Recently, state-of-the-art machine learning (ML), encompassing deep learning (DL), has emerged as a revolutionary and versatile tool transforming industries and generating new capabilities for scientific discovery. We are witnessing the accelerating adoption of ML in hydrology and water resources, either in standard or significantly altered applications of ML. Nevertheless, the demonstrated applications so far may be only scratching the surface of what could be achieved in the field of water by harnessing big data and ML. This topical collection invites submissions that expand the realms of such applications and improve the methodological arsenal of water resources scientists. Eligible topics include but are not limited to: (i) imposing physical constraints into ML models and coupling them to process-based models; (ii) novel applications of ML on water-related problems that were typically solved through other means; (iii) revealing properties of ML and its differences from traditional statistical methods; (iv) deriving process-related insights from data directly using ML; (v) retrieving important information from raw data or creation of databases; (vi) quantifying and/or reducing uncertainties associated with ML applications; or (vii) solving methodological barriers facing ML.
Recently, state-of-the-art machine learning (ML), encompassing deep learning (DL), has emerged as a revolutionary and versatile tool transforming industries and generating new capabilities for scientific discovery. We are witnessing the accelerating adoption of ML in hydrology and water resources, either in standard or significantly altered applications of ML. Nevertheless, the demonstrated applications so far may be only scratching the surface of what could be achieved in the field of water by harnessing big data and ML. This topical collection invites submissions that expand the realms of such applications and improve the methodological arsenal of water resources scientists. Eligible topics include but are not limited to: (i) imposing physical constraints into ML models and coupling them to process-based models; (ii) novel applications of ML on water-related problems that were typically solved through other means; (iii) revealing properties of ML and its differences from traditional statistical methods; (iv) deriving process-related insights from data directly using ML; (v) retrieving important information from raw data or creation of databases; (vi) quantifying and/or reducing uncertainties associated with ML applications; or (vii) solving methodological barriers facing ML.
