Aleksandra Gruca, Pedro Herruzo, Pilar Rípodas, Andrzej Kucik, Christian Briese, Michael K Kopp, Sepp Hochreiter, Pedram Ghamisi, and David P Kreil
Advances in remote sensing technology for Earth observation have radically changed the way we monitor the state of our planet. Big data are being accumulated by ground, aerial, and satellite-based remote sensors at an unprecedented scale and resolution. The collected complex large-scale heterogeneous data require efficient interpretation and invite the application of modern data-hungry machine learning methods.
The first workshop on Complex Data Challenges in Earth Observation (CDCEO) featured state-of-the-art machine learning methods for interpretation of multi-source high-dimensional remote sensing data. The CDCEO workshop was held as a satellite event at the 30th ACM International Conference on Information and Knowledge Management (CIKM). The workshop brought together researchers in the fields of remote sensing, geographic information systems, weather and climate modeling, computer vision, and others with a general interest in applying data-driven models in Earth observation. The workshop covered both method development and applications in image analysis, signal processing, data fusion, feature extraction, meta-learning, and more. A special Weather4cast session of the workshop presented the highlights from a unique multi-sensor weather forecasting competition.
Advancing research in Earth observation forms the basis for addressing urgent environmental challenges, including natural catastrophes and climate change.
Proceedings of the 30th ACM International Conference on Information & Knowledge Management, 4878–4879, 2021-10-26.