Название: Machine Learning for Civil and Environmental Engineers: A Practical Approach to Data-driven Analysis, Explainability, and CausalityАвтор: M. Z. Naser
Издательство: Wiley
Год: 2023
Страниц: 610
Язык: английский
Формат: pdf (true)
Размер: 39.5 MB
Accessible and practical framework for machine learning applications and solutions for civil and environmental engineers
This textbook introduces engineers and engineering students to the applications of Artificial Intelligence (AI), Machine Learning (ML), and machine intelligence (MI) in relation to civil and environmental engineering projects and problems, presenting state-of-the-art methodologies and techniques to develop and implement algorithms in the engineering domain.
Through real-world projects like analysis and design of structural members, optimizing concrete mixtures for site applications, examining concrete cracking via computer vision, evaluating the response of bridges to hazards, and predicating water quality and energy expenditure in buildings, this textbook offers readers in-depth case studies with solved problems that are commonly faced by civil and environmental engineers.
The approaches presented range from simplified to advanced methods, incorporating coding-based and coding-free techniques. Professional engineers and engineering students will find value in the step-by-step examples that are accompanied by sample databases and codes for readers to practice with.
In general, there are three types of learning that ML can fall under; supervised learning, unsupervised learning, and semi-supervised learning. Supervised learning is a learning process that involves inputs (x1, x2, … xn) and an output variable(s) (Y); however, a function, f(x), that represents the relation between inputs, as well as inputs and outputs is not known nor is easily derivable. Hence, the main goal behind supervised learning is to map the inputs to the output. Supervised learning can be divided into: regression (when the output variable is numeric, i.e., moment capacity of a beam, number of vehicles passing through an intersection, concentration of pollutants in air, etc.) and classification (when the output is a categorical variable, i.e., failure/no failure, minor damage/major damage/collapse).
Unsupervised learning can answer the above questions. This type of learning aims to discover the underlying structure/distribution of the data and is often grouped into clustering (grouping by behavior21 i.e., concretes of dense micro-structure tend to have a relatively high compressive strength, drivers under the influence tend to be prone to accidents, etc.), dimensionality reduction (e.g., out of all the features related to a specific phenomenon, can we identify the main features? For example, concrete mixtures comprise a multitude of raw materials. Which are such key materials that are directly related to the strength property?) and association rules (discover rules that describe the data, i.e., bridges made from green construction material tend to have a lower damaging impact on the environment, etc.).
The third type of learning is that known as semi-supervised learning. This learning process is suited where only some of the outputs are labeled (i.e., in a dataset of images, some images showing cracked buildings are labeled as such while others are not). As such, an algorithm tries to learn from the smaller (labeled) data to identify the labels of the unlabeled data correctly. Semi-supervised learning includes other types of learning such as active, transfer, reinforcement, and self-supervised learning.
The simplest of all solutions was to adopt a coding-free approach to ML where engineers with limited knowledge/resources of programming can still leverage the full potential of ML without the need to resort to traditional coding. Thus, this chapter offers a look into the two main approaches to practicing ML, coding-free and coding-based. In this journey, we will go over a few platforms that I found most suitable for engineers, and especially students, to implement and use. All of the presented platforms offer free services to engineering students and hence are adopted in this chapter. Along the way, we will cover the origins and capabilities of such platforms. Toward the end of this chapter, we will cover the use of Python and R as representatives of coding-based approaches. In all cases, I have supplemented my discussions with a series of examples and tutorials. I have listed and appended these here for you to practice along the way.
Written by a highly qualified professional with significant experience in the field, Machine Learning includes valuable information on:
• The current state of machine learning and causality in civil and environmental engineering as viewed through a scientometrics analysis, plus a historical perspective
• Supervised vs. unsupervised learning for regression, classification, and clustering problems
• Explainable and causal methods for practical engineering problems
• Database development, outlining how an engineer can effectively collect and verify appropriate data to be used in machine intelligence analysis
• A framework for machine learning adoption and application, covering key questions commonly faced by practitioners
This textbook is a must-have reference for undergraduate/graduate students to learn concepts on the use of Machine Learning, for scientists/researchers to learn how to integrate Machine Learning into civil and environmental engineering, and for design/engineering professionals as a reference guide for undertaking MI design, simulation, and optimization for infrastructure.
Скачать Machine Learning for Civil and Environmental Engineers