Elena Nafieva

Ms. Elena Nafieva

orcid

Research Focus & Metrics

Academic Career Length

2Years (2025-Present)

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

Representative Publications

View All Publications
29 October 2026 in Remote Sensing
Verified
Journal Article
Open access
PDF file
ARAbdelkader Riche
Abdelkader Riche
CACarla Arellano
Carla Arellano
ENElena Nafieva
Elena Nafieva
JEJachin Jonathan van Ek
Jachin Jonathan van Ek
YRYann Rebois
Yann Rebois
Daniel HölblingDaniel Hölbling
Daniel Hölbling
Rapid post-event landslide mapping is essential for emergency response and disaster management; however, accurately delineating rainfall-induced landslides remains challenging because of their fragmented morphology, heterogeneous landscapes, and the complementary nature of Earth Observation data. Although recent deep learning approaches have demonstrated promising performance using optical imagery, the contribution of different geo-auxiliary information to landslide segmentation and its transferability across regions remain insufficiently understood. This study proposes a Residual Dual-Branch SegFormer that integrates heterogeneous geospatial information through a lightweight residual Convolutional Neural Network (CNN) encoder and a novel Multi-Scale Geo-Auxiliary Gated Fusion Module (MGFM), enabling adaptive feature fusion while preserving the original SegFormer architecture. Using a multimodal dataset constructed from the March 2023 Tropical Cyclone Freddy event in southern Malawi, we systematically evaluate RGB imagery combined with optical, terrain, and Sentinel-1 SAR-derived auxiliary layers. The framework is assessed on a geographically independent test area and further validated through zero-shot transfer on the public Landslide4Scene and Lushan datasets. Experimental results demonstrate the following: (1) Integrating pre- and post-event SAR coherence with RGB imagery achieves the best overall performance when applied to areas that match the training data, reaching a mean Intersection over Union (mIoU) of 80.56% and an F1-score of 78.03% in the independent Malawi test area. (2) RGB combined with slope represents the most effective among the evaluated static topographic configurations in zero-shot transfer to the two external datasets, consistently outperforming the RGB baseline. (3) The proposed framework exhibits strong cross-region generalization, achieving the highest transfer performance on both external datasets while demonstrating that SAR coherence provides the most discriminative auxiliary information for post-event rainfall-induced landslide segmentation. These findings provide practical guidance for designing robust multimodal deep learning frameworks for operational landslide mapping.

15 March 2025
Verified
Conference Paper
Open access
Zahra DabiriZahra Dabiri
Zahra Dabiri
Daniel HölblingDaniel Hölbling
Daniel Hölbling
ENElena Nafieva
Elena Nafieva
VSVanessa Streifeneder
Vanessa Streifeneder
LALorena Abad
Lorena Abad
FAFlorian Albrecht
Florian Albrecht
Glacier retreats, along with associated geomorphological and periglacial processes, can significantly impact hiking infrastructure and have consequences for the local tourism industry, which heavily depends on high-altitude mountaineering. Interferometric Synthetic Aperture Radar (InSAR) time-series techniques, such as the Small Baseline Subset (SBAS) method, have gained considerable attention for analysing surface deformation and slope instability. InSAR utilises phase information to measure time-series surface deformations with sub-centimetre accuracy.The primary objective of this study is to identify and measure surface deformation and slope instability using InSAR, and to investigate the potential impacts on selected alpine huts in high mountain regions in Austria. We use time-series Sentinel-1 data and open-source software, including the InSAR Scientific Computing Environment (ISCE) tool for SAR data processing and the Miami InSAR Time-series software in PYthon (Mintpy) for SBAS analysis. By integrating the InSAR results, slope units derived from a high-resolution digital elevation model (DEM), and alpine infrastructure locations, we identify areas showing significant deformation rates. The initial results provide insights into the slope instabilities and surface deformation that may affect alpine infrastructure. The results highlight the potential of advanced InSAR time-series analysis for monitoring surface deformation in highly dynamic alpine landscapes, where increasing natural hazards, such as landslides, necessitate improved natural hazard and risk management. Future steps include discussion and validation of the results in collaboration with experts from alpine associations.

14 March 2026
Verified
Conference Paper
Open access
CACarla Mae Arellano
Carla Mae Arellano
Daniel HölblingDaniel Hölbling
Daniel Hölbling
ENElena Nafieva
Elena Nafieva
JEJachin Jonathan van Ek
Jachin Jonathan van Ek
SHStéphane Henriod
Stéphane Henriod
LALorena Abad
Lorena Abad
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.

14 March 2026
Verified
Conference Paper
Open access
ENElena Nafieva
Elena Nafieva
CACarla Arellano
Carla Arellano
Daniel HölblingDaniel Hölbling
Daniel Hölbling
JEJachin Jonathan van Ek
Jachin Jonathan van Ek
SHStéphane Henriod
Stéphane Henriod
LALorena Abad
Lorena Abad
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.

18 March 2025
Verified
Conference Paper
Open access
LALorena Abad
Lorena Abad
Daniel HölblingDaniel Hölbling
Daniel Hölbling
VSVanessa Streifeneder
Vanessa Streifeneder
ENElena Nafieva
Elena Nafieva
Zahra DabiriZahra Dabiri
Zahra Dabiri
FAFlorian Albrecht
Florian Albrecht
Satellite imagery time series (SITS) have become a powerful tool to monitor changes within complex landscapes. Opposed to single snapshots, insights and information derived from SITS expand our knowledge about dynamic processes, such as those occurring in glacier forefields. In recent decades, the decline of glaciers and the related enlargement of glacier forefields have occurred at unprecedented rates, leading to the evolution of new landscapes. For instance, climate change has accelerated the meltwater runoff from glaciers, resulting in the emergence and expansion of drainage systems. This work aims at a spatio-temporal analysis of the evolution of proglacial river courses in glacier forelands for selected areas in the High Tauern mountain range and the Ötztal Alps in Austria. For this purpose, on-demand data cubes based on high-resolution SITS from PlanetScope are created for the focus areas. A machine learning classification of distinct land cover types, focusing on water detection is performed to identify the river course at each timestamp. Ancillary data, such as topography, is integrated into the classification process to enhance accuracy. Further, an analysis of time series trajectories allows the quantification of change per pixel, providing a detailed overview of the evolution of the river courses. These changes are then related to deglaciation processes driven by climatic variations. The results of this study will contribute to a better understanding of how glacier retreat influences hydrological systems in alpine environments, offering valuable insights for future research and environmental management.

18 March 2025
Verified
Conference Paper
Open access
ENElena Nafieva
Elena Nafieva
Daniel HölblingDaniel Hölbling
Daniel Hölbling
EHEmma Hauglin
Emma Hauglin
Zahra DabiriZahra Dabiri
Zahra Dabiri
BRBenjamin Aubrey Robson
Benjamin Aubrey Robson
LALorena Abad
Lorena Abad
Rock glaciers, key indicators of permafrost dynamics and hydrological processes in alpine regions, are studied to understand their kinematics and responses to climate change. By analysing Earth observation (EO) data, it is possible to detect and delineate them, estimate rock glacier velocities including seasonal and multi-year velocity patterns, and identify shifts from rapid, erratic glacial flow to slower, more stable movements.In this study, we investigate how well InSAR-derived surface displacement measurements derived from Interferometric Synthetic Aperture Radar (InSAR) analysis of Sentinel-1 data align with rock glacier delineations from an existing inventory created through manual interpretation (Wagner et al., 2020) as well as an inventory produced by deep learning techniques by the authors of this contribution. Selected mountainous areas in the Austrian Alps serve as test sites. Specifically, we (1) evaluate the suitability of InSAR results for confirming or disconfirming rock glacier locations, (2) propose ways to improve the delineation of rock glaciers by integrating InSAR results, and (3) identify factors that may influence the InSAR results, such as topography, the size of the rock glacier, the movement rate, and slope-dependent dynamics. The findings can provide insights into the geomorphological controls on rock glacier dynamics and aid in refining feature delineation.We will present results that include adapted spatial delineations of rock glaciers, examples of alignments and discrepancies between InSAR measurements and rock glacier delineations, and an exemplary assessment of factors limiting the capability of InSAR for rock glacier detection and characterisation. These insights can contribute to advancing our understanding of rock glacier behaviour, thereby supporting water resource management and hazard mitigation efforts in alpine environments. Wagner, T., Ribis, M., Kellerer-Pirklbauer, A., Krainer, K., Winkler, G., 2020. The Austrian rock glacier inventory RGI_1 and the related rock glacier catchment inventory RGCI_1 in ArcGis (shapefile) format [dataset]. PANGAEA. https://doi.org/10.1594/PANGAEA.921629