... in the industry in terms of detection speed. upstream oil & gas neural network machine learning dataset europe government detection time deep learning well control real-time drilling data test dataset prediction false alarm rate algorithm detection model annular pressure drilling...

..., and their production throughput. One of the challenges is that the size of the dataset is less than 200 data points, largely due to the limited total number of FPSOs worldwide. Another challenge is that there are missing values for gas production, as such, imputation of missing values becomes necessary. In this study...

.... artificial intelligence background detection machine learning industrial facility variation application algorithm optimization problem accuracy productivity turnaround health & medicine dataset inspection monitoring safety milestone automation offshore technology conference scenario...

... of ANN and ANFIS models is performed using graphical and statistical analysis. The developed models are tested on an unseen dataset to verify their efficiency. An error metrics analysis, comprising of average percentage error, root mean squared error, and the correlation coefficientis performed...

... conference flowline corrosion artificial intelligence upstream oil & gas inspector high-risk defect point cloud prioritization detection dataset linear transformation correction model computer fabric maintenance inspection inspection window measurement method height measurement blister...

... quality dataset. In practice, operators have access to a detailed data repository. However, the learnings from historical jobs may be overlooked during dynamic real time operations and engineers may typically regress to simpler or experienced based models. Some of the methods are self-made to reduce time...

... characterize how the receptor responds to the stressor, such as attraction, avoidance, and behavioral change. A tag list coupled with the project's spatial location will filter all the documents and datasets linked to the Toolkit and provide information pertinent to the regulator's investigation...

... on a robust, well-documented workflow; however, some assessment areas lack sufficient data coverage or only contain vintage geologic and geophysical datasets. Machine Learning (ML) techniques may be useful in these situations to fill in data gaps, predict new data, and recognize outliers. In this study, ways...

... detection reconstruction error frequency koizumi ultrasound region international conference spectrogram drilling machine machine type artificial intelligence upstream oil & gas audio clip khz produce noise conveyor uematsu dataset offshore technology conference waive analysis...

...), XGBoost Model, and random forests (RF) as machine learning (ML) tools to predict the contact angle in the coal–water–CO 2 system. A dataset of 250 points was collected for different coal samples at different conditions. The ML methods were used to predict coal-water–CO 2 contact angle (CA) as a function...

... classification and permeability modelling, random sub-sampling cross-validation was applied to the well-log dataset to generate two subsets: training subset for model tuning; and testing subset for prediction of data points unseen during training of the model. Confusion matrices and the total correct percentage...

... assumption fpso design assumption dataset mooring system information assumption footprint moored unit weather failure mechanism calibration weather data antenna Introduction This paper explains how comparisons are currently being utilized to ensure that asset integrity is monitored...

... otherwise remain elusive when examined through individual test datasets. This database and the populated framework provides guidance to pipeline and geotechnical engineers in the form of a basis for initial estimates of axial and lateral friction of pipelines on sand and an approach for improving...

... and Nowcasting The approach is based on a unique processing of satellite (both geostationary and low earth orbit), lightning networks, radar (where available), and NWP model datasets with machine learning techniques trained against ground and space-borne radar to continuously improve the results...

... treatment modeling reservoir extra-tree model petrobras dataset water cut offshore technology conference water-in-oil emulsion rheology model Introduction Offshore oil exploitation and production bring massive challenges, especially in deep and ultra-deepwater depths. The formation...

... costs. Supervised machine learning algorithms have been successful to detect, diagnose, and forecast anomalous events in O&G industry. Nevertheless, these algorithms need a large quantity of annotated dataset and labelling data in real world scenarios is typically unfeasible because of exhaustive...

... Two distinct computational intelligence algorithms, Artificial-Neural-Network and Adaptive-Neuro-Fuzzy-Inference-System were studied and utilized to develop predictive models for oil formation volume factor. Model development was performed on a dataset extracted from published literature...

... canbaz modeling application realization complex reservoir reserves evaluation grid number cumulative oil production fracture hyperparameter petroleum engineer dataset technology conference Reservoir Proxy and Surrogate Models Table 1 Primary parameters ( Li et al., 2016...

... Abstract The Gulf of Mexico's unique circulation characteristics pose a particular threat to marine operations and play a significant role in driving the criteria used for design and life extension analyses of offshore infrastructure. Estimates from existing reanalysis datasets used...

... and the much higher-level features coming from the upsampling path. From the primary results using the TGS Salt Identification Challenge dataset, the MultiResU-Net outperformed the classic U-Net in identifying salt bodies and showed good agreement with the ground truth. Additionally, in the case of complex...