This paper summarises an updated climate change trends analysis—developed for the period from 1 October 1864 to 30 September 2021 within the scope of a Horizon 2020-funded project to increase climate resilience in European coastal cities—for a representative site of the Lisbon Metropolitan Area (Portugal). By using long ground-based daily records of rainfall and surface temperature at the Lisboa-Geofísico climatological station, the analysis aimed to identify (i) long-term and recent climate trends in rainfall and temperature, (ii) changes in extreme rainfalls, heatwaves, and droughts, and (iii) possible effects of the coupled changes of minimum and maximum daily temperatures (Tmin and Tmax, respectively) on drought development based on the diurnal temperature range (DTR) indicator. To detect these trends and quantify their magnitude, the Mann−Kendall and Sen’s slope estimator tests were implemented. The analysis of the mean annual temperatures indicated that the study area has warmed ∼1.91 °C through the 157 analysed years. Results evidenced statistically significant upward trends in both Tmin and Tmax, and in the number of Tmax heatwave days. In what concerns the extreme hydrological events, the analysis of annual maximum rainfall series and peaks-over-threshold (POT) techniques showed more frequent and intense events in recent years, reaching up to ∼120.0 mm in a single day. With regard to drought, the study proved that the characterisation based on the commonly used standardised precipitation index (SPI) might differ from that based on the standardised precipitation evapotranspiration index (SPEI), as the latter can take into account not only rainfall but also temperature, an important trigger for the development of drought. According to the SPEI index, severe and extreme drought conditions have been more frequent in the last 60 years than in any other recorded period. Finally, a decreasing DTR trend towards the present was found to influence evapotranspiration rates and thus drought characteristics.

Sediment transport in suspension can represent more than 90% of a river's total annual flux of sediment. In the case of the Yangtze River, more than 99% of the sediment supplied to the sea is suspended load. Suspended sediment is thus an important component of the total sediment load, with implications for channel dynamics, landscape evolution, ecology, and human‐related activities. For hydrological management of large basins such as the Yangtze River, knowledge of the processes governing suspended sediment concentration (SSC) is essential. An analysis of the temporal variation of SSC for the Upper Yangtze basin (defined at Pingshan station) is presented here. For this purpose, a database of 50 years of concurrent discharge and SSC measurements, made by the Yangtze River Commission, is used. The analysis is made using a novel probabilistic data‐driven technique, the Generalized Pareto Uncertainty (GPU). This technique allows for the testing of several strategies of prediction and forecast applied to a time series of SSC and streamflow. Changing between local or seasonal variables to feed these strategies, we inferred that although the main driver of the SSC transport is flow (as reported by previous authors), sediment storage is also a major control. Furthermore, the maximum necessary time lag for forecasts made with the data is on the order of one week, which provides one indication of the time scale of the local processes of SSC transport in the Upper Yangtze. In this paper, limitations and data requirements of the GPU methodology are also discussed.

Flooding is a truly ubiquitous problem. Today, it puts an estimated 1.81 billion people at risk. Floods particularly affect coastal cities, where it is expected that the damage associated with inundations exceed the staggering value of USD 50 billion by 2050. Indeed, the risk associated with flooding in coastal cities is increasing due to three unequivocal trends: growing population in large urban centres, sea level rise, and increased intensity of extreme weather events. Planning and implementation of storm drainage systems in large cities is a complex, long, and expensive process. Typically, the effective lifespan of storm drainage systems may extend to nearly a century. Accordingly, such systems should be designed for the future, not the present. Addressing these important challenges, the paper evaluates flood risks in the coastal city of Maputo, in Mozambique. Results show that, although downtown Maputo is not particularly exposed to compound flooding, accounting for rainfall-tide events is essential to understand flooding in the area and evaluating the performance of the storm drainage system.

This study explores the application of Temporal Fusion Transformers (TFTs) to improve the predictability of hourly potential hydropower production for a small run–of–the–river hydropower plant in Portugal. Accurate hourly power forecasts are essential for optimizing participation in the spot electricity market, where deviations incur penalties. This research introduces the novel application of the TFT, a deep–learning model tailored for time series forecasting and uncovering complex patterns, to predict hydropower production based on meteorological data, historical production records, and plant capacity. Key challenges such as filtering observed hydropower outputs (to remove strong, and unpredictable human influence) and adapting the historical series to installed capacity increases are discussed. An analysis of meteorological information from several sources, including ground information, reanalysis, and forecasting models, was also undertaken. Regarding the latter, precipitation forecasts from the European Centre for Medium–Range Weather Forecasts (ECMWF) proved to be more accurate than those of the Global Forecast System (GFS). When combined with ECMWF data, the TFT model achieved significantly higher accuracy in potential hydropower production predictions. This work provides a framework for integrating advanced machine learning models into operational hydropower scheduling, aiming to reduce classical modeling efforts while maximizing energy production efficiency, reliability, and market performance.

The transformative potential of deep learning models is felt in many research fields, including hydrology and water resources. This study investigates the effectiveness of the Temporal Fusion Transformer (TFT), a deep neural network architecture for predicting daily streamflow in Portugal, and benchmarks it against the popular Hydrologiska Byråns Vattenbalansavdelning (HBV) hydrological model. Additionally, it evaluates the performance of TFTs through selected forecasting examples. Information is provided about key input variables, including precipitation, temperature, and geomorphological characteristics. The study involved extensive hyperparameter tuning, with over 600 simulations conducted to fine–tune performances and ensure reliable predictions across diverse hydrological conditions. The results showed that TFTs outperformed the HBV model, successfully predicting streamflow in several catchments of distinct characteristics throughout the country. TFTs not only provide trustworthy predictions with associated probabilities of occurrence but also offer considerable advantages over classical forecasting frameworks, i.e., the ability to model complex temporal dependencies and interactions across different inputs or weight features based on their relevance to the target variable. Multiple practical applications can rely on streamflow predictions made with TFT models, such as flood risk management, water resources allocation, and support climate change adaptation measures.