Climate AI Nordics

Climate AI Nordics

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

Junior researcher in machine learning

RISE is hiring a junior researcher in machine learning for climate adaptation.

Do you want to use your expertise in AI to help build a greener future? As a junior researcher, you will conduct research in machine learning and initially work on the project “Grey to Green”, where we develop an AI-based tool that helps cities transform grey areas into multifunctional green spaces. The position offers a unique opportunity to grow within a strong professional network of leading researchers across the Nordics, with the possibility of starting PhD studies as part of your work.

Main duties include developing machine learning solutions, writing scientific articles, and collaborating with project partners. We are looking for someone with a Master’s degree in a relevant field (e.g., computer science, applied mathematics, remote sensing) and coursework in AI, machine learning, and image analysis. Experience with geospatial data is meriting.

The position is in-person, in Gothenburg, Sweden.

Link to application page will be added soon.

Full details about position.

You May Also Enjoy

Climate AI Nordics Newsletter, October 2025

Published:

In our October newsletter, we celebrate one year of Climate AI Nordics with a look back at our community's key milestones and achievements. This issue also features a new paper on urban change detection, details on upcoming workshops at EurIPS 2025, and several new job opportunities.

Multi-resolution learning with neural operators and long short-term memory neural networks

Event date:

Webinar with Katarzyna Michalowska, SINTEF. In real-world applications, collecting large amounts of high-resolution data is rarely practical. The cost of specialized equipment, time-intensive measurements, and expensive high-fidelity simulations often means that high-resolution samples are limited. Meanwhile, low-resolution data are far easier to obtain and often exist in abundance, creating a common scenario: plentiful coarse data but limited fine data. Standard neural networks, which require fixed-resolution inputs, cannot exploit this imbalance and typically perform poorly when generalizing across resolutions. Deep operator networks, or DeepONets offer a distinct advantage over standard neural networks through a property known as discretization invariance, enabling learning across varying data resolutions. However, DeepONets alone do not effectively capture long-term temporal dependencies, limiting their performance on problems involving long time horizons. In this talk, we present a framework that addresses both challenges: multi-resolution learning and long-time horizon modelling. We achieve this by extending DeepONets with long short-term memory networks (LSTMs) and introducing a multi-stage training procedure that leverages data at multiple resolutions. This hybrid architecture first learns global dynamics from abundant low-resolution data and then fine-tunes on limited high-resolution samples, capturing both multi-resolution structure and temporal dependencies. In tests on nonlinear dynamical systems, our multi-resolution DON-LSTM achieves lower generalization error and requires fewer high-resolution samples than standard DeepONet or LSTM models. Our results demonstrate that the proposed approach is well-suited for real-world scenarios where high-resolution data are limited, highlighting its potential for practical applications across science and engineering.

Self-supervised pre-training for glacier calving front extraction from synthetic aperture radar imagery

Event date:

Webinar with Nora Gourmelon, Friedrich-Alexander-Universität Erlangen-Nürnberg (FAU). The factors influencing melt at glacier fronts facing the ocean remain an active area of research. To better understand these factors, it is essential to monitor changes in glacier calving fronts. Due to the importance of weather-dependent and seasonal variations, Synthetic Aperture Radar (SAR) is the preferred imaging method for such monitoring. In recent years, deep learning models have been developed to automate the extraction of calving front positions, however, their performance on SAR data remains suboptimal. Limited labeled data and high variability in SAR images hinder traditional supervised learning. Foundation models pre-trained on large, diverse datasets could provide robust feature representations that require minimal labeled data for fine-tuning on specific SAR tasks. However, in preliminary experiments, we found that the domain gap is too large for the task of extracting calving fronts from SAR imagery, and foundation models fine-tuned on the "CAlving Fronts and where to Find thEm" (CaFFe) benchmark dataset performed subpar. Therefore, we compiled an unlabeled dataset of Sentinel-1 SAR image sequences of Arctic glaciers, each associated with a single Sentinel-2 optical reference image. Using this dataset, we developed a novel multi-modal self-supervised pre-training strategy and applied it to pre-train a hybrid CNN-transformer model. Fine-tuning on the CaFFe benchmark showed that the pre-trained model outperforms its non-pre-trained counterpart, enabling more robust calving front segmentation and demonstrating the potential of data-efficient learning for SAR imagery.

Featured paper: Continuous urban change detection from satellite image time series with temporal feature refinement and multitask integration

Published:

This paper presents a method to continuously detect urban changes in high-resolution satellite image time series (SITS). Traditional urban change detection models often rely on bi-temporal image pairs acquired multiple years apart, limiting their ability to capture gradual, ongoing urbanization processes. The paper introduces a deep learning framework, including two novel modules to enhance segmentation feature maps extracted from SITS and integrate multi-task model outputs (i.e., building segmentations and dense change information). The paper’s findings show the limitations of bi-temporal change detection methods, as they cannot exploit multitemporal information in SITS. In contrast, their continuous urban change detection method achieves accurate urbanization monitoring results even at short time intervals.