Periodic Reporting for period 1 - KAIROS (unlocKing the potential of AI-based weatheR forecasts for Operational benefitS)
Reporting period: 2023-06-01 to 2024-12-31
The KAIROS project—Unlocking the Potential of AI-based Weather Forecasts for Operational Benefits—is a three-year initiative (2023–2026) under the HORIZON-SESAR-2022-DES-IR-01 program. The project is designed to improve the accuracy and accessibility of meteorological (MET) hazard forecasts for the aviation industry through advanced artificial intelligence (AI) models.
KAIROS directly addresses these challenges by developing and deploying AI-based weather forecasting solutions tailored to aviation needs. The project’s objectives are twofold:
1 . Develop AI-based MET Forecasting Models :Leverage AI and machine learning (ML) algorithms to enhance the prediction of multiple weather hazards. Improve the accuracy, resolution, and lead times of forecasts over current Numerical Weather Prediction (NWP) models. Ensure that AI-generated forecasts can be deployed in real-time and integrated into aviation decision-support systems. AI MET Forecest are being developed for several hazards including Convective Weather, Low Visibility, Turbulence, High-Altitude Ice Crystals (HAIC), and Airborne Hazards (SO2 emissions and dust storms).
2. Assess Operational Benefits for Aviation End-Users. Demonstrate how AI-based forecasts can improve demand and capacity balancing (DCB) at all levels of air traffic management. Integrate AI models with existing ATM decision-support tools used by EUROCONTROL, ENAIRE, DSNA, and other key stakeholders. Quantify the benefits in terms of reduced delays, improved flight efficiency, and cost savings for airlines and airports.
KAIROS directly addresses these challenges by developing and deploying AI-based weather forecasting solutions tailored to aviation needs. The project’s objectives are twofold:
1 . Develop AI-based MET Forecasting Models :Leverage AI and machine learning (ML) algorithms to enhance the prediction of multiple weather hazards. Improve the accuracy, resolution, and lead times of forecasts over current Numerical Weather Prediction (NWP) models. Ensure that AI-generated forecasts can be deployed in real-time and integrated into aviation decision-support systems. AI MET Forecest are being developed for several hazards including Convective Weather, Low Visibility, Turbulence, High-Altitude Ice Crystals (HAIC), and Airborne Hazards (SO2 emissions and dust storms).
2. Assess Operational Benefits for Aviation End-Users. Demonstrate how AI-based forecasts can improve demand and capacity balancing (DCB) at all levels of air traffic management. Integrate AI models with existing ATM decision-support tools used by EUROCONTROL, ENAIRE, DSNA, and other key stakeholders. Quantify the benefits in terms of reduced delays, improved flight efficiency, and cost savings for airlines and airports.
The KAIROS Project has made significant progress in developing AI-based meteorological (MET) hazard forecasts for aviation. The project consists of two primary AI-driven forecasting solutions:
Solution 1: AI Convective Forecast – AI-based models predicting convective weather with high spatial and temporal resolution.
Solution 2: AI MET Applications – Expansion of AI methodologies for forecasting other aviation-related hazards, including low visibility, turbulence, high-altitude ice crystals (HAIC), and airborne hazards like SO2 and dust.
Solution 1: AI Convective Forecast
Three AI-driven convective models have been developed to meet different operational needs:
- Regional Forecast Model: Resolution: 0.25-degree Updates: Hourly, Forecast Horizon: Up to 48 hours
- National Forecast Model: Resolution: 0.125-degree Updates: Hourly, Forecast Horizon: Up to 48 hours
- Local Nowcast Model: Resolution: 1 km, Updates: Every 10 minutes, Forecast Horizon: Up to 3 hours
Solution 2: AI MET Applications
- Low visibility: The AI model for low visibility has been fully developed and is currently undergoing validation. It integrates observational data from METAR/TAF reports and satellite-derived fog detection to predict fog formation and dissipation patterns at airports.
- Turbulence: For turbulence forecasting, early models were initially constrained by limited historical datasets, but a major breakthrough occurred when the project secured access to real-time global turbulence reports through IATA’s Turbulence Aware initiative. This new data stream allows for continuous refinement of the AI model, improving its accuracy and applicability to airline operations.
- High Altitude Ice Crystals: Forecasting high-altitude ice crystals (HAIC) presents a more complex challenge due to the lack of overlapping observational datasets. The project has explored multiple sources, including Cloudnet lidar data, Rolls-Royce engine sensor data, and a satellite-based Ice Index developed by BIRA. However, inconsistencies between these sources have made validation difficult. Moving forward, KAIROS will integrate newly available real-time HAIC data to enhance model reliability.
- SO2/Dust: For SO2 and dust forecasting, the AI models currently rely on satellite-derived observations but are transitioning to live satellite data ingestion, enabling near-instant detection of volcanic ash and dust storms that can affect flight paths.
As the project moves forward, the next steps will focus on finalizing the validation of AI models through real-world trials with aviation end-users, refining forecast accuracy, and enhancing model interpretability for operational decision-making. The project will also quantify the operational benefits of AI-based forecasting, assessing its potential to reduce flight delays, optimize routing, and enhance airspace efficiency.
Solution 1: AI Convective Forecast – AI-based models predicting convective weather with high spatial and temporal resolution.
Solution 2: AI MET Applications – Expansion of AI methodologies for forecasting other aviation-related hazards, including low visibility, turbulence, high-altitude ice crystals (HAIC), and airborne hazards like SO2 and dust.
Solution 1: AI Convective Forecast
Three AI-driven convective models have been developed to meet different operational needs:
- Regional Forecast Model: Resolution: 0.25-degree Updates: Hourly, Forecast Horizon: Up to 48 hours
- National Forecast Model: Resolution: 0.125-degree Updates: Hourly, Forecast Horizon: Up to 48 hours
- Local Nowcast Model: Resolution: 1 km, Updates: Every 10 minutes, Forecast Horizon: Up to 3 hours
Solution 2: AI MET Applications
- Low visibility: The AI model for low visibility has been fully developed and is currently undergoing validation. It integrates observational data from METAR/TAF reports and satellite-derived fog detection to predict fog formation and dissipation patterns at airports.
- Turbulence: For turbulence forecasting, early models were initially constrained by limited historical datasets, but a major breakthrough occurred when the project secured access to real-time global turbulence reports through IATA’s Turbulence Aware initiative. This new data stream allows for continuous refinement of the AI model, improving its accuracy and applicability to airline operations.
- High Altitude Ice Crystals: Forecasting high-altitude ice crystals (HAIC) presents a more complex challenge due to the lack of overlapping observational datasets. The project has explored multiple sources, including Cloudnet lidar data, Rolls-Royce engine sensor data, and a satellite-based Ice Index developed by BIRA. However, inconsistencies between these sources have made validation difficult. Moving forward, KAIROS will integrate newly available real-time HAIC data to enhance model reliability.
- SO2/Dust: For SO2 and dust forecasting, the AI models currently rely on satellite-derived observations but are transitioning to live satellite data ingestion, enabling near-instant detection of volcanic ash and dust storms that can affect flight paths.
As the project moves forward, the next steps will focus on finalizing the validation of AI models through real-world trials with aviation end-users, refining forecast accuracy, and enhancing model interpretability for operational decision-making. The project will also quantify the operational benefits of AI-based forecasting, assessing its potential to reduce flight delays, optimize routing, and enhance airspace efficiency.
The KAIROS project has successfully developed and validated AI-based weather forecasting solutions that demonstrate significant improvements in aviation meteorology.
The successful implementation of KAIROS technologies could lead to major operational, economic, and environmental benefits for the aviation sector. By providing more accurate and timely forecasts, these AI-driven models can reduce flight delays, improve airspace capacity management, and enhance passenger safety. Airlines can optimize routing based on more reliable weather predictions, leading to fuel savings and lower CO2 emissions, directly supporting European Green Deal and SESAR environmental goals. Additionally, improved forecasts will enhance situational awareness for air traffic controllers, reducing the uncertainty that often leads to unnecessary flight diversions or holding patterns.
To fully realize the benefits of AI-based weather forecasting and ensure its adoption across the aviation industry, several key factors must be addressed:
Operational Demonstration and Deployment:
Large-scale demonstration campaigns with ANSPs, airlines, and airport operators will be needed to assess real-world performance and refine user interfaces. Continued collaboration with end-users will ensure that AI-generated forecasts are presented in an operationally meaningful and actionable format.
Regulatory and Standardization Alignment:
AI-based forecasting solutions must align with SESAR, ICAO, and WMO regulations to gain official acceptance for operational use. Participation in standardization bodies will be essential to ensure compliance with future ATM automation and AI integration frameworks.
The successful implementation of KAIROS technologies could lead to major operational, economic, and environmental benefits for the aviation sector. By providing more accurate and timely forecasts, these AI-driven models can reduce flight delays, improve airspace capacity management, and enhance passenger safety. Airlines can optimize routing based on more reliable weather predictions, leading to fuel savings and lower CO2 emissions, directly supporting European Green Deal and SESAR environmental goals. Additionally, improved forecasts will enhance situational awareness for air traffic controllers, reducing the uncertainty that often leads to unnecessary flight diversions or holding patterns.
To fully realize the benefits of AI-based weather forecasting and ensure its adoption across the aviation industry, several key factors must be addressed:
Operational Demonstration and Deployment:
Large-scale demonstration campaigns with ANSPs, airlines, and airport operators will be needed to assess real-world performance and refine user interfaces. Continued collaboration with end-users will ensure that AI-generated forecasts are presented in an operationally meaningful and actionable format.
Regulatory and Standardization Alignment:
AI-based forecasting solutions must align with SESAR, ICAO, and WMO regulations to gain official acceptance for operational use. Participation in standardization bodies will be essential to ensure compliance with future ATM automation and AI integration frameworks.