Using network theory and machine learning  to predict El Niño

Nooteboom, Peter; Feng, Qu; López, Cristóbal; Hernández-Garcı́a, Emilio; Dijkstra, Henk A.

doi:10.5194/esd-9-969-2018

Cited by 70 publications

(48 citation statements)

References 52 publications

(80 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The regression problem, i.e., forecasting the values of time series such as NINO3.4, was addressed by Nooteboom et al [73] who combined the use of network quantities with a thorough search for attributes based on the physical mechanism behind ENSO. A two-step methodology was used which resulted in a hybrid model for ENSO prediction.…”

Section: Recent Ml-based Predictionsmentioning

confidence: 99%

“…To motivate the choice of the attributes in the ANN, Nooteboom et al [73] used the ZC model [36]. In this model, the physical mechanisms of ENSO are clearly represented and it can be used for extensive testing of different attributes, specially network-based ones which contain correlations and spatial information.…”

Section: Recent Ml-based Predictionsmentioning

confidence: 99%

“…A single sinusoid is not a complete representation of the annual solar forcing, but it gives to the algorithm the phase information necessary to lock El Niño events to the annual cycle. The hybrid model improves on the CFSv2 ensemble at short lead times (up to 6 months) and it had also a better prediction result than all members of the CFSv2 ensemble in the case study of January 2010 [73]. From now on, the Normalized Root Mean Squared Error (NRMSE) is used to indicate the skill of prediction within the test set:…”

Section: Recent Ml-based Predictionsmentioning

confidence: 99%

See 2 more Smart Citations

The Application of Machine Learning Techniques to Improve El Niño Prediction Skill

et al. 2019

Self Cite

View full text Add to dashboard Cite

We review prediction efforts of El Niño events in the tropical Pacific with particular focus on using modern machine learning (ML) methods based on artificial neural networks. With current classical prediction methods using both statistical and dynamical models, the skill decreases substantially for lead times larger than about 6 months. Initial ML results have shown enhanced skill for lead times larger than 12 months. The search for optimal attributes in these methods is described, in particular those derived from complex network approaches, and a critical outlook on further developments is given.

show abstract

Section: Recent Ml-based Predictionsmentioning

confidence: 99%

Section: Recent Ml-based Predictionsmentioning

confidence: 99%

Section: Recent Ml-based Predictionsmentioning

confidence: 99%

See 1 more Smart Citation

The Application of Machine Learning Techniques to Improve El Niño Prediction Skill

et al. 2019

Self Cite

View full text Add to dashboard Cite

show abstract

“…Recently, several approaches based on climate networks were developed to forecast the onsets of El Niño around one year in advance [34][35][36][37] . One of these approaches 34 has correctly forecasted all El Niño onsets or their absence since 2012.…”

Section: Introductionmentioning

confidence: 99%

Complexity-based approach for El Niño magnitude forecasting before the spring predictability barrier

Meng

Fan

Ludescher

et al. 2019

Proc. Natl. Acad. Sci. U.S.A.

View full text Add to dashboard Cite

The El Niño Southern Oscillation (ENSO) is one of the most prominent interannual climate phenomena. An early and reliable ENSO forecasting remains a crucial goal, due to its serious implications for economy, society, and ecosystem. Despite the development of various dynamical and statistical prediction models in the recent decades, the "spring predictability barrier" (SPB) remains a great challenge for long (over 6-month) lead-time forecasting. To overcome this barrier, here we develop an analysis tool, the System Sample Entropy (SysSampEn), to measure the complexity (disorder) of the system composed of temperature anomaly time series in the Niño 3.4 region. When applying this tool to several near surface air-temperature and sea surface temperature datasets, we find that in all datasets a strong positive correlation exists between the magnitude of El Niño and the previous calendar year's SysSampEn (complexity). We show that this correlation allows to forecast the magnitude of an El Niño with a prediction horizon of 1 year and high accuracy (i.e., Root Mean Square Error = 0.23 • C for the average of the individual datasets forecasts). For the on-going 2018 El Niño event, our method forecasts a weak El Niño with a magnitude of 1.11 ± 0.23 • C. Our framework presented here not only facilitates a long-term forecasting of the El Niño magnitude but can potentially also be used as a measure for the complexity of other natural or engineering complex systems. arXiv:1909.03789v1 [physics.ao-ph] 9 Sep 2019 2/12

show abstract

“…In recent years, applications of machine learning methods for accelerating and facilitating scientific discovery have increased rapidly in various research areas. For example, in climate science, neural networks have produced promising results for parameterization of convection and simulation of clouds [20][21][22][23][24] , weather forecasting 25,26 , and predicting El Niño 27 . A class of supervised deep learning architectures, called convolutional neural network (CNN), has transformed pattern recognition and image processing in various domains of business and science 28,29 and can potentially become a powerful tool for classifying and identifying patterns in the climate and environmental data.…”

Section: Introductionmentioning

confidence: 99%

A test case for application of convolutional neural networks to spatio-temporal climate data: Re-identifying clustered weather patterns

Chattopadhyay¹,

Hassanzadeh²,

Pasha³

2018

Preprint

View full text Add to dashboard Cite

Convolutional neural networks (CNNs) can potentially provide powerful tools for classifying and identifying patterns in climate and environmental data. However, because of the inherent complexities of such data, which are often spatio-temporal, chaotic, and non-stationary, the CNN algorithms must be designed/evaluated for each specific dataset and application. Yet to start, CNN, a supervised technique, requires a large labeled dataset. Labeling demands (human) expert time, which combined with the limited number of relevant examples in this area, can discourage using CNNs for new problems. To address these challenges, here we 1) Propose an effective auto-labeling strategy based on using an unsupervised clustering algorithm and evaluating the performance of CNNs in re-identifying these clusters; 2) Use this approach to label thousands of daily large-scale weather patterns over North America in the outputs of a fully-coupled climate model and show the capabilities of CNNs in re-identifying the 4 clustered regimes. The deep CNN trained with 1000 samples or more per cluster has an accuracy of 90% or better. Accuracy scales monotonically but nonlinearly with the size of the training set, e.g. reaching 94% with 3000 training samples per cluster. Effects of architecture and hyperparameters on the performance of CNNs are examined and discussed.

show abstract

Using network theory and machine learning to predict El Niño

Cited by 70 publications

References 52 publications

The Application of Machine Learning Techniques to Improve El Niño Prediction Skill

The Application of Machine Learning Techniques to Improve El Niño Prediction Skill

Complexity-based approach for El Niño magnitude forecasting before the spring predictability barrier

A test case for application of convolutional neural networks to spatio-temporal climate data: Re-identifying clustered weather patterns

Contact Info

Product

Resources

About