Among natural hazards, floods pose the greatest threat to lives and livelihoods. To reduce flood impacts, short-term flood forecasting can contribute to early warnings that provide communities with time to react. This manuscript explores how machine learning (ML) can support short-term flood forecasting. Using two methods [strengths, weaknesses, opportunities, and threats (SWOT) and comparative performance analysis] for different forecast lead times (1–6, 6–12, 12–24, and 24–48 h), we evaluate the performance of machine learning models in 94 journal papers from 2001 to 2023. SWOT reveals that the best short-term flood forecasting was produced by hybrid, random forest (RF), long short-term memory (LSTM), artificial neural network (ANN), and adaptive neuro-fuzzy inference system (ANFIS) approaches. The comparative performance analysis, meanwhile, favors convolutional neural network, ANFIS, multilayer perceptron, k-nearest neighbors algorithm (KNN), hybrid, LSTM, ANN, and support vector machine (SVM) at 1–6 h; hybrid, ANFIS, ANN, and LSTM at 6–12 h; SVM, hybrid, and RF at 12–24 h; and hybrid and RF at 24–48 h. In general, hybrid approaches consistently perform well across all lead times. Trends such as hybridization, model selection, input data selection, and decomposition seem to improve the accuracy of models. Furthermore, effective stand-alone ML models such as ANN, SVM, RF, genetic algorithm, KNN, and LSTM, provide better outcomes through hybridization with other ML models. By including different machine learning models and parameters such as environmental, socio-economical, and climatic parameters, the hybrid system can produce more accurate flood forecasting, making it more effective for early warning operational purposes.

Efficient decision-making regarding flood risk reduction has become a priority for authorities and stakeholders in many European countries. Risk analysis methods and techniques are a useful tool for evaluating costs and benefits of possible interventions. Within this context, a methodology to estimate flood consequences was developed in this paper that is based on GIS, and integrated with a model that estimates the degree of accessibility and operability of strategic emergency response structures in an urban area. The majority of the currently available approaches do not properly analyse road network connections and dependencies within systems, and as such a loss of roads could cause significant damages and problems to emergency services in cases of flooding. The proposed model is unique in that it provides a maximum-impact estimation of flood consequences on the basis of the operability of the strategic emergency structures in an urban area, their accessibility, and connection within the urban system of a city (i.e. connection between aid centres and buildings at risk), in the emergency phase. The results of a case study in the Puglia region in southern Italy are described to illustrate the practical applications of this newly proposed approach. The main advantage of the proposed approach is that it allows for defining a hierarchy between different infrastructure in the urban area through the identification of particular components whose operation and efficiency are critical for emergency management. This information can be used by decision-makers to prioritize risk reduction interventions in flood emergencies in urban areas, given limited financial resources.