SATI is a cyber-physical infrastructure for flood risk management, currently validated in a relevant environment (TRL 5). The system specializes in Information Integration (Gap 4) by accessing external data streams from AEMET, SAIH, and the Copernicus constellation (Sentinel-1 SAR and Sentinel-2 optical). This integration is robustly implemented via RESTful APIs managed in accordance with INSPIRE and OGC standards, using structured exchange protocols to ensure interoperability with official systems. The system incorporates historical series and real-time data from both gauging stations and rain gauges, with sufficient temporal and spatial resolution for accurate multi-scale analysis. This architecture enables Real-time Detection, Monitoring, and Analysis of Threats (Gap 2), providing responders with a Common Operational Picture (COP) featuring dynamic visualization of flow levels, precipitation, and flood hazard maps for return periods T=10, T=100, and T=500 years. By processing these heterogeneous streams through a Big Data architecture (based on Apache Kafka and Spark), SATI establishes the foundation for Actionable Intelligence (Gap 9), transforming raw data into key visual information for emergency decision-making. The system's operational effectiveness was demonstrated through its pilot implementation in the Adaja River basin (Ávila), successfully integrating SAIH Duero and AEMET data to enhance local resilience against flood events.
Contact
The primary goal of this proposal is to consolidate SATI as a reference tool for hydrological resilience in Europe, evolving from a data integration infrastructure into an actionable intelligence ecosystem for first responders. Specific objectives include: Establishing an Interoperable Common Operational Picture (COP): Integrating heterogeneous external data streams (Copernicus constellation, AEMET radars, and SAIH gauging networks) through APIs based on INSPIRE and OGC standards, eliminating the information fragmentation that currently delays coordinated response. Minimizing Operational Latency in Monitoring: Utilizing a robust Big Data architecture (based on Apache Kafka and Spark) for real-time processing of high-frequency data, enabling the identification of hydrological threats in basins where global models often fail. Strengthening Critical Decision-Making: Generating actionable intelligence through the dynamic overlay of flow levels and precipitation on hazard maps (return periods T=10, T=100, and T=500 years), allowing incident commanders to assess infrastructure risk remotely. Preparing for Operational Scaling (TRL 5 to TRL 7): Validating the system’s technical robustness within Civil Protection centers, ensuring that critical intelligence for public safety is derived from verified European sources, thus contributing to the Union's technological resilience. Relevance: SATI addresses the "last mile" accuracy gap in flood management, a problem that accounts for global losses exceeding $550 billion. Unlike "Big Tech" solutions that rely on low-resolution models, SATI provides local precision and democratizes access to advanced technology for local administrations. This proposal transforms disaster management from reactive response to operational anticipation, saving lives and protecting critical infrastructure across the EU.
The core innovation of SATI lies in its Cyber-Physical Infrastructure Hybridization approach, overcoming the traditional dichotomy between slow physical models and isolated data visualization. Unlike conventional solutions that operate with static historical series, SATI introduces three disruptive innovations for European resilience: High-Frequency Distributed Processing Architecture: SATI utilizes a Big Data engine based on Apache Kafka and Spark Streaming. This technical innovation enables the automatic ingestion and cleaning of noisy data from heterogeneous sources (Copernicus satellites, AEMET radars, and SAIH networks) in real-time. The ability to process massive streams with minimal latency is critical for managing flash floods in basins with response times of less than 24 hours. Solving the "Last Mile" Accuracy Gap: Unlike "Big Tech" solutions (e.g., Google Flood Hub) that rely on low-resolution global elevation models (30m-90m), SATI innovates by integrating high-precision local mapping. This allows for the dynamic visualization of hazard layers (T=10, 100, and 500 years) tailored to the actual orography of small and medium-sized catchments, where global systems are often "blind." Native Interoperability under European Standards: SATI is not a closed ecosystem. Its architecture is strictly managed under INSPIRE and OGC standards, utilizing RESTful APIs to ensure that the integrated information is consumable by any Civil Protection control center across Europe. Strength of the Approach: SATI represents a "technological bridge" innovation: it provides the robust and standardized infrastructure necessary for Deep Learning models (CNN/LSTM) to operate on high-fidelity data in future phases. By solving the problem of real-time data fragmentation and quality, SATI transforms a passive map viewer into a Common Operational Picture (COP) tool that significantly reduces the cognitive burden on responders during a crisis.
SATI resolves the critical issue of information fragmentation in hydrological emergency management (Gap 4). Currently, first responders operate with isolated data streams from multiple agencies (meteorology, river basin authorities, and satellites), which delays the creation of a Common Operational Picture (COP). SATI consolidates these heterogeneous streams in real-time through European standards (INSPIRE and OGC), ensuring that all agencies share a single, synchronized technical reality of the incident. Regarding operational latency, the system addresses the inability of traditional tools to process high-frequency data. Utilizing a Big Data architecture (Kafka/Spark), SATI transforms raw measurements from sensors and satellites into immediate visual information, reducing analysis time from hours to minutes. This capability is vital for Real-time Detection and Monitoring (Gap 2) of flash floods, where response times are critical for successful evacuations. Furthermore, SATI solves the "geographical blindness" of global solutions in small and medium-sized basins. By integrating local mapping and precise orography data, the system visualizes flood hazard layers (T10, T100, and T500 years) with a level of accuracy that generic tools cannot match. This provides incident commanders with Actionable Intelligence (Gap 9), allowing them to remotely and safely assess real risks to critical infrastructure and populated areas without unnecessarily exposing personnel to danger zones. In summary, the solution has demonstrated through its pilot validation (TRL 5) that it transforms reactive crisis management into an operational anticipation strategy, significantly enhancing responder safety and civil society resilience.
Multidisciplinary team with expertise in hydraulic engineering and geospatial systems. We combine expert knowledge in physical hydrology (HEC-HMS/RAS modeling) with advanced capabilities in Big Data architecture (Kafka/Spark) and satellite data ingestion (Copernicus). Our strength lies in the hybridization of traditional technical knowledge and software development for proactive flood risk management.
Multidisciplinary team with expertise in hydraulic engineering and geospatial systems. We combine expert knowledge in physical hydrology (HEC-HMS/RAS modeling) with advanced capabilities in Big Data architecture (Kafka/Spark) and satellite data ingestion (Copernicus). Our strength lies in the hybridization of traditional technical knowledge and software development for proactive flood risk management.