnam Jayanthi

The predictability of northeast monsoon rainfall (NEMR) has been poorly studied. It is noted that the September-initialized multi-model ensemble (MME) of seasonal forecast systems shows modest skill in predicting NEMR over the southern peninsula of India for the October-November-December (OND) season. This study proposes an approach to improve forecast skill by selecting MME members that effectively capture the correlation between NEMR and the major modes of tropical climate variations (viz., El Niño-Southern Oscillation and Indian Ocean Dipole) during the OND season. Both deterministic and probabilistic verification results indicate that the selected ensemble outperforms the full MME in predicting NEMR, with the improved skill. The improvement can be attributed in part to the improved external forcing due to the sea surface temperature and to the realistic representation of the atmospheric processes in the ensemble of selected members. Composite analysis of extreme positive and negative precipitation seasons over the NEMR region shows the ensemble of selected members to capture the precipitation and streamfunction anomalies realistically. The MME failed to capture the correct phases of precipitation and streamfunction anomalies due to unrealistic atmospheric response to precipitation anomalies in the equatorial Pacific.

In this study, we evaluated the skill of the Scale Interaction Experiment-Frontier Research Center for Global Change, version 2 (SINTEX-F2), model in predicting precipitation over Saudi Arabia in the wet months (November–April) at 1–3-month lead times. It was found that the SINTEX-F2 model 1-month lead prediction was skillful in predicting precipitation over the southwestern regions of Saudi Arabia in November and February. Analysis revealed that the skillful prediction of precipitation in November was due to the skillful prediction of sea surface temperature anomalies in the midlatitudes of the central North Pacific and the associated atmospheric variability. In February, the skill was associated with the skillful prediction of sea surface temperature anomalies in the equatorial eastern Pacific and the associated teleconnections. Significance Statement: We tried to identify the months within the wet season in which precipitation could be predicted with high skill over Saudi Arabia. Analysis showed that the SINTEX-F2 model was skillful in predicting precipitation over the southwestern regions of Saudi Arabia in November and February at a 1-month lead time. The model skill was due to the model predicting the SST anomalies and the atmospheric variable anomalies with high skill.

In the months of March-June, India experiences high daytime temperatures (Tmax), which sometimes lead to heatwave-like conditions over India. In this study, 10 different machine learning models are evaluated for their ability to predict the daily Tmax anomalies 10 days ahead in the months of March-June. Several model experiments were carried out to identify an optimal model to predict daily Tmax anomalies over India. The results indicate that the AdaBoost regressor with Multi-layer Perceptron as the base estimator is an optimal model to predict the Tmax anomalies over India in the months of March-June. The optimal model predictions are benchmarked against 10-day persistence predictions and the predictions from the Climate Forecast System (CFS) reforecast. The results indicate that the machine learning model skill is higher than persistence and comparable to CFS reforecast 10-day predictions in April and May. In March and June, the machine learning models have low skill scores and perform no better than persistence. These results indicate that the machine learning models are promising tools to predict the surface air maximum temperature anomalies over India in April and May and can complement predictions from more sophisticated numerical models.

A large ensemble of 120 predictions of the Scale Interaction Experiment-Frontier Research Center for Global Change Version 2 (SINTEX-F2) coupled general circulation model were evaluated for their skill in predicting the surface air temperature (SAT) anomalies over Japan in the winter months December, January, and February. The predictions were initialized using November initial conditions. The members with skill scores based on anomaly correlation coefficient (ACC) were selected and an average of the selected predictions (SEM) was generated. Comparison of SAT anomaly predictions by the average of all the 120 members (ENS) to the SEM predictions shows SEM to outperform the ENS predictions in all the three winter months with higher ACC skill score, higher hit rate and low false alarm rate over the regions covering central Japan in December and January and over the northern region of Hokkaido in February. The improvement in the skill scores in the SEM is found to be due to improved representation of 200 hPa geopotential height anomalies in SEM compared to ENS predictions. The results indicate SEM to be useful for improving skill in predicting SAT anomalies over parts of Japan in the winter months.

The machine learning technique, namely Artificial Neural Networks (ANN), is used to predict the surface air temperature (SAT) anomalies over Japan in the winter months of December, January and February for the period 1949/50 to 2019/20. The predictions are made for the four regions Hokkaido, North, Central and West of Japan. The inputs to the ANN model are derived from the anomaly correlation coefficients among the SAT anomalies over the regions of Japan and the global SAT and sea surface temperature anomalies. The results are validated using anomaly correlation coefficient (ACC) skill scores with the observation. It is found that the ANN predictions over Hokkaido have higher ACC skill scores compared to the ACC scores over the other three regions. The ANN predicted SAT anomalies are compared with that of ensemble mean of 8 of the North American Multi-Model Ensemble (NMME) models besides comparing them with the persistent anomalies. The ANN predictions over all the four regions have higher ACC skill scores compared to the NMME model skill scores in the common period of 1982/83 to 2018/19. The ANN predicted SAT anomalies also have higher Hit rate and lower False alarm rate compared to the NMME predicted SAT anomalies. All these indicate that the ANN model is a promising tool for predicting the winter SAT anomalies over Japan. The machine learning technique, namely Artificial Neural Networks (ANN), is used to predict the surface air temperature (SAT) anomalies over Japan in the winter months of December, January and February for the period 1949/50 to 2019/20. The predictions are made for the four regions Hokkaido, North, Central and West of Japan. The inputs to the ANN model are derived from the anomaly correlation coefficients among the SAT anomalies over the regions of Japan and the global SAT and sea surface temperature anomalies. The results are validated using anomaly correlation coefficient (ACC) skill scores with the observation. It is found that the ANN predictions over Hokkaido have higher ACC skill scores compared to the ACC scores over the other three regions. The ANN predicted SAT anomalies are compared with that of ensemble mean of 8 of the North American Multi-Model Ensemble (NMME) models besides comparing them with the persistent anomalies. The ANN predictions over all the four regions have higher ACC skill scores compared to the NMME model skill scores in the common period of 1982/83 to 2018/19. The ANN predicted SAT anomalies also have higher Hit rate and lower False alarm rate compared to the NMME predicted SAT anomalies. All these indicate that the ANN model is a promising tool for predicting the winter SAT anomalies over Japan.

The selective ensemble mean (SEM) technique is applied to the late spring and summer months (May-August) surface air temperature anomaly predictions of the Scale Interaction Experiment-Frontier Research Center for Global Change, version 2 (SINTEX-F2), coupled general circulation model over Japan. Using the Koppen-Geiger climatic classification we chose four regions over Japan for applying the SEM technique. The SINTEX-F2 ensemble members for the SEM are chosen based on the anomaly correlation coefficients (ACC) of the SINTEX-F2 predicted and observed surface air temperature anomalies. The SEM technique is applied to generate the forecasts of the surface air temperature anomalies for the period 1983-2018 using the selected members. Analysis shows the ACC skill score of the SEM prediction to be higher compared to the ACC skill score of predictions obtained by averaging all the 24 members of the SINTEX-F2 (ENSMEAN). The SEM predicted surface air temperature anomalies also have higher hit rate and lower false alarm rate compared to the ENSMEAN predicted anomalies over a range of temperature anomalies. The results indicate the SEM technique to be a simple and easy to apply method to improve the SINTEX-F2 predictions of surface air temperature anomalies over Japan. The better performance of the SEM in generating the surface air temperature anomalies can be partly attributed to realistic prediction of 850-hPa geopotential height anomalies over Japan.

An amendment to this paper has been published and can be accessed via a link at the top of the paper.

The focus of this study is to evaluate the efficacy of Machine Learning (ML) algorithms in the long-lead prediction of El Niño (La Niña) Modoki (ENSO Modoki) index (EMI). We evaluated two widely used non-linear ML algorithms namely Support Vector Regression (SVR) and Random Forest (RF) to forecast the EMI at various lead times, viz. 6, 12, 18 and 24 months. The predictors for the EMI are identified using Kendall’s tau correlation coefficient between the monthly EMI index and the monthly anomalies of the slowly varying climate variables such as sea surface temperature (SST), sea surface height (SSH) and soil moisture content (SMC). The importance of each of the predictors is evaluated using the Supervised Principal Component Analysis (SPCA). The results indicate both SVR and RF to be capable of forecasting the phase of the EMI realistically at both 6-months and 12-months lead times though the amplitude of the EMI is underestimated for the strong events. The analysis also indicates the SVR to perform better than the RF method in forecasting the EMI.