Natural disasters are common occurrences due to extreme climatological and hydrological events. These disasters bring damage not only to infrastructure but also to human life. These natural disasters have a negative impact from many environmental perspectives. Minimizing and possibly avoiding the adverse impact of these extreme events is based on identification, understanding, modeling, validation, and prediction of climatological and hydrological events. Anthropogenic activities have clearly enhanced climate change even though many treaties aim to minimize the rate of change. Therefore, developing a robust system to predict these extreme events is still challenging under the ever-changing climate.

Predicting and comprehensively understanding the spatial extent of damage due to an extreme climatological event is difficult. This difficulty is further increased due to the scarcity of climatological data throughout the world. Furthermore, the available climatic data can be expensive for researchers to purchase, even for study purposes. However, despite these challenges, spatial and temporal analyses are still of interest to related researchers; the stochastic dynamics of climate and hydrology is often found in the literature. The utilization of advanced techniques and methodologies can be seen in solving and researching nonlinear dynamics, which vary both spatially and temporally. Non-linear theories are being explored with emerging techniques such as artificial intelligence (AI), gene expression programming, and genetic algorithms. These techniques continue to evolve to bring more accurate solutions to complex but nonlinear problems. The computational power of modern computers plays a vital role in the success of these emerging techniques. Even though AI models have found major success in solving nonlinear problems, there are still several limitations to applications in climate and hydrology. The development of a holistic solution for many of these problems is based on a prior understanding of such extreme events. Thus, examining past climate events is crucial in predicting future events and has the potential to help mitigate possible damages.

This Special Issue encourages researchers to submit original research and review articles that are focused on developing new, robust machine learning models to solve complex climatological and hydrological problems. Emerging artificial intelligence techniques could lead the research world in minimizing the adverse impacts from extreme climatological and hydrological events, significantly benefiting stakeholders such as agriculturalists, water resources managers, and flood control engineers.

Potential topics include but are not limited to the following:

• Application of artificial intelligence in climate models
• Climate change and hydrological models
• Artificial intelligence in hydrological models
• Hybrid machine learning techniques in modeling climate change
• Explainable and transparent machine learning in watershed modeling under climate change
• Sustainability of watershed management under climate change
• Disaster management using artificial intelligence
• Machine learning models to solve complex environmental problems
• Prediction of future climatological and hydrological scenarios
• Time series forecasting in hydrology