An Extreme-Adaptive Time Series Prediction Model Based on Probability-Enhanced LSTM Neural Networks (2022-11-29T00:00:00.000000Z)

TL;DR

A novel probability-enhanced neural network model, called NEC+, which concurrently learns extreme and normal prediction functions and a way to choose among them via selective back propagation is proposed, which significantly outperforms state-of-the-art baselines and exhibits superior generalization ability on data with diverse distributions.

Abstract

Forecasting time series with extreme events has been a challenging and prevalent research topic, especially when the time series data are affected by complicated uncertain factors, such as is the case in hydrologic prediction. Diverse traditional and deep learning models have been applied to discover the nonlinear relationships and recognize the complex patterns in these types of data. However, existing methods usually ignore the negative influence of imbalanced data, or severe events, on model training. Moreover, methods are usually evaluated on a small number of generally well-behaved time series, which does not show their ability to generalize. To tackle these issues, we propose a novel probability-enhanced neural network model, called NEC+, which concurrently learns extreme and normal prediction functions and a way to choose among them via selective back propagation. We evaluate the proposed model on the difficult 3-day ahead hourly water level prediction task applied to 9 reservoirs in California. Experimental results demonstrate that the proposed model significantly outperforms state-of-the-art baselines and exhibits superior generalization ability on data with diverse distributions.

Authors

D. Anastasiu

7 papers

Yanhong Li

1 papers

Jack L. Xu

1 papers

TL;DR

Abstract

Authors

References43 items

Forecasting Reservoir Water Levels Using Deep Neural Networks: A Case Study of Angat Dam in the Philippines

Short-term water level prediction of Hongze Lake by Prophet-LSTM combined model based on LAE

Quantile-Based Hydrological Modelling

Identification of Distinct Characteristics of Antibiofilm Peptides and Prospection of Diverse Sources for Efficacious Sequences

Downstream Water Level Prediction of Reservoir based on Convolutional Neural Network and Long Short-Term Memory Network

Application of Neural Network Models and ANFIS for Water Level Forecasting of the Salve Faccha Dam in the Andean Zone in Northern Ecuador

A Method of Multi-Stage Reservoir Water Level Forecasting Systems: A Case Study of Techi Hydropower in Taiwan

Class-Specific Neural Network for Video Compressed Sensing

A stream prediction model based on attention-LSTM

Efficient City-Wide Multi-Class Multi-Movement Vehicle Counting: A Survey

Deep Learning for Block-Level Compressive Video Sensing

Daily Water Level Prediction of Zrebar Lake (Iran): A Comparison between M5P, Random Forest, Random Tree and Reduced Error Pruning Trees Algorithms

Deep learning-based effective fine-grained weather forecasting model

Analysis and Prediction of Dammed Water Level in a Hydropower Reservoir Using Machine Learning and Persistence-Based Techniques

Real-time reservoir operation using recurrent neural networks and inflow forecast from a distributed hydrological model

A Decomposition-Ensemble Learning Model Based on LSTM Neural Network for Daily Reservoir Inflow Forecasting

N-BEATS: Neural basis expansion analysis for interpretable time series forecasting

Stock Price Prediction Using News Sentiment Analysis

A Comparison of ARIMA and LSTM in Forecasting Time Series

The M4 Competition: Results, findings, conclusion and way forward

Vehicle Tracking and Speed Estimation from Traffic Videos

Forecasting at Scale

Deep learning with long short-term memory networks for financial market predictions

DeepAR: Probabilistic Forecasting with Autoregressive Recurrent Networks

Deep Feature Learning Architectures for Daily Reservoir Inflow Forecasting

Expectile and quantile regression—David and Goliath?

Attention-Based Models for Speech Recognition

Show, Attend and Tell: Neural Image Caption Generation with Visual Attention

Sequence to Sequence Learning with Neural Networks

Stock Price Prediction Using the ARIMA Model

Comparison of the ARMA, ARIMA, and the autoregressive artificial neural network models in forecasting the monthly inflow of Dez dam reservoir

Extreme Learning Machine for Regression and Multiclass Classification

The Tourism Forecasting Competition

A neuro-fuzzy computing technique for modeling hydrological time series

Learning to Forget: Continual Prediction with LSTM

The M3-Competition: results, conclusions and implications

Long Short-Term Memory

Time series analysis, forecasting and control

Estimating the components of a mixture of normal distributions

Development of an Extreme Gradient Boosting Model Integrated With Evolutionary Algorithms for Hourly Water Level Prediction

Deep State Space Models for Time Series Forecasting

Adaptive neuro-fuzzy inference system for prediction of water level in reservoir

2022. An Extreme-Adaptive Time Series Prediction Model Based on Probability-Enhanced LSTM Neural Networks

Field of Study

Venue Information

Name

Type

URL

Alternate Names