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

Water ◽  
2018 ◽  
Vol 10 (12) ◽  
pp. 1849 ◽  
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).

scholarly journals Prediksi Kunjungan Wisatawan Taman Nasional Gunung Merbabu dengan Time Series Forecasting dan LSTM

2020 ◽  
Vol 11 (2) ◽  
pp. 131
Author(s):  
Josua Manullang ◽  
Albertus Joko Santoso ◽  
Andi Wahju Rahardjo Emanuel
Keyword(s):  
Time Series ◽  
National Park ◽  
Short Term Memory ◽  
Lag Time ◽  
Time Series Forecasting ◽  
Mean Square ◽  
Short Term ◽  
Term Memory ◽  
Long Short Term Memory

Abstract. Prediction of tourist visits of Mount Merbabu National Park (TNGMb) needs to be done to control the number of visitors and to preserve the national park. The combination of time series forecasting (TSF) and deep learning methods has become a new alternative for prediction. This case study was conducted to implement several methods combination of TSF and Long-Short Term Memory (LSTM) to predict the visits. In this case study, there are 18 modelling scenarios as research objects to determine the best model by utilizing tourist visits data from 2013 to 2018. The results show that the model applying the lag time method can improve the model's ability to capture patterns on time series data. The error value is measured using the root mean square error (RMSE), with the smallest value of 3.7 in the LSTM architecture, using seven lags as a feature and one lag as a label.Keywords: Tourist Visit, Taman Nasional Gunung Merbabu, Prediction, Recurrent Neural Network, Long-Short Term MemoryAbstrak. Prediksi kunjungan wisatawan Taman Nasional Gunung Merbabu (TNGMb) perlu dilakukan untul pengendalian jumlah pengunjung dan menjaga kelestarian taman nasional. Gabungan metode antara time series forecasting (TSF) dan deep learning telah menjadi alternatif baru untuk melakukan prediksi. Studi kasus ini dilakukan untuk mengimplementasi gabungan dari beberapa macam metode antara TSF dan Long-Short Term Memory (LSTM) untuk memprediksi kunjungan pada TNGMb. Pada studi kasus ini, terdapat 18 skenario pemodelan sebagai objek penelitian untuk menentukan model terbaik, dengan memanfaatkan data jumlah kunjungan wisatawan di TNGMb mulai dari tahun 2013 sampai dengan tahun 2018. Hasil prediksi menunjukkan pemodelan dengan menerapkan metode lag time dapat meningkatakan kemampuan model untuk menangkap pola pada data deret waktu. Besar nilai kesalahan diukur menggunakan root mean square error (RMSE), dengan nilai terkecil sebesar 3,7 pada arsitektur LSTM, menggunakan tujuh lag sebagai feature dan satu lag sebagai label. Kata Kunci: Kunjungan Wisatawan, Taman Nasional Gunung Merbabu, Prediksi, Recurrent Neural Network, Long-Short Term Memory

Time Series Forecasting in Retail Sales Using LSTM and Prophet

2021 ◽  
pp. 241-262
Author(s):  
Clony Junior ◽  
Pedro Gusmão ◽  
José Moreira ◽  
Ana Maria M. Tome
Keyword(s):  
Time Series ◽  
Data Science ◽  
Short Term Memory ◽  
Special Kind ◽  
Time Series Forecasting ◽  
Short Term ◽  
Term Memory ◽  
Use Of Time

Data science highlights fields of study and research such as time series, which, although widely explored in the past, gain new perspectives in the context of this discipline. This chapter presents two approaches to time series forecasting, long short-term memory (LSTM), a special kind of recurrent neural network (RNN), and Prophet, an open-source library developed by Facebook for time series forecasting. With a focus on developing forecasting processes by data mining or machine learning experts, LSTM uses gating mechanisms to deal with long-term dependencies, reducing the short-term memory effect inherent to the traditional RNN. On the other hand, Prophet encapsulates statistical and computational complexity to allow broad use of time series forecasting, prioritizing the expert's business knowledge through exploration and experimentation. Both approaches were applied to a retail time series. This case study comprises daily and half-hourly forecasts, and the performance of both methods was measured using the standard metrics.

scholarly journals Controls on short-term variations in Greenland glacier dynamics

2013 ◽  
Vol 59 (217) ◽  
pp. 883-892 ◽  
Author(s):  
A.V. Sundal ◽  
A. Shepherd ◽  
M. van den Broeke ◽  
J. Van Angelen ◽  
N. Gourmelen ◽  
...  
Keyword(s):  
Time Series ◽  
Radar Data ◽  
Early Summer ◽  
Short Term ◽  
Synthetic Aperture Radar Data ◽  
Velocity Fluctuations ◽  
Speed Up ◽  
Front Advance ◽  
Enhanced Surface ◽  
Front Dynamics

AbstractShort-term ice-dynamical processes at Greenland’s Jakobshavn and Kangerdlugssuaq glaciers were studied using a 3 day time series of synthetic aperture radar data acquired during the 2011 European Remote-sensing Satellite-2 (ERS-2) 3 day repeat campaign together with modelled meteorological parameters. The time series spans the period March–July 2011 and captures the first ∼30% of the summer melting season. In both study areas, we observe velocity fluctuations at the lower ∼10 km of the glacier. At Jakobshavn Isbræ, where our dataset covers the first part of the seasonal calving-front retreat, we identify ten calving episodes, with a mean calving-front area loss of 1.29 ± 0.4 km2. Significant glacier speed-up was observed in the near-terminus area following all calving episodes. We identify changes in calving-front geometry as the dominant control on velocity fluctuations on both glaciers, apart from a <15% early-summer speed-up at Kangerdlugssuaq Glacier during a period of calving-front advance, which we attribute to enhanced surface melt-induced basal lubrication. Our 3 day velocity maps show new spatial characteristics of the ice melange flow variability in the Jakobshavn and Kangerdlugssuaq fjord systems, which are primarily controlled by calving-front dynamics and fjord geometry.

Comparing runoff statistics simulated with a hydrological model utilizing stochastically generated lumped catchment rainfall and multiple point rainfall

2020 ◽  
Author(s):  
Luisa-Bianca Thiele ◽  
Ross Pidoto ◽  
Uwe Haberlandt
Keyword(s):  
Time Series ◽  
Hydrological Modelling ◽  
Flood Frequency ◽  
Multiple Point ◽  
Rainfall Time Series ◽  
Rainfall Runoff ◽  
Design Flood ◽  
Catchment Scale ◽  
Time Step ◽  
Rainfall Runoff Model

&lt;p&gt;For derived flood frequency analyses, stochastic rainfall models can be linked with rainfall-runoff models to improve the accuracy of design flood estimations when the length of observed rainfall and runoff data is not sufficient. In the past, when using stochastic rainfall time series for hydrological modelling purposes, catchment rainfall for use in hydrological modelling was calculated from the multiple point rainfall time series. As an alternative to this approach, it will be tested whether catchment rainfall can be modelled directly, negating the drawbacks (and need) encountered in generating spatially consistent time series. An Alternating Renewal rainfall model (ARM) will be used to generate multiple point and lumped catchment rainfall time series in hourly resolution. The generated rainfall time series will be used to drive the rainfall-runoff model HBV-IWW with an hourly time step for mesoscale catchments in Germany. Validation will be performed by comparing modelled runoff regarding runoff and flood statistics using stochastically generated lumped catchment rainfall versus multiple point rainfall. It would be advantageous if the results based on catchment rainfall are comparable to those using multiple point rainfall, so catchment rainfall could be generated directly with the stochastic rainfall models. Extremes at the catchment scale may also be better represented if catchment rainfall is generated directly.&lt;/p&gt;

scholarly journals Conjunction of ANN and threshold based wavelet de-noising approach for forecasting suspended sediment load

2013 ◽  
Vol 3 (1) ◽  
pp. 09-25
Author(s):  
Vahid Nourani ◽  
Aida Yahyavi Rahimi ◽  
Farzad Hassan Nejad
Keyword(s):  
Time Series ◽  
Suspended Sediment ◽  
Sediment Load ◽  
Data Driven ◽  
Suspended Sediment Load ◽  
Potomac River ◽  
Denoising Method ◽  
Raw Data ◽  
Daily Streamflow

Information on suspended sediment load (SSL) is fundamental for numerous water resources management and environmental protection projects. This phenomenon has the inherent complexity due to a large number of vague parameters and existence of both spatial variability of the basin characteristics and temporal climatic patterns. This complexity turns into a barrier to get accurate prediction by conventional linear methods. On the other hand, the extent of the noise on hydrological data reduces the performance of data-driven models like Artificial Neural Networks (ANNs). Although ANNs could capture the complex nonlinear relationship between input and output parameters, being data-driven method positioned it in a state of need to preprocessed data. In this paper, the application of ANN approach focusing on wavelet- based denoising method for modeling daily streamflow-sediment relationship was proposed. The daily streamflow and SSL data observed at outlet of the Potomac River in USA were used as the case study. Achieving this purpose, Daubechies (db) was used as mother wavelet to decompose both streamflow and sediment time series into detailed and approximation subseries. Decomposition at level ten via db3 and at level eight via db5 were examined for streamflow and SSL time series, respectively. At first, the appropriate input combination with raw data to estimate current SSL was determined and re-imposed to ANN with denoised data.  The comparison of results reveals that in term of determination coefficient, the obtained result by denoised data was improved up to 23.2% with raged to use noisy, raw data and this exhibits that denoised data can be employed productively in ANN-based daily SSL forecasting.

scholarly journals Temporal rainfall disaggregation using a micro-canonical cascade model: Possibilities to improve the autocorrelation

2019 ◽  
Author(s):  
Hannes Müller-Thomy
Keyword(s):  
Time Series ◽  
Extreme Event ◽  
A Priori ◽  
Extreme Rainfall ◽  
Cascade Model ◽  
Special Focus ◽  
Rainfall Time Series ◽  
Lower Saxony ◽  
Time Step ◽  
Daily Data

Abstract. In urban hydrology rainfall time series of high resolution in time are crucial. Such time series with sufficient length can be generated through the disaggregation of daily data with a micro-canonical cascade model. A well-known problem of time series generated so is the underestimation of the autocorrelation. In this paper two cascade model modifications are analysed regarding their ability to improve the autocorrelation. Both modifications are based on a state-of-the-art reference cascade model. In the first modification, a position-dependency is introduced in the first disaggregation step. In the second modification the position of a wet time step is redefined in addition. Both modifications led to an improvement of the autocorrelation, especially the position redefinition. Simultaneously, two approaches are investigated to avoid the generation of time steps with too small rainfall intensities, the conservation of a minimum rainfall amount during the disaggregation process itself and the mimicry of a measurement device after the disaggregation process. The mimicry approach shows slight better results for the autocorrelation and hence was kept for a subsequent resampling investigation using Simulated Annealing. For the resampling, a special focus was given to the conservation of the extreme rainfall values. Therefore, a universal extreme event definition was introduced to define extreme events a priori without knowing their occurrence in time or magnitude. The resampling algorithm is capable of improving the autocorrelation, independent of the previously applied cascade model variant. Also, the improvement of the autocorrelation by the resampling was higher than by the choice of the cascade model modification. The best overall representation of the autocorrelation was achieved by method C in combination with the resampling algorithm. The study was carried out for 24 rain gauges in Lower Saxony, Germany.

scholarly journals Estimation of deterministic component of monthly rainfall time series : A case study for Pantnagar

MAUSAM ◽  
2021 ◽  
Vol 69 (3) ◽  
pp. 449-458
Author(s):  
MANISHA MADHAV NAVALE ◽  
P. S. KASHYAP ◽  
SACHIN KUMAR SINGH ◽  
DANIEL PRAKASH KUSHWAHA ◽  
DEEPAK KUMAR ◽  
...  
Keyword(s):  
Time Series ◽  
Monthly Rainfall ◽  
Rainfall Time Series ◽  
Deterministic Component

scholarly journals Assimilation of Piezometric Data to Calibrate Parsimonious Daily Hydrological Models

Water ◽  
2021 ◽  
Vol 13 (17) ◽  
pp. 2342
Author(s):  
Axel Flinck ◽  
Nathalie Folton ◽  
Patrick Arnaud
Keyword(s):  
Time Series ◽  
River Flow ◽  
Hydrological Model ◽  
Water Levels ◽  
Model Parameters ◽  
Rainfall Time Series ◽  
Time Step ◽  
Processing Methods ◽  
Analysis System ◽  
Set Up

Low water levels are a seasonal phenomenon, which can be long, short, and more or less intense, affecting entire watercourses. This phenomenon has become a concern for many countries who seek better understanding of the processes that affect it and learn how to optimally manage water resources (pumping, irrigation). Consequently, a lumped rainfall model at daily time step (GR) has been defined, calibrated, and regionalised over French territories. The input data come from SAFRAN, the distributed mesoscale atmospheric analysis system, which provides daily solid and liquid precipitation and temperature data throughout the French territory. This model could be improved, in particular to more accurately simulate the hydrological response of watersheds interacting with groundwater. The idea is to use piezometric data from the ADES bank, available in France, and to use it for the calibration phase of the hydrological model. The analysis was carried out across ten French catchments that are representative of various hydrometeorological behaviours and are located in a diverse hydrogeological context. Each catchment must be represented by a piezometer that closely represents the main aquifer that interacts with the basin. This piezometer is located on part of the watershed that is most covered in terms of its drainage network, and closest to its outlet. Different signal processing methods are used to characterise the relationship between the fluctuation of river flow, piezometric levels and rainfall time series. Potential processing methods will be carried out in the temporal domain. To quantify groundwater table inertia and that of the catchment area, correlograms were calculated from daily chronicles of flows and piezometric levels. A cross-correlatory analysis was set up to see, in more detail, the correlations between the flow rates (especially base flows) and piezometric level time series. This type of analysis makes it possible to study relationships between various observations, and tests were carried out to take this information into account during the phase of the calibration of hydrological model parameters. These different analyses will hopefully help us to use piezometric data to consolidate the quality and robustness of the modelling.

scholarly journals A Quadratic–Exponential Model of Variogram Based on Knowing the Maximal Variability: Application to a Rainfall Time Series

Mathematics ◽  
2021 ◽  
Vol 9 (19) ◽  
pp. 2466
Author(s):  
Francisco Gerardo Benavides-Bravo ◽  
Roberto Soto-Villalobos ◽  
José Roberto Cantú-González ◽  
Mario A. Aguirre-López ◽  
Ángela Gabriela Benavides-Ríos
Keyword(s):  
Time Series ◽  
Exponential Model ◽  
Complete Analysis ◽  
Rainfall Time Series ◽  
Nugget Effect ◽  
Proposed Model ◽  
Experimental Variogram ◽  
Novel Model ◽  
Hurst Exponents

Variogram models are a valuable tool used to analyze the variability of a time series; such variability usually entails a spherical or exponential behavior, and so, models based on such functions are commonly used to fit and explain a time series. Variograms have a quasi-periodic structure for rainfall cases, and some extra steps are required to analyze their entire behavior. In this work, we detailed a procedure for a complete analysis of rainfall time series, from the construction of the experimental variogram to curve fitting with well-known spherical and exponential models, and finally proposed a novel model: quadratic–exponential. Our model was developed based on the analysis of 6 out of 30 rainfall stations from our case study: the Río Bravo–San Juan basin, and was constructed from the exponential model while introducing a quadratic behavior near to the origin and taking into account the fact that the maximal variability of the process is known. Considering a sample with diverse Hurst exponents, the stations were selected. The results obtained show robustness in our proposed model, reaching a good fit with and without the nugget effect for different Hurst exponents. This contrasts to previous models, which show good outcomes only without the nugget effect.

Sign in / Sign up

Export Citation Format

Share Document