elias_admin

 ClimX Challenge

 ClimX Challenge

Sep 1, 2026 | Challenges & Competitions, ELIAS Alliance, Opportunities

Competition Details

About the Challenge

The ClimX Challenge is an ML competition on Kaggle and Hugging Face focused on extreme-aware climate model emulation. Organized by the Universitat de València and supported by ESA Phi-lab, it tasks participants with building fast surrogate models for the computationally heavy NorESM2-MM Earth System Model. Driven by greenhouse gas and aerosol inputs, models predict daily 2D maps across seven surface variables. Submissions are uniquely evaluated on 15 derived extreme climate indices—such as heatwaves, droughts, and severe rainfall—to ensure emulators capture high-impact tail risks rather than simple averages.

Z
Scope & Objectives

  • Problem Tackled: Earth System Models (ESMs) like NorESM2-MM are computationally expensive, restricting dense exploration of climate forcing scenarios, initial condition ensembles, and extreme events. Traditional climate emulators often optimize for average climate state, failing to capture severe, policy-relevant tail events.

  • Objective: Build fast, accurate machine learning surrogate models (emulators) driven by greenhouse gas and aerosol forcing trajectories (and optionally past climate states) that output daily 2D climate variable maps and faithfully capture high-impact climate extremes.

  • Impact: Enables rapid climate scenario testing, robust quantification of tail risks, and decision support for climate adaptation without requiring computationally prohibitive supercomputer ESM runs.

Dataset & Resources

  • Source Simulation: High-resolution daily outputs from the NorESM2-MM Earth System Model.

  • Target Daily Variables (7 total):

    • Near-surface air temperature (tas), Daily max temperature (tasmax), Daily min temperature (tasmin)

    • Precipitation (pr), Near-surface specific humidity (huss), Sea level pressure (psl), Near-surface wind speed (sfcWind).

  • Derived Extremes (15 Leaderboard Indices): ETCCDI-style extreme climate indices derived from daily temperature and precipitation fields (e.g., TXx, SU, TR, CDD, Rx5day, R95pTOT).

  • Data Splits & Scenarios:

    • Training: Historical period (1850–2014) + SSP1-2.6, SSP3-7.0, and SSP5-8.5 scenarios (2015–2100).

    • Testing: Held-out SSP2-4.5 scenario (2015–2100).

  • Data Access Tiers:

    • Hugging Face (Full Dataset): ~172GB–200GB full-resolution dataset in Zarr/NetCDF format ($192 \times 288$ native grid, ~1° resolution) for full model training.

    • Kaggle (Lite Dataset): <1GB spatially coarsened dataset ($12 \times 18$ grid) for rapid pipeline prototyping and debugging.

  • Codebase & Baseline Resources: Official GitHub repository (IPL-UV/ClimX) containing end-to-end notebooks (playground.ipynb), environment specifications, helper utilities, and baseline benchmarks (Climatology, Linear Surrogates, Neural Networks, Graph Neural Networks).

Eligibility

  • Sign Up: Register on Kaggle for either the Main Track (deterministic) or UQ Track (probabilistic/uncertainty quantification).

  • Develop Emulator: Build an emulator that predicts the 7 daily 2D surface variables for the held-out test forcing scenario (SSP2-4.5).

  • Compute Indices & Format: Deriving the 15 extreme climate indices from your daily target predictions.

  • Submit Entry: Upload the derived extreme index maps (86 annual time steps for SSP2-4.5 at the full $192 \times 288$ grid resolution, totaling 4,755,456 rows per index) to Kaggle.

    • Rule: Models must predict daily variables first; direct prediction of leaderboard indices without generating daily intermediate fields is strictly prohibited.

Z
Expected Outcomes
  • Model Innovation: Development of state-of-the-art spatio-temporal ML emulators capable of preserving fine-scale physical tail distributions.
  • Scientific Insights: Rigorous benchmark comparison across architectures (CNNs, GNNs, Transformers, probabilistic emulators) evaluated specifically on climate extremes rather than spatial/temporal means.
  • Publication & Dissemination: Winning entries and challenge results will be highlighted and presented at the Tackling Climate Change with Machine Learning workshop at NeurIPS 2026 in Sydney.
Key Dates

  • Running Period: September 1, 2026 – November 30, 2026 (Launch Challenge).

  • Key Milestones:

    • September 1, 2026: Competition officially opens on Kaggle.

    • September 29, 2026: NeurIPS workshop paper acceptance notification.

    • November 30, 2026: Submissions close, leaderboard freezes, and finalist code reproducibility checks begin.

    • December 11–12, 2026: Results presentation at the NeurIPS 2026 Tackling Climate Change with Machine Learning workshop in Sydney (upon paper acceptance).

  • Persistence: ClimX is a persistent benchmark; all datasets, metrics, and starter code remain open and publicly available after the launch challenge concludes.

Please make sure to check out the detailed description:
GET STARTED
Evaluation Criteria

How Entries Will Be Evaluated

  • Main Track (Deterministic): Evaluated using the region-wise normalized Nash–Sutcliffe efficiency (nNSE), averaged across all 15 derived climate extreme indices over IPCC AR6 land regions:
    nNSEij = R²ij ⁄ (2 − R²ij)
    This metric maps cell-level R² to the range (-1, 1] (where 1 = perfect match, 0 = climatology/mean predictor), computes area-weighted regional scores, and averages them across indices.
  • UQ Track (Probabilistic): Evaluated using an analogous regional Continuous Ranked Probability Score (CRPS)-based metric.
  • Masking Filter: Grid cells with negligible temporal variability (Var(y) ≤ ε²) are masked out to avoid instability in ratios.

Judging Panel

  • Review Panel: Challenge chairs and research leaders from the Image Processing Laboratory (IPL / ISP) at Universitat de València.
  • Responsibilities: Leaderboard validation, code review for top entries, and verification of rule compliance (confirming models predict daily fields prior to index calculation).
Prizes

  • Sponsoring Body: ESA Phi-lab (European Space Agency).

  • Prize Pool (conditional on NeurIPS workshop paper acceptance):

    • 1st Place: €1,000

    • 2nd Place: €500

    • 3rd Place: €300

  • Travel Support: Up to €500 per winning team to support in-person presentation at NeurIPS 2026 in Sydney.

Have Questions?

For further information or queries, please contact:
📧Oscar José Pellicer Valero (oscar.pellicer@uv.es)

Repository / Technical Support: Open an issue or discussion thread on the ClimX GitHub Repository.

Registration Links & Resources
    Academic Partners
    ELIAS Unveils Winners of 2nd Open Call: Accelerating AI Solutions for European Sustainability and Resilience

    ELIAS Unveils Winners of 2nd Open Call: Accelerating AI Solutions for European Sustainability and Resilience

    Aug 20, 2026 | Press Release

    Press Release: ELIAS Unveils Winners of 2nd Open Call: Accelerating AI Solutions for European Sustainability and Resilience

    Trento, Italy – August 20th, 2026

    The European Lighthouse of AI for Sustainability (ELIAS) has officially selected four high-impact winning projects for its 2nd Open Call. These innovative initiatives receive funding, expert support, and pilot validation to advance AI technologies addressing wildfire prevention, energy-efficient digital infrastructure, edge-computed energy management, and sustainable building renovation across Europe.

    By translating frontier AI research into real-world applications, the winning projects support the goals of the European Green Deal by prioritising energy efficiency, carbon reduction, data privacy, and resource awareness.

    Interest Extending Well Beyond Europe

    ELIAS Call Results

    The call attracted remarkable interest, highlighting the vibrant European and global AI innovation ecosystem committed to tackling pressing societal and environmental challenges.

    285 Submissions
    34 Countries

    Targeted Use Cases (UCs)

    UC1: AI for Building Optimisation 64
    UC2: AI for Monitoring the Virtual Infrastructure 38
    UC3: Responsible User-centric Advertising 14
    UC4: Mitigating misinformed migrant perception in EU 12
    UC5: AI for Forecasting Vegetation State 48
    UC6: Open Materials Discovery Project 10
    UC7: Personalised Co-piloting Systems 87
    Other Relevant Topics 56
    Each selected project will enter a six-month development programme, receiving up to €60,000 in funding, alongside visibility through ELIAS channels and events.

    Thorough Evaluation Process

    Each proposal underwent a rigorous assessment by consortium members and two independent experts. Final selection was reserved strictly for the highest-scoring projects, with tie-breakers taking into account diversity, broader environmental and social impact, and submission timing.

    Excellence Technical ambition and innovation.
    Impact & Scope Sustainability alignment and market potential.
    Implementation Team execution capability.

    Meet the Winners

    RenovAIte (AI for Data-Driven Energy Renovation)

    By NOBATEK — France | Focus Area: UC1 – AI for Building Optimisation 

    Addressing Europe’s ageing infrastructure, NOBATEK’s RenovAIte platform harnesses domain-specific Natural Language Processing (NLP) and generative AI to modernise construction workflows. The tool reduces document processing times by 60% and generates context-aware renovation scenarios that lower operational energy costs by up to 30% for tenants, tackling energy poverty and reducing embodied carbon footprints.

    AdaptiveSight (AI for Sustainable Digital Out-of-Home)

    By LIBRA AI Technologies P.C. — Greece | Focus Area: UC1 – AI for Building Optimisation 

    AdaptiveSight uses on-device computer vision to cut the energy consumption of Digital Out-of-Home (DOOH) advertising screens by 30–50%. Developed by LIBRA AI Technologies, the attention-aware system dynamically adjusts brightness and refresh rates only when spectators are looking at the display. All biometric processing occurs locally on Jetson Orin Nano edge nodes, ensuring complete compliance with European privacy standards.

    HOTSPOT (Hybrid Orbital and Telemetric Sensors for Predicting On-site Threats)

    By IoTique (Igloo Srl) — Italy | Focus Area: UC5 – AI for Forecasting Vegetation State 

    Developed by Trentino-based IoTique, HOTSPOT combines satellite imagery with low-cost LoRaWAN environmental sensors measuring temperature, humidity, and vegetation dryness to prevent wildfires. By applying foundation models (such as TimesFM) for anomaly detection and geospatial optimisation, the system alerts local authorities early via a simple online dashboard while engaging citizens directly in environmental stewardship.

    GUARDIAN (Green, User-guided, Auditable Resource-aware Deployment for Industrial AI Networks)

    By Ratio1 — Romania | Focus Area: UC7 – AI for Sustainable Energy Operations 

    Ratio1’s GUARDIAN introduces a reusable toolkit and benchmarking engine that shifts operational AI workloads away from power-heavy, centralised GPU clouds onto decentralised, CPU-first edge devices. Designed for renewable energy monitoring and operations-centre co-piloting, GUARDIAN minimises unnecessary computing and data transfer while ensuring human operators remain in full control through auditable outputs

    Driving European Resilience

    As extreme weather events, rising energy costs, and digital infrastructure demands test Europe’s infrastructure, the winning projects directly reinforce regional climate resilience and technological sovereignty. Moving from research concepts to operational pilots, these solutions demonstrate how lightweight, resource-aware AI can deliver tangible environmental protection and economic stability:

    • Climate Adaptation & Ecosystem Protection: Systems like HOTSPOT empower small municipalities and rural agencies with early-warning wildfire intelligence, safeguarding biodiversity, reducing emissions from burning vegetation, and strengthening community emergency preparedness.
    • Infrastructure & Energy Decarbonisation: Platforms such as RenovAIte and AdaptiveSight reduce structural energy waste across public spaces and built environments, accelerating building retrofits while supporting the EU Green Deal’s 55% emissions reduction target.
    • Technological Autonomy & Data Sovereignty: Architectures like GUARDIAN validate that complex AI operations can run reliably on local CPU edge networks, lowering reliance on energy-intensive cloud facilities while keeping critical operational data secure, private, and fully auditable under the EU AI Act.

    The 2nd Open Call builds upon the achievements of the ELIAS 1st Open Call, which funded four pioneering projects addressing critical European sustainability challenges: https://elias-ai.eu/open-call/ 

    Access press release here: ELIAS Unveils Winners of 2nd Open Call: Accelerating AI Solutions for European Sustainability and Resilience

    For the full ranking list of evaluated proposals, visit: ELIAS 2nd Open Call – Ranking List

     

    Contact

    Aygun Garayeva, PR Manager, ELIAS

    Nicu Sebe, Coordinator, ELIAS

    elias-coordination@unitn.it

    IDEASHACK 2026 Highlights the Power of European AI Innovation

    IDEASHACK 2026 Highlights the Power of European AI Innovation

    Aug 3, 2026 | ELIAS Alliance, Events, News

    From its online launch on April 24, 2026, through weeks of intense development, to its high-energy Grand Finale in Warsaw on June 19, 2026, IDEASHACK 2026 has officially wrapped up. The pan-European “sciencepreneurship” hackathon—organized by the IDEAS Research Institute under the ELIAS project and ELLIS Unit Warsaw—brought together top emerging talent, researchers, and innovators to solve one of deep-tech’s biggest questions: How do we effectively translate cutting-edge scientific research into market-ready business solutions?

    From Academic Labs to Real-World Impact

    IDEASHACK 2026 set out with a clear mission: building a bridge between science and business. The initiative welcomed interdisciplinary teams from across Europe to design AI-driven concepts and platforms that map academic expertise and accelerate knowledge transfer.

    Out of 20 squads competing from all over Europe during the online sprint, the top 5 finalist teams earned their spot at the high-stakes Demo Day in Warsaw. Presenting before a demanding jury of experts representing science, industry, and venture capital, the finalists demonstrated both scientific rigor and entrepreneurial potential.

    Winner Spotlight & Awards

    With a total prize pool of €12,000, the jury recognized the most feasible, original, and impactful solutions for accelerating Europe’s AI ecosystem.

    • 🥇 1st Place (€5,000):  Team Master Builders

    • Project Title: ResearchRadar

      • An AI-powered research intelligence platform designed to bridge the gap between industry R&D needs and academic research. Built entirely on open data (OpenAlex, CORDIS, ORCID), it allows users to describe an industry need in plain language and returns ranked academic papers mapped to calibrated Technology Readiness Levels (TRL 1–9) with transparent, explainable evidence paths.

    • 🥈 2nd Place (€4,000): Team Lockedin

    • Project Title: LabConnectors

      •  An operating system and ecosystem designed to turn research events (hackathons, conferences, meetups) into structured pipelines for pilots, partnerships, and investments. It features AI-ranked talent discovery with commercial intent signals, EventOps workflows, and automated warm introductions between scientists, corporate R&D teams, and investors.

    • 🥉 3rd Place (€3,000):  Team Fjaka

    • Project Title: ScienceBridge

      • A translation and trust platform aimed at connecting orphaned, cross-domain scientific research with commercial industry applications. It utilizes an interactive 3D knowledge graph (GraphRAG), AI-generated synthesis cards that turn research fragments into business hypotheses, and an agentic verification system that provides tamper-proof “credibility passports” for researchers.

    Ecosystem Synergy & Strategic Partnerships

    IDEASHACK 2026 stands as a testament to the power of cross-border and cross-sector collaboration. By connecting emerging researchers with industry leaders, the initiative reinforces Europe’s vision for trustworthy, sustainable, and high-impact AI.

    The success of this year’s edition was made possible through the support of key ecosystem partners:

    • Strategic Partner (IDEAS Research Institute): ORLEN S.A.

    • Partners: Swissnex, Google, Polish Development Fund (PFR), ELIAS Project

    • Patronage: Ministry of Digital Affairs of the Republic of Poland, Polish Agency for Enterprise Development (PARP)

    • Media Partner: ITwiz

    Relive the Energy: Official Recap Video

    Check out the official video recap below to experience the highlights, pitching moments, and vibrant energy from Demo Day in Warsaw:

    ▶️ Watch the IDEASHACK 2026 Recap Video on YouTube

    From Research to Innovation: Key Insights from the Workshop on Multimodal Foundation Models

    From Research to Innovation: Key Insights from the Workshop on Multimodal Foundation Models

    Jul 27, 2026 | Events, News, TDW

    On 1 July 2026, ELIAS co-organised the workshop “Multimodal Foundation Models: From Research to Innovation” at the Institut d’Estudis Catalans in Barcelona, bringing together nearly 150 on-site participants and 100 livestream viewers. The event provided a platform to explore how open, sovereign, and trustworthy multimodal AI models can transition from frontier academic research into real-world applications across Europe.

    The event is hosted by the Computer Vision Center (CVC), co-organised by ELIAS, ELLIOT, ELLIS Unit Barcelona, the ELLIS Programme on Multimodal Learning Systems, ELIAS, and XARXA RDI-IA, and supported by the city council of Barcelona.

    Frontier Research & Technical Advances

    The morning sessions delivered deep dives into the capabilities of multimodal systems—from egocentric perception to efficient model architectures:

    • Human Behaviour Analysis: Prof. Ioannis Patras (QMUL / Tavus) presented multimodal adaptation and generation techniques for digital humans combining voice, facial dynamics, and emotional intelligence.

    • Egocentric World Modelling: Prof. Dima Damen (University of Bristol / Google DeepMind) discussed action understanding and object interactions from wearable sensor streams, leveraging benchmarks like EPIC-KITCHENS.

    • Model Merging: Dr Joost van de Weijer (CVC) introduced training-free methods to combine task-specific models into single multi-task foundation models.

    • Robot World Models: Jai Bardhan (CIIRC CTU Prague) showcased how pretrained video diffusion models serve as data-driven alternatives to simulators for robotic planning and policy evaluation.

    • Medical Diagnostic AI: Prof. Vittorio Murino (University of Verona / IIT) demonstrated few-shot adaptations of CLIP for image- and pixel-level anomaly segmentation across medical imaging modalities.

    From Research to Innovation: Key Insights from the Workshop on Multimodal Foundation Models

    Translating Science into Innovation

    Industry applications took centre stage with an invited presentation by Eric Verdaguer (CEO of LogMeal), who detailed how computer vision and depth-sensing AI are deployed in healthcare settings to monitor hospital nutrition and reduce food waste.

    A dedicated panel on commercialising frontier AI—moderated by Prof. Dimosthenis Karatzas (CVC / ELLIS Barcelona)—featured insights from Jordina Torrents (HP Inc. AI Lab), Isabelle Siegrist (Sandborn / ETH AI Center), Lukas Fischer (NXAI), and Eric Verdaguer. The discussion highlighted strategies for bridging technical research with enterprise needs, venture creation, and trustable deployment.

    Strengthening Europe’s AI Network

    Featuring opening and closing remarks from Javier Selva and Rafael González (Department of Research and Universities, Government of Catalonia), the workshop emphasised Barcelona’s role as a major hub for AI transfer.

    Hosted by the Computer Vision Center (CVC), the workshop was co-organised by ELIAS alongside ELLIOT, ELLIS Unit Barcelona, the ELLIS Programme on Multimodal Learning Systems, and XARXA RDI-IA, with municipal support from the Barcelona City Council.

    Watch the event recording here!

    Check out the previous editions: Theme Development Workshops

    ELLIOT – European Large Open Multi-Modal Foundation Models For Robust Generalization On Arbitrary Data Streams (GA No. 101214398 ) aims to develop the next generation of open Multimodal Generalist Foundation Models (MGFMs): AI systems designed to learn general knowledge and patterns from massive amounts of data of various types — from videos, images, and text to sensor signals, industrial time series, and satellite feeds — and efficiently transfer the generic knowledge learned in generalist manner to a wide variety of downstream tasks. Unlike current foundation models that face significant challenges in terms of generalisation capabilities and support for multimodal data, ELLIOT’s models will be capable of robust generalisation across conditions not seen during the training, coping well with dynamic, noisy, and temporally-evolving multimodal data streams. Real and synthetic data will be leveraged for training MGFMs and for further adapting them for specific downstream tasks in domains like media, earth observation, robot perception, mobility, computer engineering and workflow automation. European HPC infrastructure is directly included in the consortium to ensure the availability of the necessary computing resources. www.elliot-ai.eu

    AI Launchpad Batch #4

    AI Launchpad Batch #4

    Jul 23, 2026 | AI Launchpad, ELIAS Alliance, Opportunities

    Batch #4

    Are you elegible?

    Teams of 2-4 entrepreneurial students/researchers.

    Completing higher education at a European University.

    Aiming to develop AI technologies into marketable products/services.

    Goal: Launch a VC-fundable start-up with European/global impact.

    Our Programme

    Visiting Hub Program

    The two-week immersive program designed specifically for AI startups looking to navigate and strategize their entry into the European market. This initiative offers participants a deep dive into the unique challenges and opportunities of the European landscape, facilitating tailored growth and expansion strategies

    Market Exploration
    Network Building

    Understand Market Dynamics

    Analyse the current trends and economic conditions in the German and broader European markets.

    Engage with Thought Leaders

    Participate in discussions with leading thinkers in the AI and tech industries.

    Identify Sector Opportunities

    Pinpoint sectors with high growth potential and demand for your AI solutions.

    Form Strategic Alliances

    Explore opportunities for forming alliances with established businesses that can offer complementary strengths.

    Assess Competitive Landscape

    Evaluate local competition to strategize positioning of your AI startup.

    Cultivate Relationships with Local Entrepreneurs

    Forge connections with local startups and entrepreneurs for cross-cultural insights and collaboration.

    Recognise Regulatory Challenges

    Learn about specific regulatory requirements and hurdles in Europe that could impact market entry.

    Initiate Investor Dialogues

    Meet potential investors to discuss funding possibilities and gain financial insights.

     

    The local accelerators

    Participants can apply to one of our 10 local hubs to be part of a 1-2 week visiting hub program, allowing them to fully immerse themselves in a vibrant ecosystem. This period is crucial for deep engagement with the community and iterative refinement of innovative projects.

    Choose between one of ten local accelerator hubs, each offering a unique and tailored programme for your start-up:

    INiTS | Vienna, Austria
    DTU Skylab | Lyngby, Denmark
    Campus Founders | Heilbronn, Germany
    ETH AI Center &| Zurich, Switzerland
    KTH Innovation | Stockholm, Sweden
    XPLORE Venture Creator | Munich, Germany
    HPI – ELIAS Node Potsdam | Potsdam, Germany
    CVC – ELIAS Node Barcelona | Barcelona, Spain
    Yes!Delft | Delft, Netherlands
    Cyber Valley – ELIAS Node Tübingen | Tübingen, Germany

    How does it work?

    Nomination

    Startups are referred by local facilitators. No open calls, just quality.

    Onboarding

    Join 2–3 online workshops to align goals, prepare assets, and connect early.

    Immersion

    Spend 2 weeks in a new European hub, engage in curated meetings, events, and VC introductions.

    Centralised Application Process

    Say goodbye to the hassle of applying to multiple incubators. With AI Launchpad, you can apply through our central portal and gain access to a network of premier AI startup ecosystems.

    A Network of AI Experts and Entrepreneurs

    Leverage a pan-European network of AI experts and entrepreneurs. Access centralised learning from ten hubs, bridging the gap between science and entrepreneurship

    Immersion and Expansion

    Participate in either the Spring or Fall season by joining a curated 1–2 week visit to a leading European AI hub. The program is tailored to your market goals and maturity, connecting you with investors, corporate partners, and key ecosystem leaders. To maximise impact, you’ll also take part in targeted sessions before and after your visit.

    What to Submit

    1. A pitch deck or one-pager that clearly presents your startup
    2. A 1-minute video introducing your team — keep it simple, real, and authentic. Upload it to Loom or YouTube and share the link with us

      Deadline: September 1st, 2026 at 23:59 CET

      We can’t wait to discover your story — and learn how your AI venture is shaping the future.

      Get Nominated for the Fall Season!

      More info under: www.ai-launchpad.eu | For enquiries regarding nominations, programmes, or collaborations, please contact:

      Contact

       entrepreneurship@ai.ethz.ch