scholarly journals Transferring measured discharge time series: Large-scale comparison of Top-kriging to geomorphology-based inverse modeling

2016 ◽  
Vol 52 (7) ◽  
pp. 5555-5576 ◽  
Author(s):  
A. de Lavenne ◽  
J. O. Skøien ◽  
C. Cudennec ◽  
F. Curie ◽  
F. Moatar
Keyword(s):  
Time Series ◽  
Inverse Modeling ◽  
Large Scale ◽  
Discharge Time

scholarly journals Comparison of Stochastic and Machine Learning Methods for Multi-Step Ahead Forecasting of Hydrological Processes

2018 ◽  
Author(s):  
Georgia Papacharalampous ◽  
Hristos Tyralis ◽  
Demetris Koutsoyiannis
Keyword(s):  
Machine Learning ◽  
Time Series ◽  
Large Scale ◽  
Simulation Experiment ◽  
Extensive Study ◽  
Discharge Time ◽  
Machine Learning Methods ◽  
Stationary Stochastic Processes ◽  
The Subject ◽  
First Time

Research within the field of hydrology often focuses on comparing stochastic to machine learning (ML) forecasting methods. The comparisons performed are all based on case studies, while an extensive study aiming to provide generalized results on the subject is missing. Herein, we compare 11 stochastic and 9 ML methods regarding their multi-step ahead forecasting properties by conducting 12 large-scale computational experiments based on simulations. Each of these experiments uses 2 000 time series generated by linear stationary stochastic processes. We conduct each simulation experiment twice; the first time using time series of 100 values and the second time using time series of 300 values. Additionally, we conduct a real-world experiment using 405 mean annual river discharge time series of 100 values. We quantify the performance of the methods using 18 metrics. The results indicate that stochastic and ML methods perform equally well.

scholarly journals Comparison of Stochastic and Machine Learning Methods for Multi-Step Ahead Forecasting of Hydrological Processes

2019 ◽  
Author(s):  
Georgia Papacharalampous ◽  
Hristos Tyralis ◽  
Demetris Koutsoyiannis
Keyword(s):  
Machine Learning ◽  
Time Series ◽  
Large Scale ◽  
Simulation Experiment ◽  
Extensive Study ◽  
Discharge Time ◽  
Machine Learning Methods ◽  
Stationary Stochastic Processes ◽  
The Subject ◽  
First Time

Research within the field of hydrology often focuses on comparing stochastic to machine learning (ML) forecasting methods. The comparisons performed are all based on case studies, while an extensive study aiming to provide generalized results on the subject is missing. Herein, we compare 11 stochastic and 9 ML methods regarding their multi-step ahead forecasting properties by conducting 12 large-scale computational experiments based on simulations. Each of these experiments uses 2 000 time series generated by linear stationary stochastic processes. We conduct each simulation experiment twice; the first time using time series of 100 values and the second time using time series of 300 values. Additionally, we conduct a real-world experiment using 405 mean annual river discharge time series of 100 values. We quantify the performance of the methods using 18 metrics. The results indicate that stochastic and ML methods perform equally well.

scholarly journals Inverse transport modeling of volcanic sulfur dioxide emissions using large-scale ensemble simulations

2015 ◽  
Vol 8 (10) ◽  
pp. 9103-9146
Author(s):  
Y. Heng ◽  
L. Hoffmann ◽  
S. Griessbach ◽  
T. Rößler ◽  
O. Stein
Keyword(s):  
Time Series ◽  
Sulfur Dioxide ◽  
Inverse Modeling ◽  
Large Scale ◽  
Simulation System ◽  
Transport Modeling ◽  
Volcanic Emissions ◽  
Ensemble Simulations ◽  
Emission Time ◽  
Inverse Transport

Abstract. An inverse transport modeling approach based on the concepts of sequential importance resampling and parallel computing is presented to reconstruct altitude-resolved time series of volcanic emissions, which often can not be obtained directly with current measurement techniques. A new inverse modeling and simulation system, which implements the inversion approach with the Lagrangian transport model Massive-Parallel Trajectory Calculations (MPTRAC) is developed to provide reliable transport simulations of volcanic sulfur dioxide (SO2). In the inverse modeling system MPTRAC is used to perform two types of simulations, i. e., large-scale ensemble simulations for the reconstruction of volcanic emissions and final transport simulations. The transport simulations are based on wind fields of the ERA-Interim meteorological reanalysis of the European Centre for Medium Range Weather Forecasts. The reconstruction of altitude-dependent SO2 emission time series is also based on Atmospheric Infrared Sounder (AIRS) satellite observations. A case study for the eruption of the Nabro volcano, Eritrea, in June 2011, with complex emission patterns, is considered for method validation. Meteosat Visible and InfraRed Imager (MVIRI) near-real-time imagery data are used to validate the temporal development of the reconstructed emissions. Furthermore, the altitude distributions of the emission time series are compared with top and bottom altitude measurements of aerosol layers obtained by the Cloud–Aerosol Lidar with Orthogonal Polarization (CALIOP) and the Michelson Interferometer for Passive Atmospheric Sounding (MIPAS) satellite instruments. The final transport simulations provide detailed spatial and temporal information on the SO2 distributions of the Nabro eruption. The SO2 column densities from the simulations are in good qualitative agreement with the AIRS observations. Our new inverse modeling and simulation system is expected to become a useful tool to also study other volcanic eruption events.

scholarly journals Subsidence Monitoring of Fill Area in Yan’an New District Based on Sentinel-1A Time Series Imagery

2021 ◽  
Vol 13 (15) ◽  
pp. 3044
Author(s):  
Mingjie Liao ◽  
Rui Zhang ◽  
Jichao Lv ◽  
Bin Yu ◽  
Jiatai Pang ◽  
...  
Keyword(s):  
Time Series ◽  
Large Scale ◽  
Ground Deformation ◽  
Dynamic Change ◽  
Deformation Monitoring ◽  
Chinese Loess Plateau ◽  
Ground Subsidence ◽  
Shanxi Province ◽  
Environment Change ◽  
Loess Area

In recent years, many cities in the Chinese loess plateau (especially in Shanxi province) have encountered ground subsidence problems due to the construction of underground projects and the exploitation of underground resources. With the completion of the world’s largest geotechnical project, called “mountain excavation and city construction,” in a collapsible loess area, the Yan’an city also appeared to have uneven ground subsidence. To obtain the spatial distribution characteristics and the time-series evolution trend of the subsidence, we selected Yan’an New District (YAND) as the specific study area and presented an improved time-series InSAR (TS-InSAR) method for experimental research. Based on 89 Sentinel-1A images collected between December 2017 to December 2020, we conducted comprehensive research and analysis on the spatial and temporal evolution of surface subsidence in YAND. The monitoring results showed that the YAND is relatively stable in general, with deformation rates mainly in the range of −10 to 10 mm/yr. However, three significant subsidence funnels existed in the fill area, with a maximum subsidence rate of 100 mm/yr. From 2017 to 2020, the subsidence funnels enlarged, and their subsidence rates accelerated. Further analysis proved that the main factors induced the severe ground subsidence in the study area, including the compressibility and collapsibility of loess, rapid urban construction, geological environment change, traffic circulation load, and dynamic change of groundwater. The experimental results indicated that the improved TS-InSAR method is adaptive to monitoring uneven subsidence of deep loess area. Moreover, related data and information would provide reference to the large-scale ground deformation monitoring and in similar loess areas.

scholarly journals Meso- and microscale sea-ice motion in the East Siberian Sea as determined from ERS-1 SAR Data

1999 ◽  
Vol 45 (150) ◽  
pp. 370-383 ◽  
Author(s):  
Kim Morris ◽  
Shusun Li ◽  
Martin Jeffries
Keyword(s):  
Time Series ◽  
Sea Ice ◽  
Large Scale ◽  
Vector Fields ◽  
Lateral Displacement ◽  
Motion Vector ◽  
Sar Interferometry ◽  
East Siberian Sea ◽  
Pack Ice ◽  
Sar Data

Abstract Synthetic aperture radar- (SAR-)derived ice-motion vectors and SAR interferometry were used to study the sea-ice conditions in the region between the coast and 75° N (~ 560 km) in the East Siberian Sea in the vicinity of the Kolyma River. ERS-1 SAR data were acquired between 24 December 1993 and 30 March 1994 during the 3 day repeat Ice Phase of the satellite. The time series of the ice-motion vector fields revealed rapid (3 day) changes in the direction and displacement of the pack ice. Longer-term (≥ 1 month) trends also emerged which were related to changes in large-scale atmospheric circulation. On the basis of this time series, three sea-ice zones were identified: the near-shore, stationary-ice zone; a transitional-ice zone;and the pack-ice zone. Three 3 day interval and one 9 day interval interferometric sets (amplitude, correlation and phase diagrams) were generated for the end of December, the begining of February and mid-March. They revealed that the stationary-ice zone adjacent to the coast is in constant motion, primarily by lateral displacement, bending, tilting and rotation induced by atmospheric/oceanic forcing. The interferogram patterns change through time as the sea ice becomes thicker and a network of cracks becomes established in the ice cover. It was found that the major features in the interferograms were spatially correlated with sea-ice deformation features (cracks and ridges) and major discontinuities in ice thickness.

Machine-Learning for the Prediction of Lost Circulation Events - Time Series Analysis and Model Evaluation

2021 ◽  
Author(s):  
Arturo Magana-Mora ◽  
Mohammad AlJubran ◽  
Jothibasu Ramasamy ◽  
Mohammed AlBassam ◽  
Chinthaka Gooneratne ◽  
...  
Keyword(s):  
Machine Learning ◽  
Time Series ◽  
Real Time ◽  
Large Scale ◽  
Model Comparison ◽  
Drilling Fluid ◽  
Sensor Data ◽  
False Alarms ◽  
Suitable Model ◽  
Lost Circulation

Abstract Objective/Scope. Lost circulation events (LCEs) are among the top causes for drilling nonproductive time (NPT). The presence of natural fractures and vugular formations causes loss of drilling fluid circulation. Drilling depleted zones with incorrect mud weights can also lead to drilling induced losses. LCEs can also develop into additional drilling hazards, such as stuck pipe incidents, kicks, and blowouts. An LCE is traditionally diagnosed only when there is a reduction in mud volume in mud pits in the case of moderate losses or reduction of mud column in the annulus in total losses. Using machine learning (ML) for predicting the presence of a loss zone and the estimation of fracture parameters ahead is very beneficial as it can immediately alert the drilling crew in order for them to take the required actions to mitigate or cure LCEs. Methods, Procedures, Process. Although different computational methods have been proposed for the prediction of LCEs, there is a need to further improve the models and reduce the number of false alarms. Robust and generalizable ML models require a sufficiently large amount of data that captures the different parameters and scenarios representing an LCE. For this, we derived a framework that automatically searches through historical data, locates LCEs, and extracts the surface drilling and rheology parameters surrounding such events. Results, Observations, and Conclusions. We derived different ML models utilizing various algorithms and evaluated them using the data-split technique at the level of wells to find the most suitable model for the prediction of an LCE. From the model comparison, random forest classifier achieved the best results and successfully predicted LCEs before they occurred. The developed LCE model is designed to be implemented in the real-time drilling portal as an aid to the drilling engineers and the rig crew to minimize or avoid NPT. Novel/Additive Information. The main contribution of this study is the analysis of real-time surface drilling parameters and sensor data to predict an LCE from a statistically representative number of wells. The large-scale analysis of several wells that appropriately describe the different conditions before an LCE is critical for avoiding model undertraining or lack of model generalization. Finally, we formulated the prediction of LCEs as a time-series problem and considered parameter trends to accurately determine the early signs of LCEs.

Sign in / Sign up

Export Citation Format

Share Document