Operational monitoring of total water stocks in reservoirs at a large scale suffers from a lack of knowledge on the bathymetry of such water bodies. When known, a measured water area can be directly linked to the total water volume. Digital Elevation Models can be very useful to this regard, but often reservoirs bathymetry is not visible since they are filled with water. In such a context, recent developments in Artificial Intelligence might be helpful. Using an inpainting approach, a U-Net algorithm was trained on several thousands of virtual lakes to estimate reservoirs bathymetry, using a true DEM as inputs. Its capacity to determine accurate bathymetry and derived surface to volume relationship has been tested and assessed over the Guadalquivir basin in Southern Spain. The R2score of 0.79 obtained over one reservoir on volume estimation along time is encouraging for the future operational monitoring of the whole basin.

As a result of climate change, extreme hydrometeorological events are becoming increasingly frequent. Over the past 20 years, more than 2 billion people have been exposed to consequences of fluvial floods. Flood detection, rapid mapping and risk assessment products play an important role in flood emergency response and management. Within this context, FloodDAM-Digital Twin is a pre-operational prototype which provides an automated service to reliably detect, monitor, assess and predict floods at local and global scale within digital twin Franco-American collaboration. At the end of the project, a proof of concept demonstration will be realized over French and USA selected catchments. This prototype could be commercialized for both public and private entities in the field of water management and risk prevention. The work presented in this paper relies on scientific improvements for each product and services as well as on the digital Twin architecture that allows interoperability with other systems.

As part of the Copernicus Global Land Service, Proba-V was employed for monitoring water bodies every ten days at a 300m spatial resolution. As Proba-V neared its life cycle end in late 2020, Sentinel-2 was introduced as its replacement, offering an improved spatial resolution of 100m. However, due to a lower revisit rate (2-6 days), the new product could only be generated on a monthly basis. The Water Bodies Detection Algorithm (WBDA) involved three major steps: water detection using the modified Normalized Difference Water Index (MNDWI), monthly synthesis for computing maximum water extent, and global mosaic creation. Thematic accuracy assessment was conducted globally, demonstrating the product's high plausibility. The Overall Accuracy was 96.70%, User Accuracy for WB was 96.80%, and Producer Accuracy for WB was 97.09%. Future efforts involve integrating Sentinel-1 data to address cloud coverage challenges and exploring data fusion with ancillary information.

Floods are the most common natural disasters all over the world and they are increasing in frequency and intensity due to climate changes. The Space for Climate Observatory (SCO)-FloodDAM-DT project with a joint collaboration effort between CNES, NASA’s partners and JPL is devoted to developing a federated Earth System Digital Twin (ESDT) for water-cycle applications focused on flood events. In particular, SCO-FloodDAM-DT project aims to provide an automated pre-operational service to reliably detect, monitor and assess floods at global scale within digital twin collaboration with NASA/JPL. The main objective is to connect data and existing models from both agencies in order to combine multi-scale simulations taking into account multiple phases of an entire flood event, from early alerts to post-event impact assessments. At the end, a proof-of-concept demonstration, planned after 18 months, will be presented with its multi-scale aspect over French and USA selected catchments.

3D Geospatial information plays a key role in many soaring sectors such as sustainable and smart cities, climate monitoring, ecological mobility, and economic intelligence. The availability of huge volumes of satellite, airborne and insitu data now makes this production feasible at large scale. It needs nonetheless a certain level of manual intervention to secure the level of quality, which prevents mass production. This paper presents the AI4GEO program that aims at developing an end to end solution to produce automatically qualified 3D Digital model at scale together with multiple layers of information.

Flood simulation and forecast capability have been greatly improved, thanks to the advances in data assimilation (DA). Such an approach combinesin situgauge measurements with numerical hydrodynamic models to correct the hydraulic states and reduce the uncertainties in model parameters. However, these methods depend strongly on the availability and quality of observations, thus necessitating other data sources to improve the flood simulation and forecast performances. Using Sentinel-1 images, a flood extent mapping method was carried out by applying a Random Forest algorithm trained on past flood events using manually delineated flood maps. The study area concerns a 50-km reach of the Garonne Marmandaise catchment. Two recent flood events are simulated in analysis and forecast modes, with a +24-h lead time. This study demonstrates the merits of using synthetic aperture radar (SAR)-derived flood extent maps to validate and improve the forecast results based on hydrodynamic numerical models with Telemac2D-ensemble Kalman filter (EnKF). Quantitative 1-D and 2-D metrics were computed to assess water-level time-series and flood extents between the simulations and observations. It was shown that the free run experiment without DA underestimates flooding. On the other hand, the validation of DA results with respect to independent SAR-derived flood extent allows to diagnose a model–observation bias that leads to over-flooding. Once this bias is taken into account, DA provides a sequential correction of area-based friction coefficients and inflow discharge, yielding a better flood extent representation. This study paves the way toward a reliable solution for flood forecasting over poorly gauged catchments, thanks to the available remote sensing datasets.