scholarly journals Multi-time-scale input approaches for hourly-scale rainfall–runoff modeling based on recurrent neural networks

2021 ◽  
Author(s):  
Kei Ishida ◽  
Masato Kiyama ◽  
Ali Ercan ◽  
Motoki Amagasaki ◽  
Tongbi Tu
Keyword(s):  
Time Series ◽  
Time Scale ◽  
Time Series Data ◽  
Series Data ◽  
Computational Time ◽  
Rainfall Runoff ◽  
Runoff Modeling ◽  
Input Time ◽  
Target Data ◽  
Resolution Data

Abstract This study proposes two effective approaches to reduce the required computational time of the training process for time-series modeling through a recurrent neural network (RNN) using multi-time-scale time-series data as input. One approach provides coarse and fine temporal resolutions of the input time-series data to RNN in parallel. The other concatenates the coarse and fine temporal resolutions of the input time-series data over time before considering them as the input to RNN. In both approaches, first, the finer temporal resolution data are utilized to learn the fine temporal scale behavior of the target data. Then, coarser temporal resolution data are expected to capture long-duration dependencies between the input and target variables. The proposed approaches were implemented for hourly rainfall–runoff modeling at a snow-dominated watershed by employing a long short-term memory network, which is a type of RNN. Subsequently, the daily and hourly meteorological data were utilized as the input, and hourly flow discharge was considered as the target data. The results confirm that both of the proposed approaches can reduce the required computational time for the training of RNN significantly. Lastly, one of the proposed approaches improves the estimation accuracy considerably in addition to computational efficiency.

scholarly journals Periodicity Detection Method for Small-Sample Time Series Datasets

2010 ◽  
Vol 4 ◽  
pp. BBI.S5983 ◽  
Author(s):  
Daisuke Tominaga
Keyword(s):  
Time Series ◽  
Time Series Data ◽  
Small Sample ◽  
Detection Methods ◽  
Series Data ◽  
Computational Time ◽  
Signal Pathways ◽  
Periodicity Detection ◽  
Sampling Points ◽  
Sample Time

Time series of gene expression often exhibit periodic behavior under the influence of multiple signal pathways, and are represented by a model that incorporates multiple harmonics and noise. Most of these data, which are observed using DNA microarrays, consist of few sampling points in time, but most periodicity detection methods require a relatively large number of sampling points. We have previously developed a detection algorithm based on the discrete Fourier transform and Akaike's information criterion. Here we demonstrate the performance of the algorithm for small-sample time series data through a comparison with conventional and newly proposed periodicity detection methods based on a statistical analysis of the power of harmonics. We show that this method has higher sensitivity for data consisting of multiple harmonics, and is more robust against noise than other methods. Although “combinatorial explosion” occurs for large datasets, the computational time is not a problem for small-sample datasets. The MATLAB/GNU Octave script of the algorithm is available on the author's web site: http://www.cbrc.jp/%7Etominaga/piccolo/ .

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

2019 ◽  
Vol 23 (12) ◽  
pp. 5089-5110 ◽  
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.

Chaotic Identification of Hourly and Daily Water Level Time Series Data in Different Areas of Elevation at Pahang River

2021 ◽  
Vol 12 (3) ◽  
pp. 2427-2435
Author(s):  
Adib Mashuri Et.al
Keyword(s):  
Time Series ◽  
Phase Space ◽  
Water Level ◽  
Time Scale ◽  
Time Series Data ◽  
Phase Space Reconstruction ◽  
Series Data ◽  
Level Data ◽  
Water Level Data ◽  
Daily Time

This study focused on chaotic analysis of water level data in different elevations located in the highland and lowland areas. This research was conducted considering the uncertain water level caused by the river flow from highland to lowland areas. The analysis was conducted using the data collected from the four area stations along Pahang River on different time scales which were hourly and daily time series data. The resulted findings were relevant to be used by the local authorities in water resource management in these areas. Two methods were used for the analysis process which included Cao method and phase space plot. Both methods are based on phase space reconstruction that is referring to reconstruction of one dimensional data (water level data) to d-dimensional phase space in order to determine the dynamics of the system. The combination of parameters  and d is required in phase space reconstruction. Results showed that (i) the combination of phase space reconstruction’s parameters gave a higher value of parameters by using hourly time scale compared to daily time scale for different elevation; (ii) different elevation gave impact on the values of phase space reconstructions’ parameters; (iii) chaotic dynamics existed using Cao method and phase space plot for different elevation and time scale. Hence, water level data with different time scale from different elevation in Pahang River can be used in the development of prediction model based on chaos approach.

Approach to Forecasting Occurrence of Slope Failure with Nonlinear Dynamical System

2013 ◽  
Vol 438-439 ◽  
pp. 1597-1602
Author(s):  
Han Dong Liu
Keyword(s):  
Dynamical System ◽  
Time Series ◽  
Time Scale ◽  
Slope Failure ◽  
Time Series Data ◽  
Nonlinear Dynamical System ◽  
Series Data ◽  
Geologic Hazard ◽  
Nonlinear Dynamical ◽  
Short Term Prediction

Landslides constitute a major geologic hazard because they are widespread and commonly occur in connection with other major natural disasters such as earthquakes, rainstorms, wildfires and floods. Nonlinear dynamical system (NDS) techniques have been developed to analyze chaotic time series data. According to NDS theory, the correlation dimension and predictable time scale are evaluated from a single observed time series. The Xintan landslide case study is presented to demonstrate that chaos exists in the evolution of a landslide and the predictable time scale must be considered. The possibility for long-term, medium-term and short-term prediction of landslide is discussed.

scholarly journals Random Modeling of Daily Rainfall and Runoff Using a Seasonal Model and Wavelet Denoising

2014 ◽  
Vol 2014 ◽  
pp. 1-11
Author(s):  
Chien-ming Chou
Keyword(s):  
Time Series ◽  
Probability Distribution ◽  
Time Series Data ◽  
Daily Rainfall ◽  
Wavelet Denoising ◽  
Time Series Forecasting ◽  
Series Data ◽  
Perturbation Term ◽  
Seasonal Model ◽  
Runoff Modeling

Instead of Fourier smoothing, this study applied wavelet denoising to acquire the smooth seasonal mean and corresponding perturbation term from daily rainfall and runoff data in traditional seasonal models, which use seasonal means for hydrological time series forecasting. The denoised rainfall and runoff time series data were regarded as the smooth seasonal mean. The probability distribution of the percentage coefficients can be obtained from calibrated daily rainfall and runoff data. For validated daily rainfall and runoff data, percentage coefficients were randomly generated according to the probability distribution and the law of linear proportion. Multiplying the generated percentage coefficient by the smooth seasonal mean resulted in the corresponding perturbation term. Random modeling of daily rainfall and runoff can be obtained by adding the perturbation term to the smooth seasonal mean. To verify the accuracy of the proposed method, daily rainfall and runoff data for the Wu-Tu watershed were analyzed. The analytical results demonstrate that wavelet denoising enhances the precision of daily rainfall and runoff modeling of the seasonal model. In addition, the wavelet denoising technique proposed in this study can obtain the smooth seasonal mean of rainfall and runoff processes and is suitable for modeling actual daily rainfall and runoff processes.

scholarly journals Biodiversity–ecosystem functioning relationships in long-term time series and palaeoecological records: deep sea as a test bed

2016 ◽  
Vol 371 (1694) ◽  
pp. 20150282 ◽  
Author(s):  
Moriaki Yasuhara ◽  
Hideyuki Doi ◽  
Chih-Lin Wei ◽  
Roberto Danovaro ◽  
Sarah E. Myhre
Keyword(s):  
Time Series ◽  
Time Scales ◽  
Time Scale ◽  
Deep Sea ◽  
Ecosystem Functioning ◽  
Time Series Data ◽  
Series Data ◽  
Ecosystem Stability ◽  
Test Bed ◽  
Biodiversity And Ecosystem Functioning

The link between biodiversity and ecosystem functioning (BEF) over long temporal scales is poorly understood. Here, we investigate biological monitoring and palaeoecological records on decadal, centennial and millennial time scales from a BEF framework by using deep sea, soft-sediment environments as a test bed. Results generally show positive BEF relationships, in agreement with BEF studies based on present-day spatial analyses and short-term manipulative experiments. However, the deep-sea BEF relationship is much noisier across longer time scales compared with modern observational studies. We also demonstrate with palaeoecological time-series data that a larger species pool does not enhance ecosystem stability through time, whereas higher abundance as an indicator of higher ecosystem functioning may enhance ecosystem stability. These results suggest that BEF relationships are potentially time scale-dependent. Environmental impacts on biodiversity and ecosystem functioning may be much stronger than biodiversity impacts on ecosystem functioning at long, decadal–millennial, time scales. Longer time scale perspectives, including palaeoecological and ecosystem monitoring data, are critical for predicting future BEF relationships on a rapidly changing planet.

scholarly journals The Decomposition and Forecasting of Mutual Investment Funds Using Singular Spectrum Analysis

Entropy ◽  
2020 ◽  
Vol 22 (1) ◽  
pp. 83 ◽  
Author(s):  
Paulo Canas Rodrigues ◽  
Jonatha Pimentel ◽  
Patrick Messala ◽  
Mohammad Kazemi
Keyword(s):  
Time Series ◽  
Spectrum Analysis ◽  
Time Series Data ◽  
Singular Spectrum Analysis ◽  
Model Fit ◽  
Series Data ◽  
Computational Time ◽  
Investment Funds ◽  
Singular Spectrum ◽  
Non Parametric

Singular spectrum analysis (SSA) is a non-parametric method that breaks down a time series into a set of components that can be interpreted and grouped as trend, periodicity, and noise, emphasizing the separability of the underlying components and separate periodicities that occur at different time scales. The original time series can be recovered by summing all components. However, only the components associated to the signal should be considered for the reconstruction of the noise-free time series and to conduct forecasts. When the time series data has the presence of outliers, SSA and other classic parametric and non-parametric methods might result in misleading conclusions and robust methodologies should be used. In this paper we consider the use of two robust SSA algorithms for model fit and one for model forecasting. The classic SSA model, the robust SSA alternatives, and the autoregressive integrated moving average (ARIMA) model are compared in terms of computational time and accuracy for model fit and model forecast, using a simulation example and time series data from the quotas and returns of six mutual investment funds. When outliers are present in the data, the simulation study shows that the robust SSA algorithms outperform the classical ARIMA and SSA models.

Sign in / Sign up

Export Citation Format

Share Document