Data integration

Clustering well-log data into electrofacies using machine learning with a purely unsupervised approach, cluster-number optimization, and outlier removal based on spatial autocorrelation.

An Active Learning strategy for a well-known image classification problem, classically used in Machine Learning benchmarks.

Utilizing a graph view serves as the intuitive method to display categorizations, interconnections between related documents, and meta-information pertaining to the documents.

An innovative method to automatically generate maps of prospectivity, based on Machine Learning and multicriteria decision analysis.

Field trips are increasingly limited by budget, safety, footprint or inclusion issues

EOR choices are often addressed with circular processes, increasing decision time without necessarily improving final choice

Companies often accumulate very large amounts of documents stored in multiple folders

For mature fields, a long history of production data is often available, but the impact of geological factors remains hard to assess

Well logs interpretation is often rather subjective and highly time-consuming

It is often burdensome to handle large amounts of wells files

Development scenarii must optimize production or injection but consider technical and logistical constraints