2026
Journal Article MDPI RS Q2 IF 4.3
Costăchioiu, Teodor; Vasilescu, Vlad; Grivei, Alexandru-Cosmin; Griparis, Andreea; Faur, Daniela
In: Remote Sensing, vol. 18, no. 21, 2026, ISSN: 2072-4292.
@article{rs18213655,
title = {SENSERO: A Multi-Scale, Multi-Label Sentinel-2 Benchmark for Romania with Cross-Scale Land-Cover Classification Baselines},
author = { Teodor Costăchioiu and Vlad Vasilescu and Alexandru-Cosmin Grivei and Andreea Griparis and Daniela Faur},
url = {https://www.mdpi.com/2072-4292/18/21/3655},
doi = {10.3390/rs18213655},
issn = {2072-4292},
year = {2026},
date = {2026-01-01},
urldate = {2026-01-01},
journal = {Remote Sensing},
volume = {18},
number = {21},
abstract = {Patch size is an important design parameter in patch-based Earth observation (EO) learning, yet it is rarely treated as an experimental variable because existing benchmarks use a single fixed scale. We introduce SENSERO, a multi-scale, multi-label Sentinel-2 benchmark for Romania consisting of 10,000 geographically fixed locations extracted at eight patch sizes, from 64×64 to 336×336 pixels, at a constant 10 m ground sampling distance, so that all scales share identical patch centres and an identical, spatially disjoint 70/15/15 partition. Each patch provides twelve-band bottom-of-atmosphere reflectance, a rasterised CORINE Land Cover (CLC) 2018 reference map from which five deterministic multi-label annotation layers are derived (three levels of the CLC hierarchy, the BigEarthNet nomenclature, and a scheme adapted to the Romanian landscape). The benchmark task is patch-level multi-label classification; the rasterised reference maps serve to derive and trace the labels, not as a segmentation target. Using ResNet-50 baselines trained from scratch, we find that larger patches bring little benefit at CLC Level 1 but clear gains at Levels 2 and 3 (macro mAP at Level 3 rising from 0.42 at 64 px to 0.61 at 336 px), with per-location gains saturating around 224–256 pixels; that transfer across scales is asymmetric, models trained on wide patches transferring to narrow ones far better than the reverse; and that the choice of nomenclature affects measured performance as much as patch size. Leave-scene-out cross-validation, an ablation of the labelling rule, pretrained ResNet-50 and ViT-S/16 controls and bootstrap confidence intervals show that the scale effect is not attributable to spatial leakage, to the annotation rule, or to the baseline architecture. Comparison with an independent 10 m land-cover product shows that the gain from context is concentrated where CLC labels generalise over heterogeneous ground.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Journal Article U.P.B. Sci. Bull., Series C
Comparative Evaluation of Vision-Enabled LLMs for Remote Sensing Image Captioning
Vătășoiu, Robert-Ionuț; Costăchioiu, Teodor; Faur, Daniela
In: University Politehnica of Bucharest Scientific Bulletin, Series C, vol. 88, no. 2, pp. 143–154, 2026, ISSN: 2286-3540.
@article{Vatasoiu2026Comparative,
title = {Comparative Evaluation of Vision-Enabled LLMs for Remote Sensing Image Captioning},
author = { Robert-Ionuț Vătășoiu and Teodor Costăchioiu and Daniela Faur},
url = {https://www.scientificbulletin.upb.ro/static/pdfs/a2026nr2c_11_16894_C-119_R_Vatasoiu_latex_bun.pdf},
issn = {2286-3540},
year = {2026},
date = {2026-01-01},
urldate = {2026-01-01},
journal = {University Politehnica of Bucharest Scientific Bulletin, Series C},
volume = {88},
number = {2},
pages = {143–154},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Proceedings Article IGARSS 2026
On the Impact of Patch Size in LLM-Based Image Captioning of Sentinel-2 Imagery
Costachioiu, Teodor; Vasilescu, Vlad; Faur, Daniela
In: IGARSS 2026 - 2026 IEEE International Geoscience and Remote Sensing Symposium, pp. 1396-1400, 2026.
@inproceedings{11730172,
title = {On the Impact of Patch Size in LLM-Based Image Captioning of Sentinel-2 Imagery},
author = {Teodor Costachioiu and Vlad Vasilescu and Daniela Faur},
doi = {10.1109/IGARSS60577.2026.11730172},
year = {2026},
date = {2026-01-01},
urldate = {2026-01-01},
booktitle = {IGARSS 2026 - 2026 IEEE International Geoscience and Remote Sensing Symposium},
pages = {1396-1400},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Proceedings Article IGARSS 2026
Efficient Geometry-Controlled High-Resolution Satellite Image Synthesis
Vasilescu, Vlad; Faur, Daniela; Costăchioiu, Teodor
In: IGARSS 2026 - 2026 IEEE International Geoscience and Remote Sensing Symposium, pp. 160-164, 2026.
@inproceedings{11731191,
title = {Efficient Geometry-Controlled High-Resolution Satellite Image Synthesis},
author = {Vlad Vasilescu and Daniela Faur and Teodor Costăchioiu},
doi = {10.1109/IGARSS60577.2026.11731191},
year = {2026},
date = {2026-01-01},
urldate = {2026-01-01},
booktitle = {IGARSS 2026 - 2026 IEEE International Geoscience and Remote Sensing Symposium},
pages = {160-164},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
2025
Proceedings Article FM4EO
Leveraging Large Language Models and Retrieval-Augmented Generation for Enhanced Sentinel-2 Data Analysis
Costăchioiu, Teodor; Văduva, Corina; Faur, Daniela
In: ESA-NASA International Workshop on Geospatial AI Foundation Models for Earth Observation and Earth Science (FM4EO), ESA phi-lab and NASA Frascati, Italy, 2025, (Presented in the session: Agent AI, Digital Assistant, LLM, ESA–ESRIN, 6 May 2025).
@inproceedings{costachioiu2025esa,
title = {Leveraging Large Language Models and Retrieval-Augmented Generation for Enhanced Sentinel-2 Data Analysis},
author = {Teodor Costăchioiu and Corina Văduva and Daniela Faur},
year = {2025},
date = {2025-05-01},
urldate = {2025-05-01},
booktitle = {ESA-NASA International Workshop on Geospatial AI Foundation Models for Earth Observation and Earth Science (FM4EO)},
address = {Frascati, Italy},
organization = {ESA phi-lab and NASA},
note = {Presented in the session: Agent AI, Digital Assistant, LLM, ESA–ESRIN, 6 May 2025},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Proceedings Article
Exploring Image Dataset Structure through Deep Feature Extraction and Dimensionality Reduction
Vasilevschi, Ana-Mihaela; Faur, Daniela
In: Proceedings of the 25th International Conference on Control Systems and Computer Science (CSCS25), Bucharest, Romania, 2025.
@inproceedings{vasilevschi2025deepdr,
title = {Exploring Image Dataset Structure through Deep Feature Extraction and Dimensionality Reduction},
author = {Ana-Mihaela Vasilevschi and Daniela Faur},
url = {https://25.cscs-conference.com/},
year = {2025},
date = {2025-05-01},
urldate = {2025-05-01},
booktitle = {Proceedings of the 25th International Conference on Control Systems and Computer Science (CSCS25)},
address = {Bucharest, Romania},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Proceedings Article IGARSS 2025
Large Language Models with Retrieval Augmented Generation to streamline Sentinel-2 data Description
Costăchioiu, Teodor; Văduva, Corina; Faur, Daniela
In: IGARSS 2025 - 2025 IEEE International Geoscience and Remote Sensing Symposium, pp. 1022-1026, 2025.
@inproceedings{11242277,
title = {Large Language Models with Retrieval Augmented Generation to streamline Sentinel-2 data Description},
author = {Teodor Costăchioiu and Corina Văduva and Daniela Faur},
doi = {10.1109/IGARSS55030.2025.11242277},
year = {2025},
date = {2025-01-01},
urldate = {2025-01-01},
booktitle = {IGARSS 2025 - 2025 IEEE International Geoscience and Remote Sensing Symposium},
pages = {1022-1026},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Proceedings Article IGARSS2025
Fine-Tuning Adversarially-Robust Transformers for Single-Image Dehazing
Vasilescu, Vlad-Mihai; Neacșu, Ana-Antonia; Faur, Daniela
In: Proceedings of the IEEE International Geoscience and Remote Sensing Symposium (IGARSS), Brisbane, Australia, 2025, (Paper ID: TH3.M3.4, Oral presentation, Track: Data Analytics and AI Techniques in Remote Sensing, Conference dates: 3–8 August 2025. To appear.).
@inproceedings{Vasilescu2025RobustTransformer,
title = {Fine-Tuning Adversarially-Robust Transformers for Single-Image Dehazing},
author = {Vlad-Mihai Vasilescu and Ana-Antonia Neacșu and Daniela Faur},
year = {2025},
date = {2025-01-01},
urldate = {2025-01-01},
booktitle = {Proceedings of the IEEE International Geoscience and Remote Sensing Symposium (IGARSS)},
address = {Brisbane, Australia},
note = {Paper ID: TH3.M3.4, Oral presentation, Track: Data Analytics and AI Techniques in Remote Sensing, Conference dates: 3–8 August 2025. To appear.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Proceedings Article
CNN and LSTM-Based Forecasting of NDVI Trends for Environmental Monitoring
Vătășoiu, Robert-Ionuț; Faur, Daniela
In: Proceedings of the IEEE International Geoscience and Remote Sensing Symposium (IGARSS), Brisbane, Australia, 2025, (Paper ID: TUP2.PF.12, Poster presentation, Track: Change Detection and Temporal Analysis, Conference dates: 3–8 August 2025. To appear.).
@inproceedings{Vatasoiu2025NDVI,
title = {CNN and LSTM-Based Forecasting of NDVI Trends for Environmental Monitoring},
author = {Robert-Ionuț Vătășoiu and Daniela Faur},
year = {2025},
date = {2025-01-01},
urldate = {2025-01-01},
booktitle = {Proceedings of the IEEE International Geoscience and Remote Sensing Symposium (IGARSS)},
address = {Brisbane, Australia},
note = {Paper ID: TUP2.PF.12, Poster presentation, Track: Change Detection and Temporal Analysis, Conference dates: 3–8 August 2025. To appear.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Proceedings Article
Exploring Image Dataset Structure through Deep Feature Extraction and Dimensionality Reduction
Vasilevschi, Ana-Mihaela; Faur, Daniela
In: 2025 25th International Conference on Control Systems and Computer Science (CSCS), pp. 341-348, 2025.
@inproceedings{11181664,
title = {Exploring Image Dataset Structure through Deep Feature Extraction and Dimensionality Reduction},
author = {Ana-Mihaela Vasilevschi and Daniela Faur},
doi = {10.1109/CSCS66924.2025.00057},
year = {2025},
date = {2025-01-01},
urldate = {2025-01-01},
booktitle = {2025 25th International Conference on Control Systems and Computer Science (CSCS)},
pages = {341-348},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Proceedings Article DeSE
A Layered LSTM Architecture for Precipitation Prediction and Regression in Urban Areas
Nicolae, Stefan-Marius; Dandocsi, Alexandru; Faur, Daniela
In: 2025 18th International Conference on Development in eSystem Engineering (DeSE), pp. 13-18, 2025.
@inproceedings{11367928,
title = {A Layered LSTM Architecture for Precipitation Prediction and Regression in Urban Areas},
author = {Stefan-Marius Nicolae and Alexandru Dandocsi and Daniela Faur},
doi = {10.1109/DeSE68208.2025.11367928},
year = {2025},
date = {2025-01-01},
urldate = {2025-01-01},
booktitle = {2025 18th International Conference on Development in eSystem Engineering (DeSE)},
pages = {13-18},
abstract = {This paper presents a comparative analysis of three Long Short-Term Memory (LSTM) architectures for precipitation prediction and regression in urban areas. We implemented and evaluated a simple stacked bidirectional LSTM, a two-part model with separate classification and regression networks, and an integrated hurdle LSTM model. The architectures were tested on two distinct datasets: a large, highly variable dataset from Romania's National Air Quality Monitoring Network (NAQMN) and the more uniform CAMS ERA5 dataset from the European Centre for Medium-Range Forecasts (ECMWF). Results indicate that model performance is highly dependent on data characteristics. For the CAMS ERA5 dataset, all models achieved good performance, with the simple LSTM explaining data variability most effectively (R2-score of 0.63). On the more challenging and zero-biased NAQMN dataset, the hurdle LSTM model was clearly superior, providing more accurate predictions with a significantly lower Mean Absolute Error (MAE) of 0.23 compared to the other models. This study demonstrates that for complex and varied real-world data, sophisticated architectures like the hurdle LSTM are required for robust prediction, while simpler models can be effective on more homogenous datasets.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
2024
Proceedings Article
Developing a Call Detail Record Generator for Cultural Heritage Preservation and Theft Mitigation: Applications and Implications
Vatasoiu, Robert Ionut; Vulpe, Alexandru; Florescu, Robert; Sachian, Mari-Anais; Suciu, George
In: Proceedings of the 19th International Conference on Availability, Reliability and Security, pp. 1–5, 2024.
@inproceedings{vatasoiu2024developing,
title = {Developing a Call Detail Record Generator for Cultural Heritage Preservation and Theft Mitigation: Applications and Implications},
author = {Robert Ionut Vatasoiu and Alexandru Vulpe and Robert Florescu and Mari-Anais Sachian and George Suciu},
year = {2024},
date = {2024-01-01},
urldate = {2024-01-01},
booktitle = {Proceedings of the 19th International Conference on Availability, Reliability and Security},
pages = {1–5},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}