Marcus Freitag
YOU?
Author Swipe
View article: SuryaBench: Benchmark Dataset for Advancing Machine Learning in Heliophysics and Space Weather Prediction
SuryaBench: Benchmark Dataset for Advancing Machine Learning in Heliophysics and Space Weather Prediction Open
This paper introduces a high resolution, machine learning-ready heliophysics dataset derived from NASA's Solar Dynamics Observatory (SDO), specifically designed to advance machine learning (ML) applications in solar physics and space weath…
View article: Surya: Foundation Model for Heliophysics
Surya: Foundation Model for Heliophysics Open
Heliophysics is central to understanding and forecasting space weather events and solar activity. Despite decades of high-resolution observations from the Solar Dynamics Observatory (SDO), most models remain task-specific and constrained b…
View article: AI Foundation Model for Heliophysics: Applications, Design, and Implementation
AI Foundation Model for Heliophysics: Applications, Design, and Implementation Open
Deep learning-based methods have been widely researched in the areas of language and vision, demonstrating their capacity to understand long sequences of data and their usefulness in numerous helio-physics applications. Foundation models (…
View article: AI-accelerated Nazca survey nearly doubles the number of known figurative geoglyphs and sheds light on their purpose
AI-accelerated Nazca survey nearly doubles the number of known figurative geoglyphs and sheds light on their purpose Open
It took nearly a century to discover a total of 430 figurative Nazca geoglyphs, which offer significant insights into the ancient cultures at the Nazca Pampa. Here, we report the deployment of an AI system to the entire Nazca region, a UNE…
View article: Climatic & Anthropogenic Hazards to the Nasca World Heritage: Application of Remote Sensing, AI, and Flood Modelling
Climatic & Anthropogenic Hazards to the Nasca World Heritage: Application of Remote Sensing, AI, and Flood Modelling Open
Preservation of the Nasca geoglyphs at the UNESCO World Heritage Site in Peru is urgent as natural and human impact accelerates. More frequent weather extremes such as flashfloods threaten Nasca artifacts. We demonstrate that runoff models…
View article: TensorBank: Tensor Lakehouse for Foundation Model Training
TensorBank: Tensor Lakehouse for Foundation Model Training Open
Storing and streaming high dimensional data for foundation model training became a critical requirement with the rise of foundation models beyond natural language. In this paper we introduce TensorBank, a petabyte scale tensor lakehouse ca…
View article: Commissioning of an Improved Superconducting RF Photo Injector at ELBE
Commissioning of an Improved Superconducting RF Photo Injector at ELBE Open
In order to produce high-brightness electron beams in a superconducting RF photo injector, the most important point is to reach a high acceleration field in the cavity. For this reason two new 3.5-cell niobium cavities were fabricated, che…
View article: PAIRS (RE)LOADED: SYSTEM DESIGN & BENCHMARKING FOR SCALABLE GEOSPATIAL APPLICATIONS
PAIRS (RE)LOADED: SYSTEM DESIGN & BENCHMARKING FOR SCALABLE GEOSPATIAL APPLICATIONS Open
In this paper we benchmark a previously introduced big data platform that enables the analysis of big data from remote sensing and other geospatial-temporal data. The platform, called IBM PAIRS Geoscope, has been developed by leveraging op…
View article: Critical Mobility, a practical criterion and early indicator for regional COVID-19 resurgence
Critical Mobility, a practical criterion and early indicator for regional COVID-19 resurgence Open
The sharp reduction of human mobility in March 2020, as observed by anonymized cellphone data, has played an important role in thwarting a runaway COVID-19 pandemic. As the world is reopening, the risks of new flare-ups are rising. We repo…
View article: Change Detection from Remote Sensing to Guide OpenStreetMap Labeling
Change Detection from Remote Sensing to Guide OpenStreetMap Labeling Open
The growing amount of openly available, meter-scale geospatial vertical aerial imagery and the need of the OpenStreetMap (OSM) project for continuous updates bring the opportunity to use the former to help with the latter, e.g., by leverag…
View article: Learning and Recognizing Archeological Features from LiDAR Data
Learning and Recognizing Archeological Features from LiDAR Data Open
We present a remote sensing pipeline that processes LiDAR (Light Detection And Ranging) data through machine & deep learning for the application of archeological feature detection on big geo-spatial data platforms such as e.g. IBM PAIRS Ge…
View article: Towards Scalable Geospatial Remote Sensing for Efficient OSM Labeling
Towards Scalable Geospatial Remote Sensing for Efficient OSM Labeling Open
Zhang et al. (2019). Towards Scalable Geospatial Remote Sensing for Efficient OSM Labeling In: Minghini, M., Grinberger, A.Y., Juhász, L., Yeboah, G., Mooney, P. (Eds.). Proceedings of the Academic Track at the State of the Map 2019, 27-28…
View article: Event clustering & event series characterization on expected frequency
Event clustering & event series characterization on expected frequency Open
We present an efficient clustering algorithm applicable to one-dimensional\ndata such as e.g. a series of timestamps. Given an expected frequency $\\Delta\nT^{-1}$, we introduce an $\\mathcal{O}(N)$-efficient method of characterizing\n$N$ …
View article: High-Field High-Repetition-Rate Sources for the Coherent THz Control of Matter
High-Field High-Repetition-Rate Sources for the Coherent THz Control of Matter Open