Devastating floods have plagued many West African cities in the past decades. In an attempt to reduce flood damage in Bamako (Mali), an early warning system (EWS) demonstrator (Raincell App) was developed for flash floods. On 16 May 2019, while the demonstrator was partially operational, an intense rainfall event led to devastating floods. We carried out an experience feedback on this flood event by comparing EWS simulations to the results of a field survey. Given the synoptic situation and the rapid development pattern of the storm, none of the global forecasting systems were able to foresee its occurrence and magnitude. The hydrological model developed as part of the demonstrator correctly identified most of the locations where overbank flow occurred. In the absence of data, the predicted discharge and volume values could not be validated. However, they are realistic based on the water levels reported in the Post‐Disaster Needs Assessment report. It would be advisable to couple it to a two‐dimensional hydraulic model and add discharge and water level monitoring to the already existing rainfall surveillance scheme to further improve the system's performance. Increasing the local population's awareness of the dangers of clogged waterways is also mandatory.

Intensification of the hydrological cycle resulting from climate change in West Africa poses significant risks for the region’s rapidly urbanising cities, but limited research on flood risk has been undertaken at the urban domain scale. Furthermore, conventional climate models are unable to realistically represent the type of intense storms which dominate the West African monsoon. This paper presents a decision-first framing of climate research in co-production of a climate-hydrology-flooding modelling chain, linking scientists working on state-of-the-art regional climate science with decision-makers involved in city planning for future urban flood management in the city of Ouagadougou, Burkina Faso. The realistic convection-permitting model over Africa (CP4A) is applied at the urban scale for the first time and data suggest significant intensification of high-impact weather events and demonstrate the importance of considering the spatio-temporal scales in CP4A. Hydrological modelling and hydraulic modelling indicate increases in peak flows and flood extents in Ouagadougou in response to climate change which will be further exacerbated by future urbanisation. Advances in decision-makers’ capability for using climate information within Ouagadougou were observed, and key recommendations applicable to other regional urban areas are made. This study provides proof of concept that a decision-first modelling-chain provides a methodology for co-producing climate information that can, to some extent, bridge the usability gap between what scientists think is useful and what decision-makers need.

Wastewater networks are mandatory for urbanisation. Their management, including the prediction and planning of repairs and expansion operations, requires precise information on their underground components (manhole covers, equipment, nodes, and pipes). However, due to their years of service and to the increasing number of maintenance operations they may have undergone over time, the attributes and characteristics associated with the various objects constituting a network are not all available at a given time. This is partly because (i) the multiple actors that carry out repairs and extensions are not necessarily the operators who ensure the continuous functioning of the network, and (ii) the undertaken changes are not properly tracked and reported. Therefore, databases related to wastewater networks may suffer from missing data. To overcome this problem, we aim to exploit the structure of wastewater networks in the learning process of machine learning approaches, using topology and the relationship between components, to complete the missing values of pipes. Our results show that Graph Convolutional Network (GCN) models yield better results than classical methods and represent a useful tool for missing data completion.

To manage sewer networks, reliable data is needed, which is often challenging. This study proposes a novel methodology to reconstruct the sewer network topology using graph theory. Two core procedures—flow adjustment and edge addition—re-establish hydraulically consistent flow paths and restore connectivity in disconnected portions of the network by reversing and adding links. The proposed approach operates at the pipe level, repairing directional reachability. It leverages only the existing network topology to reconstruct connectivity, guided by the principle that every node must have a downstream path to an outlet. The methodology is first applied to reconstruct the sewer network of Montpellier Metropolis in the South of France. Then it is validated by deliberately removing and reversing edges and applying the algorithms to test the methodology’s capability in recovering the correct topology. Both methods performed well individually, especially at lower percentages of reversal (1%) and removal (1%), with a correctness of 0.99 for flow adjustment and 0.8 for edge addition. Although the results were poorer when combining the methods and increasing data degradation—particularly at 10% reversal and 10% removal (correctness of 0.64)—the methodology continued to produce a functionally consistent and logically coherent network, highlighting its robustness given the absence of supporting attribute data.