📊 Our findings are particularly valuable for operational flood monitoring in data-scarce regions or areas with high environmental variability, where developing robust methods is most challenging.
07.08.2025 08:30 — 👍 0 🔁 0 💬 1 📌 0
🗺️ This unified framework leverages the full diversity of available satellite imagery for more reliable #floodmapping.
07.08.2025 08:30 — 👍 0 🔁 0 💬 1 📌 0
🛰️ We developed a dual-stream multimodal architecture that seamlessly integrates both SAR (Sentinel-1) and optical (Sentinel-2) data, enabling comprehensive evaluation across single and multi-modal scenarios.
07.08.2025 08:30 — 👍 0 🔁 0 💬 1 📌 0
🔍 Even high-performing flood detection models trained on single datasets often fail when applied to new regions or different sensor conditions. However, we demonstrate that multi-dataset training strategies significantly enhance model robustness and generalization capabilities.
07.08.2025 08:30 — 👍 0 🔁 0 💬 1 📌 0
Understanding flood detection models across Sentinel-1 and Sentinel-2 modalities and benchmark datasets
In recent years, research in flood mapping from remote sensing satellite imagery has predominantly focused on deep learning methods. While new flood s…
👉New paper: "Understanding #flood detection models across Sentinel-1 and Sentinel-2 modalities and benchmark datasets"
🌊This study presents a model generalization across different regions & satellite sensors.
📄 tr.ee/Understandin...
💻Code & models: github.com/kipoju/udl4fl
#RemoteSensing
07.08.2025 08:30 — 👍 5 🔁 1 💬 1 📌 0
Radware Bot Manager Captcha
To ensure we keep this website safe, please can you confirm you are a human by ticking the box below.
🤝 This research is a collab with Tristan Williams, Álvaro Moreno, @miguelmahecha.bsky.social , Gustau Camps-Valls, Francesco Martinuzzi, and @unileipzig.bsky.social
👏 Special thanks to @icos-ri.eu for providing the data.
🔎Read the full text 👉 tr.ee/Sub-Seasonal...
04.08.2025 08:01 — 👍 1 🔁 0 💬 0 📌 0
⛈️ Overall, identifying changes in persistence could signal potential ecological destabilisation, providing key insights into how terrestrial ecosystems might cope with intensifying climate extremes.
04.08.2025 08:01 — 👍 0 🔁 0 💬 1 📌 0
⚠️ These stress pulses alter carbon dynamics long after the event, suggesting physiological damage that heightens sensitivity to future weather fluctuations.
04.08.2025 08:01 — 👍 0 🔁 0 💬 1 📌 0
🌿 Large drops in persistence can signal periods of ecosystem stress and demonstrate that drought–heat compound events can diminish resilience and prolong recovery times, with temperate and boreal forests lacking heat or drought adaptations emerging as especially vulnerable.
04.08.2025 08:01 — 👍 0 🔁 0 💬 1 📌 0
📊 Using Detrended Fluctuation Analysis, we quantify persistence and assess changes in carbon flux stability under stress.
By analysing high-frequency carbon flux data across many European sites, we reveal that ecosystem persistence is linked to hydro-meteorological conditions.
04.08.2025 08:01 — 👍 0 🔁 0 💬 1 📌 0
YouTube video by ISP · Image and Signal Processing
Sub-Seasonal Forest Carbon Dynamics Lose Persistence Under Extremes
📢 New paper at @ioppublishing.bsky.social!
"Sub-Seasonal Forest Carbon Dynamics Lose Persistence Under Extremes" ➡️ tr.ee/Sub-Seasonal...
🌳 Drought and heat can destabilize carbon exchange in ecosystems, with lasting impacts on forest resilience and recovery.
#ExtremeWeather #ClimateChange
04.08.2025 08:01 — 👍 1 🔁 0 💬 1 📌 0
🚨 Postdoc in AI + Earth Science
Join ELLIOT (€25M EU project) in València to build next-gen foundation models for climate + Earth data 🌍🤖
🔗 Apply: forms.gle/gvhCQfLB4kko...
🗓 Deadline: Sept 15
#AI #Postdoc #ML #HorizonEurope #OpenScience #ELLIS @esa @esascience
31.07.2025 16:10 — 👍 3 🔁 3 💬 0 📌 0
Read it here for free
rdcu.be/exjCO
and Act... Mindfully!
22.07.2025 18:26 — 👍 2 🔁 1 💬 0 📌 0
🚀 Here's a short recap of our participation in #LPS25, where our team shared and presented a wide variety of research focusing on #AI and #EarthObservation.
🌍📡 Looking forward to the next symposium!
📹 youtu.be/D68Hjz-93ts
18.07.2025 07:01 — 👍 1 🔁 1 💬 0 📌 0
📊 Tested on both Landsat 8 and 9 imagery, CloudRuler outperformed seven state-of-the-art methods (including GAN, CNN, and transformer-based models), providing visually and quantitatively superior cloud-free imagery for downstream applications.
16.07.2025 13:16 — 👍 1 🔁 0 💬 0 📌 0
🧠 While deep learning methods have surpassed traditional techniques, many still overlook essential aspects like spatial position or thermal band physics limitations CloudRuler is designed to overcome.
16.07.2025 13:16 — 👍 1 🔁 0 💬 1 📌 0
CloudRuler: Rule-based transformer for cloud removal in Landsat images
Clouds are a key factor influencing transmission of the radiance signal in optical remote sensing images. For mapping or monitoring the Earth's surfac…
🗞️ New paper: "CloudRuler: Rule-based transformer for cloud removal in Landsat images".
☁️ Clouds can obstruct optical remote sensing, and CloudRuler tackles this by enhancing thin cloud removal using domain-specific remote sensing insights.
🔗 Read the full paper here: tr.ee/CloudRuler
16.07.2025 13:16 — 👍 0 🔁 0 💬 1 📌 0
YouTube video by ISP · Image and Signal Processing
ISP Recap 2025 (I)
✨ What a first half of the year it’s been!
👥 During this first semester, our team has been busy sharing knowledge, learning, & making connections through a variety of #AI, #Earthobservation and #remotesensing activities.
🔁 We'll keep going for the second half of 2025!
11.07.2025 13:11 — 👍 0 🔁 0 💬 0 📌 0
A serene mountain lake (Science) surrounded by snow-covered hills and trees (AI), reflecting the snowy landscape and overcast sky (reflections of Science with AI). The lake is clear and calm, with rocky and snowy terrain in the foreground and mist-shrouded mountains rising in the background. Near Cusco, Perú.
Do we need a new #philosophy of #science for the #AI era?
What if Popper, Feyerabend & von Glasersfeld sat with us to rethink falsifiability, pluralism & knowledge in the age of machines?
Maybe it's time for a slower, humbler, more mindful science!
👉https://shorturl.at/xITyL
31.05.2025 17:37 — 👍 2 🔁 1 💬 0 📌 0
📻 Our colleague @mariapiles.bsky.social recently visited Oscilador Armónico Podcast to talk about her experience of collecting data about our planet from space, and explain how this helps us to understand what is happening on Earth.
🔗 www.ivoox.com/podcast-osci...
🔗 open.spotify.com/episode/0dpc...
03.07.2025 13:54 — 👍 2 🔁 0 💬 1 📌 0
🏆 We're thrilled to announce that Jasdeep Singh (Khalifa University) has won the AMLEC with a final score of 1.525!
ℹ️ As part of his award, his participation in #ECMLPKDD2025 will be covered ➡️ https://ecmlpkdd.org/2025
⛅ More to come on this challenge!
#DiscoveryChallenge2025
01.07.2025 09:31 — 👍 0 🔁 0 💬 0 📌 0
🌡️ Andrés Terrer with his poster “CIMR Level 2 Land Surface Temperature Retrieval Using Machine Learning Approaches” at #LPS25.
📡 This work applies ML models to improve land surface temperature retrieval from Microwave data across diverse conditions.
🔗 lps25.esa.int/programme/pr...
30.06.2025 12:20 — 👍 0 🔁 0 💬 0 📌 0
🛰️ Last week @mariapiles.bsky.social shared “CIMR multi-frequency products advancing from L-band heritage” at #LPS25.
🌐 A multi-band microwave radiometry mission continuing the L-band legacy (SMAP/SMOS) with key products: soil moisture, sea ice thickness & more.
🔗 lps25.esa.int/programme/pr...
30.06.2025 10:51 — 👍 2 🔁 0 💬 1 📌 0
🎥 Óscar Pellicer sharing his work "Video compression for spatio-temporal Earth System Data" at #LPS25.
🗂️ Xarrayvideo is a python library for efficiently compressing spatiotemporal multichannel Earth system data using standard video codecs.
🔗 lps25.esa.int/programme/pr...
27.06.2025 14:14 — 👍 4 🔁 0 💬 1 📌 0
🛰️ Moritz Link presenting “CIMR L2 Soil Moisture Algorithm Development and Testing” at #LPS25.
🌱 Developing L2 products from native & sharpened L-band data using tau-omega inversion, with enhanced resolution & uncertainty quantification.
🔗 lps25.esa.int/programme/pr...
27.06.2025 12:41 — 👍 2 🔁 0 💬 1 📌 0
The Cognitive Computational Neuroscience Conference is an annual forum for discussion among researchers in cognitive science, neuroscience, and AI, dedicated to understanding the computations that underlie complex behavior.
https://2025.ccneuro.org
European research infrastructure providing open & standardised greenhouse gas data for climate action
IOP Publishing is a society-owned scientific publisher, providing impact, recognition and value for the scientific community. IOP Publishing’s portfolio includes more than 90 journals.
CENTAUR is a Horizon Europe project contributing to the evolution of CopernicusEMS & CopernicusSESA by developing new products on urban #floods 🌊 & #FoodSecurity🌱
Official profile of Sentinel Online, part of Copernicus, the European
Union’s Earth Observation programme, and developed in partnership with @esa.int
Podcast de física que se emite cada semana desde el Instituto de Física Corpuscular de Valencia https://go.ivoox.com/sq/1799533
Remote sensing of our living environment from space-borne to UAS/UAV, from the tropics to the Arctic -- at @uni-wuerzburg.de, Germany -- https://www.remote-sensing.org http://www.earth-observation.org - managed by Dr Martin Wegmann
Working for a secure #FutureofFood for all.
Follow 👉 @faodg.fao.org | @faoarabic.bsky.social | @faoenespanol.bsky.social | @faoenfrancais.bsky.social
We are Wageningen University & Research
Provides education and generates knowledge with a focus on healthy food and living environment. To explore the potential of nature to improve the quality of life.
https://www.wur.nl/en.htm
Science Communication - Journal Manager (CSIRO Publishing) - PhD in Plant Biochemsitry (University of Melbourne) - Sport (AFL, Cricket, Rugby, Football)
Followed by 2.5k on twitter (X): https://x.com/MLEarthSciences
We tweet/retweet papers related to machine learning/data science/deep learning for Earth and Environmental Sciences. Just email your paper details to mlearthsciences@gmail.com
#research #ML
She/Her
Find me at: https://linktr.ee/thedumbbanshee
European Geosciences Union is the leading organisation supporting Earth, planetary & space science researchers in Europe. #EGU25 27 April - 2 May 2025. Online Mon-Fri 10-5 CET.
Official Twitter account of the European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases.
https://ecmlpkdd.org/
Discover our #openaccess journals devoted to the application and development of #MachineLearning and #ArtificialIntelligence for the sciences, health, earth and engineering.
ML Series: https://bit.ly/3FUYyNe
AI for Science: https://bit.ly/3QZlflu
Understanding and supporting people in their spatial interactions through computational #spatial #data #science #giscience #melbourne 🛶🚵♂️🥾🏊♂️🐕
@unimelb, own views. support 🇺🇦 www.tomko.org
Postdoctoral Researcher at Washington State University. Ph.D., IIT Bombay.
Interested in Land-Atmosphere Interactions, Water, and Carbon Cycle.
Associate Professor & Research Scientist at Image Processing Lab (
@isp-uv-es.bsky.social, #Valencia) / Earth observation, remote sensing 🌍/ #nature #water #ClimateAction
A popular science magazine geared to disseminate advances in science to scientifically minded general readers
Professor, Marine Science at the University of Hull.
