Search

The sustainable management of water cycles is crucial in the context of climate change and global warming. It involves managing global, regional, and local water cycles—as well as urban, agricultural, and industrial water cycles—to conserve water resources and their relationships with energy, food, microclimates, biodiversity, ecosystem functioning, and anthropogenic activities. Hydrological modeling is indispensable for achieving this goal, as it is essential for water resources management and mitigation of natural disasters. In recent decades, the application of artificial intelligence (AI) techniques in hydrology and water resources management has made notable advances. In the face of hydro-geo-meteorological uncertainty, AI approaches have proven to be powerful tools for accurately modeling complex, non-linear hydrological processes and effectively utilizing various digital and imaging data sources, such as ground gauges, remote sensing tools, and in situ Internet of Things (IoTs). The thirteen research papers published in this Special Issue make significant contributions to long- and short-term hydrological modeling and water resources management under changing environments using AI techniques coupled with various analytics tools. These contributions, which cover hydrological forecasting, microclimate control, and climate adaptation, can promote hydrology research and direct policy making toward sustainable and integrated water resources management.

The mitigation of societal damage from urban floods requires fast hydraulic models for emergency and planning purposes. The simplified mathematical model Cellular Automata is combined with Motion Cost fields, which score the difficulty to traverse an area, to the urban inundation model CAMC. It is implemented with simple matrix and logic operations to achieve high computational efficiency. The development concentrated on an application in dense urban built-up areas with numerous buildings. CAMC is efficient and flexible enough to be used in a “live” urban flood warning system with current weather conditions. A case study is conducted in the German city of Wuppertal with about 12,000 buildings. The water depth estimation of every time step are visualized in a web-interface on the basis of the virtual globe NASA WorldWind. CAMC is compared with the shallow water equations-based model ANUGA. CAMC is approximatively 5 times faster than ANUGA at high spatial resolution and able to maintain numerical stability. The Nash-Sutcliffe coefficient (0.61), Root Mean Square Error (0.39 m) and Index of Agreement (0.65) indicate acceptable agreement for water depth estimation but identify different areas where important deviations occur. The estimation of velocity performs considerably less well (0.34 for Nash-Sutcliffe coefficient, 0.13 ms − 1 for Root Mean Square Error, and 0.39 for Index of Agreement) because CA ignores momentum conservation.

Weather plays a critical role in outdoor agricultural production; therefore, climate information can help farmers to arrange planting and production schedules, especially for urban agriculture (UA), providing fresh vegetables to partially fulfill city residents’ dietary needs. General weather information in the form of timely forecasts is insufficient to anticipate potential occurrences of weather types and features during the designated time windows for precise cultivation planning. In this research, we intended to use a self-organizing map (SOM), which is a clustering technique with powerful feature extraction ability to reveal hidden patterns of datasets, to explore the represented spatiotemporal weather features of Taipei city based on the observed data of six key weather factors that were collected at five weather stations in northern Taiwan during 2014 and 2018. The weather types and features of duration and distribution for Taipei on a 10-day basis were specifically examined, indicating that weather types #2, #4, and #7 featured to manifest the dominant seasonal patterns in a year. The results can serve as practical references to anticipate upcoming weather types/features within designated time frames, arrange potential/further measures of cultivation tasks and/or adjustments in response, and use water/energy resources efficiently for the sustainable production of smart urban agriculture.

It is fundamentally challenging to quantify the uncertainty of data-driven flood forecasting. This study introduces a general framework for probabilistic flood forecasting conditional on point forecasts. We adopt an unscented Kalman filter (UKF) post-processing technique to model the point forecasts made by a recurrent neural network and their corresponding observations. The methodology is tested by using a long-term 6-h timescale inflow series of the Three Gorges Reservoir in China. The main merits of the proposed approach lie in: first, overcoming the under-prediction phenomena in data-driven flood forecasting, second, alleviating the uncertainty encountered in data-driven flood forecasting. Two commonly used artificial neural networks, a recurrent and a static neural network, were used to make the point forecasts. Then the UKF approach driven by the point forecasts demonstrated its competency in increasing the reliability of probabilistic flood forecasts significantly, where predictive distributions encountered in multi-step-ahead flood forecasts were effectively reduced to small ranges. The results demonstrated that the UKF plus recurrent neural network approach could suitably extract the complex non-linear dependence structure between the model&rsquo, s outputs and observed inflows and overcome the systematic error so that model reliability as well as forecast accuracy for future horizons could be significantly improved.

Practitioners often neglect the uncertainty inherent to models and their inputs. PointEstimate Methods (PEMs) offer an alternative to the common, but computationally demanding,method for assessing model uncertainty, Monte Carlo (MC) simulation. PEMs rerun the model withrepresentative values of the probability distribution of the uncertain variable. The results can estimatethe statistical moments of the output distribution. Hong&rsquo, s method is the specific PEM implementedhere for a case study that simulates water runoff using the ANUGA model for an area in Glasgow, UK.Elevation is the source of uncertainty. Three realizations of the Sequential Gaussian Simulation,which produces the random error fields that can be used as inputs for any spatial model, are scaledaccording to representative values of the distribution and their weights. The output from a MCsimulation is used for validation. A comparison of the first two statistical moments indicates thatHong&rsquo, s method tends to underestimate the first moment and overestimate the second moment. Modelefficiency performance measures validate the usefulness of Hong&rsquo, s method for the approximationof the first two moments, despite the method suffering from outliers. Estimation was less accuratefor higher moments but the moment estimates were sufficient to use the Grams-Charlier Expansionto fit a distribution to them. Regarding probabilistic flood-inundation maps, Hong&rsquo, s method showsvery similar probabilities in the same areas as the MC simulation. However, the former requires justthree 11-minute simulation runs, rather than the 500 required for the MC simulation. Hong&rsquo, s methodtherefore appears attractive for approximating the uncertainty of spatiotemporal models.

Due to nonuniform rainfall distribution in Taiwan, groundwater is an important water source in certain areas that lack water storage facilities during periods of drought. Therefore, groundwater recharge is an important issue for sustainable water resources management. The mountainous areas and the alluvial fan areas of the Jhuoshui River basin in Central Taiwan are considered abundant groundwater recharge regions. This study aims to investigate the interactive mechanisms between surface water and groundwater through statistical techniques and estimate groundwater level variations by a combination of artificial intelligence techniques and the Gamma test (GT). The Jhuoshui River basin in Central Taiwan is selected as the study area. The results demonstrate that: (1) More days of accumulated rainfall data are required to affect variable groundwater levels in low-permeability wells or deep wells, (2) effective rainfall thresholds can be properly identified by lower bound screening of accumulated rainfall, (3) daily groundwater level variation can be estimated effectively by artificial neural networks (ANNs), and (4) it is difficult to build efficient models for low-permeability wells, and the accuracy and stability of models is worse in the proximal-fan areas than in the mountainous areas.

The impacts of climate change on water resources management as well as the increasing severe natural disasters over the last decades have caught global attention. Reliable and accurate hydrological forecasts are essential for efficient water resources management and the mitigation of natural disasters. While the notorious nonlinear hydrological processes make accurate forecasts a very challenging task, it requires advanced techniques to build accurate forecast models and reliable management systems. One of the newest techniques for modelling complex systems is artificial intelligence (AI). AI can replicate the way humans learn and has the great capability to efficiently extract crucial information from large amounts of data to solve complex problems. The fourteen research papers published in this Special Issue contribute significantly to the uncertainty assessment of operational hydrologic forecasting under changing environmental conditions and the promotion of water resources management by using the latest advanced techniques, such as AI techniques. The fourteen contributions across four major research areas: (1) machine learning approaches to hydrologic forecasting; (2) uncertainty analysis and assessment on hydrological modelling under changing environments; (3) AI techniques for optimizing multi-objective reservoir operation; and (4) adaption strategies of extreme hydrological events for hazard mitigation. The papers published in this issue can not only advance water sciences but can also support policy makers toward more sustainable and effective water resources management.

Flood disasters have had a great impact on city development. Early flood warning systems (EFWS) are promising countermeasures against flood hazards and losses. Machine learning (ML) is the kernel for building a satisfactory EFWS. This paper first summarizes the ML methods proposed in this special issue for flood forecasts and their significant advantages. Then, it develops an intelligent hydroinformatics integration platform (IHIP) to derive a user-friendly web interface system through the state-of-the-art machine learning, visualization and system developing techniques for improving online forecast capability and flood risk management. The holistic framework of the IHIP includes five layers (data access, data integration, servicer, functional subsystem, and end-user application) and one database for effectively dealing with flood disasters. The IHIP provides real-time flood-related data, such as rainfall and multi-step-ahead regional flood inundation maps. The interface of Google Maps fused into the IHIP significantly removes the obstacles for users to access this system, helps communities in making better-informed decisions about the occurrence of floods, and alerts communities in advance. The IHIP has been implemented in the Tainan City of Taiwan as the study case. The modular design and adaptive structure of the IHIP could be applied with similar efforts to other cities of interest for assisting the authorities in flood risk management.

A regional inundation early warning system is crucial to alleviating flood risks and reducing loss of life and property. This study aims to provide real-time multi-step-ahead forecasting of flood inundation maps during storm events for flood early warnings in inundation-prone regions. For decades, the Kemaman River Basin, located on the east coast of the West Malaysia Peninsular, has suffered from monsoon floods that have caused serious damage. The downstream region with an area of approximately 100 km2 located on the east side of this basin is selected as the study area. We explore and implement a hybrid ANN-based regional flood inundation forecast system in the study area. The system combines two popular artificial neural networks&mdash, the self-organizing map (SOM) and the recurrent nonlinear autoregressive with exogenous inputs (RNARX)&mdash, to sequentially produce regional flood inundation maps during storm events. The results show that: (1) the 4 &times, 4 SOM network can effectively cluster regional inundation depths, (2) RNARX networks can accurately forecast the long-term (3&ndash, 12 h) regional average inundation depths, and (3) the hybrid models can produce adequate real-time regional flood inundation maps. The proposed ANN-based model was shown to very quickly carry out multi-step-ahead forecasting of area-wide inundation depths with sufficient lead time (up to 12 h) and can visualize the forecasted results on Google Earth using user devices to help decision makers and residents take precautionary measures against flooding.