Climate AI Nordics

Climate AI Nordics

Nordic network for collaborations around tackling climate change using AI and machine learning.

HydroImaging: Mining Imaging Data for Hydrological and Environmental Modelling

Event date: 2026-09-13 to 2026-09-17

Event location: Tampere, Finland

HydroImaging is a focused half-day workshop held in conjunction with the IEEE International Conference on Image Processing (ICIP) 2026 in Tampere, Finland. The event serves as a cross-disciplinary forum for experts in computer vision, hydrology, and remote sensing to catalyze new collaborations for scalable, observation-driven environmental prediction.

The workshop aims to address pressing challenges related to climate change and the water cycle by leveraging multi-modal sensing, large-scale datasets like Copernicus, and pretrained foundation models. Attendees will explore how image processing and machine learning can be applied to environmental attribute prediction, including water quality, snow depth, and vegetation cover.

Workshop Highlights

Indicative Program Format

The program features a mix of high-level academic exchange and interactive sessions:

  • Invited Keynote Address: A 45-minute talk from a leading researcher in Earth Observation or environmental AI, sponsored by the Digital Water Flagship initiative.
  • Oral Sessions: Selected accepted papers presented as 15–20 minute talks, including audience Q&A.
  • Poster Session: Authors will present 5-minute spotlights followed by an interactive viewing session for direct engagement.
  • Awards: Recognition of the best paper and poster contributions followed by a closing discussion on future research directions.

Research Topics and Applications

The organizers welcome contributions on methods, applications, and open-data initiatives:

  • Methods: Data-centric machine learning for remote sensing, Vision-Language Models (LLMs, CLIP, VLMs), generative models (GANs, diffusion), and explainability in environmental AI.
  • Applications: Disaster relief and flood detection/mapping, snow and water prediction, marine monitoring, and sustainable agriculture.
  • Data & Benchmarks: New open datasets for hydrology, annotated imaging datasets for environmental analysis, and reproducible evaluation benchmarks.

Submission Information:

  • Paper Submission Deadline: May 13, 2026, at 23:59 AoE.
  • Notification of Acceptance: June 10, 2026.
  • Submission Guidelines: Papers must be a maximum of 4 pages (plus references) following the IEEE ICIP 2026 template for double-blind review. Accepted papers will be published in IEEExplore.

More info:

Published:

Categories:

You May Also Enjoy

Climate AI Nordics Newsletter, April 2026

Published:

The April 2026 Climate AI Nordics newsletter highlights the SafeCityLearn benchmark and researcher Miguel Nobre da Costa, while sharing a wealth of upcoming events, webinars, and job opportunities at the intersection of AI and climate action across the Nordic region.

Enhanced Flood Detection through Innovative integration of PolSAR, metaheuristic optimization, and deep learning-based segmentation

Event date:

Webinar with Solmaz Khazaei, KTH Royal Institute of Technology. Flood is the most common natural disaster in the world, and can have catastrophic impacts on human society and the environment, including infrastructure damage, agricultural losses, and casualties, resulting in widespread economic and social disruptions. In early studies, water body detection relied on on-the-spot investigation, hydrological models and common remote sensing techniques that face issues like slow processing and real-time delays. By addressing this challenges we propose a novel hybrid PoLSAR-metaheuristic-DL models and high-resolution remote sensing data to generate accurate and rapid flood mapping for one of the huge recent flood in France. Compared with standard synthetic aperture radars (SAR), polarimetric synthetic aperture radar (PolSAR) is an advanced technique of SAR remote sensing. So, by using polarimetric decomposition methods, features were extracted and feature selection problem, one of the most challenging, was solved by using metaheuristic techniques. The selected features fed into three deep learning-based segmentation models- U_Net_V3, Nested_UNet and Efficient_UNet. The reliability of the generated flood maps was evaluated using Accuracy, precision and recall metrics. Our experimental results indicate that Nested_UNet integrate with optimized PolSAR data achieves the highest segmentation performance, with an accuracy of 0.910, precision of 0.914, and recall of 0.909. These findings underscore the capability of Nested_UNet, demonstrates superior feature extraction abilities, making it a promising choice for real-time flood segmentation applications. Moreover, detecting the knowledge of flooded areas, officials can actively adopt steps to reduce the potential impact of flood, ensure the sustainable management of natural resources and mitigate flood impacts.