Posters on site: Tue, 29 Apr, 16:15–18:00 | Hall A
Soil moisture (SM) is a relatively active surface parameters that are significant to the sustainable development of the water–land–air–plant–human nexus. In response to the requirements of multiscale product validation and multisource uncertainty tracking, a soil moisture monitoring network in the Qinghai Lake Basin (QLB-NET) was established in September 2019. The QLB-NET is characterized by densely distributed in situ sites (82 sites) measuring SM and ST at 5-, 10-, and 30-cm depths, with 60 sites in a large-scale network in a heterogeneous area of 36 km × 40 km, which covers the SMAP, AMSR2, SMOS pixel footprint, and 22 sites evenly distributed across two small-scale 1 km × 1 km networks for sub-grid analysis. The site deployment strategy, the installation and maintenance, the sensor calibration, and the characteristics and quality of the in situ SM measurements of QLB-NET will be introduced in detail. Quantitative analyses of the in situ measurements was carried out, which shows that the QLB-NET can provide stable and reliable ground truth for SM over coarse grid scales, facilitating product validation and uncertainty tracking, spatiotemporal analysis of SM change optimization of the SM retrieving algorithms and scaling methods in heterogeneous regions.
How to cite: Zhu, Z.: The Dataset of Dense Soil Moisture Monitoring Network in the Qinghai Lake Basin on the Qinghai–Tibetan Plateau, EGU General Assembly 2025, Vienna, Austria, 27 Apr–2 May 2025, EGU25-1605, https://doi.org/10.5194/egusphere-egu25-1605, 2025.
As many other European countries, Germany has been affected by an increasing number of both drought and flood events in the last couple of years that had considerable negative impacts on the agricultural and forestry sector. These events led to an increasing information demand of stakeholders, practitioners and the general public on critical variables such as soil moisture. Area-wide information on soil moisture is most often derived indirectly from hydrological model simulations, one of them being DWD’s soil moisture viewer which is based on the soil-vegetation-atmosphere-model AMBAV. Besides model-based soil moisture information, which is strongly influenced by model assumptions and parameterisation, a number of institutions started to build-up local soil moisture observation networks, such as the TERENO network, that also provide in-situ observations of soil moisture states. However, a nationwide observation network for (standardised) soil moisture observations is still lacking in Germany.
The project IsaBoM (“Integration of standardised and automatized soil moisture measurements in the DWD observation network”), an internal project of the German Meteorological Service (DWD), strives to establish the technical and scientific basis for introducing standardised soil moisture observations in DWD’s operational meteorological observation network. This includes e.g. the choice of suitable sensors and measurement protocols, calibration procedures for selected sensors, quality-control measures and establishing data flow and automated data provisioning. The final goal is to equip about 25 stations throughout Germany with cosmic-ray neutron sensing (CRNS)-devices and in-situ profile measurements of soil moisture where the chosen locations should provide a representative subset in terms of soil properties and climatic conditions. Here we present the overall network design as well as first comparisons between soil moisture data obtained by different CRNS-sensors at two sites that have a broad range of complementary agrometeorological measurements in place that facilitate a thorough interpretation of the results.
How to cite: Kurtz, W., Albert, M., Herbst, M., Hufnagl, L., and Lenkeit, J.: Integration of soil moisture measurements into the observation network of the German Meteorological Service – the project IsaBoM, EGU General Assembly 2025, Vienna, Austria, 27 Apr–2 May 2025, EGU25-11764, https://doi.org/10.5194/egusphere-egu25-11764, 2025.
The prediction of soil moisture plays a vital role in assessing water availability, optimizing agricultural resources, and preparing for climate-induced disasters. However, significant gaps remain in soil moisture observation networks due to data sparsity, inconsistent temporal coverage, and limited spatial resolution, particularly in underrepresented regions. The International Soil Moisture Network (ISMN), the largest archive of in situ soil moisture data, highlights these challenges, with many datasets averaging only a decade of temporal coverage and biased spatial distribution heavily skewed toward the Global North. This study presents a data-driven modeling framework designed to enhance soil moisture prediction by leveraging advanced machine learning techniques, diverse geospatial datasets, and in situ observations.
Our multi-stream model integrates high-resolution data from Sentinel-2 (NDVI, B4, B8), ECMWF weather forecasts, and SRTM elevation models to predict surface and rootzone soil moisture at six-hour intervals. Validation against SMAP L4 datasets demonstrates high accuracy, achieving mean RMSE values of 0.1087 m³/m³ for surface moisture and 0.1183 m³/m³ for rootzone moisture across 20 Köppen-Geiger climate zones. The modular design enables the model to adapt to diverse climatic conditions and refine predictions through continuous validation. Performance analysis reveals strong temporal generalization and superior results in wet climates, though arid and extreme environments pose challenges, highlighting areas for targeted improvements.
To address data sparsity, the study emphasizes balanced sampling and the integration of citizen science initiatives, which supplement traditional networks by providing localized, high-frequency observations. By incorporating in situ ISMN datasets, the framework aligns with the session's focus on improving observation networks and leveraging data quality assurance. Additionally, hybrid approaches that combine physical constraints with machine learning models ensure predictions are grounded in realistic soil behavior and spatial consistency.
This research underscores the importance of sustained investment in developing and maintaining soil moisture observation networks, particularly in underrepresented regions. It highlights the need for standardized data collection protocols, advanced calibration techniques, and open-access platforms that integrate in situ and satellite observations. By bridging gaps in traditional networks, the model advances global soil moisture monitoring, supporting applications in sustainable agriculture, water resource planning, and climate resilience.
Aligned with session HS8.3.2, this study exemplifies the role of innovative measurement techniques and data-driven approaches in enhancing the utility of soil moisture datasets. The findings advocate for a collaborative scientific effort to address the pressing challenges of data availability, quality assurance, and network deployment. Through scalable modeling frameworks, this research sets the foundation for predictive systems that provide actionable insights to policymakers and practitioners in hydrology, agriculture, and climate science.
How to cite: Hristopoulos, S., Moraga, G., and Pearson Kramer, N.: Enhancing Soil Moisture Prediction with Data-Driven Models: A Global Perspective, EGU General Assembly 2025, Vienna, Austria, 27 Apr–2 May 2025, EGU25-13338, https://doi.org/10.5194/egusphere-egu25-13338, 2025.
Soil moisture (SM) is a key factor influencing the interactions between the atmosphere and processes at the Earth’s surface. Recent advances in remote sensing and land surface modelling have improved the estimation of soil moisture in ungauged areas.
This study evaluates the performance of four state-of-the-art gridded SM products - SPL4SMAU, GLDAS, ERA5 and ERA5-Land - compared to in situ measurements at ten sites located in near-natural shrublanbd and native forest ecosystems of the semi-arid and humid regions of central and southern Chile (five in the semi-arid north and five in the humid south). The unbiased root mean square error (ubRMSE), Pearson’s product-moment correlation coefficient (r) and modified Kling-Gupta efficiency (KGE') were used as performance metrics to evaluate the representation of surface soil moisture (SSM) and root zone soil moisture (RZSM). In addition, event rising time (RT) and amplitude (A) were used as SM signatures to assess the dynamic aspects of the soil moisture time series and to enable process-based model evaluations.
Our results show that SPL4SMAU achieves the lowest ubRMSE for both SSM and RZSM, especially in the northern region. However, ERA5 and ERA5-Land outperformed SPL4SMAU in terms of linear correlation and KGE', with particularly good results in the humid south. In terms of SM responses to the first precipitation event of the year, SSM amplitude was generally higher in the humid south, with SPL4SMAU and ERA5-Land very close to in situ values, while GLDAS showed a lower sensitivity to precipitation. As expected, all datasets showed a slower response for RZSM compared to SSM, with GLDAS showing the longest rising times in both regions. On the other hand, SPL4SMAU and GLDAS showed a stronger increase in SSM amplitude in the south for the most intense precipitation event of the year, while ERA5-Land showed more moderate rising times, which is consistent with the in-situ data.
Overall, ERA5-Land and ERA5 proved to be reliable datasets for representing the spatio-temporal variability of SM in central and southern Chile, especially in the southern ecosystems, while SPL4SMAU performed well in terms of uRMSE but showed large variability in the other metrics analysed.
We gratefully acknowledge the financial support of ANID-Fondecyt Regular 1212071, 1210932, ANID-PCI NSFC 190018, and ANID/FONDAP 1523A0002.
How to cite: Zambrano-Bigiarini, M., Nuñez-Ibarra, D., and Galleguillos, M.: How well do gridded products represent soil moisture signatures in natural ecosystems during precipitation events?, EGU General Assembly 2025, Vienna, Austria, 27 Apr–2 May 2025, EGU25-13801, https://doi.org/10.5194/egusphere-egu25-13801, 2025.
Soil moisture observations have been collected since the late 1950s and are relatively abundant in the northern hemisphere. These readings are generally taken at shallow depths with sensors rarely installed more than 2 metres below the surface. However, deep soil moisture dynamics can play a crucial role in determining ecosystem services, land-atmosphere water fluxes, plant water use, nutrient cycle and, eventually, groundwater recharge. In thick unsaturated zones, shallow soil moisture observations are likely to fail to capture important hydrological processes, and their feedback with the atmosphere, generating significant uncertainties.
Here we present the results from a soil moisture monitoring network established as part of the Recharge in a Changing Climate (RiCC) project. The network aims to capture soil moisture dynamics in deep sandy profiles of a Mediterranean-like zone in Western Australia, where traditional shallow and surface soil moisture observations fall short of detecting significant hydrological processes. The monitoring network, deployed since 2022, comprises over 75 sensors strategically distributed across 7 locations over the Swan Coastal Plain at depths of up to 9 m to provide continuous high-frequency soil moisture data. These soil moisture sensors are complemented by 14 access tubes where neutron moisture probe readings are taken to characterize the spatial heterogeneity.
Findings reveal complex patterns of moisture movement through the profile, with significant temporal variations in wetting front depths and propagation patterns, improving the representation of soil water/vegetation interaction, and providing unique insights into groundwater recharge processes in sandy aquifer systems. These observations challenge existing assumptions about soil water movement in sandy soils and provide crucial validation data for improving ecohydrological models and recharge quantification. Information from the RiCC monitoring campaign can significantly reduce uncertainties in water resources management and, by including transpiration from deeper soil moisture pools, enhance the accuracy of modelled land-atmosphere feedback. These insights are also beneficial for understanding the resilience of ecosystems and agroecosystems under transient climate conditions.
How to cite: Gelsinari, S., Bourke, S., Silberstein, R., and Thompson, S.: Monitoring deep unsaturated zones in Western Australia to reveal crucial insights for water resources management, EGU General Assembly 2025, Vienna, Austria, 27 Apr–2 May 2025, EGU25-15016, https://doi.org/10.5194/egusphere-egu25-15016, 2025.
Soil moisture plays a vital role in agriculture, drought management, and flood prevention. It is essential for plant growth and sustainable farming practices. In flood-prone areas, soil's ability to retain water helps absorb excess moisture and reduce runoff, mitigating flood risks. Therefore, effective soil moisture monitoring is crucial for informed irrigation and water management decisions. Various methods exist for measuring soil moisture, both in-situ and remote. In-situ techniques, like volumetric and gravimetric sampling, provide real-time data but are limited to specific locations unless interpolation is applied. On the other hand, remote sensing offers broader spatial coverage but often with lower resolution and accuracy. While remote sensing can validate ground-based data, it is less effective for capturing short-term changes, such as those resulting from irrigation, at fine temporal scales.
To address these challenges, we are developing UAV-RADAR, the first multiband Synthetic Aperture Radar (SAR) mounted on a drone. Unlike conventional SAR platforms (e.g., Sentinel-1), UAV-RADAR provides rapid, high-resolution, and scalable soil moisture data tailored to specific agricultural and environmental contexts. Its customizable flight plans enable detailed pre- and post-treatment analyses, capturing temporal changes with unprecedented flexibility.
In this presentation, we will showcase our current research and development of UAV-RADAR to date, demonstrating its capability to measure soil moisture across diverse soil types, landscapes, and agricultural practices. Using data from proof-of-concept experiments carried out in England and Wales, we will show soil moisture maps and demonstrate their applications. We will highlight use cases, and explore how UAV-RADAR can contribute to initiatives like the International Soil Moisture Network.
How to cite: Evans, D., Candido, B., and Marino, A.: Drone-based multiband Synthetic Aperture Radar (UAV-RADAR) for soil moisture assessment, EGU General Assembly 2025, Vienna, Austria, 27 Apr–2 May 2025, EGU25-15693, https://doi.org/10.5194/egusphere-egu25-15693, 2025.
The Network of stations for the Monitoring of physical Parameters of Soils in Catalonia (XMS-Cat) acquires and provides continuous data on in situ soil temperature and moisture at different depths of the soil profile. Initiated in 2015, this relatively young network currently comprises 19 stations and is expanding at a steady rate of two stations per year, aiming for full coverage of the region. Accelerated coverage expansion is planned through data-hosting agreements with privately owned stations, such as those associated with wine protected designations.
The network has recently undertaken a comprehensive review and assessment of its deployment, installation, and data quality assurance protocols to ensure adherence to established best practices, long-term viability, and consistency with other networks.
This contribution provides an overview of the XMS-Cat network and presents the preliminary results of the ongoing review. The aim is to foster dialogue among networks and stakeholders while leveraging the collective knowledge of this dynamic community.
How to cite: Portell, X., Boquera, L., Vicens, M., and Lladós, A.: Review and assessment of current protocols of the Network of stations for the Monitoring of Physical Parameters of Soils in Catalonia (XMS-Cat), EGU General Assembly 2025, Vienna, Austria, 27 Apr–2 May 2025, EGU25-15705, https://doi.org/10.5194/egusphere-egu25-15705, 2025.
Cosmic Rays Neutron Sensing (CRNS) is a well-known method in Hydrology that allows to measure soil water content on a large scale and in depth. It is based on the detection of cosmogenic neutrons, particles generated by the interaction of cosmic rays with the atmosphere, after their interaction with the soil where they can be effectively absorbed by water molecules. The signal collected by a single CRNS probe in terms of neutron count rate is sensitive to soil moisture within a volume spanning up to a dozen hectares and up to 50 cm depth, in real-time, positioning itself in a horizontal spatial scale in between point measurements and satellites.
In order to evaluate the effectiveness of CRNS to give information about soil moisture in an agricultural system with different soil conditions, a site in the Alto Monferrato vine-growing area (Piedmont, NW Italy) was equipped with a Finapp CRNS probe since August 2023. The site has two vineyard-field-scale plots with inter-rows managed with conventional tillage (CT) and grass cover (GC), respectively. More than 20 sensors are located in different positions and depths (from 10 to 50 cm) in the vineyard, including the STEMS network that is part of the International Soil Moisture Network. Precipitation measurements on site are available over more than 20 years, show that 2023 was very dry, with Standardized Precipitation Index lower than -1 for most of the year, whereas 2024 was increasingly wet, with exception of first two months of the year.
Available soil moisture data from CRNS and sensors have been compared until autumn 2024, using statistical indexes such as the efficiency coefficient of Nash and Sutcliffe (NSE), root mean square error of residuals (RMSE) and the coefficient of determination of the linear regression (R2). The analysis was carried out separately for the two years, which were considered respectively dry and wet.
Statistics showed that in the last 5 months of 2023 (dry period) there was a good agreement of soil moisture values measured by sensors between 10 and 20 cm of depth with both soil management, with different results according to the position, the best reported in the middle of the GC inter-row at depth of 20 cm (R2=0.913, NSE=0.756, RMSE=0.25). The results for 2024, which was a wetter year, showed great variability, such as the values recorded by the sensors, with unsatisfactory statistics, since best values for indexes were obtained for the sensor placed in the middle of CT inter-row (R2=0.598, NSE=0.485, RMSE=0.118).
Thus, in the dry period the CRNS probe gave good information on soil moisture conditions in the most superficial layer disregarding the soil management of the vineyard. On the contrary, the difficulty in having good agreement in wet conditions can be due to the high spatial variability of soil moisture both in the horizontal and in-depth directions, soil saturation and ponding, in addition to variable conditions of soil conditions (i.e. soil density) depending to soil management and tractor traffic during the growing season.
How to cite: Biddoccu, M., Enrico, G., Capello, G., Gisolo, D., Gianessi, S., Bechis, S., and Ferraris, S.: Cosmic Rays Neutron Sensing for soil moisture monitoring in vineyard with variable soil conditions, EGU General Assembly 2025, Vienna, Austria, 27 Apr–2 May 2025, EGU25-15709, https://doi.org/10.5194/egusphere-egu25-15709, 2025.
Surface soil moisture (SSM) plays a significant role in the energy exchanges and the complex interaction within the air–soil–water–plant-human nexus. To better evaluate and utilize the microwave remote sensing (RS) SSM products at coarse scale (e.g., 0.25°) and the retrieved SSM data at fine-scale (e.g., 1 km), a pixel-scale reference dataset should be generated within the area of in-situ network. However, in the Tibetan Plateau (TP), where in-situ SSM data is sparse and limited, the current fine-scale SSM datasets generated using machine learning (ML) methods face certain limitations in terms of spatial extrapolation capability. In this study, we developed a framework that integrated ML method with geostatistical spatiotemporal fusion method to generate long-term and seamless 1 km SSM dataset with higher spatial extrapolation accuracy. The study area included five ground observation network regions (Shiquanhe, Pali, Naqu, Heihe and Maqu). Firstly, the incomplete 1 km scale SSM was retrieved by upscaling the in-situ SSM using the Residual Dense Network (RDN) model. Then, the Bayesian maximum entropy (BME) method, considering the uncertainties of the upscaled SSM, was employed to spatiotemporally fuse upscaled and in-situ SSM to improve the accuracy of spatial extrapolation. Validation based test sites shows that the accuracy of the fused SSM data was improved across all five regions, with the improvement in ubRMSE ranging from 3.33% to 21.28%, resulting in an overall increase of 8.2%. The fused SSM can more effectively capture the temporal variability of the measurements of test stations. The results demonstrate that the proposed framework effectively generates a reference SSM dataset within the ground observation network area.
How to cite: Zhu, Z.: Generation of long-term and seamless 1 km surface soil moisture dataset within the area of in-situ network, EGU General Assembly 2025, Vienna, Austria, 27 Apr–2 May 2025, EGU25-18617, https://doi.org/10.5194/egusphere-egu25-18617, 2025.
Posters virtual: Mon, 28 Apr, 14:00–15:45 | vPoster spot A
EGU25-20070 | ECS | Posters virtual | VPS8
Enhancing Soil Moisture Estimation through Machine Learning Models and Remote Sensing DataMon, 28 Apr, 14:00–15:45 (CEST) | vPA.19
Moisture content available in soil, is a critical parameter for understanding the health of ecosystems, agricultural productivity, and the management of water resources. Soil moisture is an essential component in the growth of vegetation, climate regulation, and the hydrological cycle. The correct estimation of soil moisture is very crucial for optimizing irrigation, enhancing crop yields, and managing water resources. Spatial coverage limits traditional in-situ measurements, while remote sensing-based approaches, especially using SAR imagery, provide scalability to large-scale spatial coverage for soil moisture estimation. This study compares five machine learning-based models- Long Short-Term Memory (LSTM), Random Forest (RF), Multiple Linear Regression (MLR), Multi-layer Perceptron (MLP), and Support Vector Machines (SVM)-for deriving estimates of soil moisture using features based on VV and VH polarizations and incidence angle from SAR imagery. Model performance was also evaluated using in-situ measurements from Vaira Ranch in California's Central Valley, which comprises grasslands and wetlands. Meteorological data, which include precipitation and antecedent rainfall from the ERA5, were used to improve prediction. Each model was hyperparameter tuned, with LSTM adjusting layers, units, and learning rate; RF optimizing tree number, depth, and feature selection; MLR modifying regularization strength; MLP refining layers, neurons, and activation function; and SVM fine-tuning kernel type, C, and gamma. Performance metrics used for evaluation included R² and Root Mean Square Error (RMSE). The results indicated that LSTM outperformed other models with a R² of 0.89, followed by SVM at a value of 0.81 and RF at a value of 0.78. MLP and MLR values were lower at 0.67. This research focuses on the advantages of the integration of remote sensing data and meteorological information for better soil moisture estimation using machine learning and show that the advanced models such as LSTM and RF can effectively predict soil moisture, with important implications for improving agricultural management and resource planning.
How to cite: Sharma, V., Barbhuiya, S., and Gupta, V.: Enhancing Soil Moisture Estimation through Machine Learning Models and Remote Sensing Data, EGU General Assembly 2025, Vienna, Austria, 27 Apr–2 May 2025, EGU25-20070, https://doi.org/10.5194/egusphere-egu25-20070, 2025.
