Research Group Xiaoxiang Zhu
Xiaoxiang Zhu
Prof. Dr.
Principal Investigator
Data Science in Earth Observation
Xiaoxiang Zhu
is Professor of Data Science in Earth Observation at TU Munich.
Her research focuses on signal processing and data science in earth observation. Geoinformation derived from Earth observation satellite data is indispensable for many scientific, governmental and planning tasks. Furthermore, Earth observation has arrived in the Big Data era with ESA's Sentinel satellites and NewSpace companies. Professor Zhu develops explorative signal processing and machine learning algorithms, such as compressive sensing and deep learning, to improve information retrieval from remote sensing data, and to enable breakthroughs in geoscientific and environmental research. In particular, by the fusion of petabytes of EO data from satellite to social media, she aims at tackling challenges such as mapping of global urbanization.
Team members @MCML
Publications @MCML
Continent-wide urban tree canopy fine-scale mapping and coverage assessment in South America with high-resolution satellite images.
ISPRS Journal of Photogrammetry and Remote Sensing 212 (Jun. 2024). DOI.
MCML Authors
Vision-Language Models in Remote Sensing: Current progress and future trends.
IEEE Geoscience and Remote Sensing Magazine 62 (Apr. 2024). DOI.
MCML Authors
HyperLISTA-ABT: An Ultralight Unfolded Network for Accurate Multicomponent Differential Tomographic SAR Inversion.
IEEE Transactions on Geoscience and Remote Sensing 62 (Apr. 2024). DOI.
MCML Authors
High-resolution satellite images reveal the prevalent positive indirect impact of urbanization on urban tree canopy coverage in South America.
Landscape and Urban Planning 247 (Apr. 2024). DOI.
MCML Authors
A Review of Building Extraction From Remote Sensing Imagery: Geometrical Structures and Semantic Attributes.
IEEE Transactions on Geoscience and Remote Sensing 62 (Mar. 2024). DOI.
MCML Authors
A high-resolution calving front data product for marine-terminating glaciers in Svalbard.
Earth System Science Data 16.2 (Feb. 2024). DOI.
MCML Authors
Multimodal Co-Learning for Building Change Detection: A Domain Adaptation Framework Using VHR Images and Digital Surface Models.
IEEE Transactions on Geoscience and Remote Sensing 62 (Feb. 2024). DOI.
MCML Authors
Opening the Black-Box: A Systematic Review on Explainable AI in Remote Sensing.
Preprint at arXiv (Feb. 2024). arXiv.
Abstract
In recent years, black-box machine learning approaches have become a dominant modeling paradigm for knowledge extraction in Remote Sensing. Despite the potential benefits of uncovering the inner workings of these models with explainable AI, a comprehensive overview summarizing the used explainable AI methods and their objectives, findings, and challenges in Remote Sensing applications is still missing. In this paper, we address this issue by performing a systematic review to identify the key trends of how explainable AI is used in Remote Sensing and shed light on novel explainable AI approaches and emerging directions that tackle specific Remote Sensing challenges. We also reveal the common patterns of explanation interpretation, discuss the extracted scientific insights in Remote Sensing, and reflect on the approaches used for explainable AI methods evaluation. Our review provides a complete summary of the state-of-the-art in the field. Further, we give a detailed outlook on the challenges and promising research directions, representing a basis for novel methodological development and a useful starting point for new researchers in the field of explainable AI in Remote Sensing.
MCML Authors
Task Specific Pretraining with Noisy Labels for Remote sensing Image Segmentation.
Preprint at arXiv (Feb. 2024). arXiv.
MCML Authors
MedSat: A Public Health Dataset for England Featuring Medical Prescriptions and Satellite Imagery.
37th Conference on Neural Information Processing Systems (NeurIPS 2023). New Orleans, LA, USA, Dec 10-16, 2023. URL.
MCML Authors
Deep Learning for Subtle Volcanic Deformation Detection With InSAR Data in Central Volcanic Zone.
IEEE Transactions on Geoscience and Remote Sensing 61 (Oct. 2023). DOI.
MCML Authors
HTC-DC Net: Monocular Height Estimation From Single Remote Sensing Images.
IEEE Transactions on Geoscience and Remote Sensing 61 (Oct. 2023). DOI.
MCML Authors
Smooth and accurate predictions of joint contact force timeseries in gait using overparameterised deep neural networks.
Frontiers in Bioengineering and Biotechnology 11 (Jul. 2023). DOI.
MCML Authors
Exploring Self-Attention for Crop-type Classification Explainability.
Preprint at arXiv (Oct. 2022). arXiv.
MCML Authors
©all images: LMU | TUM