Arabic is a complex language with limited resources which makes it challenging to produce accurate text classification tasks such as sentiment analysis. The utilization of transfer learning (TL) has recently shown promising results for advancing accuracy of text classification in English. TL models are pre-trained on large corpora, and then fine-tuned on taskspecific datasets. In particular, universal language models (ULMs), such as recently developed BERT, have achieved state-of-the-art results in various NLP tasks in English. In this paper, we hypothesize that similar success can be achieved for Arabic. The work aims at supporting the hypothesis by developing the first Universal Language Model in Arabic (hUL-MonA-meaning our dream), demonstrating its use for Arabic classifications tasks, and demonstrating how a pre-trained multilingual BERT can also be used for Arabic. We then conduct a benchmark study to evaluate both ULM successes with Arabic sentiment analysis. Experiment results show that the developed hULMonA and multilingual ULM are able to generalize well to multiple Arabic data sets and achieve new state of the art results in Arabic Sentiment Analysis for some of the tested sets.

No abstract

No abstract

In this paper, we discuss the development of an end-to-end waterflood optimization solution that provides monitoring and surveillance dashboards with artificial intelligence (AI) and machine learning (ML) components to generate and assess insights into waterflood operational efficiency in an automated manner. The solution allows for fast screening of waterflood performance at diverse levels (reservoir, sector, pattern, well) enabling prompt identification of opportunities for immediate uptake into an opportunity management process and for evaluation in AI-driven production forecast solution and/or a reservoir simulator. The process starts with the integration of a wide range of production and reservoir engineering data types from multiple sources. Following this, a series of monitoring and surveillance dashboards of key units and elements of the entire waterflood operations are created. The workflows in these dashboards are framed with key waterflood reservoir and production engineering concepts in mind. The optimization opportunity insights are then extracted using automated traditional and AI/ML algorithms. The identified opportunities are consolidated in an optimization action list. This list is passed to an AI-driven production forecast solution and/or a reservoir simulator to assess the impact of each scenario. The system is designed to improve the business-time decision-making cycle, resulting in increased operational performance and lower waterflood operating costs by consolidating end-to-end optimization workflows in one platform. It incorporates both surface and subsurface aspects of the waterflood and provides a comprehensive understanding of waterflood operations from top-down field, reservoir, sector, pattern and well levels. Its AI/ML components facilitate understanding of producer-injector relationships, injector dynamic performance, underperformance of patterns in the sector as well as evaluating the impact of different optimization scenarios on incremental oil production. The data-driven production forecast component consists of several ML models and is tailored to assess their impact on oil production of different scenarios such as changes in voidage replacement ratio (VRR) in reservoir, sector, pattern and well levels. Opportunities are also converted into reservoir simulator compatible format in an automated manner to assess the impact of different scenarios using more rigorous numerical methods. The scenarios that yield the highest impact are passed to the field operations team for execution. The solution is expected to serve as a benchmark, upon successful implementation, for optimizing injection schemas in any field or reservoir. The novelty of the system lies in automating the insights generation process, in addition to integrating with an AI/ML production forecasting solution and/or a reservoir simulator to assess different optimization scenarios. It is an end-to-end solution for waterflood optimization because of the integration of various components that allow for the identification and assessment of opportunities all in one environment.

Gas injection pressure-volume-temperature (PVT) laboratory data play an important role in assessing the efficiency of enhanced oil recovery (EOR) processes. Although typically there is a large conventional PVT data set, gas injection laboratory studies are relatively scarce. On the other hand, performing EOR laboratory studies may be either unnecessary in the case of EOR screening, or unfeasible in the case when reservoir fluid composition at current conditions is different from initial conditions. Given that gas injection is to be widely assessed as an optimal EOR process, there is increased demand on time- and cost-effective solutions to predict the outcome of associated gas injection lab experiments. While machine learning (ML) is extensively used to predict black-oil properties, it is not the case for compositional reservoir properties, including those related to gas injection. Can we use the typically extensive conventional laboratory data to help predict the needed gas injection parameters? This is the core of this paper. We present an ML-based solution that predicts pertinent gas injection studies from known fluid properties such as fluid composition and black oil properties. That is, learning from samples with gas injection laboratory studies and predicting gas injection fluid parameters for the remaining, much larger, data set. We applied the proposed algorithms on an extensive corporate-wide database. Swelling tests were predicted using the trained ML models for samples lacking gas injection laboratory data. Several ML models were tested, and results were analyzed to select the most optimal one. We present the algorithms and the associated results. We discuss associated challenges and applicability of the proposed models for other fields and data sets.