Data Science and Cases in Sustainability

This book discusses the fascinating world of data science and cases in sustainability focusing on topics related to pattern recognition and machine learning, emphasizing applications that directly address topics related to SDG 9 (Industry, Innovation and Infrastructure). Recognizing the sustainable applications of big data, this text emphasizes the shift from traditional statistical analyses to more sophisticated methods. Each of these techniques—pattern recognition and machine learning—plays a crucial role in extracting hidden knowledge from vast amount of data. Targeted to students, researchers and professionals, it highlights the multidisciplinary and sustainable nature of the field and showcasing real-world applications and equips the readers to navigate the data-driven future.


The first of the two volumes, the book highlights the multidisciplinary nature of data science in the fields of computer science, statistics, physics and economics. It meticulously guides its readers through the data science workflow, covering data collection, preparation, storage, analysis, management and visualization. It highlights specific techniques and algorithms used in each of the above-mentioned stages and offers explanations of major learning mechanisms: dimensionality reduction, classification, clustering and outlier analysis. Additionally, it sheds light on the modern field of deep learning and unfolds the complexity of its mechanism with explanation. Case studies showcase the practical applications and successes of data science across various domains.