palubad.bsky.social
Postdoctoral researcher in Earth Observation @ Charles University, Prague, Czechia | SAR | Time Series | 🌳🌲Forests | Machine Learning | 🎓 Capacity Building | 🚴🏼🏐
46 posts
1,054 followers
357 following
Regular Contributor
Active Commenter
comment in response to
post
@tandfresearch.bsky.social
comment in response to
post
Best-performing models available on Hugging Face: huggingface.co/palubad/SAR-...
Demo-code for running the models on GitHub: github.com/palubad/SAR-...
MMTS-GEE to generate multi-modal time series data: github.com/palubad/MMTS... , developed in our previous work: karolinum.cz/data/clanek/...
comment in response to
post
✅ Achieved temp. resolution of up to 240 measurements/year using SAR-based VIs with 2 S1 satellites in 2021 [soon to be restored with Sentinel-1C]
✅ Early disturbance detection: within 4 days vs 35 days with optical indices
✅ Fine-tuned #XGBoost and #RandomForest regressors outperformed #AutoML
comment in response to
post
👉 Temporally and spatially aligned SAR, DEM-based & meteo. features trained to estimate time series of #NDVI, #EVI, #LAI & #FAPAR
👉 Trained and tested in Czechia for healthy deciduous and coniferous forests, as well as disturbed areas ⏩ transferability tested for the whole Central Europe
comment in response to
post
Great to see it in action. Looks cool!
It reminded me that for larger countries, I should add a selection for smaller administrative units. I will try to implement it soon.
comment in response to
post
👉 Sign up for our newsletter here: eo4landscape.natur.cuni.cz/newsletter-2/
The Copernicus Academy CZ newsletter is prepared by the EO4Landscape research team at @sciencecharles.bsky.social Department of Applied Geoinformatics and Cartography, with support from the FPCUP project.
comment in response to
post
🌍 @copernicusland.bsky.social LMS General Assembly 2025 – registration & abstracts open for Krakow (May 20–22)
🚨 Copernicus Emergency Monitoring Service Conference – insights into flood monitoring (April 2–3)
🥦 Zero Hunger Online Course series by @EO College – explore EO’s role in food security
comment in response to
post
💨 WEkEO Workshop on Atmospheric Monitoring – live demos and user experiences (March 24 & 26)
📡 @esa.int ESA Earth Observation Workshop 2025 – hands-on training at ESA Academy in Belgium (July 14–18)
🛰️ DLR/ESA Open PolInSAR Course – deep dive into Polarimetric InSAR techniques (March 28 deadline)
comment in response to
post
What’s inside?
🚀 Advanced Use of Copernicus Browser – an interactive webinar on exploring Copernicus data by the Copernicus Data Space Ecosystem (April 8)
🌲 Remote Sensing of Forests Summer School – UAV, SAR and LiDAR applications at the Czech University of Life Sciences Prague (June 2–6)
comment in response to
post
Some thoughts on NotebookLM:
👉 5 free tokens per day to generate such podcasts.
👉 No way to edit or fine-tune the podcast. Need to regenerate it with additional hints or notes.
👉 Sometimes misinterprets information - the effect of precipitation caused false negatives, not false positives.
comment in response to
post
🎧 Full-length podcast: eo4landscape.natur.cuni.cz/wp-content/uploads/2025/03/Sentinel-1-SAR-for-Wildfire-Mapping-in-Greece-2.wav
Papers:
1️⃣ doi.org/10.1109/JSTARS.2024.3427382
2️⃣ doi.org/10.1109/IGARSS52108.2023.10283130
comment in response to
post
While the newsletter is in Czech 🇨🇿 , most of the workshops and events are in English, so don’t miss them out!
👉 Sign up for our newsletter here: eo4landscape.natur.cuni.cz/newsletter-2/
comment in response to
post
I think that the AUC Geograhica journal by @sciencecharles.bsky.social @charlesuni.cuni.cz could fit:
karolinum.cz/en/journal/a...
No fees at all, with a broad geographical scope: from human geography to geoinformatics and remote sensing. With a Scopus and WoS indexing. With an IF as well.
comment in response to
post
Could you add me to the starter pack, please? :)
comment in response to
post
+4 #GEE open-access tools were developed to:
Correct terrain effects github.com/palubad/LC-SLIAC
Automatic forest classification github.com/palubad/Automatic-Forest-Classification-GEE
Track burned area progression github.com/palubad/S1-BAP
Generate multimodal time series github.com/palubad/MMTS-GEE
comment in response to
post
5️⃣ Identification of Optimal Sentinel-1 SAR Polarimetric Parameters for Forest Monitoring in Czechia doi.org/10.14712/23361980.2024.18
6️⃣ Estimating Vegetation Indices and Biophysical Parameters for Central European Temperate Forests with Sentinel-1 SAR Data and ML - Accepted, not online yet
comment in response to
post
3️⃣ Unsupervised Burned Area Mapping in Greece: Investigating the Impact of Precipitation, Pre- and Post-Processing of S-1 Data in GEE doi.org/10.1109/IGARSS52108.2023.10283130
4️⃣ Tracking Burned Area Progression in an Unsupervised Manner Using Sentinel-1 SAR in GEE
doi.org/10.1109/JSTARS.2024.3427382
comment in response to
post
2️⃣ Automatic Forest Cover Classification Using Sentinel-2 Multispectral Satellite Data and Machine Learning Algorithms in Google Earth Engine. www.researchgate.net/publication/...
comment in response to
post
The core of my thesis is built on six research papers published over the course of my doctoral studies:
1️⃣ Land Cover-Specific Local Incidence Angle Correction: A Method for Time-Series Analysis of Forest Ecosystems. doi.org/10.3390/rs13091743
comment in response to
post
Hi Florent, it seems that there will be no online streaming. If it changes, I will update you with the link.
comment in response to
post
📈 The wide variety of tasks was often challenging and required to learn new things and adapt to new tools. But this made the work very enjoyable. It was an amazing experience where I learned a lot!
🤘🏼 What’s next?
Defend my dissertation thesis in February, then dive deeper into EO research!
comment in response to
post
🔥 I concluded my web-related efforts by being part of the core team responsible for managing and testing the implementation of the faculty’s new website. It was successfully launched on September 1, 2024, at natur.cuni.cz/en
comment in response to
post
🎓 I was managing the web presentation of our study programmes, created online handbooks for students and employees, promoted our programmes to candidates at national and international events.
🔬🧬 I also assisted numerous research teams in creating their own professional websites.
comment in response to
post
💡 It was a unique experience because I could contribute to or directly propose and implement solutions for various departments, esteemed professors, vice-deans and other key figures within the faculty.
comment in response to
post
🛠 The MMTS-GEE, a #GoogleEarthEngine tool generates multi-modal time series datasets, including temporally and spatially aligned Sentinel-1 #SAR, Sentinel-2 #multispectral, topographic and #climatic variables to support #timeseries analysis and #machinelearning applications.