This special issue is devoted to original and innovative applications of statistical methods to the study of the meteorological drivers of weather and climate extremes, such as atmospheric moisture transport or heat transport. The relationship between these meteorological drivers and the occurrence of droughts, combined drought–heat waves, extreme precipitation, and floods will be a key topic of this issue. It also includes the role of land–atmosphere interactions in the occurrence and development of those natural hazards.

Statistics have a long-standing relationship with climate and weather sciences, spanning a variety of techniques (from probabilistic forecasting to the analysis of complex phenomena, forecast evaluation, and extreme-event modelling). The emergence of machine learning (ML) and artificial intelligence (AI), as well as their ability to make sense of complex datasets, has created new opportunities in the scientific community. AI and ML offer the potential to overcome computational and modelling barriers, such as the complex interactions among co-occurring processes and scalability to large datasets, that have been historically prohibitive in advancing climate and weather sciences. This special issue focuses on recent advances in ML and AI in climate and weather sciences. Topics on synergies between ML/AI and statistics in the context of atmospheric sciences are highly welcomed.

This special issue is devoted to original and innovative applications of statistical methods to the study of the meteorological drivers of weather and climate extremes, such as atmospheric moisture transport or heat transport. The relationship between these meteorological drivers and the occurrence of droughts, combined drought–heat waves, extreme precipitation, and floods will be a key topic of this issue. It also includes the role of land–atmosphere interactions in the occurrence and development of those natural hazards.

Statistics have a long-standing relationship with climate and weather sciences, spanning a variety of techniques (from probabilistic forecasting to the analysis of complex phenomena, forecast evaluation, and extreme-event modelling). The emergence of machine learning (ML) and artificial intelligence (AI), as well as their ability to make sense of complex datasets, has created new opportunities in the scientific community. AI and ML offer the potential to overcome computational and modelling barriers, such as the complex interactions among co-occurring processes and scalability to large datasets, that have been historically prohibitive in advancing climate and weather sciences. This special issue focuses on recent advances in ML and AI in climate and weather sciences. Topics on synergies between ML/AI and statistics in the context of atmospheric sciences are highly welcomed.