Our work includes evaluating baseline AI algorithms. While results show promise for automated monitoring, they also highlight the task's complexity, inviting further research to enhance scalability & accuracy.

Dataset: zenodo.org/records/1374...
Preprint: arxiv.org/abs/2410.09032

To address this, we developed the Alberta Wells Dataset (AWD): the first large-scale benchmark for this critical challenge. AWD provides over 213,000 well instances (abandoned, suspended, active) in Alberta, Canada, with high-resolution, multi-spectral satellite imagery.

I’m happy to share that our paper on detecting oil & gas wells with AI has been accepted to ICML 2025! Millions of such wells exist, leaking methane & other toxins. We show how remote sensing can help find them, using high-resolution, multi-spectral satellite imagery.

@icmlconf.bsky.social