Application of temporal convolutional network for flood forecasting

Abstract Rainfall–runoff modeling is a complex nonlinear time-series problem in the field of hydrology. Various methods, such as physical-driven and data-driven models, have been developed to study the highly random rainfall–runoff process. In the past 2 years, with the advancement of computing hardware resources and algorithms, deep-learning methods, such as temporal convolutional network (TCN), has been shown good prospects in time-series prediction tasks. The aim of this study is to develop a prediction model based on TCN structure to simulate the hourly rainfall–runoff relationship. We use two datasets in the Jingle and Kuye watersheds to test the model under different network structures and compare with the other four models. The results show that the TCN model outperforms the EIESM, artificial neural network, and long short-term memory and improves the flood forecasting accuracy at different foreseeable periods. It is shown that the TCN has a faster convergence rate and is an effective method for hydrological forecasting.

Download Full-text

2-D Convolutional Deep Neural Network for the Multivariate Prediction of Photovoltaic Time Series

Energies ◽

10.3390/en14092392 ◽

2021 ◽

Vol 14 (9) ◽

pp. 2392

Author(s):

Antonello Rosato ◽

Rodolfo Araneo ◽

Amedeo Andreotti ◽

Federico Succetti ◽

Massimo Panella

Keyword(s):

Time Series ◽

Short Term Memory ◽

Time Series Prediction ◽

Short Term ◽

Neural Architecture ◽

Network Layers ◽

Learning Scheme ◽

World Energy ◽

Multivariate Prediction ◽

Long Short Term Memory

Here, we propose a new deep learning scheme to solve the energy time series prediction problem. The model implementation is based on the use of Long Short-Term Memory networks and Convolutional Neural Networks. These techniques are combined in such a fashion that inter-dependencies among several different time series can be exploited and used for forecasting purposes by filtering and joining their samples. The resulting learning scheme can be summarized as a superposition of network layers, resulting in a stacked deep neural architecture. We proved the accuracy and robustness of the proposed approach by testing it on real-world energy problems.

Download Full-text

Empirical Mode Decomposition, Extreme Learning Machine and Long Short-Term Memory for Time Series Prediction: A Comparative Study

2018 7th Brazilian Conference on Intelligent Systems (BRACIS) ◽

10.1109/bracis.2018.00091 ◽

2018 ◽

Author(s):

Elivelto Ebermam ◽

Gabriel G. De Angelo ◽

Helder Knidel ◽

Renato A. Krohling

Keyword(s):

Time Series ◽

Comparative Study ◽

Extreme Learning Machine ◽

Short Term Memory ◽

Time Series Prediction ◽

Short Term ◽

Term Memory ◽

Mode Decomposition ◽

Long Short Term Memory ◽

Learning Machine

Download Full-text

Online reliability time series prediction via convolutional neural network and long short term memory for service-oriented systems

Knowledge-Based Systems ◽

10.1016/j.knosys.2018.07.006 ◽

2018 ◽

Vol 159 ◽

pp. 132-147 ◽

Cited By ~ 17

Author(s):

Hongbing Wang ◽

Zhengping Yang ◽

Qi Yu ◽

Tianjing Hong ◽

Xin Lin

Keyword(s):

Neural Network ◽

Time Series ◽

Convolutional Neural Network ◽

Short Term Memory ◽

Time Series Prediction ◽

Short Term ◽

Term Memory ◽

Service Oriented ◽

Long Short Term Memory

Download Full-text

Deep Learning with Long Short-Term Memory for Time Series Prediction

IEEE Communications Magazine ◽

10.1109/mcom.2019.1800155 ◽

2019 ◽

Vol 57 (6) ◽

pp. 114-119 ◽

Cited By ~ 43

Author(s):

Yuxiu Hua ◽

Zhifeng Zhao ◽

Rongpeng Li ◽

Xianfu Chen ◽

Zhiming Liu ◽

...

Keyword(s):

Time Series ◽

Deep Learning ◽

Short Term Memory ◽

Time Series Prediction ◽

Short Term ◽

Term Memory ◽

Long Short Term Memory

Download Full-text

Simplifying Long Short-Term Memory for Fast Training and Time Series Prediction

Journal of Physics Conference Series ◽

10.1088/1742-6596/1213/4/042039 ◽

2019 ◽

Vol 1213 ◽

pp. 042039 ◽

Cited By ~ 1

Author(s):

Yuyan Zhang ◽

Xin Hao ◽

Yong Liu

Keyword(s):

Time Series ◽

Short Term Memory ◽

Time Series Prediction ◽

Short Term ◽

Term Memory ◽

Fast Training ◽

Long Short Term Memory

Download Full-text

A note on leveraging synergy in multiple meteorological datasets with deep learning for rainfall-runoff modeling

10.5194/hess-2020-221 ◽

2020 ◽

Author(s):

Frederik Kratzert ◽

Daniel Klotz ◽

Sepp Hochreiter ◽

Grey S. Nearing

Keyword(s):

Deep Learning ◽

Short Term Memory ◽

Rainfall Runoff ◽

Data Set ◽

Simulation Accuracy ◽

Meteorological Forcing ◽

Runoff Modeling ◽

Long Short Term Memory ◽

Rainfall Runoff Model ◽

Runoff Model

Abstract. A deep learning rainfall-runoff model can take multiple meteorological forcing products as inputs and learn to combine them in spatially and temporally dynamic ways. This is demonstrated using Long Short Term Memory networks (LSTMs) trained over basins in the continental US using the CAMELS data set. Using multiple precipitation products (NLDAS, Maurer, DayMet) in a single LSTM significantly improved simulation accuracy relative to using only individual precipitation products. A sensitivity analysis showed that the LSTM learned to utilize different precipitation products in different ways in different basins and for simulating different parts of the hydrograph in individual basins.

Download Full-text

Towards learning universal, regional, and local hydrological behaviors via machine learning applied to large-sample datasets

Hydrology and Earth System Sciences ◽

10.5194/hess-23-5089-2019 ◽

2019 ◽

Vol 23 (12) ◽

pp. 5089-5110 ◽

Cited By ~ 12

Author(s):

Frederik Kratzert ◽

Daniel Klotz ◽

Guy Shalev ◽

Günter Klambauer ◽

Sepp Hochreiter ◽

...

Keyword(s):

Time Series Data ◽

Short Term Memory ◽

Series Data ◽

Hydrological Models ◽

Rainfall Runoff ◽

Runoff Modeling ◽

Data Driven Approach ◽

Long Short Term Memory ◽

Deep Learning Model ◽

Regional Rainfall

Abstract. Regional rainfall–runoff modeling is an old but still mostly outstanding problem in the hydrological sciences. The problem currently is that traditional hydrological models degrade significantly in performance when calibrated for multiple basins together instead of for a single basin alone. In this paper, we propose a novel, data-driven approach using Long Short-Term Memory networks (LSTMs) and demonstrate that under a “big data” paradigm, this is not necessarily the case. By training a single LSTM model on 531 basins from the CAMELS dataset using meteorological time series data and static catchment attributes, we were able to significantly improve performance compared to a set of several different hydrological benchmark models. Our proposed approach not only significantly outperforms hydrological models that were calibrated regionally, but also achieves better performance than hydrological models that were calibrated for each basin individually. Furthermore, we propose an adaption to the standard LSTM architecture, which we call an Entity-Aware-LSTM (EA-LSTM), that allows for learning catchment similarities as a feature layer in a deep learning model. We show that these learned catchment similarities correspond well to what we would expect from prior hydrological understanding.

Download Full-text