CACarla Arellano

Carla Arellano

*This is an algorithmically generated author record based on publicly available information.

Carla Arellano has a total of 18 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    PROMETHEUS: City-scale material mapping with large vision models for emissivity-based airborne thermography

    by Dirk Tiede, Martin Sudmanns, Max Aragon, Jose Gomez, Carla Arellano, Daniel Rüdisser, Sophia Klaußner, Günter Koren

    Deriving land surface temperatures (LST) from aerial thermography requires surface emissivity information, which is typically assumed uniform despite considerable variation across urban materials. We present PROMETHEUS, a workflow that uses a fine-tuned Large Vision Model (LVM) to produce city-scale material classification at airborne resolution. This classification enables emissivity-based LST estimation following the GRAZ method, which uses three-dimensional Monte Carlo sampling to determine view factors for reflected thermal radiation and models elevation-dependent atmospheric transmittance, upwelling and downwelling radiation. We applied this workflow to a 100×100 km area centred on Klagenfurt, Austria, where thermal infrared imagery at 1 m resolution was acquired on August 10-11, 2024 during a summer heat period, with daytime and nighttime flights at 1600 m altitude. A team of 12 surveyors collected concurrent in-situ land and water surface temperatures across 13 stations throughout the city. Using existing 5 cm RGB and near-infrared orthoimagery combined with photogrammetric building segmentation, expert annotators labelled rooftop materials across 30 classes via a collaborative platform with a standardized material guide. These labels were used to fine-tune an LVM that then classified materials across the full study area. The output was merged with municipal land cover data and converted to emissivity values using a look-up table derived from spectral libraries. Atmospheric parameters were obtained from ECMWF profiles. Comparison with in-situ measurements shows improved LST retrieval relative to uniform emissivity assumptions, particularly for low-emissivity surfaces such as metal roofing. This workflow demonstrates a practical approach for scaling limited expert annotations to city-wide material mapping.

  • Open Access

    An Overview of Earth Observation Resources and Services for Landslide Detection in Humanitarian Contexts

    by Elena Nafieva, Carla Arellano, Daniel Hölbling, Jachin Jonathan van Ek, Stéphane Henriod, Yann Rebois, Albert Schwingshandl, Sarah Forcieri, Zahra Dabiri, Raimund Heidrich, et al.

    Landslides cause numerous fatalities and extensive infrastructure damage every year, resulting in human and economic losses. Climate change and its cascading impacts are increasing both the frequency and magnitude of landslides, rockfalls, and debris flows. Humanitarian organisations, such as Médecins Sans Frontières (MSF), play a crucial role in disaster response, where timely, reliable, and up-to-date information is essential for effective hazard and damage assessments, as well as for coordinating rescue operations and humanitarian aid. Earth observation (EO) data and technologies have demonstrated strong potential for supporting emergency response and disaster risk management following landslide events. However, despite continuous methodological advances in academic research, EO-based approaches are rarely tested under real operational conditions, such as direct support to humanitarian organisations during ongoing emergencies. In addition, many existing solutions do not adequately address the specific user requirements and information needs that arise at different stages of the disaster cycle. This study therefore aims to generate targeted EO-based landslide information tailored to the operational needs of humanitarian aid. The landslides triggered by Tropical Cyclone Freddy in Malawi in 2023 are used as an illustrative example to demonstrate typical information needs and constraints during real emergency situations. We test and evaluate a range of landslide mapping tools and methods based on optical and radar satellite data, focusing on the detection, delivery, accuracy, and communication of landslide information for humanitarian applications. The approaches are assessed under typical emergency constraints, including processing time, limited data availability, unstable connectivity, and unsafe field conditions. Suitable methods are identified and customised in close alignment with MSF’s operational requirements. To enhance usability and impact, EO-derived results are combined with principles of risk communication, supporting humanitarian staff in interpreting and applying landslide information during response operations. Thus, this work contributes to bridging the gap between scientific EO research and practical humanitarian applications.

  • Open Access

    Interpreting landslide susceptibility models using explainable machine learning

    by Carla Mae Arellano, Daniel Hölbling, Elena Nafieva, Jachin Jonathan van Ek, Stéphane Henriod, Yann Rebois, Albert Schwingshandl, Sarah Forcieri, Raimund Heidrich, Isabella Hörbe, et al.

    Machine learning approaches are increasingly applied to landslide susceptibility mapping. Despite their growing use, limited insight into model behavior and variable influence remains a major challenge, particularly in data-scarce settings where inventories are incomplete and input data are heterogeneous. This study explores how explainability methods can be used to analyze and interpret machine learning-based landslide susceptibility models. First, a landslide susceptibility dataset is constructed by combining an available landslide inventory with commonly used environmental conditioning factors. These include topographic data (e.g. elevation, slope, curvature, flow accumulation), proximity variables (e.g. distance to rivers and roads), and land cover or vegetation proxies derived from Earth Observation (EO) data, such as the Normalized Difference Vegetation Index (NDVI). Our focus is on understanding how different input variables influence model predictions and how these influences vary spatially. For this, explainability techniques are applied to assess variable importance and spatial patterns in model responses. Feature attribution methods such as SHapley Additive exPlanations (SHAP) are used to quantify the contribution of individual conditioning factors at both the global model level and locally in space. The results are examined for consistency with established geomorphological understanding, and sensitivities related to data limitations, inventory characteristics, and sampling strategies are identified. This study provides insight into the strengths and limitations of machine learning-based landslide susceptibility modelling in data-scarce contexts and demonstrates how explainability can support more transparent and critically assessed susceptibility analyses. This work contributes to the development of interpretable susceptibility mapping approaches suited to preparedness and decision-support applications.