Using network theory and machine learning to predict El Niño

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.

• Publication year

  2018

• Venue

  Earth System Dynamics

• Publication date

  2018-03-27

• Fields of study

  Mathematics, Physics, Computer Science, Environmental Science

• Identifiers
  DOI 10.5194/esd-9-969-2018arXiv 1803.10076
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Machine learning for quantum physics

  2017cited by this paper
• Coherent Tropical Indo-Pacific Interannual Climate Variability

  2016cited by this paper
• Mastering the game of Go with deep neural networks and tree search

  2016cited by this paper
• Percolation-based precursors of transitions in extended systems

  2016influential reference
• ClimateLearn: A machine-learning approach for climate prediction using network measures

  2016cited by this paper
• Percolation framework to describe El Niño conditions.

  2016cited by this paper
• Oceanic El-Niño wave dynamics and climate networks

  2015cited by this paper
• A Complex Network Approach to Understand Climate Variability

  2015cited by this paper
• Using causal discovery for feature selection in multivariate numerical time series

  2015cited by this paper
• Climate network stability measures of El Niño variability.

  2015cited by this paper
• ENSO in CMIP5 simulations: network connectivity from the recent past to the twenty-third century

  2015cited by this paper
• El Niño, La Niña, and the Southern Oscillation

  2014cited by this paper
• Very early warning of next El Niño

  2014cited by this paper
• Characterizing the evolution of climate networks

  2014cited by this paper
• On the Warm Water Volume and Its Changing Relationship with ENSO

  2014cited by this paper
• Extended Reconstructed Sea Surface Temperature Version 4 (ERSST.v4). Part I: Upgrades and Intercomparisons

  2014cited by this paper
• Topology and seasonal evolution of the network of extreme precipitation over the Indian subcontinent and Sri Lanka

  2014cited by this paper
• Distinguishing the effects of internal and forced atmospheric variability in climate networks

  2013cited by this paper
• Multivariate and multiscale dependence in the global climate system revealed through complex networks

  2012cited by this paper
• On the use of cross-validation for time series predictor evaluation

  2012cited by this paper
• Support vector machines in water quality management.

  2011cited by this paper
• Stability of Climate Networks with Time

  2011cited by this paper
• A novel hybridization of artificial neural networks and ARIMA models for time series forecasting

  2011cited by this paper
• Cold tongue/Warm pool and ENSO dynamics in the Pliocene

  2011cited by this paper
• Emergence of El Niño as an autonomous component in the climate network.

  2010cited by this paper
• Networks: An Introduction

  2010cited by this paper
• Forecasting nonlinear time series with a hybrid methodology

  2009cited by this paper
• El Niño in a changing climate

  2009cited by this paper
• Pattern of climate network blinking links follows El Niño events

  2008cited by this paper
• Hybridization of intelligent techniques and ARIMA models for time series prediction

  2008cited by this paper
• Observed equatorial Rossby waves and ENSO-related warm water volume changes in the equatorial Pacific Ocean - art. no. C06003

  2008cited by this paper
• Statistical prediction of ENSO (Nino 3) using sub‐surface temperature data

  2006cited by this paper
• The ENSO phenomenon: theory and mechanisms

  2006cited by this paper
• Pattern Recognition and Machine Learning

  2006cited by this paper
• Neural network forecasts of the tropical Pacific sea surface temperatures

  2006cited by this paper
• What Do Networks Have to Do with Climate

  2006cited by this paper
• ARMA Model Order Determination Using Edge Detection: A New Perspective

  2005cited by this paper
• To combine or not to combine: selecting among forecasts and their combinations

  2005cited by this paper
• A hybrid ARIMA and support vector machines model in stock price forecasting

  2005cited by this paper
• Predictability of El Niño over the past 148 years

  2004cited by this paper
• Global analyses of sea surface temperature, sea ice, and night marine air temperature since the late nineteenth century

  2003cited by this paper
• Correlation-based Feature Selection for Machine Learning

  2003cited by this paper
• An Introduction to Variable and Feature Selection

  2003cited by this paper
• How Predictable is El Niño

  2003cited by this paper
• Time series forecasting using a hybrid ARIMA and neural network model

  2003cited by this paper
• Current Approaches to Phenomenology

  2001cited by this paper
• Current approaches to seasonal to interannual climate predictions

  2001cited by this paper
• The Pacific Cold Tongue and the ENSO mode: a unified theory within the Zebiak-Cane model

  2000cited by this paper
• CURRENT APPROACHES TO SEASONAL-TO-INTERANNUAL CLIMATE PREDICTIONS

  2000cited by this paper
• Stochastic forcing of ENSO by the intraseasonal oscillation

  1999influential reference
• An equatorial ocean recharge paradigm for ENSO. Part II: a stripped-down coupled model

  1997cited by this paper
• El Ni�o Chaos: Overlapping of Resonances Between the Seasonal Cycle and the Pacific Ocean-Atmosphere Oscillator

  1994cited by this paper
• El Ni�o on the Devil's Staircase: Annual Subharmonic Steps to Chaos

  1994cited by this paper
• Observations of the 40-50-day tropical oscillation - a review

  1994cited by this paper
• The Response of a Coupled Ocean-Atmosphere General Circulation Model to Wind Bursts.

  1988cited by this paper
• A Model El Niñ–Southern Oscillation

  1987influential reference
• Relations Between Sea Level, Thermocline Depth, Heat Content, and Dynamic Height in the Tropical Pacific Ocean

  1985cited by this paper
• Some simple solutions for heat‐induced tropical circulation

  1980cited by this paper
• Modeling By Shortest Data Description*

  1978cited by this paper
• A new look at the statistical model identification

  1974cited by this paper
• ATMOSPHERIC TELECONNECTIONS FROM THE EQUATORIAL PACIFIC1

  1969cited by this paper

• Predicting ENSO dynamics with network and complexity analyses.

  2026cites this paper
• Climate network and complexity based ENSO forecast for 2026

  2026cites this paper
• Application of swarm-based deep neural networks and ensemble models for reconstruction of specific conductance data

  2026cites this paper
• Can CMIP6 models simulate the network-based early warning signals for El Niño? Insights for climate modeling and network analyses

  2026cites this paper
• Assessing the Spatiotemporal Impact of ENSO on Coastal Vegetation in Peru Using Random Forest and MODIS Data

  2026cites this paper
• Tropical monsoon rainfall can be predicted with lead times up to 10 months

  2025cites this paper
• Unraveling the mystery of tropical monsoon long-term prediction

  2025cites this paper
• Forecasting springtime rainfall in southeastern Australia using empirical orthogonal functions and neural networks

  2025cites this paper
• Evaluation of the real-time El Niño forecasts by the climate network approach between 2011 and present

  2024cites this paper
• Analysis of a Predictive Mathematical Model of Weather Changes Based on Neural Networks

  2024cites this paper
• MULTIDIMENSIONAL FORECASTING OF PRECIPITATION AND POTENTIAL EVAPOTRANSPIRATION IN THE PARANAPANEMA RIVER BASIN USING NEURAL NETWORK TIME SERIES

  2024cites this paper
• Harnessing evolutionary algorithms for enhanced characterization of ENSO events

  2024cites this paper
• Tipping points in river deltas

  2024cites this paper
• Forecasting the El Niño southern oscillation: physics, bias correction and combined models

  2024cites this paper
• Spatio-temporal data generation based on separated attention for ENSO prediction

  2024cites this paper
• Predicting daily maximum temperature over Andhra Pradesh using machine learning techniques

  2024cites this paper
• Forecasting seasonal rainfall in SE Australia using Empirical Orthogonal Functions and Neural Networks

  2024cites this paper
• The Added Value of Statistical Seasonal Forecasts

  2024cites this paper
• A review of artificial intelligence in marine science

  2023cites this paper
• Network percolation provides early warnings of abrupt changes in coupled oscillatory systems: An explanatory analysis.

  2023cites this paper
• CNN‐Based ENSO Forecasts With a Focus on SSTA Zonal Pattern and Physical Interpretation

  2023cites this paper
• Predicting maximum temperatures over India 10-days ahead using machine learning models

  2023cites this paper
• A New Hybrid Prediction Method of El Niño/La Niña Events by Combining TimesNet and ARIMA

  2023cites this paper
• The efficacy of tropical and extratropical predictors for long‐lead El Niño‐Southern Oscillation prediction: A study using a machine learning algorithm

  2023cites this paper
• On the origin of quasi-periodicity in the atmospheres of Earth, Jupiter, Saturn and the Sun

  2023cites this paper
• El Niño Index Prediction Based on Deep Learning with STL Decomposition

  2023cites this paper
• Unpacking the black box of deep learning for identifying El Niño-Southern oscillation

  2023cites this paper
• Optimizing the Spatial-Temporal Extent of Environmental Factors in Forecasting El Niño and La Niña Using Recurrent Neural Network

  2023cites this paper
• Long Lead ENSO Forecast Using an Adaptive Graph Convolutional Recurrent Neural Network

  2023cites this paper
• A Transformer‐Based Deep Learning Model for Successful Predictions of the 2021 Second‐Year La Niña Condition

  2023cites this paper
• A Neural Network‐Based Scale‐Adaptive Cloud‐Fraction Scheme for GCMs

  2023cites this paper
• Very early warning of a moderate-to-strong El Ni\~no in 2023

  2023cites this paper
• A Hybrid Neural Network Model for ENSO Prediction in Combination with Principal Oscillation Pattern Analyses

  2022cites this paper
• Improving the prediction of the Madden-Julian Oscillation of the ECMWF model by post-processing

  2022cites this paper
• Feature Selection and Spatial-Temporal Forecast of Oceanic Niño Index Using Deep Learning

  2022cites this paper
• Forecasting El Niño and La Niña events using decision tree classifier

  2022cites this paper
• Application of deep learning to understanding ENSO dynamics

  2022cites this paper
• A Place‐Based Approach to Drought Forecasting in South‐Central Oklahoma

  2022cites this paper
• Survey on the Application of Artificial Intelligence in ENSO Forecasting

  2022cites this paper
• Evaluating the Predictability of Eight Atmospheric-Oceanic Signals Affecting Iran’s Droughts, Employing Intelligence Based and Stochastic Methods

  2022cites this paper
• ENSO analysis and prediction using deep learning: A review

  2022cites this paper
• Forecasting the El Niño type well before the spring predictability barrier

  2022cites this paper
• A New Hybrid Machine Learning Model for Short-Term Climate Prediction by Performing Classification Prediction and Regression Prediction Simultaneously

  2022influential citation
• Climate network and complexity based El Ni\~no forecast for 2022

  2021cites this paper
• Machine learning for Earth System Science (ESS): A survey, status and future directions for South Asia

  2021cites this paper
• Network-based forecasting of climate phenomena

  2021cites this paper
• Short‐Term Precipitation Prediction for Contiguous United States Using Deep Learning

  2021cites this paper
• Bibliography

  2021cites this paper
• Reservoir Computing with Delayed Input for Fast and Easy Optimisation

  2021cites this paper
• A Novel Deep Neural Network model approach to predict Indian Ocean dipole and Equatorial Indian Ocean oscillation indices

  2021cites this paper
• Spatial-Temporal Forecast of the probability distribution of Oceanic Nino Index for various lead times

  2021cites this paper
• Spatiotemporal Model Based on Deep Learning for ENSO Forecasts

  2021cites this paper
• Simple, low-cost and accurate data-driven geophysical forecasting with learned kernels

  2021cites this paper
• Strengthening of Indian Ocean teleconnections permits predictions of springtime rainfall in SE Australia

  2021cites this paper
• Ensemble Empirical Mode Decomposition with Adaptive Noise with Convolution Based Gated Recurrent Neural Network: A New Deep Learning Model for South Asian High Intensity Forecasting

  2021cites this paper
• Committor Functions for Climate Phenomena at the Predictability Margin: The example of El Ni\~no Southern Oscillation in the Jin and Timmerman model

  2021cites this paper
• Prediction of Synoptic-Scale Sea Level Pressure Over the Indian Monsoon Region Using Deep Learning

  2021cites this paper
• Data-Driven Deep Learning Emulators for Geophysical Forecasting

  2021cites this paper
• Performance of backpropagation artificial neural network to predict el nino southern oscillation using several indexes as onset indicators

  2021cites this paper
• Data-driven geophysical forecasting: Simple, low-cost, and accurate baselines with kernel methods

  2021cites this paper
• Opportunities and challenges for machine learning in weather and climate modelling: hard, medium and soft AI

  2021cites this paper
• A Training-Efficient Hybrid-Structured Deep Neural Network With Reconfigurable Memristive Synapses

  2020cites this paper
• Bibliometric Analysis of Methods and Tools for Drought Monitoring and Prediction in Africa

  2020cites this paper
• Machine Learning Models for the Seasonal Forecast of Winter Surface Air Temperature in North America

  2020cites this paper
• Applying Convolutional LSTM Network to Predict El Niño Events: Transfer Learning from The Data of Dynamical Model and Observation

  2020cites this paper
• El Niño Index Prediction Using Deep Learning with Ensemble Empirical Mode Decomposition

  2020cites this paper
• Temporal Convolutional Networks for the Advance Prediction of ENSO

  2020cites this paper
• Probabilistic Forecasting of El Niño Using Neural Network Models

  2020cites this paper
• El Niño forecasting based on the global atmospheric oscillation

  2020cites this paper
• Dynamic Time Lag Regression: Predicting What & When

  2020cites this paper
• A machine learning based prediction system for the Indian Ocean Dipole

  2020cites this paper
• The Application of Machine Learning Techniques to Improve El Niño Prediction Skill

  2019influential citation
• Complexity-based approach for El Niño magnitude forecasting before the spring predictability barrier

  2019cites this paper
• NAO Index Prediction using LSTM and ConvLSTM Networks Coupled with Discrete Wavelet Transform

  2019cites this paper
• ENSO Forecasting over Multiple Time Horizons Using ConvLSTM Network and Rolling Mechanism

  2019cites this paper
• Machine Learning of Atmospheric Turbulence in a Variational Multiscale Model

  2019cites this paper
• Very early warning signal for El Niño in 2020 with a 4 in 5 likelihood

  2019cites this paper
• Confronting Grand Challenges in Environmental Fluid Dynamics

  2019cites this paper
• Machine Learning of committor functions for predicting high impact climate events

  2019cites this paper
• Supplementary material to "Weather and climate forecasting with neural networks: using GCMs with different complexity as study-ground"

  2019cites this paper
• Hilbert analysis of air temperature dynamics

  2019cites this paper
• Weather and climate forecasting with neural networks: using general circulation models (GCMs) with different complexity as a study ground

  2019cites this paper
• DLENSO: A Deep Learning ENSO Forecasting Model

  2019cites this paper
• Confronting Grand Challenges in environmental fluid mechanics

  2019cites this paper
• Predicting clustered weather patterns: A test case for applications of convolutional neural networks to spatio-temporal climate data

  2018cites this paper
• Challenges and design choices for global weather and climate models based on machine learning

  2018cites this paper
• ENHANCED MACHINE LEARNING MODEL FOR METEO-OCEANOGRAPHIC TIME-SERIES PREDICTION

  year unknowncites this paper
• Complexity-based approach for El Ni ˜no magnitude forecasting before the spring predictability barrier

  year unknowncites this paper