Merge remote-tracking branch 'refs/remotes/origin/main'

Author: ngbountos

content/authors/christina-diamanti/_index.md

@@ -0,0 +1,73 @@
+---
+# The following command determines whether or not the author
+# has his/her own page, and is listed on the /People/ page.
+_build:
+  render: always
+cascade:
+  _build:
+    render: never
+    list: always
+
+# Display name
+title: Christina Diamanti
+
+# Full Name (for SEO)
+first_name: Christina
+last_name: Diamanti
+
+# Is this the primary user of the site?zaf
+superuser: true
+
+# Role/position
+role: ML Researcher
+
+# Organizations/Affiliations
+#organizations:
+#  - name: 
+#    url: ''
+
+# Short bio (displayed in user profile at end of posts)
+#bio: 
+interests:
+  - Deep Learning 
+  - Explainable AI
+  - Earth Observation
+  
+
+education:
+ courses:
+   - course: MEng Electrical and Computer Engineering 
+     institution: National Technical University of Athens
+     year: "2018-2024"
+
+# Social/Academic Networking
+# For available icons, see: https://wowchemy.com/docs/getting-started/page-builder/#icons
+#   For an email link, use "fas" icon pack, "envelope" icon, and a link in the
+#   form "mailto:your-email@example.com" or "#contact" for contact widget.
+social:
+  - icon: linkedin
+    icon_pack: fab
+    link: 'https://www.linkedin.com/in/christinadiamanti/'
+  - icon: envelope
+    icon_pack: fas
+    link: 'mailto:cdiamanti30@gmail.com'
+
+# Link to a PDF of your resume/CV from the About widget.
+# To enable, copy your resume/CV to `static/files/cv.pdf` and uncomment the lines below.
+# - icon: cv
+#   icon_pack: ai
+#   link: files/cv.pdf
+
+# Enter email to display Gravatar (if Gravatar enabled in Config)
+email: ''
+
+# Highlight the author in author lists? (true/false)
+highlight_name: false
+
+# Organizational groups that you belong to (for People widget)
+#   Set this to `[]` or comment out if you are not using People widget.
+user_groups:
+  - Core team
+---
+
+Christina Diamanti holds an Integrated Master’s degree in Electrical and Computer Engineering from the National Technical University of Athens (NTUA) with a focus on software engineering, computer systems, and computer networks. Her diploma thesis focused on custom load balancing in serverless distributed systems, combining systems design and cloud-native computing. She has previous experience as a DevOps Engineer in the private factor, working on telecom microservices and automation. She is currently a Junior ML Researcher at the Orion Lab. Her research interests lie at the intersection of Machine Learning, Explainable AI, and Earth Observation.

content/authors/christina-diamanti/avatar.jpeg

@@ -0,0 +1,15 @@
+@misc{anastasiou_wildfire_2025,
+ abstract = {Accurate prediction of wildfire spread is crucial for effective risk management, emergency response, and strategic resource allocation. In this study, we present a deep learning (DL)-based framework for forecasting the final extent of burned areas, using data available at the time of ignition. We leverage a spatio-temporal dataset that covers the Mediterranean region from 2006 to 2022, incorporating remote sensing data, meteorological observations, vegetation maps, land cover classifications, anthropogenic factors, topography data, and thermal anomalies. To evaluate the influence of temporal context, we conduct an ablation study examining how the inclusion of pre- and post-ignition data affects model performance, benchmarking the temporal-aware DL models against a baseline trained exclusively on ignition-day inputs. Our results indicate that multi-day observational data substantially improve predictive accuracy. Particularly, the best-performing model, incorporating a temporal window of four days before to five days after ignition, improves both the F1 score and the Intersection over Union by almost 5% in comparison to the baseline on the test dataset. We publicly release our dataset and models to enhance research into data-driven approaches for wildfire modeling and response.},
+ annote = {Comment: 10 pages, 9 figures},
+ author = {Anastasiou, Nikolaos and Kondylatos, Spyros and Papoutsis, Ioannis},
+ doi = {10.48550/arXiv.2505.17556},
+ file = {Preprint PDF:/Users/skondylatos/Zotero/storage/Y4L2BSQ2/Anastasiou et al. - 2025 - Wildfire spread forecasting with Deep Learning.pdf:application/pdf;Snapshot:/Users/skondylatos/Zotero/storage/JHHQGAZN/2505.html:text/html},
+ keywords = {Computer Science - Machine Learning, Computer Science - Computer Vision and Pattern Recognition},
+ month = {May},
+ note = {arXiv:2505.17556 [cs]},
+ publisher = {arXiv},
+ title = {Wildfire spread forecasting with Deep Learning},
+ url = {http://arxiv.org/abs/2505.17556},
+ urldate = {2025-07-07},
+ year = {2025}
+}

content/authors/spyros-kondylatos/avatar.jpg

@@ -0,0 +1,35 @@
+---
+title: Wildfire spread forecasting with Deep Learning
+authors:
+- Nikolaos Anastasiou
+- Spyros Kondylatos
+- Ioannis Papoutsis
+date: '2025-05-01'
+publishDate: '2025-09-24T07:23:04.817650Z'
+publication_types:
+- manuscript
+publication: '*arXiv*'
+doi: 10.48550/arXiv.2505.17556
+abstract: Accurate prediction of wildfire spread is crucial for effective risk management,
+  emergency response, and strategic resource allocation. In this study, we present
+  a deep learning (DL)-based framework for forecasting the final extent of burned
+  areas, using data available at the time of ignition. We leverage a spatio-temporal
+  dataset that covers the Mediterranean region from 2006 to 2022, incorporating remote
+  sensing data, meteorological observations, vegetation maps, land cover classifications,
+  anthropogenic factors, topography data, and thermal anomalies. To evaluate the influence
+  of temporal context, we conduct an ablation study examining how the inclusion of
+  pre- and post-ignition data affects model performance, benchmarking the temporal-aware
+  DL models against a baseline trained exclusively on ignition-day inputs. Our results
+  indicate that multi-day observational data substantially improve predictive accuracy.
+  Particularly, the best-performing model, incorporating a temporal window of four
+  days before to five days after ignition, improves both the F1 score and the Intersection
+  over Union by almost 5% in comparison to the baseline on the test dataset. We publicly
+  release our dataset and models to enhance research into data-driven approaches for
+  wildfire modeling and response.
+tags:
+- Computer Science - Machine Learning
+- Computer Science - Computer Vision and Pattern Recognition
+links:
+- name: URL
+  url: http://arxiv.org/abs/2505.17556
+---

content/publication/anastasiou-wildfire-2025/cite.bib

@@ -0,0 +1,20 @@
+@article{camps-valls_artificial_2025,
+ abstract = {In recent years, artificial intelligence (AI) has deeply impacted various fields, including Earth system sciences, by improving weather forecasting, model emulation, parameter estimation, and the prediction of extreme events. The latter comes with specific challenges, such as developing accurate predictors from noisy, heterogeneous, small sample sizes and data with limited annotations. This paper reviews how AI is being used to analyze extreme climate events (like floods, droughts, wildfires, and heatwaves), highlighting the importance of creating accurate, transparent, and reliable AI models. We discuss the hurdles of dealing with limited data, integrating real-time information, and deploying understandable models, all crucial steps for gaining stakeholder trust and meeting regulatory needs. We provide an overview of how AI can help identify and explain extreme events more effectively, improving disaster response and communication. We emphasize the need for collaboration across different fields to create AI solutions that are practical, understandable, and trustworthy to enhance disaster readiness and risk reduction.},
+ author = {Camps-Valls, Gustau and Fernández-Torres, Miguel-Ángel and Cohrs, Kai-Hendrik and Höhl, Adrian and Castelletti, Andrea and Pacal, Aytac and Robin, Claire and Martinuzzi, Francesco and Papoutsis, Ioannis and Prapas, Ioannis and Pérez-Aracil, Jorge and Weigel, Katja and Gonzalez-Calabuig, Maria and Reichstein, Markus and Rabel, Martin and Giuliani, Matteo and Mahecha, Miguel D. and Popescu, Oana-Iuliana and Pellicer-Valero, Oscar J. and Ouala, Said and Salcedo-Sanz, Sancho and Sippel, Sebastian and Kondylatos, Spyros and Happé, Tamara and Williams, Tristan},
+ copyright = {2025 The Author(s)},
+ doi = {10.1038/s41467-025-56573-8},
+ file = {Full Text PDF:/Users/skondylatos/Zotero/storage/G9L98CYW/Camps-Valls et al. - 2025 - Artificial intelligence for modeling and understan.pdf:application/pdf},
+ issn = {2041-1723},
+ journal = {Nature Communications},
+ keywords = {Climate sciences, Natural hazards},
+ language = {en},
+ month = {February},
+ note = {Publisher: Nature Publishing Group},
+ number = {1},
+ pages = {1919},
+ title = {Artificial intelligence for modeling and understanding extreme weather and climate events},
+ url = {https://www.nature.com/articles/s41467-025-56573-8},
+ urldate = {2025-05-05},
+ volume = {16},
+ year = {2025}
+}

content/publication/anastasiou-wildfire-2025/index.md

@@ -0,0 +1,56 @@
+---
+title: Artificial intelligence for modeling and understanding extreme weather and
+  climate events
+authors:
+- Gustau Camps-Valls
+- Miguel-Ángel Fernández-Torres
+- Kai-Hendrik Cohrs
+- Adrian Höhl
+- Andrea Castelletti
+- Aytac Pacal
+- Claire Robin
+- Francesco Martinuzzi
+- Ioannis Papoutsis
+- Ioannis Prapas
+- Jorge Pérez-Aracil
+- Katja Weigel
+- Maria Gonzalez-Calabuig
+- Markus Reichstein
+- Martin Rabel
+- Matteo Giuliani
+- Miguel D. Mahecha
+- Oana-Iuliana Popescu
+- Oscar J. Pellicer-Valero
+- Said Ouala
+- Sancho Salcedo-Sanz
+- Sebastian Sippel
+- Spyros Kondylatos
+- Tamara Happé
+- Tristan Williams
+date: '2025-02-01'
+publishDate: '2025-09-23T07:45:30.672101Z'
+publication_types:
+- article-journal
+publication: '*Nature Communications*'
+doi: 10.1038/s41467-025-56573-8
+abstract: In recent years, artificial intelligence (AI) has deeply impacted various
+  fields, including Earth system sciences, by improving weather forecasting, model
+  emulation, parameter estimation, and the prediction of extreme events. The latter
+  comes with specific challenges, such as developing accurate predictors from noisy,
+  heterogeneous, small sample sizes and data with limited annotations. This paper
+  reviews how AI is being used to analyze extreme climate events (like floods, droughts,
+  wildfires, and heatwaves), highlighting the importance of creating accurate, transparent,
+  and reliable AI models. We discuss the hurdles of dealing with limited data, integrating
+  real-time information, and deploying understandable models, all crucial steps for
+  gaining stakeholder trust and meeting regulatory needs. We provide an overview of
+  how AI can help identify and explain extreme events more effectively, improving
+  disaster response and communication. We emphasize the need for collaboration across
+  different fields to create AI solutions that are practical, understandable, and
+  trustworthy to enhance disaster readiness and risk reduction.
+tags:
+- Climate sciences
+- Natural hazards
+links:
+- name: URL
+  url: https://www.nature.com/articles/s41467-025-56573-8
+---

content/publication/camps-valls-artificial-2025/cite.bib

@@ -0,0 +1,7 @@
+@article{karavias2025,
+ author = {Karavias, Andreas and Anastasiou, Dimitrios and Svigkas, Nikos and Papanikolaou, Xanthos and De Astis, Gianfilippo and Atzori, Simone and Papoutsis, Ioannis},
+ journal = {ESS Open Archive},
+ title = {Santorini Inflates Again: Geodetic Monitoring and Modeling of the 2024–2025 Volcanic Unrest},
+ url = {https://essopenarchive.org/users/917515/articles/1290136-santorini-inflates-again-geodetic-monitoring-and-modeling-of-the-2024-2025-volcanic-unrest},
+ year = {2025}
+}

content/publication/camps-valls-artificial-2025/index.md

@@ -0,0 +1,19 @@
+---
+title: "Santorini Inflates Again: Geodetic Monitoring and Modeling of the 2024–2025 Volcanic Unrest"
+authors:
+- Andreas Karavias
+- Dimitrios Anastasiou
+- Nikos Svigkas
+- Xanthos Papanikolaou
+- Gianfilippo De Astis
+- Simone Atzori
+- Ioannis Papoutsis
+date: '2025-04-28'
+publication_types:
+- manuscript
+publication: "ESS Open Archive (Research Letter, Preprint)"
+url_pdf: "https://essopenarchive.org/users/917515/articles/1290136-santorini-inflates-again-geodetic-monitoring-and-modeling-of-the-2024-2025-volcanic-unrest"
+featured: true
+abstract: >
+  We analyze and discuss surface deformation patterns related to the Santorini Caldera unrest, spanning from summer 2024 to January 2025. Synthetic Aperture Radar (SAR) interferometry was performed exploiting the Persistent Scatterer Interferometry (PSI) technique. We used both satellite geometries of the Sentinel-1 mission, producing line-of-sight (LOS) deformation maps and displacement decomposition in vertical and horizontal components. The observed displacements were combined with measurements from four GNSS stations across Santorini island. The results highlight horizontal movements and uplift up to 70 mm/yr with a radial inflation pattern centered around the Kameni islands, reminiscent of the 2011-2012 inflation episode. The geophysical model for the 2024-2025 period suggests a positive volume rate change at 2.9 km depth. Compared to the 2011-2012 unrest, the volume rate change is smaller; potentially a mix of magma and gas may be causing pressure along Kameni’s volcano-tectonic line, this time with a shallower source than the previous unrest.
+---

content/publication/karavias-2025/cite.bib

@@ -1,13 +1,14 @@
-@misc{kondylatos_mesogeos_2023,
- abstract = {We introduce Mesogeos, a large-scale multi-purpose dataset for wildfire modeling in the Mediterranean. Mesogeos integrates variables representing wildfire drivers (meteorology, vegetation, human activity) and historical records of wildfire ignitions and burned areas for 17 years (2006-2022). It is designed as a cloud-friendly spatio-temporal dataset, namely a datacube, harmonizing all variables in a grid of 1km x 1km x 1-day resolution. The datacube structure offers opportunities to assess machine learning (ML) usage in various wildfire modeling tasks. We extract two ML-ready datasets that establish distinct tracks to demonstrate this potential: (1) short-term wildfire danger forecasting and (2) final burned area estimation given the point of ignition. We define appropriate metrics and baselines to evaluate the performance of models in each track. By publishing the datacube, along with the code to create the ML datasets and models, we encourage the community to foster the implementation of additional tracks for mitigating the increasing threat of wildfires in the Mediterranean.},
- author = {Kondylatos, Spyros and Prapas, Ioannis and Camps-Valls, Gustau and Papoutsis, Ioannis},
- date = {2023-06-08},
- eprint = {2306.05144 [cs]},
- eprinttype = {arxiv},
- number = {arXiv:2306.05144},
- publisher = {arXiv},
+@article{kondylatos_mesogeos_2023,
+ author = {Kondylatos, Spyridon and Prapas, Ioannis and Camps-Valls, Gustau and Papoutsis, Ioannis},
+ file = {Full Text PDF:/Users/skondylatos/Zotero/storage/BJ72LPZD/Kondylatos et al. - 2023 - Mesogeos A multi-purpose dataset for data-driven .pdf:application/pdf},
+ journal = {Advances in Neural Information Processing Systems},
+ language = {en},
+ month = {December},
+ pages = {50661--50676},
  shorttitle = {Mesogeos},
  title = {Mesogeos: A multi-purpose dataset for data-driven wildfire modeling in the Mediterranean},
- url = {http://arxiv.org/abs/2306.05144},
- urldate = {2023-11-04}
+ url = {https://proceedings.neurips.cc/paper_files/paper/2023/hash/9ee3ed2dd656402f954ef9dc37e39f48-Abstract-Datasets_and_Benchmarks.html},
+ urldate = {2024-04-20},
+ volume = {36},
+ year = {2023}
 }