a project to join

Rplace is an Israeli AI/ML company building the decision layer for water basin management. We don't monitor water ourselves — we fuse data authorities and researchers already have (IoT sensors, lab results, satellite data, academic studies, field surveys) into one objective picture of basin health. Our machine-learning engine, trained on each basin's historical data, filters sensor noise, detects true pollution anomalies, correlates them against known pollution signatures, and identifies likely pollution sources. The output is not raw data or monitoring hardware, but actionable operational insights and recommendations — what is happening, why, and what to do next — plus audit-grade MRV (Monitoring, Reporting, Verification) reporting for regulatory and funding compliance.

Our validated predictive model on the Kishon River estuary (Israel) reaches ~80% accuracy forecasting pollution events, supporting the river authority's emerging boating-safety standard. We are expanding this AI decision layer to the Yarkon River (with Ben-Gurion University's water research institute) and to a constructed-wetland carbon/biodiversity MRV deployment (Hefer).

Keywords: machine learning for environmental data fusion, AI-driven pollution-source attribution, predictive analytics for basin management, MRV decision layer, operational recommendation systems for river authorities.

Topic 1. Integrated Monitoring and Assessment for Sustainable Water Management

Rplace is seeking to join a Water4All consortium under Topic 1 to validate and scale our AI/ML decision-support layer for water basin management across additional European river basins and hydrological contexts, beyond our current Israeli case studies (Kishon, Yarkon Rivers). We want to contribute our operational track record — a predictive pollution model already reaching ~80% forecasting accuracy in real-world deployment — as a working use case a research consortium can build on, test, and extend, rather than starting from a blank slate.

Joining a European consortium would let us: (1) validate our data-fusion and anomaly-detection methodology against different regulatory frameworks, basin types, and data-sharing standards, including alignment with the Water Framework Directive; (2) collaborate with academic and monitoring institutions holding complementary environmental datasets and domain expertise across diverse basin conditions; and (3) contribute practical, field-tested operational insight to research on integrated monitoring and assessment, helping bridge the gap between raw environmental data and actionable water-management decisions for river authorities and municipalities.

We see this as a genuine two-way contribution: transnational validation strengthens our methodology, while our real-world deployment experience strengthens the consortium's practical impact and commercialization pathway.

water quality monitoring, integrated water management, machine learning, artificial intelligence, pollution detection, predictive analytics, river basin management, data fusion, mrv (monitoring reporting verification), decision support systems

I will attend the 12th Kinneret Conference and Exhibition on Water Engineering and Innovation