Modelling the complexity of hydrological processes is essential to understand the processes involved with different components of hydrological cycles and their changes due to anthropogenic interventions. Hydrological processes control the water movement in the hydrological cycle and thus determine all forms of hydrological processes (e.g., evapotranspiration, precipitation, groundwater recharge, and river flow). These are considered to be challenging engineering problems owing to their complexity.

The development of computer aid models can be used for the planning and management of water resources, assessment of hydro-climatic hazard risk, evaluation of agricultural potential, understanding ecological distribution, etc. Physically-based models are most widely used for the simulation of hydrological processes where analytical or numerical methods are generally used. The physically-based models need a large amount of information for reliable modelling of hydrological processes which is often compromised through simplification of the real-word system. Therefore, such models often fail to provide reliable results. Different statistical models based on the relationship between data among the different components of the hydrological cycle have gained popularity in recent years due to their higher capability to simulate different hydrological processes. The relationship among various components responsible for a hydrological process is always non-linear, non-stationary, and stochastic. In many cases, the relationship is extremely non-linear and highly stochastic and is not possible to solve using conventional statistical methods. The artificial intelligence (AI) models and their advanced versions have the capability to model highly non-linear and stochastic phenomena and therefore it has been widely used in recent years for successful monitoring, analysis and forecasting of different hydrological processes. The AI models have been evidenced to demonstrate an excellent advanced computer aid machine learning model. AI models can be used for the construction of predictive models for decision support in water resources management, hydrological hazard risk reduction, and environmental management.

The aim of this Special Issue is to welcome novel research and review articles on the applications of primitive and modern-day soft computing modelling strategies for the simulation of hydrological processes. The submitted work should advance the knowledge of machine learning to describe, understand, analyse, model, and forecast hydrological processes.

Potential topics include but are not limited to the following:

• Advanced artificial intelligence models in hydrology
• Hydrological process simulation
• Climate change
• Decision tools and agent-based models
• Uncertainty analysis in hydrology
• Time series forecasting in hydrology
• Watershed monitoring and sustainability
• Hybrid machine learning models in hydrology
• Environmental engineering in hydrology
• Hydro-climatic hazard risk management
• Water resource planning and management
• Non-linear, non-stationary, and stochastic problems in hydrology