Flood forecasting in small catchments using deep learning LSTM networks

Long short-term memory (LSTM) networks are able to learn and replicate the relationships of multiple climate and hydrological temporal variables, and therefore are theoretically suitable for data driven modelling and forecasting of rainfall-runoff behavior. However, they inherit some prediction errors occasionally found in data-driven models: phase shift errors, oscillations and total failures. The phase shift error is a particularly significant challenge due to its occurrence when using hourly precipitation and runoff data for catchments with short response times.In order to detect and eliminate these errors, we investigated four approaches, of which the first two are of structural nature, while the last two modify the input time series by certain transformations: 1. The use of encoder-decoder architectures for LSTM networks. 2. Offsetting the start of the flood forecast to the forecast time step of interest. 3. The inversion of the input time series. 4. Including subsequently observed precipitation data as a &#8220;best precipitation forecast&#8221;.We tested the four approaches on five different pilot catchments located in Saxony, Germany with relatively short response times. The results show no advantage of the structural approaches. In contrast, the modification of the input time series shows potential for improving the predictive quality of flood forecasting in a potential operational application.

Download Full-text

Detecting dynamical anomalies in time series from different palaeoclimate proxy archives using windowed recurrence network analysis

10.5194/npg-2019-41 ◽

2019 ◽

Author(s):

Jaqueline Lekscha ◽

Reik V. Donner

Keyword(s):

Time Series ◽

Network Analysis ◽

Nonlinear Filtering ◽

Ice Cores ◽

Second Step ◽

Different Types ◽

Output Time ◽

Input Time ◽

Past Climate Variability ◽

Input Time Series

Abstract. Analysing palaeoclimate proxy time series using windowed recurrence network analysis (wRNA) has been shown to provide valuable information on past climate variability. In turn, it has also been found that the robustness of the obtained results differs among proxies from different palaeoclimate archives. To systematically test the suitability of wRNA for studying different types of palaeoclimate proxy time series, we use the framework of forward proxy modelling. For this, we create artificial input time series with different properties and, in a first step, compare the time series properties of the input and the model output time series. In a second step, we compare the areawise significant anomalies detected using wRNA. For proxies from tree and lake archives, we find that significant anomalies present in the input time series are sometimes missed in the input time series after the nonlinear filtering by the corresponding models. For proxies from speleothems, we observe falsely identified significant anomalies that are not present in the input time series. Finally, for proxies from ice cores, the wRNA results show the best correspondence with those for the input data. Our results contribute to improve the interpretation of windowed recurrence network analysis results obtained from real-world palaeoclimate time series.

Download Full-text

Multilayer Perceptron (MLP) and Autoregressive Integrated Moving Average (ARIMA) Models in Multivariate Input Time Series Data: Solar Irradiance Forecasting

International Journal on Advanced Science Engineering and Information Technology ◽

10.18517/ijaseit.9.1.6426 ◽

2019 ◽

Vol 9 (1) ◽

pp. 220

Author(s):

Devi Munandar

Keyword(s):

Time Series ◽

Multilayer Perceptron ◽

Solar Irradiance ◽

Time Series Data ◽

Moving Average ◽

Series Data ◽

Arima Models ◽

Autoregressive Integrated Moving Average ◽

Input Time ◽

Input Time Series

Download Full-text

Comparison of ITRF2014 station coordinate input time series of DORIS, VLBI and GNSS

Advances in Space Research ◽

10.1016/j.asr.2016.07.016 ◽

2016 ◽

Vol 58 (12) ◽

pp. 2742-2757 ◽

Cited By ~ 6

Author(s):

Vincenza Tornatore ◽

Emine Tanır Kayıkçı ◽

Marco Roggero

Keyword(s):

Time Series ◽

Input Time ◽

Input Time Series

Download Full-text

A Data-Driven Surrogate Modelling Approach for Acceleration of Short-Term Simulations of a Dynamic Urban Drainage Simulator

Water ◽

10.3390/w10121849 ◽

2018 ◽

Vol 10 (12) ◽

pp. 1849 ◽

Cited By ~ 2

Author(s):

Mahmood Mahmoodian ◽

Jairo Arturo Torres-Matallana ◽

Ulrich Leopold ◽

Georges Schutz ◽

Francois H. L. R. Clemens

Keyword(s):

Time Series ◽

Storage Tank ◽

Data Driven ◽

Urban Drainage ◽

Rainfall Time Series ◽

Short Term ◽

Time Step ◽

Speed Up ◽

Error Indicators

In this study, applicability of a data-driven Gaussian Process Emulator (GPE) technique to develop a dynamic surrogate model for a computationally expensive urban drainage simulator is investigated. Considering rainfall time series as the main driving force is a challenge in this regard due to the high dimensionality problem. However, this problem can be less relevant when the focus is only on short-term simulations. The novelty of this research is the consideration of short-term rainfall time series as training parameters for the GPE. Rainfall intensity at each time step is counted as a separate parameter. A method to generate synthetic rainfall events for GPE training purposes is introduced as well. Here, an emulator is developed to predict the upcoming daily time series of the total wastewater volume in a storage tank and the corresponding Combined Sewer Overflow (CSO) volume. Nash-Sutcliffe Efficiency (NSE) and Volumetric Efficiency (VE) are calculated as emulation error indicators. For the case study herein, the emulator is able to speed up the simulations up to 380 times with a low accuracy cost for prediction of the total storage tank volume (medians of NSE = 0.96 and VE = 0.87). CSO events occurrence is detected in 82% of the cases, although with some considerable accuracy cost (medians of NSE = 0.76 and VE = 0.5). Applicability of the emulator for consecutive short-term simulations, based on real observed rainfall time series is also validated with a high accuracy (NSE = 0.97, VE = 0.89).

Download Full-text

Estimating the Information Extracted by a Single Spiking Neuron from a Continuous Input Time Series

Frontiers in Computational Neuroscience ◽

10.3389/fncom.2017.00049 ◽

2017 ◽

Vol 11 ◽

Cited By ~ 5

Author(s):

Fleur Zeldenrust ◽

Sicco de Knecht ◽

Wytse J. Wadman ◽

Sophie Denève ◽

Boris Gutkin

Keyword(s):

Time Series ◽

Spiking Neuron ◽

Input Time ◽

Continuous Input ◽

Input Time Series

Download Full-text

Detecting dynamical anomalies in time series from different palaeoclimate proxy archives using windowed recurrence network analysis

10.5194/egusphere-egu2020-12938 ◽

2020 ◽

Author(s):

Reik Donner ◽

Jaqueline Lekscha

Keyword(s):

Time Series ◽

Network Analysis ◽

Ice Cores ◽

Linear Filtering ◽

Different Types ◽

Output Time ◽

Input Time ◽

Past Climate Variability ◽

Network Transitivity ◽

Input Time Series

Analysing palaeoclimate proxy time series using windowed recurrence network analysis (wRNA) has been shown to provide valuable information on past climate variability. In turn, it has also been found that the robustness of the obtained results differs among proxies from different palaeoclimate archives. To systematically test the suitability of wRNA for studying different types of palaeoclimate proxy time series, we use the framework of forward proxy modelling. For this, we create artificial input time series with different properties and compare the areawise significant anomalies detected using wRNA of the input and the model output time series. Also, taking into account results for general filtering of different time series, we find that the variability of the network transitivity is altered for stochastic input time series while being rather robust for deterministic input. In terms of significant anomalies of the network transitivity, we observe that these anomalies may be missed by proxies from tree and lake archives after the non-linear filtering by the corresponding proxy system models. For proxies from speleothems, we additionally observe falsely identified significant anomalies that are not present in the input time series. Finally, for proxies from ice cores, the wRNA results show the best correspondence with those for the input data. Our results contribute to improve the interpretation of windowed recurrence network analysis results obtained from real-world palaeoclimate time series.

Download Full-text

A Data-Driven Long Time-Series Electrical Line Trip Fault Prediction Method Using an Improved Stacked-Informer Network

Sensors ◽

10.3390/s21134466 ◽

2021 ◽

Vol 21 (13) ◽

pp. 4466

Author(s):

Li Guo ◽

Runze Li ◽

Bin Jiang

Keyword(s):

Time Series ◽

Prediction Accuracy ◽

Time Series Data ◽

Short Term Memory ◽

Fault Prediction ◽

Data Driven ◽

Series Data ◽

Sequence Prediction ◽

Long Time Series ◽

Long Time

The monitoring of electrical equipment and power grid systems is very essential and important for power transmission and distribution. It has great significances for predicting faults based on monitoring a long sequence in advance, so as to ensure the safe operation of the power system. Many studies such as recurrent neural network (RNN) and long short-term memory (LSTM) network have shown an outstanding ability in increasing the prediction accuracy. However, there still exist some limitations preventing those methods from predicting long time-series sequences in real-world applications. To address these issues, a data-driven method using an improved stacked-Informer network is proposed, and it is used for electrical line trip faults sequence prediction in this paper. This method constructs a stacked-Informer network to extract underlying features of long sequence time-series data well, and combines the gradient centralized (GC) technology with the optimizer to replace the previously used Adam optimizer in the original Informer network. It has a superior generalization ability and faster training efficiency. Data sequences used for the experimental validation are collected from the wind and solar hybrid substation located in Zhangjiakou city, China. The experimental results and concrete analysis prove that the presented method can improve fault sequence prediction accuracy and achieve fast training in real scenarios.

Download Full-text

Uncertain Time Series Classification

Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence ◽

10.24963/ijcai.2021/683 ◽

2021 ◽

Author(s):

Michael Franklin Mbouopda

Keyword(s):

Time Series ◽

Time Series Analysis ◽

Large Range ◽

Time Series Classification ◽

Classification Methods ◽

Series Analysis ◽

Input Time ◽

Uncertain Time ◽

Interpretable Classification ◽

Input Time Series

Time series analysis has gained a lot of interest during the last decade with diverse applications in a large range of domains such as medicine, physic, and industry. The field of time series classification has been particularly active recently with the development of more and more efficient methods. However, the existing methods assume that the input time series is free of uncertainty. However, there are applications in which uncertainty is so important that it can not be neglected. This project aims to build efficient, robust, and interpretable classification methods for uncertain time series.

Download Full-text

Combining LSTM Network Ensemble via Adaptive Weighting for Improved Time Series Forecasting

Mathematical Problems in Engineering ◽

10.1155/2018/2470171 ◽

2018 ◽

Vol 2018 ◽

pp. 1-8 ◽

Cited By ~ 15

Author(s):

Jae Young Choi ◽

Bumshik Lee

Keyword(s):

Time Series ◽

Short Term Memory ◽

State Of The Art ◽

Real Life ◽

Life Time ◽

Time Series Forecasting ◽

Ensemble Method ◽

Prediction Errors ◽

Time Step ◽

Ensemble Techniques

Time series forecasting is essential for various engineering applications in finance, geology, and information technology, etc. Long Short-Term Memory (LSTM) networks are nowadays gaining renewed interest and they are replacing many practical implementations of the time series forecasting systems. This paper presents a novel LSTM ensemble forecasting algorithm that effectively combines multiple forecast (prediction) results from a set of individual LSTM networks. The main advantages of our LSTM ensemble method over other state-of-the-art ensemble techniques are summarized as follows: (1) we develop a novel way of dynamically adjusting the combining weights that are used for combining multiple LSTM models to produce the composite prediction output; for this, our method is devised for updating combining weights at each time step in an adaptive and recursive way by using both past prediction errors and forgetting weight factor; (2) our method is capable of well capturing nonlinear statistical properties in the time series, which considerably improves the forecasting accuracy; (3) our method is straightforward to implement and computationally efficient when it comes to runtime performance because it does not require the complex optimization in the process of finding combining weights. Comparative experiments demonstrate that our proposed LSTM ensemble method achieves state-of-the-art forecasting performance on four real-life time series datasets publicly available.

Download Full-text