A comparison of turbine mass flow models based on pragmatic identification data sets for turbogenerator model development

Abstract. Quantitative precipitation nowcasting (QPN) has become an essential technique in various application contexts, such as early warning or urban sewage control. A common heuristic prediction approach is to track the motion of precipitation features from a sequence of weather radar images, and then to extrapolate that motion to the imminent future (minutes to hours), assuming that the intensity of the features remains constant (Lagrangian persistence). In that context, optical flow has become one of the most popular tracking techniques. Yet, the present landscape of computational QPN models still struggles with producing open software implementations. Focusing on this gap, we have developed and extensively benchmarked a stack of models based on different optical flow algorithms for the tracking step, and a set of parsimonious extrapolation procedures based on image warping and advection. We demonstrate that these models provide skillful predictions comparable with or even superior to state-of-the-art operational software. Our software library (rainymotion) for precipitation nowcasting is written in Python programming language, and openly available at GitHub (https://github.com/hydrogo/rainymotion). That way, the library may serve as a tool for providing fast, free and transparent solutions that could serve as a benchmark for further model development and hypothesis testing – a benchmark that is far more advanced than the conventional benchmark of Eulerian persistence commonly used in QPN verification experiments.

Download Full-text

Classification of Clinically Significant Prostate Cancer on Multi-Parametric MRI: A Validation Study Comparing Deep Learning and Radiomics

Cancers ◽

10.3390/cancers14010012 ◽

2021 ◽

Vol 14 (1) ◽

pp. 12

Author(s):

Jose M. Castillo T. ◽

Muhammad Arif ◽

Martijn P. A. Starmans ◽

Wiro J. Niessen ◽

Chris H. Bangma ◽

...

Keyword(s):

Prostate Cancer ◽

Deep Learning ◽

Characteristic Curve ◽

Model Development ◽

Learning Model ◽

Multiparametric Mri ◽

Data Sets ◽

Data Set ◽

Test Sets ◽

Deep Learning Model

The computer-aided analysis of prostate multiparametric MRI (mpMRI) could improve significant-prostate-cancer (PCa) detection. Various deep-learning- and radiomics-based methods for significant-PCa segmentation or classification have been reported in the literature. To be able to assess the generalizability of the performance of these methods, using various external data sets is crucial. While both deep-learning and radiomics approaches have been compared based on the same data set of one center, the comparison of the performances of both approaches on various data sets from different centers and different scanners is lacking. The goal of this study was to compare the performance of a deep-learning model with the performance of a radiomics model for the significant-PCa diagnosis of the cohorts of various patients. We included the data from two consecutive patient cohorts from our own center (n = 371 patients), and two external sets of which one was a publicly available patient cohort (n = 195 patients) and the other contained data from patients from two hospitals (n = 79 patients). Using multiparametric MRI (mpMRI), the radiologist tumor delineations and pathology reports were collected for all patients. During training, one of our patient cohorts (n = 271 patients) was used for both the deep-learning- and radiomics-model development, and the three remaining cohorts (n = 374 patients) were kept as unseen test sets. The performances of the models were assessed in terms of their area under the receiver-operating-characteristic curve (AUC). Whereas the internal cross-validation showed a higher AUC for the deep-learning approach, the radiomics model obtained AUCs of 0.88, 0.91 and 0.65 on the independent test sets compared to AUCs of 0.70, 0.73 and 0.44 for the deep-learning model. Our radiomics model that was based on delineated regions resulted in a more accurate tool for significant-PCa classification in the three unseen test sets when compared to a fully automated deep-learning model.

Download Full-text

Automated Compartment Model Development Based on Data from Flow-Following Sensor Devices

Processes ◽

10.3390/pr9091651 ◽

2021 ◽

Vol 9 (9) ◽

pp. 1651

Author(s):

Jonas Bisgaard ◽

Tannaz Tajsoleiman ◽

Monica Muldbak ◽

Thomas Rydal ◽

Tue Rasmussen ◽

...

Keyword(s):

Large Scale ◽

Model Development ◽

Axial Flow ◽

Compartment Model ◽

Mixing Times ◽

Flow Rates ◽

Stirred Vessel ◽

Compartment Models ◽

Flow Models ◽

Sensor Devices

Due to the heterogeneous nature of large-scale fermentation processes they cannot be modelled as ideally mixed reactors, and therefore flow models are necessary to accurately represent the processes. Computational fluid dynamics (CFD) is used more and more to derive flow fields for the modelling of bioprocesses, but the computational demands associated with simulation of multiphase systems with biokinetics still limits their wide applicability. Hence, a demand for simpler flow models persists. In this study, an approach to develop data-based flow models in the form of compartment models is presented, which utilizes axial-flow rates obtained from flow-following sensor devices in combination with a proposed procedure for automatic zoning of volume. The approach requires little experimental effort and eliminates the necessity for computational determination of inter-compartmental flow rates and manual zoning. The concept has been demonstrated in a 580 L stirred vessel, of which models have been developed for two types of impellers with varying agitation intensities. The sensor device measurements were corroborated by CFD simulations, and the performance of the developed compartment models was evaluated by comparing predicted mixing times with experimentally determined mixing times. The data-based compartment models predicted the mixing times for all examined conditions with relative errors in the range of 3–27%. The deviations were ascribed to limitations in the flow-following behavior of the sensor devices, whose sizes were relatively large compared to the examined system. The approach provides a versatile and automated flow modelling platform which can be applied to large-scale bioreactors.

Download Full-text

Random forest predictive model development with uncertainty analysis capability for the estimation of evapotranspiration in an arid oasis region

Hydrology Research ◽

10.2166/nh.2020.012 ◽

2020 ◽

Vol 51 (4) ◽

pp. 648-665

Author(s):

Min Wu ◽

Qi Feng ◽

Xiaohu Wen ◽

Ravinesh C. Deo ◽

Zhenliang Yin ◽

...

Keyword(s):

Random Forest ◽

Uncertainty Analysis ◽

Predictive Model ◽

Air Temperature ◽

Model Development ◽

Influential Factor ◽

Weather Data ◽

Data Sets ◽

Oasis Area ◽

Lower Uncertainty

Abstract The study evaluates the potential utility of the random forest (RF) predictive model used to simulate daily reference evapotranspiration (ET0) in two stations located in the arid oasis area of northwestern China. To construct an accurate RF-based predictive model, ET0 is estimated by an appropriate combination of model inputs comprising maximum air temperature (Tmax), minimum air temperature (Tmin), sunshine durations (Sun), wind speed (U2), and relative humidity (Rh). The output of RF models are tested by ET0 calculated using Penman–Monteith FAO 56 (PMF-56) equation. Results showed that the RF model was considered as a better way to predict ET0 for the arid oasis area with limited data. Besides, Rh was the most influential factor on the behavior of ET0, except for air temperature in the proposed arid area. Moreover, the uncertainty analysis with a Monte Carlo method was carried out to verify the reliability of the results, and it was concluded that RF model had a lower uncertainty and can be used successfully in simulating ET0. The proposed study shows RF as a sound modeling approach for the prediction of ET0 in the arid areas where reliable weather data sets are available, but relatively limited.

Download Full-text

Transferability of intercity disaggregate mode choice models in Canada

Canadian Journal of Civil Engineering ◽

10.1139/l91-003 ◽

1991 ◽

Vol 18 (1) ◽

pp. 20-26 ◽

Cited By ~ 6

Author(s):

Walid M. Abdelwahab

Keyword(s):

Travel Behavior ◽

Travel Demand ◽

Mode Choice ◽

Model Development ◽

Predictive Ability ◽

Multinomial Logit ◽

Choice Models ◽

Data Sets ◽

Policy Analysts ◽

Transportation Studies

In many transportation studies, the time span of data collection, model development, and analysis is often too long to be responsive to the needs of policy analysts and decision makers. This problem is often exacerbated in situations with severely constrained analysis resources. Therefore, it is often useful to transfer a model from one area to another. Model transfer is defined as the application of a model developed in one area to describe the corresponding behavior in another area. This paper examines the transferability of a class of models used in intercity travel demand analysis. Specifically, disaggregate mode choice models of the multinomial logit type are developed for two regions in Canada, and some established measures of transferability are applied to assess the potential of calibrating these models in one region and applying them in the other. Comparison of mode choice models estimated on data sets from the two regions yielded inconclusive results regarding model transferability. In general, transferred models were found to be 18–23% less accurate than local models in predicting modal shares. Adjusting models' parameters to reflect observed modal shares in the application context improved the predictive ability of the models by about 10%. Key words: transferability, mode choice, disaggregate, travel behavior, multinomial logit, intercity.

Download Full-text

Electromechanical Actuator Test Stand Coupling Design to Support Actuator Prognostic Model Development

Volume 2: 31st Computers and Information in Engineering Conference, Parts A and B ◽

10.1115/detc2011-47869 ◽

2011 ◽

Author(s):

Michael T. Koopmans ◽

Irem Y. Tumer

Keyword(s):

Prognostic Model ◽

Model Development ◽

Uncertainty Assessment ◽

Test Stand ◽

System Level ◽

Data Sets ◽

Component Level ◽

Electromechanical Actuator ◽

Response Data ◽

Failure Data

Uncertainty assessment and management is becoming an increasingly essential aspect of good prognostic design for engineering complex systems. Uncertainty surrounding diagnostics, loads, and fault progression models is very real and propagating this uncertainty from component-level health estimates to the system-level remains difficult at best. In this work, a test stand is used to conduct real-time failure experiments aboard various aircraft platforms to collect failure response data, expanding the actuator knowledge base that forms the foundation of component health estimations. The research takes a step towards standardizing a test stand design to produce comparable and scalable failure data sets, fostering uncertainty reduction within the electromechanical actuator prognostic model. This paper specifically presents a method to optimize the actuator coupling for a commercially available actuator where a model was built to minimize the coupling deflection and estimate the coupling life. Using this model, researchers can rapidly develop their own electromechanical actuator test stands.

Download Full-text

MODELING CHILLING INFLUENCE ON CUMULATIVE FLOWERING OF RABBITEYE BLUEBERRY

HortScience ◽

10.21273/hortsci.27.6.609e ◽

1992 ◽

Vol 27 (6) ◽

pp. 609e-609

Author(s):

D.C. Bridges ◽

D.S. NeSmith

Keyword(s):

Distribution Function ◽

Weibull Distribution ◽

Model Development ◽

Growing Degree Days ◽

Data Sets ◽

Independent Data ◽

Degree Days ◽

Weibull Distribution Function ◽

Fruit Species

A Weibull distribution function was used to develop a model for estimating cumulative flowering and the distribution of flowers of `Tifblue' rabbiteye blueberry (Vaccinium ashei Reade) as a function of growing degree days (GDD) after chilling for chill hours ranging from 300 to 1200. Controlled chilling and flowering conditions were imposed on blueberry plants to obtain data for model development. Once developed the model was validated using independent data sets which were available in the literature. Given information concerning chilling and historical GDD, the model can be used to predict the onset of flowering, cumulative flowering, total number of flowers, and flower frequency at discrete intervals. It is expected that the techniques developed will be applicable to a range of fruit species in which chilling influences flowering habit.

Download Full-text

Optimizing the parameterization of mass flow models

Landslides and Engineered Slopes. Experience, Theory and Practice ◽

10.1201/9781315375007-135 ◽

2018 ◽

pp. 1195-1203

Author(s):

J. Krenn ◽

M. Mergili ◽

J.T. Fischer ◽

P. Frattini ◽

S.P. Pudasaini

Keyword(s):

Mass Flow ◽

Flow Models

Download Full-text

Comparison of MOBED and HEC-6 river flow models

Canadian Journal of Civil Engineering ◽

10.1139/l85-054 ◽

1985 ◽

Vol 12 (3) ◽

pp. 464-471 ◽

Cited By ~ 16

Author(s):

B. G. Krishnappan

Keyword(s):

River Flow ◽

Degradation Process ◽

Data Sets ◽

Predictive Tool ◽

Data Set ◽

Flow Models ◽

River Hydraulics ◽

Model Predictions ◽

River Reach ◽

Key Words Computers

The MOBED and HEC-6 models of river flow were compared in this study. The comparison consisted of two steps. In step one, the major differences between the models were identified by examining the theoretical base of each model. In step two, the predictive capabilities of the models were compared by applying the models to identical data sets. The data set comes from the South Saskatchewan River reach below Gardiner Dam and relates to the degradation process that has taken place since the creation of Lake Diefenbaker. Comparison of model predictions with measurements reveals that MOBED has predictive capability superior to that of HEC-6 and that use of HEC-6 as a predictive tool requires an extensive model calibration by the adjustment of Manning's 'n' and the moveable bed width. Key words: computers, models, sediment transport, river hydraulics erosion.

Download Full-text