Conference Agenda

This project focuses on artificial intelligence (AI)-driven approaches for monitoring extreme climate events with environmental and societal impact, like floods and droughts, to better support disaster preparedness and inform climate adaptation strategies.

Specifically, four main objectives are defined: a) Perform a joint China-ESA Earth Observations (EO) missions synergy analysis, b) Establish joint EO benchmark datasets for flood and drought monitoring, c) Build multimodal EO models to create climate-related information extraction for multi-source and multi-temporal data, and d) Develop AI-enabled flood and drought prediction algorithms.

Climate change is altering atmospheric dynamics and Earth's water cycle. It leads to the amplification of existing climate patterns and an increase in water-related climate extremes, reinforcing the observed trend of wet regions becoming wetter and dry regions drier. The integration of data across sensor modalities becomes critical. Recognizing the potential of EO Big Data - with its varied sensing platforms and broad spatial-temporal coverage - we seek to harness these resources and integrate them with multi-modal geophysical and environmental measurements.

However, multi-modal remote sensing remains challenging due to significant variations across instruments, including domain gaps and inconsistencies in spatial and temporal resolution. In parallel, many AI and deep learning approaches in remote sensing rely on data-intensive supervised algorithms to achieve high accuracy results, but they often fall short in terms of interpretability and explainability. The cost of obtaining semantically annotated datasets is an expensive task, essentially for large satellite image time series (SITS) and in scenarios where ground truth data is scarce or unavailable. Additionally, while climate change Earth System Models describe phenomena at scales of thousands of kilometers over many decades, climate change adaptation measures need to be applied at the scale of human activities (e.g., temporal: days/months, spatial: 10 m - 1 km, etc.).

We showcase four recent studies that are consistent with our research objectives and in which core members of our team have been involved before the Batch 3 Kickoff. Particularly, they present approaches in multi-temporal analysis, multi-source data integration, and label annotation optimization by active learning, as follows:

• A Memory-based Multimodal Change Detection (MMCD) method was proposed in [1], where distinct images for change detection are treated like video frames. Historical optical images are fused with current synthetic aperture radar (SAR) data to improve detection accuracy, and a difference map enhancement module is introduced to suppress false alarms caused by cross-modality inconsistencies.
• The newly introduced method Diff-MRCD [2] implements a diffusion-based framework which directly generates change maps through reverse denoising. This method is reinforced with a feature alignment module, which ensures robust handling of inputs with differing resolutions by preserving both fine details and semantic meaning.
• The label data scarcity in remote sensing can be addressed through active learning strategies. The comprehensive review from [3] examines the integration of deep learning with active learning in remote sensing and how this paradigm enables optimization of training data under annotation constraints.
• In [4], a framework to analyze and visualize changes in Sentinel-1 SAR image time series with limited ground truth data is proposed. An expert-knowledge-enhanced classifier is paired with an unsupervised Latent Dirichlet Allocation (LDA)-based method to discover and analyze temporal dynamics and change signatures. Visualization is emphasized by obtaining color-coded change maps of temporal evolution at image patch level.

In the project “Remote Sensing of Environmental Effects on Materials - Application to the Degradation of Cultural Heritage Monuments” (ID: 95481), we have outlined three tasks focused on Cultural Heritage Monuments.

Task 1 will develop two indices: the Limestone Deterioration Index (LDI) to assess environmental deterioration potential on limestone, and the Soiling Index (SI) to evaluate soiling potential. These indices will be created for the monuments listed in Table 1.

Table 1. The selected archaeological sites in China and Europe for this project.

Chinese sites

• Fujian Tulou
• Historic Centre of Macao
• Ancient Building Complex in the Wudang Mountains
• Dazu Rock Carvings
• Circular Mound Altar - Temple of Heaven

European sites

• Acropolis
• Colosseum
• Historic Centre of Vienna
• Historic City of Toledo
• Palace of Versailles

For this task, we are gathering essential satellite environmental data from both European and Chinese databases. Next, we will utilize Satellite Sensed Data Dose-Response Functions (SSD-DRFs) to develop deterioration model tools that estimate the annual degradation and soiling characteristics of the atmosphere at various sites.

Task 2 is focused on developing two new SSD-DRFs for copper and stainless steel. These materials are significant because they are linked to cultural heritage artifacts and monuments, and they are also commonly used in modern construction. To support this task, we are collecting both environmental satellite data and deterioration data from relevant exposure specimen campaigns. Both types of data are crucial for developing the new SSD-DRFs.

Task 3 focuses on monitoring seismic activity in archaeologically significant areas using satellite observations. The case studies include the archaeological site of Delphi, identified as a European candidate site, as well as the Temple and Cemetery of Confucius and the Kong Family Mansion in Qufu, recognized as a Chinese candidate location. Both sites are part of the UNESCO World Heritage Convention. This research effort aims to develop tools to protect cultural heritage sites from degradation and natural hazards by utilizing satellite data.

To support this task, we have begun collecting satellite data from the China Seismo-Electromagnetic Satellite (CSES) database. The data, obtained from ZH-1(01), covers the period from February 2018 to the present. Our next steps will involve analyzing this data to study earthquake dynamics at the aforementioned archaeological sites.