Application of machine learning and emerging remote sensing techniques in hydrology: A state-of-the-art review and current research trends.

• A review has been conducted on the application of ML and RS in hydrology domain. • Analyses were conducted on surface hydrology, hydro-climatic extremes and GWM & WQ. • GIS and ML algorithms prove valuable in the realm of hydrological investigations. • State-of-the-art approach is attributed to hydrology and water resources. Water, one of the most valuable resources on Earth, is the subject of the study of hydrology, which is of utmost importance. Satellite remote sensing (RS) has emerged as a critical tool for comprehending Earth and atmospheric dynamics, including hydrology. With the assistance of satellite RS, the scientific community has achieved significant progress in recent years. Since machine learning (ML) and RS techniques were initially applied to the study of hydrology, there has been a tremendous increase in interest in studying potential areas for future advancements in hydrology. The growth can see in the publications of related papers. Considering these initiatives, the current review paper attempts to give a thorough analysis of the function of ML and RS techniques in four fields of hydrology. This review study considers hydrological topics of streamflow, rainfall-runoff, groundwater modelling and water quality, and hydroclimatic extremes. The use of learning strategies in the hydrological sciences is examined in all reviews and research papers. Several databases were utilised for this purpose, including Scopus-index, science direct, Web of Science, and Google Scholar. The overall results of this study show that employing RS techniques, ML and ensemble approaches is incomparably superior to using traditional methods in hydrological studies. [ABSTRACT FROM AUTHOR]