Conference Agenda

The past year’s work has consolidated a fine-scale monitoring network covering various ecosystems at the field observation level and advanced the understanding of the complex environmental systems of the Eurasia. The following research progress have been made in monitoring and modelling climate change in water, energy and carbon cycles in Eurasia.

Initially, systematic observational studies were conducted on the mechanisms of atmospheric-soil water and heat exchange over the Tibetan Plateau. Hourly land-atmosphere interaction datasets were released. High-precision evapotranspiration datasets were constructed by integrating multi-source data. Radiosonde and microwave radiometer data were combined to effectively monitor the evolution of the water and heat structure in the convective boundary layer over the plateau. These datasets provide essential observational data for in-depth research on energy and water cycling in the Tibetan Plateau region.

Additionally, Tibetan Plateau evapotranspiration observational data were integrated to reveal the trends in evapotranspiration over the past 40 years and the next century. The relationships between evapotranspiration and meteorological and remote sensing variables were clarified. The main factors influencing the trends in plateau evapotranspiration were quantified, and the potential evolution patterns of evapotranspiration under different climate scenarios were predicted. These efforts provide a scientific basis for regional water cycle and climate change research.

Concurrently, simulations of the weather and climate effects of the Tibetan Plateau were conducted. On one hand, the gravel parameterization scheme of the CLM4.5 model was optimized to reveal the regulatory mechanisms of gravel on soil water and heat transfer in permafrost regions and quantify its impact on water and freeze-thaw processes. On the other hand, the Noah albedo scheme was improved to enhance the WRF model’s ability to simulate heavy snowfall over the Tibetan Plateau, providing a reference for improving the accuracy of weather and climate simulations in this region.

The STEMMUS-SCOPE Digital Twin Earth system component has been further enhanced that simulates water-energy-carbon fluxes and states in the land-atmosphere system by integrating key terrestrial processes such as radiative transfer, photosynthesis, and soil moisture and soil temperature dynamics, as well as vegetation growth dynamics.

An emulator based on the STEMMUS-SCOPE digital twin and machine learning has been developed and a global dataset is generated at 9 km and hourly resolution from 2000 to 2020, including seven variables (net radiation, latent heat flux, sensible heat flux, soil heat flux, gross primary productivity and solar induced fluorescence at 685, and 740 nm). This product has been used for detecting and monitoring droughts on global scale by developing a new method that reveals more quantitative information compared to conventional indices based approaches.

On the scientific exchange side, the team led by Prof. Ma from ITP engaged in close collaboration and exchange with the team led by Professor Su from UT in the Netherlands. In April, Prof. Ma led a delegation to visit the UT, where a specialized discussion was held with Professor Su’s team on satellite remote sensing observation technology for energy and water cycle over the Tibetan Plateau. Subsequently, Prof. Ma and Prof. Su, as co-conveners, hosted the “TPE” session at the European Geosciences Union (EGU 2025) General Assembly. International peers systematically presented the latest research findings in the fields of hydro-meteorology, glacier changes, and ecological environment in the Himalayan region. Three joint PhD graduations were successfully completed at the University of Twente (Dr. Yunfei Wang, Dr. Jan Hofste, Dr. Qianqian Han).

The goal of this project is to develop an AI-based holistic approach that enables fine-scale monitoring accounting with multi-source ESA and Chinese EO data. The objectives are:1) Joint China - ESA EO missions synergy analysis；2) Establish joint EO benchmark datasets for floods and drought monitoring；3) Build a multimodal EO model to climate-related information extraction for multisource and multitemporal EO data； Develop AI-enabled flood and drought prediction model.

The project addresses key challenges in current EO-based disaster monitoring, including heterogeneous sensor characteristics, unstable observations, scarce labels, limited model generalization, and insufficient interpretability. Disaster intelligence requires not only image-level recognition, segmentation, and change detection, but also the extraction of physically meaningful and decision-relevant variables from remote sensing observations.

To this end, the project proposes a task-centred hybrid intelligence framework organized around “task requirements–disaster variables–observation capabilities–model methods.” It will integrate knowledge graphs, disaster ontologies, physical priors, neuro-symbolic AI, evidence tracking, and uncertainty representation to support rapid identification, continuous monitoring, risk reasoning, impact assessment, and validation across the full disaster lifecycle.

The joint team has established a solid foundation in SAR–optical registration, multimodal fusion, and unsupervised learning, including the Grid-Reg method for robust cross-modal EO image matching. The project is expected to advance remote sensing analysis from data-driven single-task recognition toward task-oriented, multi-source collaborative intelligent reasoning, supporting disaster intelligence, risk governance, and climate adaptation.