Services Main Text

AI ELM

Artifcial Intelligence (AI) platforms

Artifcial Intelligence (AI) platforms have shown their ability in learning and solving incomplete information problems. With extremely large training samples, AI can self-adapt to evolve into experienced masters of many application areas.

Automation and artificial intelligence are terms that have been thrown around interchangeably, but there is a distinction. Automation is about replacing mostly repetitive tasks, with machines. Automation has been in heavy use in factory processes for almost a century. Software has also automated many tasks such as matching data records, looking for exceptions and making calculations. Artificial intelligence is about replacing human decision making with more sophisticated technologies. These are not repetitive tasks, but rather judgment-based work which requires complex set of algorithms and machine learning which can use a variety of inputs to recognise patterns, predict future outcomes and make decisions.

PetroFinde Introduction

AI’s application in financial markets, with significantly large amounts of publicly available data, including news, social media, company reports, analyst reports, price-volume data spanning a 20 year period or longer as well as many other information sources, an analysis and predictive system can be trained to produce market / financial indicators, generate trading signals, construct trading portfolios, and perform risk management.

PetroFinde Introduction

Oil and gas exploration in sedimentary basins is very complicated, since all the targets are buried underground and they cannot be viewed or touched directly. So all the properties for the buried targets have to be predicted or estimated by using modern electrical or magnetic tools. e physical properties of the geologic formations include pored pressure, rock lithology, porosity, permeability, and oil or water saturation. Nowadays the conventional tool for characterising these geophysical properties is well logging, and some logs such as gamma ray (GR), dual induction log, formation density (DEN) compensated, deep resistivity (REID), self-potential (SP), and sonic log (DT) are usually recorded. Among them, the sonic log (DT) has largely been used to predict rock porosity, to perform petrophysical analysis, or to carry out well-to-seismic inversion.

Owing to historical operation mistakes or recording loss, the sonic log may not be available in well logging suites. A traditional way of solving this problem is to transform the DEN or REID log to DT log based on some experimental formula built between these logs. Although feasible for some areas, the occurring errors are unacceptable.

Artificial intelligence techniques have the advantage in connecting unrelated parameters and solving nonlinear problems. Such techniques, including BP neural network, fuzzy reasoning, or evolutionary computing for data anal- ysis and interpretation have become effective tools in the work for well drilling and reservoir characterisation. However, traditional neural networks have many known drawbacks in the learning process, such as multiple local minima, slow learning speed, and poor generalisation performances.