Bernhard Raml

Mr. Bernhard Raml

Technical University of Vienna, Vienna, Wien, Austria
orcid

Research Focus & Metrics

Academic Career Length

5Years (2022-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
24 August 2022 in Electronics
Verified
Journal Article
Open access
PDF file
DSDaniel Soukup
Daniel Soukup
CKChristian Kapeller
Christian Kapeller
BRBernhard Raml
Bernhard Raml
JRJohannes Ruisz
Johannes Ruisz
We investigated optimal implementation strategies for industrial inspection systems aiming to detect cracks on ground steel billets’ surfaces by combining state-of-the-art AI-based methods and classical computational imaging techniques. In 2D texture images, the interesting patterns of surface irregularities are often surrounded by visual clutter, which is to be ignored, e.g., grinding patterns. Even neural networks struggle to reliably distinguish between actual surface disruptions and irrelevant background patterns. Consequently, the image acquisition procedure already has to be optimised to the specific application. In our case, we use photometric stereo (PS) imaging to generate 3D surface models of steel billets using multiple illumination units. However, we demonstrate that the neural networks, especially in high-speed scenarios, still suffer from recognition deficiencies when using raw photometric stereo camera data, and are unable to generalise to new billets and image acquisition conditions. Only the additional application of adequate state-of-the-art image processing algorithms guarantees the best results in both aspects. The neural networks benefit when appropriate image acquisition methods together with image processing algorithms emphasise relevant surface structures and reduce overall pattern variation. Our proposed combined strategy shows a 9.25% better detection rate on validation data and is 14.7% better on test data, displaying the best generalisation.

20 January 2025
Verified
Conference Paper
Open access
BRBernhard Raml
Bernhard Raml
RQRaphael Quast
Raphael Quast
MSMartin Schobben
Martin Schobben
CRChristoph Reimer
Christoph Reimer
WWWolfgang Wagner
Wolfgang Wagner
In remote sensing applications, the ability to efficiently fit models to vast amounts of observational data is vital for deriving high-quality data products, as well as accelerating research and development. Addressing this challenge, we developed a high-performance non-linear Trust Region Reflectance solver specialised for datacubes, by integrating Python's interoperability with C++ and Dask's distributed computing capabilities. Our solution achieves high throughput both locally and potentially on any Dask-compatible backend, such as EODC's Dask Gateway. The Dask framework takes care of chunking the datacube, and streaming each chunk efficiently to available workers where our specialised solver is applied. Introducing Dask for distributed computing enables our algorithm to run on different compatible backends. This approach not only broadens operational flexibility, but also allows us to focus on enhancing the algorithm's efficiency, free from concerns about concurrency. This enabled us to implement a highly efficient solver in C++, which is optimised to run on a single core, but still utilise all available resources effectively. For the heavy lifting, such as performing singular value decompositions and matrix operations we rely on Eigen, a powerful open-source C++ library specialized on linear algebra. To describe the spatial reference and other auxiliary data associated with our datacube, we employ the Xarray framework. Importantly, Xarray integrates seamlessly with Dask. Finally, to ensure robustness and extensibility of our framework, we applied state-of-the-art software engineering practices, including Continuous Integration and Test-Driven Development. In our work we demonstrate the significant performance gains achievable by effectively utilising available open-source frameworks, and adhering to best engineering practices. This is exemplified by our practical workflow demonstration to fit a soil moisture estimation model.

14 March 2026
Verified
Other
Open access
WPWolfgang Preimesberger
Wolfgang Preimesberger
PSPietro Stradiotti
Pietro Stradiotti
Maria PilesMaria Piles
Maria Piles
DFDong Fan
Dong Fan
BRBernhard Raml
Bernhard Raml
WDWouter Dorigo
Wouter Dorigo
Since the launch of ESA’s Sentinel-1 mission, openly accessible soil moisture products at ~1 km spatial sampling have become popular for regional scientific studies and numerous applications in agriculture, on land use/change, and water resource management, among others. However, while community-agreed approaches exist for estimating data quality in the temporal domain - e.g., through comparison with in situ measurement time series - comparable quantitative assessments of spatial performance are still largely lacking. This is due to the limited availability of reference measurements and the lack of methods that can effectively exploit them for spatial evaluation.Recently, a new Point-Scale-Downsampling (PSD) framework was proposed, which enables the computation of both temporal and spatial performance metrics between satellite observations and in situ point measurements. The framework uses coarse-scale benchmark data to assess relative differences between products across spatial scales.In this presentation, we show results from a recent intercomparison study of native (Sentinel-1) and downscaled (SMAP, SMOS, ASCAT, ESA CCI) 1 km soil moisture products over Europe. We compute temporal and spatial performance metrics using the PSD framework with respect to reference in situ measurements from the International Soil Moisture Network (ISMN). We place our findings in the context of traditional temporal quality assessments and correlogram-based spatial variability characteristics. We conclude that, while high-resolution products overall outperform coarse-resolution benchmark products in terms of spatial information content, the downscaled products at this stage tend to show better spatio-temporal agreement with the available in situ measurements than native SAR retrievals. Additional reference measurements and novel, qualitative approaches to assess the suitability of satellite soil moisture for specific applications could further improve the understanding and reliability of these data in the future.This study received funding from the European Space Agency (ESA) "Hyper-resolution Earth observations and land-surface modeling for a better understanding of the water cycle" (4Dhydro) project, with tender reference: ESA AO/1-11298/22/I-EF.

1 January 2026 in IEEE Transactions on Geoscience and Remote Sensing
Verified
Journal Article
Open access
BRBernhard Raml
Bernhard Raml
WWWolfgang Wagner
Wolfgang Wagner
BBBernhard Bauer-Marschallinger
Bernhard Bauer-Marschallinger
TMThomas Melzer
Thomas Melzer
MVMariette Vreugdenhil
Mariette Vreugdenhil

23 May 2026 in EarthArXiv
Verified
Preprint
Open access
CVCarina Villegas-Lituma
Carina Villegas-Lituma
MVMariette Vreugdenhil
Mariette Vreugdenhil
SMSamuel Massart
Samuel Massart
IBIgnacio Borlaf-Menal
Ignacio Borlaf-Menal
BRBernhard Raml
Bernhard Raml
WWWolfgang Wagner
Wolfgang Wagner
Agricultural drought monitoring is essential for food security in tropical regions where rain-fed agriculture predominates. Operational early warning systems rely primarily on optical vegetation indices, but cloud cover limits their usability during critical growing periods. SAR satellites can observe through clouds, yet their adoption in agricultural drought monitoring remains limited. This study evaluates Sentinel-1 CR, a SAR-based vegetation indicator sensitive to crop water content and canopy structure, for drought monitoring across six districts in central and southern Mozambique. Using data from 2019 to 2024, we track drought propagation from precipitation (CHIRPS) through soil moisture (ASCAT) to vegetation response (CR and NDVI). Results show that CR correlates positively with NDVI over cropland, and that vegetation response corresponds more closely with soil moisture than with precipitation across most land cover types, though shrubland shows stronger precipitation dependence, indicating land-cover-specific pathways. CR captured the 2019/2020 El Niño drought and subsequent recovery across all districts. However, CR interpretation depends on land cover composition: cropland-dominated areas show clear seasonal patterns enabling anomaly-based drought detection, while heterogeneous cropland-forest/shrub mosaics typical of rain-fed systems require land cover stratified analysis at high resolution to isolate cropland-specific responses. These findings demonstrate that SAR-based vegetation monitoring can complement optical approaches for drought early warning in cloud-prone tropical regions.

20 January 2025
Verified
Conference Paper
Open access
CVCarina Villegas-Lituma
Carina Villegas-Lituma
MVMariette Vreugdenhil
Mariette Vreugdenhil
SMSamuel Massart
Samuel Massart
PSPavan Muguda Sanjeevamurthy
Pavan Muguda Sanjeevamurthy
BRBernhard Raml
Bernhard Raml
WWWolfgang Wagner
Wolfgang Wagner
Sentinel-1, a pair of Synthetic Aperture Radar (SAR) sensors, provides valuable all-weather and day-night imaging capabilities, enabling continuous monitoring of vegetation dynamics even in the presence of cloud cover. SAR sensors excel at penetrating vegetation canopies and providing information on crucial factors like vegetation structure, biomass, and moisture content. However, most remote sensing vegetation studies have primarily relied on optical data, benefiting from longer historical datasets but facing challenges due to atmospheric interference, limited temporal resolution. Moreover, there is no research assessing the sensitivity of optical and radar data to the dynamics of vegetation in Mozambique. This study investigates the sensitivity of the Sentinel-1 (S-1) backscatter signal to vegetation dynamics over Mozambique. We compare it with the Normalized Difference Vegetation Index (NDVI) from MODIS data and explore its relationship with precipitation variability and droughts across different land covers, including forest, cropland, herbaceous vegetation, and herbaceous wetland in Mozambique.The Sentinel-1 VV and VH polarized images were used to calculate the Cross Ratio (CR=VH/VV). Temporal behaviors of CR S-1 and MODIS NDVI were analyzed from 2017 to 2022, examining seasonal patterns, inter-annual variability, trends, and outliers. NDVI anomalies were calculated to identify the spatial and temporal occurrence of agricultural droughts, while CHIRPS precipitation data was utilized to detect fluctuations in the CR S-1 and NDVI time series relative to precipitation. The analysis revealed distinct seasonality in the CR time series data across all land cover types. Notably, croplands, herbaceous vegetation, and herbaceous wetlands exhibited a consistent increase in CR during winter months, followed by a decline during summer months. In contrast, forests displayed an inverse trend, with CR decreasing in winter and increasing in summer. Furthermore, no pronounced CR patterns were observed in herbaceous wetlands during 2019, coinciding with the agricultural drought between 2018 and 2019. Additionally, the seasonality of MODIS NDVI time series remained consistent across all land cover types, with no noticeable differences. It was observed that fluctuations in NDVI time series preceded those in CR for these specific land cover types, suggesting a potential correlation with photosynthetic activity and subsequent biomass production. Significantly, this trend was found to be opposite in forested areas. Overall, the CR trend exhibited a clear correlation with rainfall seasonality across the various land cover types, except for forests where an inverse relationship was observed. On the other hand, NDVI demonstrated a higher sensitivity to changes in precipitation across the different land cover categories.These findings highlight the unique sensitivity of Sentinel-1 SAR data in capturing the intricate dynamics of vegetation across diverse land cover types in Mozambique, providing valuable complementary information to traditional optical data sources.