Conference Agenda

This year’s work has not only established a fine-scale monitoring network covering various ecosystem types at the field observation level but also deepened the understanding of the complex environmental system of the Eurasia in the fields of remote sensing technology and digital twin earth approach. 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. The newest development prognostically generates biomass of storage organs (i.e., yield), leaves, stems, and roots that closely matched with the observed data. It offers also a process-based and mechanistic framework to link remote sensing measurements (e.g., solar-induced chlorophyll fluorescence) to land surface fluxes (radiation, heat, water and carbon fluxes), LAI, plant biomass, and root-zone soil water in a physically consistent manner.

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 and other finer scale data will be used for case studies for detecting and monitoring droughts and floods and other environmental changes in Eurasia.

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 2024) General Assembly, which attracted 30 oral presentations and 23 poster presentations. International peers systematically presented the latest research findings in the fields of hydro-meteorology, glacier changes, and ecological environment in the Himalayan region. In November, Professor Su paid a return visit to the ITP, and the two sides discussed cooperation mechanisms such as Tibetan Plateau land-atmosphere interaction observation and joint graduate student training.

The Dragon-6 project Multi-Sensor Remote Sensing for Cultural Heritage Climate Change Resilience explores how remote sensing can be applied to assess and enhance the resilience of cultural heritage sites facing increasing threats from climate change. Many UNESCO World Heritage Sites, as well as other significant archaeological locations, are vulnerable to a range of climate-induced hazards—including flooding, permafrost thaw, desertification, and intensified storm activity, as well as active tectonics.

Remote sensing offers essential capabilities for monitoring and evaluating these evolving risks. Our project aims to address methodological gaps and to apply advanced multi-sensor remote sensing techniques to a diverse selection of heritage sites located in complex environmental contexts around the world.

Key study areas include the Wushaoling, Jiayuguan and Hongguozi sections of the Great Wall in Gansu Province and Ningxia Hui Autonomous Region, China; rapidly melting ice patches in the Mongolian Altai; riverine regions in Alaska affected by rising temperatures and increased erosion; and the archaeological landscape of Metaponto, Italy, which faces multiple climate-related threats.

We plan to begin fieldwork prior to the 2025 Dragon-6 Symposium, with an initial campaign focused on collecting ground data from the Great Wall sites in Gansu Province and Ningxia Hui Autonomous Region, China.

Through this project, we demonstrate the critical role of remote sensing technologies in supporting global efforts to monitor, protect, and build climate resilience for vulnerable cultural heritage sites.

The Soil Moisture and Ocean Salinity (SMOS) mission has played a key role in monitoring global soil moisture, providing valuable measurements over the last 15 years. This research has focused on improving SMOS products by refining the algorithms, integrating data from multiple sensors, and addressing spatial and temporal gaps in soil moisture data. While SMOS, equipped with an L-band microwave radiometer, has delivered important insights, there have been ongoing challenges in improving the accuracy and consistency of SMOS soil moisture product, especially when comparing data from SMOS with other missions like SMAP. One major achievement of this research has been the development of techniques to reduce the discrepancies between SMOS and SMAP products. By correcting systematic biases in the brightness temperature (TB) measurements, particularly those arising from differences in observation angles and atmospheric effects, the research has helped improve data consistency. Additionally, the research has explored the use of multi-angular data from SMOS to enhance soil moisture retrieval through a Multi Channel Collaborative Algorithm (MCCA). This approach has effectively utilized multi-angular brightness temperature data and vegetation optical depth to improve the accuracy of soil moisture retrieval, especially in regions with varying surface characteristics. Another important outcome has been the enhancement of spatial resolution. The research combined passive and active microwave measurements with optical and infrared data to downscale SMOS and SMAP soil moisture products to finer spatial resolutions, such as 1 km. The incorporation of machine learning techniques has further improved the temporal resolution of these products, enabling the creation of long-term, high-resolution datasets spanning several decades. In addition, this research has utilized in-situ data from regions such as the Tibetan Plateau, which has been crucial in validating satellite-derived soil moisture products. These data have improved our understanding of soil moisture dynamics, particularly in challenging environments like permafrost and seasonally frozen ground. By combining in-situ data with satellite observations, this research has provided better insights into drought monitoring and agricultural forecasting, supporting more accurate assessments of global water cycles and climate variability. The work has led to the development of a harmonized soil moisture product with improved spatial and temporal resolution, filling important gaps in global change research. By improving the consistency of SMOS and SMAP products, the research has laid the groundwork for a more reliable, long-term soil moisture monitoring system, which will be valuable for research in hydrology, agriculture, and climate science.

Glaciers in High Mountain Asia (HMA) are important water sources for millions of people in arid regions. Mass balance states of the glaciers exhibit significant differences in different subregions. However, the reasons for this have been unclear due to limited accurate temperature and precipitation datasets in extremely high altitudes, bringing great uncertainty to the survival and development of the people in different subregions. In this work, the ablation index and seasonal accumulation index are proposed based on firn and snow state observation from satellite, which present the ablation and accumulation pattern of the glaciers in HMA. The results show that glaciers with the lowest ablation index, lowest summer accumulation ratio which locates in the center of the HMA region, has the most balanced state (+0.05 m w.e/a). In contrast, the type with high ablation, median summer accumulation ratio, presents a severely negative mass balance (-0.47 m w.e/a). Under similar ablation intensity, the type of glaciers with higher summer precipitation is more negative. To assess the reliability of our method, we compare the index with the summer snow line, weather station records, and precipitation data. This work provides novel methods and knowledge to understand and project the glacier mass balance heterogeneity in HMA.

Microwave and optical remote sensing data, including Sentinel-1, Sentinel-2, GF-3, Landsat-8, and ICESat-2, were utilized to analyze the salt field types, salt crust types, lake water depth, and sediment thickness in the Qarhan Salt Lake region. The classification and inversion capabilities of different data sources were comprehensively assessed. The application potential of polarimetric SAR data in salt lake monitoring was systematically evaluated, demonstrating its advantages in type identification, change detection, and inversion accuracy enhancement.

For multi-temporal polarimetric SAR (PolSAR) feature extraction, a time correlation entropy feature was proposed based on satellite-borne Sentinel-1 data. A multi-temporal correlation matrix of dominant scattering mechanisms was constructed, and the degree of target variation over the entire observation period was quantified using Shannon entropy. This approach overcomes the limitation of traditional multi-temporal features that only capture changes between two time points, enabling a more comprehensive representation of cumulative changes in surface cover types. Furthermore, by incorporating the principle of maximum entropy, a classification method based on interval estimation of distribution parameters was developed, which enhances spatial consistency and noise robustness. The proposed method was applied to feature extraction and classification in the Qarhan Salt Lake region, achieving superior performance compared to conventional PolSAR features and classification approaches.

To optimize polarization features, we addressed the challenge of high similarity in the polarimetric scattering characteristics of different salt crust types in the Qarhan Salt Lake. These features are predominantly governed by surface scattering and mixed with a small amount of volume scattering, resulting in considerable redundancy among features. To address this, a feature selection method based on polarimetric feature similarity metrics was developed using high-resolution GF-3 polarimetric SAR data. A statistical and textural similarity-based metric, referred to as the Statistical Similarity-based Feature Similarity Measure (SSFSM), was proposed to quantify inter-feature similarity. Based on this metric, seven representative polarimetric features were selected, effectively reducing feature dimensionality while maintaining high classification accuracy (>95%), which is comparable to the performance using the full feature set. This approach not only enhances the efficiency of salt crust classification but also provides a reliable technical foundation for subsequent high-precision identification and automated classification of salt lake surface features.

For fine classification of salt crusts, we proposed a feature optimization and reconstruction method based on neighborhood autoencoder (AE). This method addresses two major challenges: speckle noise interference in high-resolution polarimetric SAR images of homogeneous salt lake surfaces, and the high similarity and redundancy among the polarized scattering features of different salt crust types. The method reconstructs and compresses the original polarimetric features from fully polarized and dual-polarized SAR data, improving feature representation and alleviating redundancy. We performed classification validation experiments based on field survey results. The results show that the method is effective in extracting salt crust distributions and significantly enhances classification accuracy and efficiency.

Optical remote sensing demonstrates outstanding capabilities in water body monitoring. Therefore, research on the water depth inversion of salt lakes and the fine classification of salt fields based on optical remote sensing has been conducted, expanding the means for fine monitoring of salt lake resources. For water depth inversion inversion, a remote sensing method based on the multilayer perceptron (MLP) model was used. Time-series monitoring of salt lake depth changes was achieved through the combined use of multispectral and LiDAR data. Seven spectral bands from Landsat-8 L2 data were used as inputs, with ICESat-2 ATL13 data serving as labels for model training and fitting. This method provides an effective technical solution for salt lake water depth inversion. By integrating multispectral data with LiDAR, the inversion accuracy was improved, achieving a high accuracy (>85%). This approach provides strong support for predicting salt lake water depth and optimizing salt field processes.

In terms of salt field refined classification, Sentinel-2 multispectral data were used to classify and study the sediment thickness in carnallite pool areas. Four types of sediment situation were labeled based on actual collection data. To address the linear operation characteristics in carnallite pools, a line target recognition method incorporating the attention mechanism was proposed. Based on this, a semi-empirical and semi-structural line target classification model was developed. This model integrates linear geometric features and structural information, improving the accuracy of sediment thickness recognition in carnallite pools. Field investigations and comparisons demonstrated the feasibility of this method in distinguishing sedimentation levels, providing effective support for the timing of carnallite collection and resource distribution assessment.

At present, the inversion of salt crust roughness and water content based on PolSAR, estimation of regional salt content in salt fields, water depth changes using optical remote sensing, and monitoring of dynamic changes in sediment thickness are all included in the research plan. These objectives aim to further enhance the capability for high-precision inversion and quantitative monitoring of salt lake resource parameters.

The project aims to produce high-precision, high-resolution forest type classification maps, monitor forest growth dynamics using multi-temporal LiDAR data, invert forest vertical structure parameters from LiDAR data, and develop multi-scale forest quality evaluation methods. Currently, research has been conducted on forest parameter estimation based on TECIS data, optimization of forest type classification algorithms, and extraction of understory sapling parameters, providing critical data support for further analysis of forest ecosystems.

A forest parameter extraction method was developed based on TECIS data. By extracting waveform characteristics from TECIS LiDAR spot data and integrating airborne forest carbon stock data, a machine learning model was constructed to estimate forest carbon stocks at the spot scale. Subsequently, reflectance, texture, and BRDF features derived from multi-angle imagery were combined with spot-scale carbon stock estimates to build a deep learning model for regional forest carbon stock mapping. The mapping results were validated using both airborne and plot-level carbon stock data. Multi-scale accuracy assessments of the TECIS active-passive collaborative carbon stock maps were conducted using ALS-derived carbon data and field measurements, demonstrating high precision across different scales (plot scale: R²=0.45, RMSE=13.24 t/ha; 25m scale: R²=0.58, RMSE=11.74 t/ha; 100m scale: R²=0.70, RMSE=10.12 t/ha; 1km scale: R²=0.85, RMSE=5.18 t/ha).

A forest type mapping methodology integrating Sentinel-1/Sentinel-2 data with Digital Terrain Models (DTM) was developed. The approach utilized Sentinel-1's VV and VH backscattering coefficients, Sentinel-2's original spectral bands, three vegetation indices (NDVI, MSAVI2, and GEMI), along with three DTM-derived topographic variables (elevation in meters above sea level, aspect, and slope) to construct a random forest classification model for forest type discrimination. The resulting forest type map was validated against Switzerland's National Forest Inventory (NFI) plot data. Experimental results demonstrated that the synergistic use of Sentinel-1/Sentinel-2 and DTM effectively mitigates challenges posed by complex terrain and atmospheric conditions in mountainous regions. This model leverages freely available Sentinel-1/Sentinel-2 data and open-source software, featuring reproducible procedures with updatable training datasets. The implemented workflow proves robust, cost-efficient, and highly automated, significantly supporting forestry sector activities requiring precise spatial characterization of forest resources.

A LiDAR-based method for understory sapling parameter extraction was developed. The approach first optimized a spectral clustering-based individual tree segmentation algorithm to accurately delineate larch canopy trees and identify their trunk positions in the study area. After effectively removing overstory tree information, the method employed a mean shift algorithm with adaptive kernel bandwidth, incorporating local stem density, to segment understory spruce saplings. Subsequently, individual sapling height and crown phenotypic parameters were extracted from the segmented point clouds. The detection rate for understory saplings ranged from 94.41% to 152.78%, with matching accuracy improving from 62.59% to 95.65% as canopy closure decreased. Airborne Laser Scanning (ALS)-derived sapling heights showed strong correlation with field measurements (R²=0.71, N=3241, RMSE=0.26 m, p<0.01) and high consistency with Terrestrial Laser Scanning (TLS) data (R²=0.78, N=443, RMSE=0.23 m, p<0.01). ALS-extracted crown widths also demonstrated acceptable accuracy compared to TLS measurements (R²=0.64, N=443, RMSE=0.24 m). The results indicated systematic underestimation of sapling dimensions by ALS due to overstory occlusion effects. This research establishes a foundation for enhancing forest carbon sequestration capacity through regulating gap dynamics and optimizing light resource utilization in managed forests.

翻译

搜索

复制

In the past year, the project team has conducted a range of studies on AI approaches to analyseelectromagnetic satellite data (Swarm and CSES), several machine learning algorithms have been developed, including predictive models (Long Short-Term Memory, LSTM) and generative models (Generative Adversarial Networks, GANs) for generating synthetic time series data based on Swarm satellite data, as well as STL (Seasonal-Trend decomposition using LOESS) algorithm, EMD (Empirical Mode Decomposition) algorithm, etc. for extracting anomalous disturbance signals and obtaining the spatiotemporal distribution characteristics of anomalies under seismic and non-seismic conditions. These provide new insights into the analysis of electromagnetic anomalies from Swarm and CSES satellites, and Sentinel imaginary.

These studies expose the limitations of current machine learning methods and help us propose a novel research direction, such as, integrating LSTM-based and GAN-based models to enrich seismic datasets through synthetic data generation. This hybrid approach not only helps in accurately reproducing authentic temporal trends in seismic activities but also offers a promising avenue for further research in seismic data analysis.

Based on ground-based extremely low-frequency (ELF) observations, we also developed a differential ant colony inversion algorithm to invert anomalous data from multiple frequency points and multiple response functions, which can be used to obtain relevant parameters of equivalent radiation sources in multiple underground media. The Preliminary results show that the anomalous azimuth has a good indicative effect on future epicenters.

In addition, using remote sensing data, the tectonic deformation characteristics of earthquakes were inverted, the results reveal the rupture characteristics and disaster effects of thrust faults under deep-seated thick-skinned geological structures.

This report will present the progressing results from both European and China partners sides, highlighting the potential and challenges of applying AI-approaches to detect seismic anomalies and generate synthetic electromagnetic satellite data, and underscoring the contribution of such methods to seismic anomaly detection from electromagnetic satellite data.

In the first year of the Dragon 6 program, our researches are focused on the development of efficient time-series InSAR algorithms and their applications in infrastructure deformation monitoring. Progress has been achieved in the following aspects.

• PSSformer: persistent scatters selection method for SAR interferometry based on temporal-spatial vision transformers

The selection of persistent scatters (PS) candidates is a crucial step for the classic PSI method, and the result quality has a strong impact on the final deformation measurements. Existing approaches failed to fully exploit the contextual relationships between phase, amplitude, temporal, and spatial dimensions of SAR datasets, leading to a suboptimal PS selection. Therefore, we propose a novel deep learning method for persistent scatters (PS) selection that leverages the temporal-spatial context features of amplitude images and interferometric phase. Specifically, a temporal-spatial vision transformer (TS-ViT) architecture is employed to process input amplitude and phase time-series stacks simultaneously. Then, a phase consistency attention mechanism (PCAM) is adopted to improve the model's perception. Furthermore, an amplitude and phase interaction (API) module is embedded to achieve multi-scale fusion. After training on the TerraSAR-X datasets over Barcelona, the proposed method achieved good results in urban areas and tall buildings.

• Interferometric phase optimization by joining polarimetric and temporal dimensions

Most existing MT-PolInSAR methods optimize interferometric phase separately in the temporal and polarimetric dimensions, failing to leverage the inter-dimensional relationships fully. Aiming at this problem, a novel multi-polarization optimization method is proposed to achieve one-step phase optimization by combining the temporal and polarimetric dimensions using a joint probability density function and maximum likelihood estimation, named JPTPO. The effectiveness of the proposed approach is validated using both simulated and real Radarsat-2 quad-pol datasets, and the comparison with a few state-of-the-art phase optimization methods show its advantage of improved phase quality in terms of a significantly higher coherence.

• Review of Phase Linking methods in time-series InSAR data processing

The performance of InSAR technology is severely limited by decorrelations arising from temporal changes in scatterer characteristics. The Phase Linking (PL) methods, which can recover the systematic phase series through multi-temporal interferometric phase analysis, have become a core technique for addressing the challenge of monitoring low-coherence areas in time-series InSAR. The motivation, fundamental model, methodological advancements, performance comparison, and future trends of the PL methods have been reviewed systematically. In total, five state-of-the-art PL methods, including PTA, PCA, EMI, StBAS, and AdpPL, are compared with each other using both simulated and real Sentinel-1 SAR datasets. The experimental results show the advantages of the AdpPL method in terms of cumulative phase standard deviation and deformation rate accuracy.

• Progressive sequential polarimetric phase optimization concerning land surface variations

In the era of SAR big data, time-series DInSAR processing approaches, which are capable of near-real-time dynamic monitoring of geological hazards, are essentially needed. However, mountainous areas covered by dense vegetation in dynamic changes are prone to suffering from severe decorrelation, imposing higher requirements on the accuracy, efficiency, and dynamic processing capabilities of phase optimization. For this purpose, a novel progressive sequential polarimetric phase optimization (PSPPO) method based on the previously proposed Sequential Polarimetric Phase Optimization Estimator (SETP-EMI) has been developed. By considering the temporal variations of PS/DS targets and fully utilizing a weight scheme based on polarimetric information for progressive sequential phase optimization, better phase optimization results have been achieved. The progressive polarimetric sequential phase optimization method adopts a recursive processing strategy that incrementally optimizes phases for DS and PS targets in SAR images according to land surface variations. Through adaptively weighting among multiple polarization channels subject to the equivalent scattering mechanism constraint, this method enables refined phase optimization processing and effectively enhances phase optimization accuracy.

• Time-series polarimetric InSAR analysis based on adaptive coherence matrix decomposition

We propose a novel efficient polarimetric time-series InSAR method based on adaptive polarization coherence matrix decomposition (ADCMD-PolMTI), which enables efficient adaptive polarimetric optimization for phases of both PS and DS pixels. Experimental results in Southern California demonstrate that compared with the single VV-polarization method, ADCMD-PolMTI significantly enhances the interferometric phase quality, providing a 494% increase in density of high-quality monitoring points. Validation against GPS data has shown that the proposed method exhibits a lower average root mean square error (RMSE) than the single VV-polarization method, demonstrating a higher in deformation monitoring accuracy. Compared with the ESPO algorithm, it improves the processing speed for PS and DS targets by 235 times and 13 times, respectively. Therefore, the proposed method demonstrates superior adaptive optimization capability and computational efficiency, making it suitable for large-scale surface deformation monitoring.

• Deformation monitoring and prediction of the Hong Kong-Zhuhai-Macao Bridge

A deformation prediction method based on ARIMA-PF (autoregressive integral moving average particle filter) is proposed for modeling the complex deformation characteristics of the Hong Kong-Zhuhai-Macao Bridge (bridge-island-tunnel) structure measured by time-series InSAR analysis. Firstly, the ARIMA model is applied to preliminarily model the InSAR deformation monitoring data. Then, the PF algorithm is introduced for dynamic parameter optimization to enhance the predictive ability of the model under nonlinear conditions and improve the capture effect of complex deformation trends. Selecting the artificial islands of Zhuhai and Macau, Hong Kong Port (affected by soft soil consolidation and construction disturbance), and Qingzhou Channel Bridge (a cross-sea bridge structure) as typical research targets, the predictive performances of ARIMA and ARIMA-PF models are compared. The results showed that ARIMA-PF model exhibited big advantages and significantly improved the prediction accuracy.

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.

This project leverages the ESA and NRSCC opportunity to access satellite observations of Earth’s surface to assess precipitation and temperature biases in climate reanalyses, and, building on our previous project (ID 59199), to quantify blue runoff), green (evapotranspiration), and white (sublimation) water fluxes in high elevation catchments. We are applying the land surface models Tethys & Chloris (T&C), validated by independent observations, to deepen our understanding of the cryosphere and water cycle of key water towers in High Mountain Asia (HMA). The T&C model allows us to bridge the disciplinary gaps between snow, permafrost, and glaciers, which generate the runoff that ultimately feeds major rivers, and to consider downstream vegetation, which buffers, delays or amplifies that runoff.

Our main aim is to use Earth Observation data to constrain glacio- and eco-hydrological processes, in order to quantify the interplay of blue, green, and white water fluxes in glacierized catchments across High Mountain Asia. The focus of remote sensing data analysis is the observation and understanding of the relation between climate forcing through the surface energy balance of snow and ice and the cryosphere dynamics in terms of both mass and dynamics of snowpack and glaciers. The validated T&C model can assess how ecosystems and vegetation enhances or reduces glacier contributions to streamflow under climate change in HMA. The glacierized study sites span a range of climatic regimes, with several sites in the Pamir-Karakoram Anomaly domain. In addition to the remote sensing observations, field measurements allow independent evaluation of the model results, where available.
We determined seasonal and interannual variations in catchment snowline altitudes from multiple satellite imagers. We also determined seasonal and interannual changes in land surface temperature (Ren et al, 2024a) and snow/ice albedo. Ice thickness change data are being actively collected for Pamir locations.
A proof-of-concept of the method to estimate biases in climate reanalysis through ecohydrological modelling has been completed and tested for 4 sites with differing climates, using a Bayesian particle filter.
The hyper-resolution eco-hydrological modelling system has been improved, particularly as regards computationally efficiency. This has enabled long-term simulations with a dynamic glacier geometry module.
We developed an improved method to retrieve glacier surface velocity with an optimized image pair selection scheme and post-processing methods. We used the near-infrared images (10 m spatial resolution) acquired by the Sentinel-2 MSI L2A products and the Co-registration of Optically Sensed Images and Correlation (COSI-Corr) method to retrieve the glacier velocity in Yanong glacier between 2020 and 2024.
We used daily China surface climate data and five machine learning methods to classify precipitation phases, and evaluated their performance in the temperature range (-7℃～10℃) that is difficult to accurately identify with traditional methods. By training and testing different models, their recognition accuracy was analyzed and compared with traditional empirical methods.
We determined daily 500 m river ice cover changes in six major high-latitude river basins in the Northern Hemisphere region from 2002 to 2022 and produced a daily 12.5 km river ice coverage dataset and a 20-year dataset on river ice phenology.

The China-ESA Forest Observation (CEFO-2) project focuses on temperate and subtropical forests in China, and forest of temperate forests in United Kingdom. Recognizing the critical role of forests in carbon sequestration and the current limitations in quantifying carbon stocks and predicting trends, the project aims to conduct national-scale dynamic forest resource surveys by integrating ground-based and satellite remote sensing technologies. Over the 1^st year, CEFO-2 has achieved following results: (1) integration of multi-platform LiDAR and high resolution optical imageries for forest parameter extraction, and (2) forest dynamics classification and prediction.

In terms of multi-source data integration for forest parameter extraction, CEFO-2 utilized multi-platform LiDAR (terrestrial, airborne, spaceborne) and optical imagery to estimate key forest parameters—height, carbon stocks, volume, and DBH (diameter at breast height). Motivated by the limitations of legacy inventory systems such as the Sub-Compartment Database, the initiative addressed emerging forestry challenges including climate resilience, species diversity, and precision silviculture. A canopy detection algorithm was applied to delineate individual trees and generate detailed Treelists including height, crown dimensions, and spatial coordinates. Species-specific allometric models, developed using a combination of the global Tallo database and permanent sample plots in the UK, were used to estimate DBH from LiDAR-derived tree metrics. Results showed an exciting accuracy for coniferous species such as Douglas fir and Scots pine yielded high model accuracy (R² > 0.85), while broadleaved species showed greater structural variability, necessitating more nuanced modelling approaches. Volume estimates were calculated using species-calibrated equations, enabling accurate prediction of merchantable timber volume across the district. Complementary satellite-based species classification using PlanetScope imagery and Random Forest algorithms achieved over 92% accuracy by leveraging seasonal spectral variation. Integration of ALS, TLS, and satellite data facilitated the assignment of species attributes to individual trees, enabling the creation of a spatially coherent forest inventory. For spaceborne LiDAR, CEFO-2 acquired and processed spaceborne waveform LiDAR datasets of the Terrestrial Ecosystem Carbon Inventory Satellite (TECIS) from three representative temperate forest sites in northern China (Genhe site, Mengjiagang site, and Saihanba site) and across the UK. Using TECIS data, we extracted critical forest structural parameters such as vegetation height and carbon stocks.

In terms of forest dynamics classification and prediction, CEFO-2 firstly addressed the shortcomings of existing algorithms in disturbance type identification by employing a novel monitoring method based on Temporal Extended Convolutional Neural Network (TempCNN). This model employs 1D CNN to thoroughly analyze temporal dynamic features and spectral information from time-series remote sensing data. The classification result of Mengjiagang site indicated that the TempCNN can precisely classify the anthropogenic disturbance types including thinning, clear-cutting, canopy opening, selective canopy thinning, growth-enhancing silviculture, ecological thinning, forest closure and natural regeneration with the overall classification accuracy of 75%. The TempCNN is expected to provide a reliable tool for forest degradation attribution analysis. Secondly, this project focused on the improvement of forest management in the context of natural regrowth and managed plantation contexts. Work explored the integration of Digital Twin (DT) frameworks with artificial intelligence for improved forest management, particularly in natural regrowth and managed plantation contexts. A modular DT approach using remote sensing data, neural networks, and reinforcement learning was used to optimise forest operations such as thinning. A key contribution is the use of a custom reinforcement learning agent to simulate decision-making in silvicultural scenarios, demonstrating improved performance over traditional benchmarks. Complementing this, Physics-Informed Neural Networks (PINNs), incorporated biological growth models, specifically the Chapman-Richards equation, into the learning process to predict forest growth using sparse and noisy LiDAR data. This biologically grounded architecture significantly outperformed conventional data-driven models in robustness and generalisation, showing strong potential for use in DT systems. Together, these projects illustrated the viability of combining domain-specific ecological knowledge with machine learning to enhance forest simulation and prediction. Both highlight that embedding biological or procedural understanding into AI systems could improve interpretability and reliability. This interdisciplinary approach supported the UK's movement toward precision forestry practices, offering scalable digital tools for planning, carbon accounting, and climate resilience.

This year’s progress demonstrated that multi-source remote sensing integration enables spatially explicit forest inventory as Tree Lists and dynamic management strategies. Future efforts will strengthen the China-Europe scientific collaboration network, developed methods for monitor changes, improving species classification and the upscaling to estimates at a national level by engaging both Chinese and British datasets. The project will to facilitate policy applications of research outcomes, while cultivating interdisciplinary young researchers through project participation.

The China-Laos Railway, a critical Belt and Road Initiative infrastructure project traversing geologically complex mountainous terrains (including fault zones, karst systems, and monsoon-affected regions), faces persistent geological risks threatening its long-term stability. Systematic deformation monitoring emerges as an indispensable safeguard to mitigate cascading risks – from landslides and subsidence to slope instability – while enhancing cross-border risk governance. As a strategic transnational corridor, the deformation monitoring approach not only ensures operational resilience but also fosters international cooperation in ecological security, underpinning the sustainable development of Asia's economic connectivity framework.

This study employs advanced Interferometric Synthetic Aperture Radar (InSAR) technology to evaluate the sensitivity of deformation detection and identify early-stage ground subsidence along the railway corridor. By integrating multi-temporal Sentinel-1 datasets with InSAR techniques, the research quantifies millimeter-scale surface displacements and maps deformation hotspots. Results reveal spatially heterogeneous subsidence patterns influenced by geological conditions, anthropogenic activities, and hydrological factors. The findings demonstrate InSAR’s capability to detect potential deformation signal, offering a proactive approach to infrastructure monitoring.