a project to join

QuoData is an SME specialised in statistics, data science and AI for quality assurance, monitoring and decision support in environmental, health and industrial domains.

For Water4All Topic 1, we focus on subtopics 1.2 (data integration & AI/ML modelling) and 1.3 (decision support & scenario analysis). Our contribution: AI- and statistics-based fusion of heterogeneous, multi-source monitoring data (sensors, remote sensing, legacy records) into harmonised, quality-assured data streams, with automated plausibility checks, uncertainty quantification and anomaly detection across varying spatial/temporal resolutions. On this basis, we build ML models for prediction, risk assessment and early-warning (e.g. water stress, contamination), and transparent, uncertainty-aware decision-support tools (dashboards, scenario analysis) for water managers and policymakers.

We bring long-standing experience turning complex, multi-country datasets into robust, reproducible, regulator-ready statistical pipelines (chemical risk assessment, proficiency testing, environmental monitoring), and specialise in making methods transferable across regions with differing data quality and availability.

We are looking for partners with hydrology/hydrogeology domain knowledge, monitoring data and stakeholder/end-user access, to jointly design and test a transferable, cross-country integrated monitoring and decision-support concept.

Topic 1. Integrated Monitoring and Assessment for Sustainable Water Management

We are looking for partners to jointly develop a transnational, integrated water monitoring and decision-support concept under Water4All Topic 1 (subtopics 1.2 and 1.3), building an AI- and statistics-based data harmonisation and fusion layer for heterogeneous national monitoring data (in-situ sensors, remote sensing, legacy records), combined with a transparent, uncertainty-aware decision-support tool (scenario analysis, risk/early-warning indicators) for water managers and policymakers.

The concept is designed to be tested and validated across at least two countries with contrasting monitoring infrastructures (e.g. dense sensor networks vs. sparse/legacy data), to demonstrate genuine methodological transferability rather than a single-case solution.

We (QuoData, Germany) contribute the AI/statistical methodology: data integration, quality assurance, uncertainty quantification, and the decision-support/scenario tool.

We are seeking partners who can contribute: (1) hydrological/hydrogeological domain expertise, (2) access to real monitoring data (sensor, remote sensing or legacy) from at least one additional country, and (3) stakeholder/end-user links (water authorities, utilities, policymakers) for co-design and validation of the assessment indicators and decision-support outputs. Partners with nature-based or infrastructure angles (Topics 2/3) are also welcome if interested in a joint cross-topic proposal.

artificial intelligence / machine learning, data integration, data harmonisation, decision support systems, uncertainty quantification, anomaly detection, statistical modelling, scenario analysis, data quality assurance, water quality monitoring

-