Granger causality (GC) is often considered not an actual form of causali...
Wildfires are increasingly exacerbated as a result of climate change,
ne...
We introduce Mesogeos, a large-scale multi-purpose dataset for wildfire
...
Physics is a field of science that has traditionally used the scientific...
Earth observation (EO) is a prime instrument for monitoring land and oce...
Cirrus clouds are key modulators of Earth's climate. Their dependencies ...
This paper presents the kernelized Taylor diagram, a graphical framework...
Anomaly detection is a field of intense research. Identifying low probab...
Earth observation from satellites offers the possibility to monitor our
...
The synergistic combination of deep learning models and Earth observatio...
Learning the manifold structure of remote sensing images is of paramount...
Wildfire forecasting is of paramount importance for disaster risk reduct...
In many inference problems, the evaluation of complex and costly models ...
The modelling of Earth observation data is a challenging problem, typica...
We introduce a method for manifold alignment of different modalities (or...
In the last years we have witnessed the fields of geosciences and remote...
The coloured dissolved organic matter (CDOM) concentration is the standa...
Gaussian Processes (GPs) has experienced tremendous success in geoscienc...
This paper introduces a modular processing chain to derive global
high-r...
In this work we evaluate multi-output (MO) Gaussian Process (GP) models ...
Developing accurate models of crop stress, phenology and productivity is...
Convolutional neural networks (CNN) have proven to be state of the art
m...
Gaussian Processes (GPs) are a class of kernel methods that have shown t...
This paper introduces a novel statistical regression framework that allo...
Anomalous change detection (ACD) is an important problem in remote sensi...
In this paper we present a combined strategy for the retrieval of atmosp...
Water quality parameters are derived applying several machine learning
r...
Establishing causal relations between random variables from observationa...
Current anomaly detection algorithms are typically challenged by either
...
Establishing causal relations between random variables from observationa...
This paper introduces deep Gaussian processes (DGPs) for geophysical
par...
Hyperspectral acquisitions have proven to be the most informative Earth
...
Dealing with land cover classification of the new image sources has also...
Earth observation from satellite sensory data poses challenging problems...
Leaf area index (LAI) is a key biophysical parameter used to determine
f...
Atmospheric correction of Earth Observation data is one of the most crit...
Computationally expensive Radiative Transfer Models (RTMs) are widely us...
With current and upcoming imaging spectrometers, automated band analysis...
Kernel-based machine learning regression algorithms (MLRAs) are potentia...
Remote sensing image classification exploiting multiple sensors is a ver...
Global warming is leading to unprecedented changes in our planet, with g...
The availability of satellite optical information is often hampered by t...
Density destructors are differentiable and invertible transforms that ma...
In the current context of climate change, extreme heatwaves, droughts, a...
Most problems in Earth sciences aim to do inferences about the system, w...
Information theory is an excellent framework for analyzing Earth system ...
Information theory is an outstanding framework to measure uncertainty,
d...
Kernel methods are powerful machine learning techniques which implement
...
Earth observation (EO) by airborne and satellite remote sensing and in-s...
Gaussian processes (GPs) are a class of Kernel methods that have shown t...