The ever-growing number of venues publishing academic work makes it difficult for researchers to identify venues that publish data and research most in line with their scholarly interests. A solution is needed, therefore, whereby researchers can identify information dissemination pathways in order to both access and contribute to an existing body of knowledge.In this study, we present a system to recommend scholarly venues rated in terms of relevance to a given researcher's current scholarly pursuits and interests. We collected our data from an academic social network and modeled researchers' scholarly reading behavior in order to propose a new and adaptive implicit rating technique for venues. We present a way to recommend relevant, specialized scholarly venues using these implicit ratings that can provide quick results, even for new researchers without a publication history and for emerging scholarly venues that do not yet have an impact factor. We performed a large-scale experiment with real data to evaluate the current scholarly recommendation system and showed that our proposed system achieves better results than the baseline. The results provide important up-to-the-minute signals that compared with postpublication usage-based metrics represent a closer reflection of a researcher's interests.

No abstract

Acid-fracturing operations are mainly applied in tight carbonate formations to create a highly conductive path. Estimating the conductivity of a hydraulic fracture is essential for predicting the fractured well productivity. Several models were developed previously to estimate the conductivity of acid-fractured rocks. In this research, machine learning methods were applied to 560 acid fracture experimental datapoints to develop several conductivity correlations that honor the rock types and etching patterns. Developing one universal correlation often results in significant error. To develop conductivity correlations, various data preprocessing methods were applied to remove the outliers and failed experiments. Features that did not contribute to precise predictions were removed through regularization. A machine learning classifier was built to predict the etching pattern based on the input data. We generated a multivariate linear regression model and compared it with other models generated through ridge regression. In addition to that, artificial neural network-based model was proposed to predict the fracture conductivity of several carbonate rocks such as dolomite, chalk, and limestone. The performance of the developed models was assessed using well-known metrics such as precision, accuracy, mean squared error, recall, and correlation coefficients. Cross-validation was also employed to assure accuracy and avoid overfitting. The classifier accuracy was 93%, while the regression model resulted in a relatively high correlation coefficient.

No abstract