SubscribeSWIFTT’s findings are communicated at scientific conferences and published in open-access journals. Find below the current list of publications.
Access all publication on the project's Zenodo community clicking here.
A Deep Semantic Segmentation Approach to Map Forest Tree Dieback in Sentinel-2 Data
This paper illustrates a deep learning approach that trains a U-Net model for the semantic segmentation of Sentinel-2 images of forest areas.
G. Andresini, A. Appice and D. Malerba, in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, vol. 17, pp. 17075-17086, 2024, doi: 10.1109/JSTARS.2024.3460981
A Multimodal Dataset for Forest Damage Detection and Machine Learning
This paper provides a useful and reliable dataset for territory of Ukraine for scientists, conservationists, foresters and other stakeholders involved in monitoring forest damage and its consequences for forest ecosystems and their services.
H. Yailymova, B. Yailymov, Y. Salii, V. Kuzin, N. Kussul and A. Shelestov, IGARSS 2024 - 2024 IEEE International Geoscience and Remote Sensing Symposium, Athens, Greece, 2024, pp. 2949-2953, doi: 10.1109/IGARSS53475.2024.10641873.
A Novel Approach for Rapid Detection of Forest Degradation and Diseases Through Anomaly Analysis of Sentinel-2 Spectral Data
This paper presents a simple yet effective method for detecting forest degradation using freely available Sentinel-2 satellite data and an anomaly detection approach.
S. Drozd, N. Kussul, H. Yailymova, Proceedings of the 13th International Conference On Applied Innovations In IT, 2025, pp. 87-93. DOI: 10.25673/119219
AI-Powered Digital Twin Framework for Land Use Change in Disaster Affected Regions
This article presents a novel AI-powered Digital Twin (DT) framework tailored for disaster-affected regions, integrating multimodal satellite data, climate reanalysis, and in situ observations.
N. Kussul et al., in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, vol. 18, pp. 27473-27492, 2025, doi: 10.1109/JSTARS.2025.3623870.
An Attention-Based CNN Approach to Detect Forest Tree Dieback Caused by Insect Outbreak in Sentinel-2 Images
This paper proposes a deep learning-based approach, named AVALON, that implements a CNN to detect tree dieback events in Sentinel-2 images of forest areas.
Recchia, V., Andresini, G., Appice, A., Fontana, G., Malerba, D. (2025). Discovery Science. DS 2024. Lecture Notes in Computer Science, vol 15244. DOI: 10.1007/978-3-031-78980-9_12
Conservation policies and management in the Ukrainian Emerald Network have maintained reforestation rate despite the war.
This works explores the impact of the Russian-Ukrainian War on institutional links supporting environmental sustainability and conservation efforts. Using satellite data, the authors analyzed tree cover changes in the Luhansk region’s Emerald Network protected areas from 1996 to 2020.
L. Shumilo et al., in Commun Earth Environ 4, 443 (2023). DOI: 10.1038/s43247-023-01099-4
Current Advances on Cloud-Based Distributed Computing for Forest Monitoring
This work analyzes Sentinel-2 satellite spectral channels, which distribution of pixel values was constructed for diseased and healthy forests, and the possibility of separating these two classes was analyzed based on the Bhattacharya distance.
Shelestov, A., Salii, Y., Hordiiko, N., Yailymova, H. (2023). In Lecture Notes in Networks and Systems, vol 809. Springer, Cham. DOI: 10.1007/978-3-031-46880-3_20.
Deep Change Vector Analysis to Map Bark Beetle Outbreaks in Open Sentinel-2 Data
This paper explores the potential of an unsupervised learning method designed to process Sentinel-2 images of Earth’s forest scenes and automate the inventory of forest tree dieback caused by bark beetle outbreaks.
G. Andresini, A. Appice, D. Malerba and V. Recchia, 2025 International Joint Conference on Neural Networks (IJCNN), Rome, Italy, 2025, pp. 1-8, doi: 10.1109/IJCNN64981.2025.11229013.
DIAMANTE: A data-centric semantic segmentation approach to map tree dieback induced by bark beetle infestations via satellite images
This paper explores the performance of a data-centric semantic segmentation approach to detect forest tree dieback events due to bark beetle infestation in satellite images.
Andresini, G., Appice, A., Ienco, D. et al. J Intell Inf Syst (2024). doi: 10.1007/s10844-024-00877-6
Features’ Selection for Forest State Classification using Machine Learning on Satellite Data
This paper discusses the use of advanced computer vision and artificial intelligence techniques for analysing remote sensing data, specifically focusing on the semantic segmentation of forest areas.
Y. Salii, V. Kuzin, A. Lavreniuk, N. Kussul and A. Shelestov, IGARSS 2024 - 2024 IEEE International Geoscience and Remote Sensing Symposium, Athens, Greece, 2024, pp. 9874-9878, doi: 10.1109/IGARSS53475.2024.10642681.
Forest Stress Detection Using Feature Engineering and Selection Approach Optimized for Satellite Imagery
This study introduces an efficient and interpretable feature selection strategy that identifies optimal combinations of spectral features from generalized vegetation index classes rather than fixed indices.
Y. Salii, V. Kuzin, N. Kussul and A. Lavreniuk, in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, vol. 19, pp. 2461-2473, 2026, doi: 10.1109/JSTARS.2025.3644488.
GANDALF: A LLM-based approach to map bark beetle outbreaks in semantic stories of Sentinel-2 images
This paper describes GANDALF: an approach that leverages the potential of LLMs for mapping bark beetle outbreaks in Sentinel-2 images of forest areas.
Vincenzo Pasquadibisceglie, Vito Recchia, Annalisa Appice, Donato Malerba, and Giuseppe Fiameni. 2025. Proceedings of the 40th ACM/SIGAPP Symposium on Applied Computing. Association for Computing Machinery, New York, NY, USA, 1074–1081.DOI: 10.1145/3672608.3707751
Google Earth Engine Framework for Satellite Data-Driven Wildfire Monitoring in Ukraine
This study proposes an integrated methodology and a novel framework integrating burned area mapping from Sentinel-2 data and fire risk modeling using the Fire Potential Index (FPI) in Google Earth Engine.
Yailymov B, Shelestov A, Yailymova H, Shumilo L. Fire. 2023; 6(11):411. DOI: 10.3390/fire6110411
Leveraging Sentinel-2 time series for bark beetle-induced forest dieback inventory
This work explores the performance of remote sensing methods used to perform the inventory mapping of bark beetle-induced forest dieback.
Giuseppina Andresini, Annalisa Appice, and Donato Malerba. 2024. In Proceedings of the 39th ACM/SIGAPP Symposium on Applied Computing (SAC '24), 875–882. https://doi.org/10.1145/3605098.3635908
Machine Learning for Ukraine’s Forest Cover Damage Assessment based on Satellite Data
This research presents a comprehensive machine learning approach for assessing forest cover damage in Ukraine based on satellite data from 2016 to 2024.
H. Yailymova, B. Yailymov, A. Shelestov and N. Kussul, 2025 IEEE 13th International Conference on Intelligent Data Acquisition and Advanced Computing Systems: Technology and Applications (IDAACS), Gliwice, Poland, 2025, pp. 1241-1245, doi: 10.1109/IDAACS68557.2025.11322046.
Machine Learning Models and Technology for Classification of Forest on Satellite Data
The paper deals with the problem of semantic segmentation of satellite imagery to deliver forest type map with high resolution. To solve the problem, the researchers propose 4 machine learning models.
Y. Salii, V. Kuzin, A. Hohol, N. Kussul and H. Yailymova, IEEE EUROCON 2023 - 20th International Conference on Smart Technologies, Torino, Italy, 2023, pp. 93-98, DOI: 10.1109/EUROCON56442.2023.10199006.
Monitoring of Fires Caused by War in Ukraine Based on Satellite Data
The focus of this paper is on fire monitoring studies which utilize a variety of satellite data that are used to automatically detect fires at a national level in Ukraine.
B. Yailymov, H. Yailymova, A. Shelestov and L. Shumilo, 2023 13th International Conference on Dependable Systems, Services and Technologies (DESSERT), Athens, Greece, 2023, pp. 1-5, doi: 10.1109/DESSERT61349.2023.10416520.
Potential of Spectral-Spatial Analysis to Map Forest Tree Dieback Due to Bark Beetle Hotspots in Sentinel-2 Images
This paper explores the performance of a spectral-spatial machine learning approach used to analyse Sentinel-2 images to detect forest tree dieback events due to bark beetle infestation.
G. Andresini, A. Appice, D. Ienco, D. Malerba and V. Recchia, IGARSS 2024 - 2024 IEEE International Geoscience and Remote Sensing Symposium, Athens, Greece, 2024, pp. 5227-5230, doi: 10.1109/IGARSS53475.2024.10641479.
