WaterSENSE EC Project
Why was WaterSENSE needed?
Water scarcity and inefficient water use pose significant challenges to global agriculture, ecosystems, and economies. Sustainable water management is critical, particularly in regions heavily reliant on irrigation. Traditional methods of monitoring water use – such as ground-based measurements – were often costly, labor-intensive, and limited in scale.
WaterSENSE addressed this gap by leveraging Earth Observation (EO) technology, providing reliable, near real-time insights into water availability and use. The project enabled data-driven decision-making in agriculture, water governance, and environmental sustainability by offering scalable, cost-effective, and transparent water monitoring services.
What was WaterSENSE?
WaterSENSE was a Horizon 2020-funded project that developed and demonstrated an EO-based water monitoring system. It integrated satellite data, hydrological models, and in-situ observations to deliver high-precision, real-time information on water productivity, irrigation efficiency, and resource allocation.
Key technical achievements of WaterSENSE:
-
- EO-based evapotranspiration (ET) monitoring: Advanced satellite-derived algorithms were used to estimate actual ET, helping identify areas of over- or under-irrigation.
- Irrigated land classification: The project developed machine-learning models to detect and map irrigated land dynamically, improving water-use monitoring.
- Farm Water Balance Toolbox: A decision-support tool combined EO data with hydrological models to optimize farm-scale water management.
- Integration with HydroNET: WaterSENSE’s data was operationalized through HydroNET, allowing users to visualize and analyze water data interactively.
- Basin-scale water allocation insights: The project successfully scaled monitoring from field-level assessments to regional and national applications, particularly in Australia’s Murray-Darling Basin.
How was WaterSENSE set up?
WaterSENSE followed a structured approach, ensuring scientific rigor, operational feasibility, and real-world applicability:
- EO Data Integration & Processing
- The project used Copernicus Sentinel-2 and Sentinel-3 data combined with in-situ hydrological data.
- Machine-learning models refined EO-based irrigation estimates for greater accuracy and scalability.
- Hydrological Model Development & Validation
- Hybrid hydrological models combined EO-derived water cycle data with on-ground measurements.
- The system was validated using benchmark datasets to ensure precision in different climate zones.
- User-Centric Demonstration & Capacity Building
- The Murray-Darling Basin served as a primary testbed, where the tools were applied to real-world water challenges.
- WaterSENSE engaged with farmers, water agencies, and policymakers, refining its tools based on user feedback.
By providing a scalable, operational, and science-backed approach, WaterSENSE significantly advanced EO-based water management, paving the way for its successor project, REINFORM.