scholarly journals Artificial Intelligence Method for Shear Wave Travel Time Prediction considering Reservoir Geological Continuity

2021 ◽  
Vol 2021 ◽  
pp. 1-18
Author(s):  
Shanshan Liu ◽  
Yipeng Zhao ◽  
Zhiming Wang
Keyword(s):  
Artificial Intelligence ◽  
Travel Time ◽  
Shear Wave ◽  
Single Point ◽  
Oil And Gas Industry ◽  
Support Vector ◽  
Travel Times ◽  
Sand Production ◽  
Travel Time Prediction ◽  
Wave Travel

The existing artificial intelligence model uses single-point logging data as the eigenvalue to predict shear wave travel times (DTS), which does not consider the longitudinal continuity of logging data along the reservoir and lacks the multiwell data processing method. Low prediction accuracy of shear wave travel time affects the accuracy of elastic parameters and results in inaccurate sand production prediction. This paper establishes the shear wave prediction model based on the standardization, normalization, and depth correction of conventional logging data with five artificial intelligence methods (linear regression, random forest, support vector regression, XGBoost, and ANN). The adjacent data points in depth are used as machine learning eigenvalues to improve the practicability of interwell and the accuracy of single-well prediction. The results show that the model built with XGBoost using five points outperforms other models in predicting. The R2 of 0.994 and 0.964 are obtained for the training set and testing set, respectively. Every model considering reservoir vertical geological continuity predicts test set DTS with higher accuracy than single-point prediction. The developed model provides a tool to determine geomechanical parameters and give a preliminary suggestion on the possibility of sand production where shear wave travel times are not available. The implementation of the model provides an economic and reliable alternative for the oil and gas industry.

scholarly journals Dynamic Bus Travel Time Prediction Models on Road with Multiple Bus Routes

2015 ◽  
Vol 2015 ◽  
pp. 1-9 ◽  
Author(s):  
Cong Bai ◽  
Zhong-Ren Peng ◽  
Qing-Chang Lu ◽  
Jian Sun
Keyword(s):  
Travel Time ◽  
Dynamic Model ◽  
Kalman Filtering ◽  
Prediction Models ◽  
Support Vector ◽  
Travel Times ◽  
Travel Time Prediction ◽  
Real World Data ◽  
Time Prediction ◽  
Bus Travel Time

Accurate and real-time travel time information for buses can help passengers better plan their trips and minimize waiting times. A dynamic travel time prediction model for buses addressing the cases on road with multiple bus routes is proposed in this paper, based on support vector machines (SVMs) and Kalman filtering-based algorithm. In the proposed model, the well-trained SVM model predicts the baseline bus travel times from the historical bus trip data; the Kalman filtering-based dynamic algorithm can adjust bus travel times with the latest bus operation information and the estimated baseline travel times. The performance of the proposed dynamic model is validated with the real-world data on road with multiple bus routes in Shenzhen, China. The results show that the proposed dynamic model is feasible and applicable for bus travel time prediction and has the best prediction performance among all the five models proposed in the study in terms of prediction accuracy on road with multiple bus routes.

scholarly journals Shear-wave travel times and amplitudes for two well-constrained earthquakes

1978 ◽  
Vol 68 (4) ◽  
pp. 973-985
Author(s):  
Robert S. Hart ◽  
Rhett Butler
Keyword(s):  
Travel Time ◽  
Shear Wave ◽  
Correlation Technique ◽  
Travel Times ◽  
Time Data ◽  
Data Set ◽  
A Value ◽  
Travel Time Data ◽  
Distance Dependence ◽  
Wave Travel

abstract The wave-form correlation technique (Hart, 1975) for determining precise teleseismic shear-wave travel times is extended to two large earthquakes with well-constrained source mechanisms, the 1968 Borrego Mountain, California earthquake and the 1973 Hawaii earthquake. A total of 87 SH travel times in the distance range of 30° to 92° were obtained through analysis of WWSSN and Canadian Network seismograms from these two events. Major features of the travel-time data include a trend toward faster travel times at a distance of about 40° (previously noted by Ibrahim and Nuttli, 1967; Hart, 1975); another somewhat less pronounced trend toward faster times at about 75°; a +6 sec base line shift, with respect to the Jeffreys-Bullen Table, for the Borrego Mountain data; and large azimuthally-dependent scatter for the Hawaiian data, probably reflecting dramatic lateral variations in the near-source region. When azimuthal variations in the Hawaii data are removed, the travel times from both events show very low scatter. The correlations were also used to investigate SH amplitudes for possible distance dependence in the data and variations in tβ*. The Borrego Mountain data show very low scatter and no discernible distance dependence. All of the data are compatible with a value of tβ* = 5.2 ± 0.5. The amplitudes from the Hawaii earthquake show the same azimuthal variations found in the travel-time data. When those effects are removed, the Hawaii data satisfies a value of tβ* equal to 4.0 ± 0.5 and, as with the other data set, no distance dependence is apparent.

Day-to-Day Travel-Time Trends and Travel-Time Prediction from Loop-Detector Data

2000 ◽  
Vol 1717 (1) ◽  
pp. 120-129 ◽  
Author(s):  
Jaimyoung Kwon ◽  
Benjamin Coifman ◽  
Peter Bickel
Keyword(s):  
Linear Regression ◽  
Travel Time ◽  
Prediction Errors ◽  
Travel Times ◽  
Travel Time Prediction ◽  
Time Prediction ◽  
Loop Detectors ◽  
Stepwise Variable Selection ◽  
Planning Models ◽  
Current Implementation

An approach is presented for estimating future travel times on a freeway using flow and occupancy data from single-loop detectors and historical travel-time information. Linear regression, with the stepwise-variable-selection method and more advanced tree-based methods, is used. The analysis considers forecasts ranging from a few minutes into the future up to an hour ahead. Leave-a-day-out cross-validation was used to evaluate the prediction errors without underestimation. The current traffic state proved to be a good predictor for the near future, up to 20 min, whereas historical data are more informative for longer-range predictions. Tree-based methods and linear regression both performed satisfactorily, showing slightly different qualitative behaviors for each condition examined in this analysis. Unlike preceding works that rely on simulation, real traffic data were used. Although the current implementation uses measured travel times from probe vehicles, the ultimate goal is an autonomous system that relies strictly on detector data. In the course of presenting the prediction system, the manner in which travel times change from day to day was examined, and several metrics to quantify these changes were developed. The metrics can be used as input for travel-time prediction, but they also should be beneficial for other applications, such as calibrating traffic models and planning models.

Seismic wave travel times from nuclear explosions

1958 ◽  
Vol 48 (4) ◽  
pp. 377-398
Author(s):  
Dean S. Carder ◽  
Leslie F. Bailey
Keyword(s):  
Travel Time ◽  
Travel Times ◽  
Strong Variation ◽  
Time Data ◽  
Owens Valley ◽  
Central California ◽  
Nuclear Explosions ◽  
Travel Time Data ◽  
The Pacific ◽  
Wave Travel

Abstract A large number of seismograph records from nuclear explosions in the Nevada and Pacific Island proving grounds have been collected and analyzed. The Nevada explosions were well recorded to distances of 6°.5 (450 mi.) and weakly recorded as far as 17°.5, and under favorable circumstances as far as 34°. The Pacific explosions had world-wide recording except that regional data were necessarily meager. The Nevada data confirm that the crustal thickness in the area is about 35 km., with associations of 6.1 km/sec. speeds in the crust and 8.0 to 8.2 km/sec. speeds beneath it. They indicate that there is no uniform layering in the crust, and that if higher-speed media do exist, they are not consistent; also, that the crust between the proving grounds and central California shows a thickening probably as high as 70 or 75 km., and that this thickened portion may extend beneath the Owens Valley. The data also point to a discontinuity at postulated depths of 160 to 185 km. Pacific travel times out to 14° are from 4 to 8 sec. earlier than similar continental data partly because of a thinner crust, 17 km. or less, under the atolls and partly because speeds in the top of the mantle are more nearly 8.15 km/sec. than 8.0 km/sec. More distant points, at 17°.5 and 18°.5, indicate slower travel times—about 8.1 km/sec. A fairly sharp discontinuity at 19° in the travel-time data is indicated. Travel times from Pacific sources to North America follow closely Jeffreys-Bullen 1948 and Gutenberg 1953 travel-time curves for surface foci except they are about 2 sec. earlier on the continent, and Arctic and Pacific basin data are about 2 sec. still earlier. The core reflection PcP shows a strong variation in amplitude with slight changes in distance at two points where sufficient data were available.

Teleseismic P-wave travel time tomography of the Alpine upper mantle using AlpArray seismic network data

2020 ◽  
Author(s):  
Marcel Paffrath ◽  
Wolfgang Friederich ◽  
Keyword(s):  
Travel Time ◽  
Upper Mantle ◽  
High Velocity ◽  
Eastern Alps ◽  
Alpine Region ◽  
Seismic Network ◽  
P Wave ◽  
Travel Times ◽  
Travel Time Tomography ◽  
Wave Travel

<p>We perform a teleseismic P-wave travel time tomography to examine geometry and slab structure of the upper mantle beneath the Alpine orogen. Vertical component data of the extraordinary dense seismic network AlpArray are used which were recorded at over 600 temporary and permanent broadband stations deployed by 24 different European institutions in the greater Alpine region, reaching from the Massif Central to the Pannonian Basin and from the Po plain to the river Main. Mantle phases of 347 teleseismic events between 2015 and 2019 of magnitude 5.5 and higher are evaluated automatically for direct and core diffracted P arrivals using a combination of higher-order statistics picking algorithms and signal cross correlation. The resulting database contains over 170.000 highly accurate absolute P picks that were manually revised for each event. The travel time residuals exhibit very consistent and reproducible spatial patterns, already pointing at high velocity slabs in the mantle.</p><p>For predicting P-wave travel times, we consider a large computational box encompassing the Alpine region up to a depth of 600 km within which we allow 3D-variations of P-wave velocity. Outside this box we assume a spherically symmetric earth and apply the Tau-P method to calculate travel times and ray paths. These are injected at the boundaries of the regional box and continued using the fast marching method. We invert differences between observed and predicted travel times for P-wave velocities inside the box. Velocity is discretized on a regular grid with an average spacing of about 25 km. The misfit reduction reaches values of up to 75% depending on damping and smoothing parameters.</p><p>The resulting model shows several steeply dipping high velocity anomalies following the Alpine arc. The most prominent structure stretches from the western Alps into the Apennines mountain range reaching depths of over 500 km. Two further anomalies extending down to a depth of 300 km are located below the central and eastern Alps, separated by a clear gap below the western part of the Tauern window. Further to the east the model indicates a possible high-velocity connection between the eastern Alps and the Dinarides. Regarding the lateral position of the central and eastern Alpine slabs, our results confirm previous studies. However, there are differences regarding depth extent, dip angles and dip directions. Both structures dip very steeply with a tendency towards northward dipping. We perform various general, as well as purpose-built resolution tests, to verify the capabilities of our setup to resolve slab gaps as well as different possible slab dipping directions.</p>

scholarly journals Travel Time Prediction in a Multimodal Freight Transport Relation Using Machine Learning Algorithms

Logistics ◽  
2019 ◽  
Vol 4 (1) ◽  
pp. 1 ◽  
Author(s):  
Nikolaos Servos ◽  
Xiaodi Liu ◽  
Michael Teucke ◽  
Michael Freitag
Keyword(s):  
Machine Learning ◽  
Travel Time ◽  
Absolute Error ◽  
Machine Learning Algorithms ◽  
Support Vector ◽  
Tracking Data ◽  
Travel Time Prediction ◽  
Adaptive Boosting ◽  
Time Prediction ◽  
The Usa

Accurate travel time prediction is of high value for freight transports, as it allows supply chain participants to increase their logistics quality and efficiency. It requires both sufficient input data, which can be generated, e.g., by mobile sensors, and adequate prediction methods. Machine Learning (ML) algorithms are well suited to solve non-linear and complex relationships in the collected tracking data. Despite that, only a minority of recent publications use ML for travel time prediction in multimodal transports. We apply the ML algorithms extremely randomized trees (ExtraTrees), adaptive boosting (AdaBoost), and support vector regression (SVR) to this problem because of their ability to deal with low data volumes and their low processing times. Using different combinations of features derived from the data, we have built several models for travel time prediction. Tracking data from a real-world multimodal container transport relation from Germany to the USA are used for evaluation of the established models. We show that SVR provides the best prediction accuracy, with a mean absolute error of 17 h for a transport time of up to 30 days. We also show that our model performs better than average-based approaches.

scholarly journals The Use of a Machine Learning Method to Predict the Real-Time Link Travel Time of Open-Pit Trucks

2018 ◽  
Vol 2018 ◽  
pp. 1-14 ◽  
Author(s):  
Xiaoyu Sun ◽  
Hang Zhang ◽  
Fengliang Tian ◽  
Lei Yang
Keyword(s):  
Machine Learning ◽  
Travel Time ◽  
Prediction Accuracy ◽  
Prediction Models ◽  
Open Pit ◽  
Support Vector ◽  
Travel Time Prediction ◽  
Open Pit Mines ◽  
Optimal Dispatch ◽  
Link Travel Time

Accurate truck travel time prediction (TTP) is one of the critical factors in the dynamic optimal dispatch of open-pit mines. This study divides the roads of open-pit mines into two types: fixed and temporary link roads. The experiment uses data obtained from Fushun West Open-pit Mine (FWOM) to train three types of machine learning (ML) prediction models based on k-nearest neighbors (kNN), support vector machine (SVM), and random forest (RF) algorithms for each link road. The results show that the TTP models based on SVM and RF are better than that based on kNN. The prediction accuracy calculated in this study is approximately 15.79% higher than that calculated by traditional methods. Meteorological features added to the TTP model improved the prediction accuracy by 5.13%. Moreover, this study uses the link rather than the route as the minimum TTP unit, and the former shows an increase in prediction accuracy of 11.82%.

Sign in / Sign up

Export Citation Format

Share Document