Search

With climate change, decreases in winter snow storage and increases in precipitation duration and intensities will alter the occurrence of floods in high-latitude countries. The state-of-the-art hydrological climate-impact model chain consists of one or more global climate models, downscaling and bias-correction techniques, and one or more hydrological models. Machine learning offers a complementary approach to hydrological climate-impact modelling by facilitating direct downscaling from large-scale atmospheric variables to streamflow. This paper presents the development of multilayer perceptron (MLP) and long short-term memory (LSTM) neural networks benchmarked against regression tree models for reconstruction of daily streamflow and floods from atmospheric reanalysis data with comparable resolution to global climate model outputs. Catchment-specific, physically-based input features representing the dominant flood drivers were identified for 27 catchments in Norway. Overall, the LSTM obtained the highest accuracy. This article provides a springboard for future research on hydrological climate-impact modelling with neural networks in high-latitude countries. [ABSTRACT FROM AUTHOR]

The wellbore stability is an important issue in the drilling operation. Wellbore instability can interrupt the drilling and waste lots of time and money. The drilling mud is used to keep up the stability of the wellbore. Therefore, selecting the proper mud weight is an important issue in the drilling industry. The goal of this research is presenting an efficient mud weight estimator using deep learning techniques. To obtain this goal, a relatively big dataset (contained more than half-million samples) has been compiled from 116 wells of two fields in the United Kingdom and Norway. Our main contributions are assembling this large dataset, and applying the deep learning techniques to obtain efficient mud weight estimators. Our estimator is an artificial neural network with five hidden layers and 256 nodes in each layer that is able to estimate the mud weight for new wells and depths with the mean absolute error (MAE) of less than ±0.04 pound per gallon (ppg). In various experiments, the presented model has been challenged and the real-world conditions have been simulated. The results have shown that our model can be reliable and efficient in the real world. [ABSTRACT FROM AUTHOR]