This book presents a comprehensive overview of state‑of‑the‑art research at the intersection of machine learning, network science, and Earth and climate sciences. This book places particular emphasis on causal and explainable machine learning approaches, alongside predictive modeling techniques, as applied to climate data. These methodologies are introduced and discussed through representative research studies published in recent years. A substantial number of the case studies focus on the Indian Monsoon, a complex and critically important climatic phenomenon that profoundly influences the lives and livelihoods of more than a billion people across South Asia. This book begins with two introductory chapters. The first chapter outlines the ongoing climate crisis and introduces Earth System Models, highlighting their key limitations and the challenges they face. It also provides a perspective on how machine learning and artificial intelligence can help address some of these challenges. The second chapter offers a concise primer on the Indian Monsoon, describing its fundamental characteristics, variability, and the major scientific questions for which AI‑ and ML‑based approaches may offer new insights. The subsequent chapters each focus on a specific methodological theme—such as network‑based analysis, causal inference, explainable machine learning, or predictive modeling—providing conceptual explanations alongside concrete examples drawn from recent research literature. Through these chapters, this book demonstrates how modern data‑driven methods can be applied to longstanding problems in monsoon and climate science. This book is designed for graduate students and early‑career researchers in climate and Earth sciences who seek to incorporate machine learning and data science into their research.

Adway Mitra is an assistant professor in the Department of Artificial Intelligence, Indian Institute of Technology Kharagpur. He obtained his Ph.D. from Indian Institute of Science, Bangalore in 2016. His main area of research is machine learning applied to the domain of Earth and Climate Science, especially Indian Monsoon. He has been working on this topic for almost 10 years and has published a number of research papers in reputed journals in this domain. These papers focus on important problems related to extracting spatio-temporal patterns of Indian Monsoon rainfall, identifying its causal drivers, downscaling rainfall estimates to high resolution and correcting for biases in simulations, evaluating climate model simulations and developing machine learning based surrogates for such models. He has advised multiple Masters' and PhD students, and also led a number of workshops, summer/winter schools and conference sessions to promote research collaborations between climate scientists and AI scientists

Auroop Ratan Ganguly is a COE distinguished professor at Northeastern University in Boston, MA, where his research in sustainability and security blends process understanding and physics models with data science methods ranging from nonlinear dynamics and extreme value analysis to machine learning and artificial intelligence. Ganguly holds a joint appointment as a chief scientist at the Pacific Northwest National Laboratory and has 28 years’ prior experience including at the US DOE’s Oak Ridge National Laboratory and Oracle Corporation. He has published in high-impact journals such as Nature, Science, and PNAS, delivered keynotes at the United Nations and US National Academy, won awards at major AI and data mining conferences, participated in $72 Million of funded research, and been highlighted by global media including Newsweek, The New York Times, and The Wall Street Journal.