This paper examines the potential of the support vector machine (SVM) in long-term prediction of lake water levels. Lake Erie mean monthly water levels from 1918 to 2001 are used to predict future water levels up to 12 months ahead. The results are compared with a widely used neural network model called a multilayer perceptron (MLP) and with a conventional multiplicative seasonal autoregressive model (SAR). Overall, the SVM showed good performance and is proved to be competitive with the MLP and SAR models. For a 3- to 12-month-ahead prediction, the SVM model outperforms the two other models based on root-mean square error and correlation coefficient performance criteria. Furthermore, the SVM exhibits inherent advantages due to its use of the structural risk minimization principle in formulating cost functions and of quadratic programming during model optimization. These advantages lead to a unique optimal and global solution compared to conventional neural network models.

The issues of downscaling the outputs of a global climate model (GCM) to a scale that is appropriate to hydrological impact studies are investigated using a temporal neural network approach. The time-lagged feed-forward neural network (TLFN) is proposed for downscaling daily total precipitation and daily maximum and minimum temperature series for the Serpent River watershed in northern Quebec (Canada). The downscaling models are developed and validated using large-scale predictor variables derived from the National Centers for Environmental Prediction–National Center for Atmospheric Research (NCEP–NCAR) reanalysis dataset. Atmospheric predictors such as specific humidity, wind velocity, and geopotential height are identified as the most relevant inputs to the downscaling models. The performance of the TLFN downscaling model is also compared to a statistical downscaling model (SDSM). The downscaling results suggest that the TLFN is an efficient method for downscaling both daily precipitation and temperature series. The best downscaling models were then applied to the outputs of the Canadian Global Climate Model (CGCM1), forced with the Intergovernmental Panel on Climate Change (IPCC) IS92a scenario. Changes in average precipitation between the current and the future scenarios predicted by the TLFN are generally found to be smaller than those predicted by the SDSM model. Furthermore, application of the downscaled data for hydrologic impact analysis in the Serpent River resulted in an overall increasing trend in mean annual flow as well as earlier spring peak flow. The results also demonstrate the emphasis that should be given in identifying the appropriate downscaling tools for impact studies by showing how a future climate scenario downscaled with different downscaling methods could result in significantly different hydrologic impact simulation results for the same watershed.

Recent years have witnessed considerable developments in multiple fields with the potential to enhance our capability of forecasting pluvial flash floods, one of the most costly environmental hazards in terms of both property damage and loss of life. This work provides a summary and description of recent advances related to insights on atmospheric conditions that precede extreme rainfall events, to the development of monitoring systems of relevant hydrometeorological parameters, and to the operational adoption of weather and hydrological models towards the prediction of flash floods. With the exponential increase of available data and computational power, most of the efforts are being directed towards the improvement of multi-source data blending and assimilation techniques, as well as assembling approaches for uncertainty estimation. For urban environments, in which the need for high-resolution simulations demands computationally expensive systems, query-based approaches have been explored for the timely retrieval of pre-simulated flood inundation forecasts. Within the concept of the Internet of Things, the extensive deployment of low-cost sensors opens opportunities from the perspective of denser monitoring capabilities. However, different environmental conditions and uneven distribution of data and resources usually leads to the adoption of site-specific solutions for flash flood forecasting in the context of early warning systems.

Floods are major water-related disasters that affect millions of people resulting in thousands of mortalities and billiondollar losses globally every year. Flood Early Warning Systems (FEWS) - one of the floods risk management measures - are currently operational in many countries. The UN Office for Disaster Risk Reduction recognises their importance and strongly advocates for an increase in their availability under the targets of the Sendai Framework for Disaster Risk Reduction, and Sustainable Development Goals (SDGs). However, despite widespread recognition of the importance of FEWS for disaster risk reduction (DRR), there’s a lack of information on their availability and status around the world, their benefits and costs, challenges and trends associated with their development. This report contributes to bridging these gaps by analyzing the responses to a comprehensive online survey with over 80 questions on various components of FEWS (risk knowledge, monitoring and forecasting, warning dissemination and communication, and response capabilities), investments into FEWS, their operational effectiveness, benefits, and challenges. FEWS were classified as technologically “basic”, “intermediate” and “advanced” depending on the existence and sophistication of FEWS` components such as hydrological data = collection systems, data transfer systems, flood forecasting methods, and early warning communication methods. The survey questionnaire was distributed to flood forecasting and warning centers around the globe; the primary focus was developing and least-developed countries (LDCs). The questionnaire is available here: https://inweh.unu.edu/questionnaireevaluation-of-flood-early-warning-systems/ and can be useful in its own right for similar studies at national or regional scales, in its current form or with case-specific modifications. Survey responses were received from 47 developing (including LDCs) and six developed countries. Additional information for some countries was extracted from available literature. Analysis of these data suggests the existence of an equal number of “intermediate” and “advanced” FEWS in surveyed river basins. While developing countries overall appear to progress well in FEWS implementation, LDCs are still lagging behind since most of them have “basic” FEWS. The difference between types of operational systems in developing and developed countries appear to be insignificant; presence of basic, intermediate or advanced FEWS depends on available investments for system developments and continuous financing for their operations, and there is evidence of more financial support — on the order of USD 100 million — to FEWS in developing countries thanks to international aid. However, training the staff and maintaining the FEWS for long-term operations are challenging. About 75% of responses indicate that river basins have inadequate hydrological network coverage and back-up equipment. Almost half of the responders indicated that their models are not advanced and accurate enough to produce reliable forecasts. Lack of technical expertise and limited skilled manpower to perform forecasts was cited by 50% of respondents. The primary reason for establishing FEWS, based on the survey, is to avoid property damage; minimizing causalities and agricultural losses appear to be secondary reasons. The range of the community benefited by FEWS varies, but 55% of FEWS operate in the range between 100,000 to 1 million of population. The number of flood disasters and their causalities has declined since the year 2000, while 50% of currently operating FEWS were established over the same period. This decline may be attributed to the combined DRR efforts, of which FEWS are an integral part. In lower-middle-income and low-income countries, economic losses due to flood disasters may be smaller in absolute terms, but they represent a higher percentage of such countries’ GDP. In high-income countries, higher flood-related losses accounted for a small percentage of their GDP. To improve global knowledge on FEWS status and implementation in the context of Sendai Framework and SDGs, the report’s recommendations include: i) coordinate global investments in FEWS development and standardise investment reporting; ii) establish an international hub to monitor the status of FEWS in collaboration with the national responsible agencies. This will support the sharing of FEWS-related information for accelerated global progress in DRR; iii) develop a comprehensive, index-based ranking system for FEWS according to their effectiveness in flood disaster mitigation. This will provide clear standards and a roadmap for improving FEWS’ effectiveness, and iv) improve coordination between institutions responsible for flood forecasting and those responsible for communicating warnings and community preparedness and awareness.