Application of Neural Network and Dual-Energy Radiation-Based Detection Techniques to Measure Scale Layer Thickness in Oil Pipelines Containing a Stratified Regime of Three-Phase Flow

General machine learning concepts

It is beyond the scope of this article to give a detailed hands-on introduction to Deep Learning. There are many materials for this purpose, for example, the free online book “Neural Networks and Deep Learning” by Michael Nielsen (http://neuralnetworksanddeeplearning.com), Deep Learning by Goodfellow et al.21, and multiple online courses at Coursera, Udemy, and so on. Rather, this article aims to motivate materials scientist researchers in the types of problems that are amenable to DL, and to introduce some of the basic concepts, jargon, and materials-specific databases and software (at the time of writing) as a helpful on-ramp to help get started. With this in mind, we begin with a very basic introduction to Deep learning.
Artificial intelligence (AI)13 is the development of machines and algorithms that mimic human intelligence, for example, by optimizing actions to achieve certain goals. Machine learning (ML) is a subset of AI, and provides the ability to learn without explicitly being programmed for a given dataset such as playing chess, social network recommendation etc. DL, in turn, is the subset of ML that takes inspiration from biological brains and uses multilayer neural networks to solve ML tasks. A schematic of AI-ML-DL context and some of the key application areas of DL in the materials science and engineering field are shown in Fig. 1.
Fig. 1: Schematic showing an overview of artificial intelligence (AI), machine learning (ML), and deep learning (DL) methods and its applications in materials science and engineering.

Deep learning is considered a part of machine learning, which is contained in an umbrella term artificial intelligence.
Some of the commonly used ML technologies are linear regression, decision trees, and random forest in which generalized models are trained to learn coefficients/weights/parameters for a given dataset (usually structured i.e., on a grid or a spreadsheet).
Applying traditional ML techniques to unstructured data (such as pixels or features from an image, sounds, text, and graphs) is challenging because users have to first extract generalized meaningful representations or features themselves (such as calculating pair-distribution for an atomic structure) and then train the ML models. Hence, the process becomes time-consuming, brittle, and not easily scalable. Here, deep learning (DL) techniques become more important.
DL methods are based on artificial neural networks and allied techniques. According to the “universal approximation theorem”50^,51, neural networks can approximate any function to arbitrary accuracy. However, it is important to note that the theorem doesn’t guarantee that the functions can be learnt easily52.