Optimized ensemble deep learning framework for scalable forecasting of dynamics containing extreme events

Abstract

The remarkable flexibility and adaptability of both deep learning models and ensemble methods have led to the proliferation for their application in understanding many physical phenomena. Traditionally, these two techniques have largely been treated as independent methodologies in practical applications. This study develops an optimized ensemble deep learning (OEDL) framework wherein these two machine learning techniques are jointly used to achieve synergistic improvements in model accuracy, stability, scalability, and reproducibility prompting a new wave of applications in the forecasting of dynamics. Unpredictability is considered as one of the key features of chaotic dynamics, so forecasting such dynamics of nonlinear systems is a relevant issue in the scientific community. It becomes more challenging when the prediction of extreme events is the focus issue for us. In this circumstance, the proposed OEDL model based on a best convex combination of feed-forward neural networks, reservoir computing, and long short-term memory can play a key role in advancing predictions of dynamics consisting of extreme events. The combined framework can generate the best out-of-sample performance than the individual deep learners and standard ensemble framework for both numerically simulated and real world data sets. We exhibit the outstanding performance of the OEDL framework for forecasting extreme events generated from Lienard-type system, prediction of COVID-19 cases in Brazil, dengue cases in San Juan, and sea surface temperature in Nino 3.4 region.

arXiv comment14 pages, 8 figures, any comments are welcome

References in corpus (26)

• Ensemble deep learning: A review
• Recent Advances in Physical Reservoir Computing: A Review
• Consistency of random forests
• Real-time forecasts and risk assessment of novel coronavirus (COVID-19) cases: A data-driven analysis
• The Unreasonable Effectiveness of Deep Learning in Artificial Intelligence
• Data-Driven Forecasting of High-Dimensional Chaotic Systems with Long Short-Term Memory Networks
• Why M Heads are Better than One: Training a Diverse Ensemble of Deep Networks
• Predictability and suppression of extreme events in complex systems
• Extreme events in excitable systems and mechanisms of their generation
• Machine learning algorithms for predicting the amplitude of chaotic laser pulses
• Dynamical indicators for the prediction of bursting phenomena in high-dimensional systems
• Dynamical learning of dynamics
• Intermittent large deviation of chaotic trajectory in Ikeda map: Signature of extreme events
• Distance dependent competitive interactions in a frustrated network of mobile agents
• Using reservoir computer to predict and prevent extreme events
• Extreme events in globally coupled chaotic maps
• Data-driven prediction and prevention of extreme events in a spatially extended excitable system
• Machine learning dynamical phase transitions in complex networks
• Detection of Generalized Synchronization using Echo State Networks
• Understanding the origin of extreme events in El Niño-Southern Oscillation
• Using Machine Learning to Assess Short Term Causal Dependence and Infer Network Links
• Using Machine Learning to predict extreme events in the Hénon map
• Closed-loop adaptive control of extreme events in a turbulent flow
• Model-free prediction of emergence of extreme events in a parametrically driven nonlinear dynamical system by Deep Learning
• Comparison of Deep learning models on time series forecasting : a case study of Dissolved Oxygen Prediction
• Machine Learning assisted Chimera and Solitary states in Networks

Cited by in corpus (5)

• Extreme events in dynamical systems and random walkers: A review
• Early warning signals for critical transitions in complex systems
• Extreme events in a complex network: interplay between degree distribution and repulsive interaction
• Role of assortativity in predicting burst synchronization using echo state network
• Probabilistic AutoRegressive Neural Networks for Accurate Long-range Forecasting