The main challenges are discussed together with the lessons learned from past and ongoing research along the development cycle of machine learning systems. This will be done by taking into account intrinsic conditions of nowadays deep learning models, data and software quality issues and human-centered artificial intelligence (AI) postulates, including confidentiality and ethical aspects. The analysis outlines a fundamental theory-practice gap which superimposes the challenges of AI system engineering at the level of data quality assurance, model building, software engineering and deployment. The aim of this paper is to pinpoint research topics to explore approaches to address these challenges.

Inverse problems appear in multiple industrial applications. Solving such inverse problems require the repeated solution of the forward problem. This is the most time-consuming stage when employing inversion techniques, and it constitutes a severe limitation when the inversion needs to be performed in real-time. In here, we focus on the real-time inversion of resistivity measurements for geosteering. We investigate the use of a deep neural network (DNN) to approximate the forward function arising from Maxwell’s equations, which govern the electromagnetic wave propagation through a media. By doing so, the evaluation of the forward problems is performed offline, allowing for the online real-time evaluation (inversion) of the DNN.