scholarly journals Using Network Theory and Machine Learning to predict El Niño

2018 ◽  
Author(s):  
Peter D. Nooteboom ◽  
Qing Yi Feng ◽  
Cristóbal López ◽  
Emilio Hernández-García ◽  
Henk A. Dijkstra
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
El Niño ◽  
Lead Time ◽  
El Nino ◽  
Southern Oscillation ◽  
Moving Average ◽  
Ensemble Prediction ◽  
Type Model ◽  
Average Technique

Abstract. The skill of current predictions of the warm phase of the El Niño Southern Oscillation (ENSO) reduces significantly beyond a lag of six months. In this paper, we aim to increase this prediction skill at lags up to one year. The new method to do so combines a classical Autoregressive Integrated Moving Average technique with a modern machine learning approach (through an Artificial Neural Network). The attributes in such a neural network are derived from topological properties of Climate Networks and are tested on both a Zebiak–Cane-type model and observations. For predictions up to six months ahead, the results of the hybrid model give a better skill than the CFSv2 ensemble prediction by the National Centers for Environmental Prediction (NCEP). Moreover, results for a twelve-month lead time prediction have a similar skill as the shorter lead time predictions.

scholarly journals Using network theory and machine learning to predict El Niño

2018 ◽  
Vol 9 (3) ◽  
pp. 969-983 ◽  
Author(s):  
Peter D. Nooteboom ◽  
Qing Yi Feng ◽  
Cristóbal López ◽  
Emilio Hernández-García ◽  
Henk A. Dijkstra
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
El Niño ◽  
Lead Time ◽  
El Nino ◽  
Southern Oscillation ◽  
Moving Average ◽  
Ensemble Prediction ◽  
Type Model ◽  
Average Technique

Abstract. The skill of current predictions of the warm phase of the El Niño Southern Oscillation (ENSO) reduces significantly beyond a lag time of 6 months. In this paper, we aim to increase this prediction skill at lag times of up to 1 year. The new method combines a classical autoregressive integrated moving average technique with a modern machine learning approach (through an artificial neural network). The attributes in such a neural network are derived from knowledge of physical processes and topological properties of climate networks, and they are tested using a Zebiak–Cane-type model and observations. For predictions up to 6 months ahead, the results of the hybrid model give a slightly better skill than the CFSv2 ensemble prediction by the National Centers for Environmental Prediction (NCEP). Interestingly, results for a 12-month lead time prediction have a similar skill as the shorter lead time predictions.

Predictability of Two Types of El Niño Assessed Using an Extended Seasonal Prediction System by MIROC

2015 ◽  
Vol 143 (11) ◽  
pp. 4597-4617 ◽  
Author(s):  
Yukiko Imada ◽  
Hiroaki Tatebe ◽  
Masayoshi Ishii ◽  
Yoshimitsu Chikamoto ◽  
Masato Mori ◽  
...  
Keyword(s):  
El Niño ◽  
Lead Time ◽  
General Circulation ◽  
El Nino ◽  
Southern Oscillation ◽  
Circulation Model ◽  
Seasonal Prediction ◽  
Ocean General Circulation Model ◽  
Prediction System ◽  
Central Pacific

Abstract Predictability of El Niño–Southern Oscillation (ENSO) is examined using ensemble hindcasts made with a seasonal prediction system based on the atmosphere and ocean general circulation model, the Model for Interdisciplinary Research on Climate, version 5 (MIROC5). Particular attention is paid to differences in predictive skill in terms of the prediction error for two prominent types of El Niño: the conventional eastern Pacific (EP) El Niño and the central Pacific (CP) El Niño, the latter having a maximum warming around the date line. Although the system adopts ocean anomaly assimilation for the initialization process, it maintains a significant ability to predict ENSO with a lead time of more than half a year. This is partly due to the fact that the system is little affected by the “spring prediction barrier,” because increases in the error have little dependence on the thermocline variability. Composite analyses of each type of El Niño reveal that, compared to EP El Niños, the ability to predict CP El Niños is limited and has a shorter lead time. This is because CP El Niños have relatively small amplitudes, and thus they are more affected by atmospheric noise; this prevents development of oceanic signals that can be used for prediction.

scholarly journals El-Nino/Southern Oscillation (ENSO): Recent Evolution and Possibilities for Long Range Flow Forecasting in the Brahmaputra-Jamuna River

2013 ◽  
Vol 8 (3) ◽  
pp. 179-185 ◽  
Keyword(s):  
Long Range ◽  
El Niño ◽  
Stream Flow ◽  
Lead Time ◽  
El Nino ◽  
Southern Oscillation ◽  
Flood Forecasting ◽  
El Niño Southern Oscillation ◽  
El Nino Southern Oscillation ◽  
The World

The El Nino-Southern Oscillation is the dominant pattern of short-term climate variation, and is therefore of great importance in climate studies. Some recent studies showed the teleconnection between stream flow and the El-Nino Southern Oscillation (ENSO) of the equatorial Pacific Ocean. This paper presents an overview of the relationship between ENSO and stream flow in the Brahmaputra-Jamuna and the potential for wet season flow forecasting. This seasonal forecast of stream flow is very invaluable to the management of land and water resources, particularly in Bangladesh to improve the predictability of severe flooding. Over the years, large investments have been made to build physical infrastructure for flood protection, but it has been proved that it is not feasible, both economically and technically, to adopt solely structural mitigation approach. The choice of non-structural measures in this country focused mainly on flood forecasting because many of the nonstructural measures including flood plain zoning, compulsory acquisition of flood prone land, relocation etc have also been proved inappropriate for Bangladesh. The aim of this research is to find out an effective and long-lead flow forecasting method with lead time greater than hydrological time scale, using El Nino-Southern Oscillation index. Some studies indicate that SST can be predicted one to two years in advance using several ocean/ coupled ocean atmosphere models, therefore the ability to predict flow patterns in rivers will be highly enhanced if a strong relationship between river discharge and ENSO exists, and is quantified. With this view, to assess the strength of teleconnection between river flow and ENSO, at first correlation analyses between ENSO indices of any year and wet season flow of that year have been done. Here sea surface temperature (SST) has been used as ENSO index. This correlation analysis demonstrates a noteworthy relationship between natural variability of average flow of the months July-August-September (JAS) of the Brahmaputra-Jamuna River with SST of the corresponding months. Then discriminant prediction approach, also known as “Categoric Prediction” has been used here for the assessment of long range flood forecasting possibilities. This approach will be able to forecast the category of flow (high, average or low) using the category of predictor (predicted SST) at a sufficient lead time. In order to judge the forecast skill, a synoptic parameter “Forecasting Index” has also been used. This discriminant approach will improve the forecasting lead-time while the hydrologic forecast through rainfall-runoff modeling could provide a lead time on the order of the basin response time, which is several days or so. As the Ganges–Brahmaputra river basin is one of the most populous river basins of the world and is occupied by some developing countries of the world like Bangladesh, any reduction in the uncertainty about the flood in the Brahmaputra-Jamuna River would contribute a lot to the improvement in flow forecasting as well as to the economic development of the country.

scholarly journals Classifying El Niño-Southern Oscillation Combining Network Science and Machine Learning

IEEE Access ◽  
2020 ◽  
Vol 8 ◽  
pp. 55711-55723
Author(s):  
Matheus A. De Castro Santos ◽  
Didier A. Vega-Oliveros ◽  
Liang Zhao ◽  
Lilian Berton
Keyword(s):  
Machine Learning ◽  
El Niño ◽  
Network Science ◽  
El Nino ◽  
Southern Oscillation ◽  
El Niño Southern Oscillation ◽  
El Nino Southern Oscillation

scholarly journals The roles of the Quasi-Biennial Oscillation and El Nino for entry stratospheric water vapour in observations and coupled chemistry-ocean CCMI and CMIP6 models

2022 ◽  
Author(s):  
Shlomi Ziskin Ziv ◽  
Chaim I. Garfinkel ◽  
Sean Davis ◽  
Antara Banerjee
Keyword(s):  
Machine Learning ◽  
Water Vapor ◽  
El Niño ◽  
El Nino ◽  
Southern Oscillation ◽  
Machine Learning Techniques ◽  
Nonlinear Interactions ◽  
Quasi Biennial Oscillation ◽  
Learning Techniques ◽  
Biennial Oscillation

Abstract. The relative importance of two processes that help control the concentrations of stratospheric water vapor, the Quasi-Biennial Oscillation (QBO) and El Nino-Southern Oscillation (ENSO), are evaluated in observations and in comprehensive coupled ocean-atmosphere-chemistry models. The possibility of nonlinear interactions between these two is evaluated both using Multiple Linear Regression (MLR) and three additional advanced machine learning techniques. The QBO is found to be more important than ENSO, however nonlinear interactions are non-negligible, and even when ENSO, the QBO, and potential nonlinearities are included the fraction of entry water vapor variability explained is still substantially less than what is accounted for by cold point temperatures. While the advanced machine learning techniques perform better than an MLR in which nonlinearities are suppressed, adding nonlinear predictors to the MLR mostly closes the gap in performance with the advanced machine learning techniques. Comprehensive models suffer from too weak a connection between entry water and the QBO, however a notable improvement is found relative to previous generations of comprehensive models. Models with a stronger QBO in the lower stratosphere systematically simulate a more realistic connection with entry water.

scholarly journals Dynamical, Statistical–Dynamical, and Multimodel Ensemble Forecasts of Australian Spring Season Rainfall

2011 ◽  
Vol 139 (3) ◽  
pp. 958-975 ◽  
Author(s):  
Eun-Pa Lim ◽  
Harry H. Hendon ◽  
David L. T. Anderson ◽  
Andrew Charles ◽  
Oscar Alves
Keyword(s):  
El Niño ◽  
El Nino ◽  
Southern Oscillation ◽  
Prediction Method ◽  
Rainfall Anomaly ◽  
Ensemble Prediction ◽  
Spring Season ◽  
Multimodel Ensemble ◽  
Austral Spring ◽  
Probabilistic Forecasts

Abstract The prediction skill of the Australian Bureau of Meteorology dynamical seasonal forecast model Predictive Ocean Atmosphere Model for Australia (POAMA) is assessed for probabilistic forecasts of spring season rainfall in Australia and the feasibility of increasing forecast skill through statistical postprocessing is examined. Two statistical postprocessing techniques are explored: calibrating POAMA prediction of rainfall anomaly against observations and using dynamically predicted mean sea level pressure to infer regional rainfall anomaly over Australia (referred to as “bridging”). A “homogeneous” multimodel ensemble prediction method (HMME) is also introduced that consists of the combination of POAMA’s direct prediction of rainfall anomaly together with the two statistically postprocessed predictions. Using hindcasts for the period 1981–2006, the direct forecasts from POAMA exhibit skill relative to a climatological forecast over broad areas of eastern and southern Australia, where El Niño and the Indian Ocean dipole (whose behavior POAMA can skillfully predict at short lead times) are known to exert a strong influence in austral spring. The calibrated and bridged forecasts, while potentially offering improvement over the direct forecasts because of POAMA’s ability to predict the main drivers of springtime rainfall (e.g., El Niño and the Southern Oscillation), show only limited areas of improvement, mainly because strict cross-validation limits the ability to capitalize on relatively modest predictive signals with short record lengths. However, when POAMA and the two statistical–dynamical rainfall forecasts are combined in the HMME, higher deterministic and probabilistic skill is achieved over any of the single models, which suggests the HMME is another useful method to calibrate dynamical model forecasts.

scholarly journals The effects of model climate bias on ENSO variability and ensemble prediction

2019 ◽  
Vol 60 ◽  
pp. C215-C230
Author(s):  
S. L. Osbrough ◽  
J. S. Frederiksen ◽  
C. S. Frederiksen
Keyword(s):  
Southern Hemisphere ◽  
El Niño ◽  
El Nino ◽  
Southern Oscillation ◽  
Ensemble Prediction ◽  
Computational Techniques ◽  
Ensemble Forecasts ◽  
Ocean Atmosphere ◽  
Atmosphere Model

New methods are presented for determining the role of coupled ocean-atmosphere model climate bias on the strength and variability of the El Nino-Southern Oscillation (ENSO) and on the seasonal ensemble prediction of El Nino and La Nina events. An intermediate complexity model with a global atmosphere coupled to a Pacific basin ocean is executed with parallelised algorithms to produce computationally efficient year-long forecasts of large ensembles of coupled flow fields, beginning every month between 1980 and 1999. Firstly, the model is provided with forcing functions that reproduce the average annual cycle of climatology of the atmosphere and ocean based on reanalysed observations. We also configure the model to generate realistic ENSO fluctuations. Next, an ensemble prediction scheme is employed which produces perturbations that amplify rapidly over a month. These perturbations are added to the analyses and give the initial conditions for the ensemble forecasts. The skill of the forecasts is presented and the dependency on the annual and ENSO cycles determined. Secondly, we replace the forcing functions in our model with functions that reproduce the averaged annual cycles of climatology of two state of the art, comprehensive Coupled General Circulation Models. The changes in skill of subsequent ensemble forecasts elucidate the roles of model bias in error growth and potential predictability. References C. S. Frederiksen, J. S. Frederiksen, and R. C. Balgovind. ENSO variability and prediction in a coupled ocean-atmosphere model. Aust. Met. Ocean. J., 59:35–52, 2010a. URL http://www.bom.gov.au/jshess/papers.php?year=2010. C. S. Frederiksen, J. S. Frederiksen, and R. C. Balgovind. Dynamic variability and seasonal predictability in an intermediate complexity coupled ocean-atmosphere model. In Proceedings of the 16th Biennial Computational Techniques and Applications Conference, CTAC-2012, volume 54 of ANZIAM J., pages C34–C55, 2013a. doi:10.21914/anziamj.v54i0.6296. C. S. Frederiksen, J. S. Frederiksen, J. M. Sisson, and S. L. Osbrough. Trends and projections of Southern Hemisphere baroclinicity: the role of external forcing and impact on Australian rainfall. Clim. Dyn., 48:3261–3282, 2017. doi:10.1007/s00382-016-3263-8. J. S. Frederiksen, C. S. Frederiksen, and S. L. Osbrough. Seasonal ensemble prediction with a coupled ocean-atmosphere model. Aust. Met. Ocean. J., 59:53–66, 2010b. URL http://www.bom.gov.au/jshess/papers.php?year=2010. J. S. Frederiksen, C. S. Frederiksen, and S. L. Osbrough. Methods of ensemble prediction for seasonal forecasts with a coupled ocean-atmosphere model. In Proceedings of the 16th Biennial Computational Techniques and Applications Conference, CTAC-2012, volume 54 of ANZIAM J., pages C361–C376, 2013b. doi:10.21914/anziamj.v54i0.6509. P. R. Gent, G. Danabasoglu, L. J. Donner, M. M. Holland, E. C. Hunke, S. R. Jayne, D. M. Lawrence, R. B. Neale, P. J. Rasch, M. Vertenstein, P. H. Worley, Z.-L. Yang, and M. Zhang. The community Climate System Model version 4. J. Clim., 24:4973–4991, 2011. doi:10.1175/2011JCLI4083.1. S. Grainger, C. S. Frederiksen, and X. Zheng. Assessment of modes of interannual variability of Southern Hemisphere atmospheric circulation in CMIP5 models. J. Clim., 27:8107–8125, 2014. doi:10.1175/JCLI-D-14-00251.1. E. Kalnay, M. Kanamitsu, R. Kistler, W. Collins, D. Deaven, L. Gandin, M. Iredell, S. Saha, G. White, J. Woollen, Y. Zhu, M. Chelliah, W. Ebisuzaki, W. Higgins, J. Janowiak, K. C. Mo, C. Ropelewski, J. Wang, A. Leetmaa, R. Reynolds, R. Jenne, and D. Joseph. The NCEP/NCAR 40-year reanalysis project. B. Am. Meteorol. Soc., 77:437–472, 1996. doi:10.1175/1520-0477(1996)077<0437:TNYRP>2.0.CO;2. H. A. Rashid, A. Sullivan, A. C. Hirst, D. Bi, X. Zhou, and S. J. Marsland. Evaluation of El Nino-Southern Oscillation in the ACCESS coupled model simulations for CMIP5. Aust. Met. Ocean. J., 63:161–180, 2013. doi:10.22499/2.6301.010. K. E. Taylor, R. J. Stouffer, and G. A. Meehl. An overview of CMIP5 and the experiment design. Bull. Am. Meteorol. Soc., 93:485–498, 2012. doi:10.1175/BAMS-D-11-00094.1.

Sign in / Sign up

Export Citation Format

Share Document