This paper reviews the current GeoAI and machine learning applications in hydrological and hydraulic modeling, hydrological optimization problems, water quality modeling, and fluvial geomorphic and morphodynamic mapping. GeoAI effectively harnesses the vast amount of spatial and non-spatial data collected with the new automatic technologies. The fast development of GeoAI provides multiple methods and techniques, although it also makes comparisons between different methods challenging. Overall, selecting a particular GeoAI method depends on the application’s objective, data availability, and user expertise. GeoAI has shown advantages in non-linear modeling, computational efficiency, integration of multiple data sources, high accurate prediction capability, and the unraveling of new hydrological patterns and processes. A major drawback in most GeoAI models is the adequate model setting and low physical interpretability, explainability, and model generalization. The most recent research on hydrological GeoAI has focused on integrating the physical-based models’ principles with the GeoAI methods and on the progress towards autonomous prediction and forecasting systems.

Inadequate Monitoring and Evaluation (M&E) is often thought to hinder adaptive management of socio-ecological systems. A key influence on environmental management practices are environmental policies: however, their consequences for M&E practices have not been well-examined. We examine three policy areas - the Water Framework Directive, the Natura 2000 Directives, and the Agri-Environment Schemes of the Common Agricultural Policy - whose statutory requirements influence how the environment is managed and monitored across Europe. We use a comparative approach to examine what is monitored, how monitoring is carried out, and how results are used to update management, based on publicly available documentation across nine regional and national cases. The requirements and guidelines of these policies have provided significant impetus for monitoring: however, we find this policy-driven M&E usually does not match the ideals of what is needed to inform adaptive management. There is a tendency to focus on understanding state and trends rather than tracking the effect of interventions; a focus on specific biotic and abiotic indicators at the expense of understanding system functions and processes, especially social components; and limited attention to how context affects systems, though this is sometimes considered via secondary data. The resulting data are sometimes publicly-accessible, but it is rarely clear if and how these influence decisions at any level, whether this be in the original policy itself or at the level of measures such as site management plans. Adjustments to policy-driven M&E could better enable learning for adaptive management, by reconsidering what supports a balanced understanding of socio-ecological systems and decision-making. Useful strategies include making more use of secondary data, and more transparency in data-sharing and decision-making. Several countries and policy areas already offer useful examples. Such changes are essential given the influence of policy, and the urgency of enabling adaptive management to safeguard socio-ecological systems.

HIGHLIGHTS. In this commentary, we highlight new possibilities and suggest vital steps forward for the scientific discipline within the Nordic hydrological rese

The representativeness of aquatic ecosystem monitoring and the precision of the assessment results are of high importance when implementing the EU’s Water Framework Directive that aims to secure a good status of waterbodies in Europe. However, adapting monitoring designs to answer the objectives and allocating the sampling resources effectively are seldom practiced. Here, we present a practical solution how the sampling effort could be re-allocated without decreasing the precision and confidence of status class assignment. For demonstrating this, we used a large data set of 272 intensively monitored Finnish lake, coastal, and river waterbodies utilizing an existing framework for quantifying the uncertainties in the status class estimation. We estimated the temporal and spatial variance components, as well as the effect of sampling allocation to the precision and confidence of chlorophyll-a and total phosphorus. Our results suggest that almost 70% of the lake and coastal waterbodies, and 27% of the river waterbodies, were classified without sufficient confidence in these variables. On the other hand, many of the waterbodies produced unnecessary precise metric means. Thus, reallocation of sampling effort is needed. Our results show that, even though the studied variables are among the most monitored status metrics, the unexplained variation is still high. Combining multiple data sets and using fixed covariates would improve the modeling performance. Our study highlights that ongoing monitoring programs should be evaluated more systematically, and the information from the statistical uncertainty analysis should be brought concretely to the decision-making process.

The use of satellite-based remote sensing imagery for water quality monitoring of inland and coastal waters has become widespread over the last few decades, with the expansion of, and investment in, operational Earth-observing missions. Satellite-based sensors are uniquely suited to provide synoptic, system-wide water quality parameter estimates that supplement traditional field-based sampling methods. The remote sensing of water quality parameter estimates is particularly valuable in systems with high temporal and spatial variability, as well as in areas that are difficult to access, or where agencies lack funding for routine monitoring. However, optically complex inland and coastal waters pose additional challenges for developing robust remote sensing retrieval models for optical properties and water quality parameters. One of the biggest challenges is collecting high quality field measurements that are used to calibrate and validate the retrieval algorithms. Here, we present the current status of satellite missions, field methods that include instruments used and commonly measured parameters, and repositories of historical field data that are relevant to inland and coastal water studies. We then present data requirements for model validation and highlight gaps in validation coverage. Finally, we provide considerations for future field campaigns to improve coordination with remote sensing data collection and ensure that field data is well suited for use in model or algorithm development.

River ice plays a critical role in Arctic freshwater routing, navigation safety, and biogeochemical exchange. However, consistent, daily-resolved observations across the pan-Arctic remain scarce. Here we present a harmonized, multi-decadal dataset of daily river ice concentration (RIC) and annual phenology (freeze-up, breakup, and ice duration) for the six largest Arctic rivers—Yukon, Mackenzie, Ob, Yenisey, Lena, and Kolyma—covering hydrological years 2001–2024. Built from >590,000 MODIS Terra/Aqua scenes, our workflow integrates a scalable threshold-based classifier on Google Earth Engine with dual-satellite daily synthesis, temporal-window cloud reclassification, and a high-latitude dark-period correction. Technical validation against higher-resolution optical imagery shows a mean RIC accuracy of 0.83 across basins. Phenological metrics derived from MODIS agree with in situ records with mean absolute errors (MAE) of 10.8 days for freeze-up and 11.4 days for breakup (improving to 8.4 days relative to the onset of ice drift), and with Landsat-based river-section phenology with MAE of 10.5 days (freeze-up) and 16.0 days (breakup). RIC correlates strongly with surface air temperature (mean Pearson r = −0.91) and increases systematically with latitude. Trend analysis from 2001 through 2024 shows delayed freeze-up in over 66 % of river segments, earlier breakup in more than 65 %, and shorter ice seasons in over 65 %. On average, freeze-up is delayed by 9.0 days, breakup occurs 7.8 days earlier, and ice duration shortens by 14.1 days over the study period. These basin-consistent, temporally resolved records provide an open benchmark for diagnosing cryospheric change in Arctic river corridors and for constraining model–data intercomparisons. The river-ice dataset is available via Zenodo (https://doi.org/10.5281/zenodo.17054619, Qiu et al., 2025).