دانلود کتاب یادگیری ماشین در مهندسی عمران و توسعه زیرساخت‌ها

Machine learning (ML) no longer sits at the edges of civil engineering practice. Yet for many practising engineers, ML still feels like something that belongs to computer science or data science – a powerful but distant set of methods, rather than a natural extension of the modelling and empirical thinking they already use every day which are, in fact, embedded in various building codes. Machine Learning in Civil Engineering and Infrastructure Development: A Practitioner’s Handbook was conceived to narrow that gap. This is not a theoretical volume on algorithms, nor a collection of opaque code snippets. This handbook is a practitioner oriented volume that shows, through diverse examples, how civil engineers can incorporate ML into real projects while remaining grounded in engineering judgement, physical understanding and professional responsibility. The book rests on three straightforward premises. First, civil engineering is becoming irreversibly data-rich, as we continue to collect measurements from sensors, images from drones and phones, time-series data from environmental monitors, and large archives of test results and project records. Second, ML provides a flexible toolkit for extracting patterns and making predictions from this data ‒ especially when we respect the role of physics, uncertainty and domain expertise. Third, engineers remain central, where ML should augment, not replace, the professional’s ability to reason, critique results and make decisions that affect public safety and societal wellbeing. To align with these premises, the chapters housed in this book are organised into three parts that move from foundations and modelling philosophy, through structural and material behaviour, to systemlevel applications and questions of practice, ethics and education. The progression is intentional: readers first encounter overarching concepts and mindsets, then see them applied to components and materials, and finally explore how these tools are implemented in infrastructure systems, risk management and the modernisation of the profession.