AI for the environment
This page contains information about projects, publications and other things that relate specifically to my research on ML systems for various environmental applications (both regarding mitigation of further environmental harm, as well as adaptation with respect to existing or locked in harm). It is thus in a sense a subset of my full professional bio which can be found on the main page.
Publications and preprints
Impacts of Color and Texture Distortions on Earth Observation Data in Deep Learning (2024) – Accepted for the 2nd ML-for-RS Workshop at ICLR 2024
NBS Initiative Position Paper: Embracing Nature-Based Solutions for Sustainable Development (2024) – Presented at the ECTP conference 2024
Creating and Leveraging a Synthetic Dataset of Cloud Optical Thickness Measures for Cloud Detection in MSI (Remote Sensing 2024) – arXiv – Code & Data – Also to appear as oral presentation at the 2nd ML-for-RS Workshop at ICLR 2024
Fully Convolutional Networks for Dense Water Flow Intensity Prediction in Swedish Catchment Areas (SAIS 2023) – arXiv – Code – Video – Popular summary
Aerial View Localization with Reinforcement Learning: Towards Emulating Search-and-Rescue (ML-for-RS Workshop at ICLR 2023) – SAIS 2023 paper – Code – Video
Few-shot Bioacoustic Event Detection using a Prototypical Network Ensemble with Adaptive Embedding Functions (DCASE Workshop 2022) – Code – Popular summary
Media and public communication
January 2024: Commentary on AI for tackling climate change (Naturvetarna, in Swedish).
December 2023: Guest lecture for a class of master students at Lund University on the theme AI for the environment. Similar presentation also for Digitaliseringskonsulterna.
October 2023: Presentation for Lantbrukarnas Riksförbund (Federation of Swedish Farmers) about AI within the agricultural sector. Title: AI within horticulture: Where we are today, and where we may be headed.
September 2023: Commentary on AI for tackling climate change (Miljö och utveckling, in Swedish)
September 2022: AI for climate (Naturvetarna podcast, in Swedish) – Extended conversation
May 2022: Keynote presentation about AI for tackling the climate challenges at Stockholm Tech.
January 2022: AI and climate change (RISE Learning Machines) – Article about the talk
Past and ongoing projects
Spring 2024 - Spring 2026 (ongoing): AI-based Power Production Models for Increased Wind Farm Efficiency together with PhD candidate Maria Bånkestad (among others). Funded by the Swedish Energy Agency.
2023: ML for cloud optical thickness estimation together with the Swedish Meteorological and Hydrological Institute (SMHI), AI Sweden, Luleå University of Technology and the Swedish Forestry Agency. The work was published in the journal Remote Sensing (2024), got accepted as an oral at the 2nd ML-for-RS Workshop at ICLR 2024, and was presented as a poster at EUMETSAT 2023. Funded by Vinnova. One of the project deliverables was a developer event (Hackathon) for university students. Code & data available!
Fall 2022: Pre-study about using ML for wetland monitoring in Sweden together with and funded by the Swedish Environmental Protection Agency. Code is available here.
Past and ongoing supervision
Spring 2024 (ongoing): Co-main supervisor (jointly with Martin Willbo) of the master thesis students Agnes Eriksson and Malte Åhman, Lund University. Academic supervisor: Assoc. Prof. Mikael Nilsson. Thesis (preliminary title): Privileged Learning Techniques for Improving Earth Observation-based Land Cover Mapping.
Spring 2024 (ongoing): Co-main supervisor (jointly with Dr. Olof Mogren) of the master thesis students Emma Amnemyr and Daniel Björklund, Lund University. Academic supervisor: Prof. Kalle Åström. Thesis (preliminary title): Active Learning for Improving Machine Learning-based Detection of Coffee Berry Disease. The thesis topic is within the area of climate adaptation and will be conducted with collaborators in Tanzania (Mpendakazi Agribusiness), who provide data and use-cases.
Summer-Fall 2023: Co-main supervisor (jointly with Dr. Olof Mogren) of the master thesis students Axel Eiman and Nils Eickhoff, Chalmers University of Technology. Thesis: Weakly semi-supervised object detection for annotation efficiency: Leveraging a mix of strong bounding box labels and weak point labels for detecting coffee berry disease. The thesis topic is within the area of climate adaptation and was conducted with collaborators in Tanzania (Mpendakazi Agribusiness), who provided data and use-cases. A popular summary can be found here.
Spring 2023: Main supervisor of the master thesis student Ennio Rampello, KTH Royal Institute of Technology. Academic supervisors: Prof. Yifang Ban and Dr. Puzhao Zhang. Thesis: High-altitude navigation to improve the performance of AiRLoc: An RL model for drone navigation. The thesis is related to the area of UAV-based disaster response and management.
Spring 2023: Main supervisor of the master thesis student Vishal Nedungadi, KTH Royal Institute of Technology. Academic supervisors: Prof. Yifang Ban and Ritu Yadav (PhD candidate). Thesis: Active street to aerial view geo-localization. The thesis is related to the area of UAV-based disaster response and management.
Spring 2022: Main supervisor of the master thesis students Anton Samuelsson and John Backsund, Lund University. Academic supervisor: Prof. Kalle Åström. Thesis: Aerial View Goal Localization with Reinforcement Learning. The thesis was subsequently condensed and accepted to a remote sensing workshop at ICLR 2023 (see Publications and preprints above). The thesis is related to the area of UAV-based disaster response and management.
Review work
I have served as a reviewer for the ISPRS Journal of Photogrammetry and Remote Sensing (2023), Remote Sensing (2023), IEEE Transactions on Geoscience and Remote Sensing (2024), and the International Degrowth Conference (2024).