Deep Similarity Learning for Well Test Model Identification

Over the years, well test analysis or pressure transient analysis (PTA) methods have progressed from straight lines via type curve analysis to pressure derivatives and deconvolution methods. Today, analysis of the log-log (pressure and its derivative) response is the most used method for PTA. Although these methods are widely available through commercial software, they are not fully automated, and human interaction is needed for their application. Furthermore, PTA is described as an inverse problem, whose solution in general is non-unique, and several models (well, reservoir and boundary) can be found applicable to similar pressure-derivative response. This tends to always bring about confusion in choosing the correct model using the conventional approach. This results in multiple iterations that are time consuming and requires constant human interaction. Our approach automates the process of PTA using a Siamese neural network (SNN) architecture comprised of Convolutional neural network (CNN) and Long Short-Term Memory (LSTM) layers. The SNN model is trained on simulated experimental data created using a design of experiments (DOE) approach involving most common 14 interpretation scenarios across well, reservoir, and boundary model types. Across each model type, parameters such as permeability, horizontal well length, skin factor, and distance to the boundary were sampled to compute 560 different pressure derivative responses. SNN is trained using a self-supervised training strategy where the positive and negative pairs are generated from the training data. We use transformations such as compression and expansion to generate positive pairs and negative pairs for the well test model responses. For a given well test model response, similarity scores are computed against the candidates in each model class, and the best match from each class is identified. These matches are then ranked according to the similarity scores to identify optimal candidates. Experimental analysis indicated that the true model class frequently appeared among the top ranked classes. The model achieves an accuracy of 93% for the top one model recommendations when tested on 70 samples from the 14 interpretation scenarios. Prior information on the top ranked probable well test models, significantly reduces the manual effort involved in the analysis. This machine learning (ML) approach can be integrated with any PTA software or function as a standalone application in the interpreter's system. Current work using SNN with LSTM layers can be used to speed up the process of detecting the pressure derivative response explained by a certain combination of well, reservoir and boundary models and produce models with less user interaction. This methodology will facilitate the interpretation engineer in making the model recognition faster for detailed integration with additional information from sources such as geophysics, geology, petrophysics, drilling, and production logging.

Pengaruh Pengunaan Model Jigsaw Terhadap Kemampuan Mengidentifikasi Teks Ceramah Siswa Kelas XI SMK Negeri 3 Padang

This research is motivated by the problem that some students do not understand the material about identifying lecture texts. The purpose of this study was to describe the ability to identify lecture texts for class XI students at SMK N 3 Padang without and using the Jigsaw learning model, and to describe the effect of the Jigsaw learning model on the ability to identify lecture texts for class XI students at SMK N 3 Padang. This type of research is quantitative research. The design of this study was a posttest only control design. The population in this study were class XI students of SMK N 3 Padang who were registered in 2019/2020. The research sample consisted of 30 control classes and 30 sample classes. The data of this study is the score of the test results of the ability to identify lecture texts without and using the Jigsaw learning model. Based on the results of the study, it was concluded as follows: First, the level of Ability to Identify Lecture Texts without using the Jigsaw model, class XI students of SMK N 3 Padang obtained an average score of 71.30 with a classification of 66-75%, which is more than adequate (LdC). Second, the level of ability to identify lecture texts after using the Jigsaw model, class XI students of SMK N 3 Padang obtained an average score of 79.68 with a classification of 76-85%, which is good (B). Third, from the results of data analysis that has been carried out that the use of the Jigsaw model has a significant effect on increasing the ability to identify lecture texts, it can be seen that the alternative hypothesis (H1) is accepted at a significant level of 95% and dk = n-2 because tcount > ttable ( 5.17 > 1.67).

Is eliciting dependency worth the effort? A study for the multivariate Poisson-Gamma probability model

We examine whether it is worthwhile eliciting subjective judgements to account for dependency in a multivariate Poisson-Gamma probability model. The challenge of estimating reliability during product design motivated the choice of model class. For the multivariate Poisson-Gamma model we adopt an empirical Bayes methodology to present an estimator with improved accuracy. A simulation study investigates the estimation error of this estimator for different degrees of dependency and examines the impact of dependency being mis-specified when assessed by subjective judgement. Our theoretical and simulation findings give analysts insights about the value of eliciting dependency.

Comparison of Collaborative Learning Models to Improve Programming Competence

The purpose of this research is how collaborative learning strategies should be arranged in three classes as Wang & Hwang model class, control class and experimental class with different treatments in Algorithm and Programming courses. Three learning strategies were tested to see students' cognitive abilities in computer programming skills. Three collaborative learning scenarios were tested, namely: 1) conventional collaborative learning 2) problem-based collaborative learning using an online environment and 3) inquiry-based collaborative learning also using an online environment. The results of the t-test with the one-way ANOVA test showed that the pretest results of the students' ability levels were not different because they had not been treated. While the results of the t-test with the posttest t-test results obtained a very significant difference in student final results, namely the control class 71.30, Wang & Hwang model class 73.0 and the experimental class 81.13. The benefit of the results of this study is that collaborative learning with an inquiry approach allows students to transfer knowledge and does not make lecturers the only source of learning

On the selection of the most plausible non-linear axial stress–strain model for railway ballast under different impulse magnitudes

The effective maintenance and health monitoring of ballasted railway tracks, which involves the determination of differential settlement, track support stress and stiffness, and the strain-hardening property of ballast, is essential. The vertical stress–strain behavior of the ballast layer is primarily responsible for the irrecoverable strains and settlements in tracks, leading to further track degradation. This article reports the development of a series of applicable yet simple uniaxial models and the selection of the most plausible one for capturing the behavior of vertical stresses and strains in ballasts utilizing a set of measured vibration data of the rail–sleeper–ballast system from a Bayesian perspective. From the literature, the dynamic behavior of ballast can be divided into linear and non-linear regions. Under small amplitude vibration, the stress–strain property is linear and elastic, while the behavior becomes non-linear and inelastic once the elasticity limit is exceeded. By integrating the linear phase to some well-known non-linear engineering material laws, a list of new ballast stress–strain model classes was developed. An enhanced Markov chain Monte Carlo–based Bayesian scheme was utilized to explicitly handle the uncertainties in the model updating process, while the Bayesian model class selection method was employed to select the most plausible ballast stress–strain model class under the prevailing system conditions. The proposed methodology was verified using three sets of measured acceleration data from impact hammer tests on an in situ sleeper with simulated ballast damage. The obtained results suggest that the linear-elastic model is sufficient for small amplitude vibrations, while the modified Voce model is the most plausible amongst the investigated model classes for high impact load. The results also demonstrate the importance of the non-linear ballast model in ballast damage identification and the potential applicability of the selected ballast model in field track monitoring.

Improving Science Learning Outcomes About the Solar System Using the STAD Model Class VI SDN 1 Rawoh

<pre><em>This study purpose to improve learning outcomes in Science Theme 9 Sub-theme 2 about the solar system in grade VI students of SD Negeri 1 Rawoh, Karangrayung District, 2019/2020 academic year. This study uses a Classroom Action Research (CAR) model which is carried out in 2 cycles. The results showed that there was an increase in student learning outcomes using the STAD (Student Teach Achievement Division) cooperative method. In the pre-cycle stage of 24 students who achieved learning completeness 6 students (25%). Then in the first cycle of learning completeness reached 17 students (70.83%) and in the second cycle there was an increase to 23 students (95.83%). So the conclusion of this study shows that learning with the STAD type cooperative method improves science learning outcomes about the solar system in grade VI students of SD Negeri 1 Rawoh, Karangrayung District, semester II of the 2019/2020 school year.</em></pre>

Improved Mathematical Problem Solving Ability and Self Efficacy of Class VIII Students of SMP Negeri 1 Percut Sei Tuan through Problem Based Learning Models

This study aims to describe whether the increase in mathematical problem solving abilities and Self Efficacy of students who are taught using problem-based learning models is higher than students who are taught with ordinary learning, to describe whether there is an interaction between students' initial mathematical abilities and learning towards increased mathematical problem solving abilities. students, as well as to describe whether there is an interaction between students' initial mathematical abilities and learning towards increasing student Self-Efficacy. Based on the ANOVA 2 x 2 calculation, it is obtained Fcount = 88.82 while the Ftable value = 2.36 for dk (1.62) and a significant level of 5%. It turns out that the value of Fcount> Ftable, so that Ho is rejected and Ha is accepted. Then from table 4. The probability value (sig) is smaller than 0.05 so that H0 is rejected. Thus it can be concluded that the results of students' mathematical problem-solving abilities taught by problem-based learning models are better than those taught with ordinary learning models. The results of students' Self Efficacy in the problem-based learning model class were higher than in the ordinary learning model class. This can also be seen from the average results of the mathematics Self Efficacy questionnaire of students with the experimental class (99.7) which are higher than the average results of the mathematics Self Efficacy questionnaire of students with the control class (96.8). The results of students' Self Efficacy in the problem-based learning model class were higher than in the ordinary learning model class. This can also be seen from the average results of the mathematics Self Efficacy questionnaire of students with the experimental class (99.7) which are higher than the average results of the mathematics Self Efficacy questionnaire of students with the control class (96.8).X ̅=X ̅=