Skip to main content
KTH Ri.se Stockholm University
Navigation

Activities & Results

Find out what’s going on!

Activities, awards, and other outputs

  • Two Apps developed within this project, one for the SDG Indicator 11.3.1 Land Use Efficiency Calculation and the other for Urban Data Comparison, won the 2022 Group on Earth Observation (GEO)’s SDG Award at the GEO Plenary in early November in Ghana. (Note: GEO is a partnership of more than 100 national governments and in excess of 100 Participating Organizations that envisions a future where decisions and actions for the benefit of humankind are informed by coordinated, comprehensive and sustained Earth observations.)
  • EO-AI4Wildfire within this project was selected among the Royal Swedish Engineering Academy’s 2020 Innovation 100 List.

Notable Presentations

  • Ban, Y. 2022. invited speaker and panellist at “Implementing the Harmonized Global Urban Monitoring Framework (UMF)” and at “Training Sessions on EO4SDG Toolkit” at the 11th UN World Urban Forum, June 28-30, 2022, in Katowice, Poland, oral presentation, panel discussion, and training.
  • Ban, Y. 2022. “EO-AI4GlobalChange” at the Geo for Good Lighting Talk Series #10 (virtual): Climate Action & Science, June 22, 2022, oral presentation.
  • Ban, Y. 2022. “Earth Observation Big Data & AI for Monitoring Urban SDG Indicators”. ISPRS congress SDGs Forum, June 7, 2022, oral presentation and panel discussion (virtual).
  • Mörtberg, U. 2022. Digital tools for ecological assessment of landcover changes. Digital Futures seminar: DF-Fly High Seminar, March 15th, 2022
  • Ban, Y. 2021. EO-AI4GlobalChange, Keynote, the 28th International Conference on Geoinformatics, Nov. 2021, virtual.
  • Ban, Y. 2021. EO4ResilientCities, UN COP26 Side Event “Earth Observations to build sustainable and climate resilient cities and communities”, Nov. 2021, virtual.
  • Ban, Y. 2021. EO-AI4EnvironmentalChange, Invited speaker, Vinnova and Swedish National Space Agency’s event on Horizon Europe Cluster 4 – Digital, Industry and Space and Cluster 6 – Food, Bioeconomy, Natural Resources, Agriculture and Environment, May 26, 2021.
  • Ban, Y. 2021. EO-AI4Wildfire at Google GEO for Good Virtual Summit 2021.
  • Ban, Y. 2021. EO-AI4Wildfire at Google GEO for Good Seminar Series on Crisis Response.
  • Ban, Y. 2020. EO-Enabled Global Urban Observation and Information to Support SDG and NUA, The 10th UN World Urban Forum, 2020, Abu Dhabi, UAE.
  • Y. Ban. 2020-2021. EO-AI for Global Environmental Change Monitoring. Presented at KTH Space Rendezvous, Seminar Series of the International Space University, DF Fly-High, etc.

Conference Presentations

  • Ban, Y., H. Azzizpour, A. Nascetti, J. Sullivan, U. Mörtberg. EO-AI4GlobalChange, ESA Living Planet Symposium, May 23-27, 2022, Bonn, Germany.
  • Fang, H., Hao Hu, Andrea Nascetti, Yifang Ban, Hossein Azizpour. Multi-temporal Consistency Regularization for Change Detection on Satellite Imagery, ESA Living Planet Symposium, May 23-27, 2022, Bonn, Germany.
  • Gerard, S. Y. Shi, D. Kerekes, Y. Ban, H. Azizpour, J. Sullivan. 2022. Critical Components of Strong Supervised Baselines for Building Damage Assessment in Satellite Imagery and their Limitations. ESA Living Planet Symposium, May 23-27, 2022, Bonn, Germany.
  • Gerard, G. J. Sullivan. 2022. False temporal positives in self-supervised learning on satellite images. ESA Living Planet Symposium, May 23-27, 2022, Bonn, Germany.
  • Hafner, S., Y. Ban and A. Nascetti, 2022. Urban Change Detection Using a Dual-Task Siamese Network and Semi-Supervised Learning. IGARSS’2022, Kuala Lumpur, Malaysia.
  • Hu, X., P. Zhang and Y. Ban, 2022. Gan-Based SAR to Optical Image Translation in Fire-Disturbed Regions. IGARSS’2022, Kuala Lumpur, Malaysia, virtual.
  • Kerekes, D., A. Nascetti, Y. Ban. 2022. Object detection methods for dark vessel detection and classification using SAR imagery. Living Planet Symposium, May 23-27, 2022, Bonn, Germany.
  • Yadav, R., A. Nascetti and Y. Ban, 2022. Flood Detection and Mapping using Customized U- net Architectures based on Sentinel-1 SAR Imagery, Living Planet Symposium, May 23-27, 2022, Bonn, Germany.
  • Yadav, R., A. Nascetti and Y. Ban, 2022. Building Change Detection Using Multi-Temporal Airborne Lidar Data. The 2022 ISPRS, June 6-11, 2022, Nice, France.
  • Zhang, P., X. Hu, and Y. Ban, 2022. Wildfire-S1S2-Canada: A Large-Scale Sentinel-1/2 Wildfire Burned Area Mapping Dataset Based on the 2017-2019 Wildfires in Canada. IGARSS’2022, Kuala Lumpur, Malaysia, virtual.
  • Zhao, Y. and Y. Ban, 2022. Global Scale Burned Area Mapping Using Bi-Temporal ALOS-2 PALSAR-2 L-Band Data. IGARSS’2022, Kuala Lumpur, Malaysia, virtual.
  • Zhao, Y. and Y. Ban, 2022. VIIRS Time-series for wildfire progression mapping using Transformer Network. ESA Living Planet Symposium, May 23-27, 2022, Bonn, Germany.
  • Yadav, R., A. Nascetti and Y. Ban, 2022. Attentive Dual Stream Siamese U-net for Flood Detection on Multi-temporal Sentinel-1 Data. IGARSS’2022, Kuala Lumpur, Malaysia, virtual.
  • Hafner, S., Y. Ban and A. Nascetti, 2021. Exploring the Fusion of Sentinel-1 SAR and Sentinel-2 MSI Data for Built-Up Area Mapping Using Deep Learning. Proceedings of IGARSS’2021, Brussels, Belgium.
  • Zhao, Y., Y. Ban and A. Nascetti, 2021. Early Detection of Wildfires with GOES-R Time-Series and Deep GRU Network. Proceedings of IGARSS’2021, Brussels, Belgium.
  • Pang, X., Zhang, P., Mörtberg, U., Ban, Y. 2022. Ecological impacts of wildfire severity and pyrodiversity quantified with remote sensing and deep learning. Poster presentation at the 41th EARSeL Symposium, 13-16 September 2022, Paphos, Cyprus.
  • Pang, X., Georganos, S., et al. 2022. Using remote sensing data with machine learning to predict distribution of near-threatened forest species. Poster presentation at the 41th EARSeL Symposium, 13-16 September 2022, Paphos, Cyprus.
  • Pang, X.-L. 2021. Ecological impact of forest wild-fires vs clear-cuts—Digitalization on forest habitat networks and virtual species. Digital Futures seminar: DF-Dive Deep Seminar, October 14th, 2021, digital (https://www.youtube.com/watch?v=bTDEhlD8XEo).
  • Pang, X.-L. 2022. Bridging the gap between essential biodiversity variables and indicators for forest species diversity detection by using remote sensing data. Oral presentation at Internationalization project of Visiting Tokyo University, 3rd Feb 2022, digital.

Results

The overall objective of the EO-AI4GlobalChange project is to develop innovative and robust methods for monitoring environmental changes using Earth Observation big data and deep learning. This research will focus on three major global environmental challenges: urbanization, wildfires and flooding.

The specific objectives are:

  1. to develop novel, automatic and globally applicable methods for effective change detection using deep learning and big data analytics to exploit all available Earth Observation data;
  2. to adapt the developed methods for continuous urban change detection, for flood mapping, and for wildfire monitoring including early detection of active fires, near real-time monitoring of wildfire progression and rapid damage estimation;
  3. to assess the environmental impacts of urbanization and wildfires on biodiversity and ecosystem services.

The research achievements are:

  • Change Detection Methodology Development
    • Change detection methods based on Segmentation networks with better generalization
    • Temporal change detection using continuous observation
  • Deep Learning for Environmental Change Monitoring
    • Urban mapping and change detection
    • Wildfire detection and monitoring
    • Flood mapping
  • Environmental impact assessment

List of open-data repositories and developed software

  • We have started to collect historical wildfire data and satellite images to prepare a large-scale wildfire dataset.
  • We have started collecting the reference and satellite images to prepare a large-scale 3D change detection dataset.