My research focuses on statistical learning for modeling and understanding the Earth system.

My interests are related to machine learning and signal and image processing. The application domains are remote sensing data analysis and hyperspectral images with special focus on cloud screening.

I’m interested in understanding human vision from information theoretic principles. This statistical view has implications in experimental and computational neuroscience. See the ex-cathedra statement

The topic of my thesis was Distance Metric Learning. Currently, I am working on kernel methods, dependence estimation and Machine Learning in general. I am interested on the applications of Machine Learning techniques to solve the Remote Sensing challenges.

I am a data scientist and project manager. As a remote sensing specialist I have experience in several application areas like ocean colour and thermal algorithm development and validation.

My current research involves signal processing to develop new interactive man-machine interfaces and haptics, and real-time multispectral sensors and actuators. I’m also with Analog Devices Inc.

At present I’m focused on kernel methods, support vector machines, semi-supervised and active learning. The main application field is on remote sensing data. I have recently worked with one-class classifiers applied to hyperspectral images.

I’m working on image fusion, developing downscaling and pansharpening methods. The goal is to tackle multitemporal image fusion and change detection problems with improved resolution.

My research interests include microwave remote sensing, estimation of soil moisture and vegetation biogeophysical parameters and development of multisensor techniques for enhanced retrievals with focus on agriculture, forestry, wildfire prediction, extreme detection, and climate studies.

I’m working in image statistics and vision science. I have developed several methods for density estimation, measure independence, manifold learning and visual quality assessment.

My research focuses on remote sensing in vegetation. I develop physical and statistical models and implement methodologies for studying vegetation cover through satellite imagery at various spatial and temporal scales.

My background is in statistics, machine learning and causal inference. My research interests include kernel methods, graphical models, deep learning and causal discovery with a focus on Earth system science applications.

I research probabilistic graphical models: Bayesian networks, Gaussian graphical models, and staged event trees. Recently, I focus on structural recovery from spatio-temporal data and causal discovery in Earth sciences applications.

Currently, I am working on learning parameters of differential equations, HPC for linear solvers, and causality. I am interested in machine learning, especially statistical learning and deep neural networks.

I applied machine learning to medical image analysis for prostate cancer detection during my PhD. Now focusing on deep learning for satellite imaging and developing models for forecasting tasks.

My current research focuses on cloud screening in multispectral imagery using machine learning techniques. Previously I was also involved in the algorithm improvement for the retrieval of soil moisture and vegetation parameters from microwave observations.

I am broadly interested in developing machine learning methods for complex dynamical systems, including but not limited to stochastic generative models, dimensionality reduction, causality, Bayesian statistical methods, Earth climate applications. At ISP, I will particularly focus on implementation and testing of new ML-based parameterizations for Earth system models.

I’m working on novel deep learning architectures for cloud detection from remote sensing images, with special focus on domain adaptation and transfer learning strategies.

My research at the intersection of AI and geoscience focuses on creating reliable tools. I specialize in applying and evaluating Explainable AI (XAI), with a strong emphasis on its faithfulness, alongside causal inference and spatio-temporal deep learning, to deepen our insight into Earth systems.

My work involves atmospheric radiative transfer models, statistical regression emulation, and image processing algorithms development and optimization. Focusing on remote sensing data analysis and hyperspectral images for atmospheric correction.

I hold a PhD in Theoretical Particle Physics. My current research focuses on developing multimodal foundation models for Earth observation within the ELLIOT project,. Previously, I applied deep learning to multivariate time series forecasting, downscaling of air quality data and reconstruction of climate variables.

I have a PhD in Geomatics Engineering. My research focused on remote sensing for urban and georisk applications using spatial and statistical methods. At ISP, my work will focus on explainable AI to better understand extreme weather events.

I hold a PhD in Mathematics and am interested in applying my mathematical expertise towards utilizing manifold structures and causal relationships to develop dimensionality reduction algorithms for multimodal spatio-temporal datasets.

I’m working on the inclusion of equivariant transformations, inspired by the human visual system, in the latest deep learning algorithms, with a focus on computer vision.

“I hold a PhD in Computer Science with a background in Computer Vision and Remote Sensing. My current research at the ISP Lab focuses on developing multimodal foundation models for Earth observation. My research interests include self-supervised learning, vision–language models, representation learning, and interpretable AI, with the goal of advancing environmental monitoring, biodiversity assessment, and sustainable agriculture using satellite imagery.”

I hold a PhD in Computer Science and a background in Physics. My research focuses on the development of Graph Neural Networks to address Earth System science problems, blending principles of physics-aware ML, causality, and trustworthy AI.

I hold a PhD in Statistical and Biological Physics. My research has focused on time-series analysis, feature selection, and causal inference. At ISP, I apply causal discovery and graph-theoretic methods to compare climate models and improve the reliability of climate projections.

I’m a physicist and data scientist working with ISP researchers on the upcoming CIMR mission. I’m developing ML models and other thechniques to retrieve physical magnitudes from microwave measurements.

My background is in Theoretical Physics. I am currently a PhD student working on machine learning for remote sensing image processing, focusing on the development of new methods for methane detection from satellite imagery.

I have a background in abstract mathematics. I’m conducting research within the ELLIOT project, which focuses on developing multimodal foundation models for Earth modelling.

I am working on the development of machine learning techniques for super-resolution in the ESA OpenSR project. My background is in Earth Observation.

I am doing my PhD on causal inference and complex system characterization of climate extremes.

I have a background in applied physics and complex systems. My current research within the EarthGenerator project focuses on developing a next-generation foundation model for the Earth system, unifying the atmosphere, ocean, and land surface into a single physically coherent model.

I have a background in Applied mathematics and Statistics and, actually, my research focuses on Causal Representation Learning and applications for Earth Sciences. I’m particularly interested in methods involving kernels and graphical models.

My background in environmental sciences includes remote sensing for vegetation studies, focusing on monitoring and estimating crop yield, water needs, forest biomass, change detection, and soil moisture.

I’m currently working on the development and testing of the CauseMe website, a platform to benchmark causal discovery methods. My background is in physics and data science.

My research combines bio-optical radiative transfer modelling with machine learning, aiming to retrieve biogeochemical constituents in water through hyperspectral sensors.

I’m currently working on introducing human-like behaviours in deep learning models and measuring perceptual distances. I’m interested as well in generative models and reinforcement learning.

My research interest is to study the impact of climate change on human mobility through machine-learning methods. At ISP I am working on the H2020 DeepCube Climate Induced Migrations use case.

I am working on super-resolution and cloud-segmentation of satellite imagery, automating advanced geospatial analysis pipelines with scalable machine-learning algorithms worldwide.

My general research interest lies in Bayesian inference, deep learning and how to incorporate prior knowledge into machine learning models. Currently I am working on hybrid modeling in physics and how to overcome equifinality issues.

I’m working on anomaly and extreme event detection from remote sensing images with attention networks and video prediction techniques.

I’m working on hybrid machine learning for drought and heatwave detection.

My research focuses on characterizing microwave sensor data with focus on soil moisture and vegetation optical depth. I’m involved in several ESA projects around the upcoming CIMR mission.

Nuria Alabau-Bosque has a degree in Computer Science from the University of Valencia. She then studied a MSC in Computer Engineering and Mathematics at the Rovira i Virgili University. She is currently doing her PhD at the Image Processing Laboratory of the University of Valencia. Her research interests include computer vision, image processing and machine learning. Her current work focuses on the inclusion of invariance in image quality models and classification models.

I am pursuing my PhD thesis in the iMIRACLI project on hybrid and interpretable machine learning for cloud-aerosol interaction problems.

I have a background in GIS and remote sensing with applications in the humanitarian and development sectors. I am currently pursuing a PhD focused on developing risk assessment maps to better understand the impacts of climate extremes and support evidence-based decision-making.

My research focuses on collecting and analyzing human data to support the development, tuning, and evaluation of deep learning models for vision science.

I am working on the development of machine learning techniques for super-resolution in the ESA OpenSR project. My background is in Earth Observation.

I have a background in environmental sciences and remote sensing. I am pursuing a PhD within the XAIDA project where I will be using AI to attribute extreme climate impacts on European ecosystems.

My mission at ISP is to control the economic management of projects, as well as perform administrative tasks.

During my PhD studies at Politecnico di Torino, Italy, my research focused on preventive coastal flood assessment and mapping. While visiting ISP, I worked on coastal flood susceptibility by integrating remote sensing, GIS, and ML.

For my PhD studies at BOKU University, Vienna, I am helping to assess conservation farming in Austria using data from remote sensing, soil samples and management surveys with interpretable machine learning methods. During my visit at ISP I focused on deepening my experience with IML techniques.

While working as a Research Associate at DLR with a Ph.D. in Atmospheric Science, I combined causal discovery and deep learning methods to address systematic errors in climate models and improve projections and understanding. During my time at ISP, I contributed to advancing these methodologies.

During my PhD studies at ScaDS.AI and RSC4Earth (Leipzig University), I explored nonlinear dynamics with machine learning, focusing on applications to Earth sciences. My visit to ISP allowed me to extend this research further in collaboration with their team.

As a researcher at the Orion Lab, National Observatory of Athens, and the University of Valencia, I worked on Deep Learning for the Earth System sciences. During my time at ISP, I aimed to improve fire prediction systems through innovative ML techniques.

During my PhD studies at Leipzig University, I focused on understanding aerosol-cloud interactions directly from satellite observations using ML. My visit to ISP enriched my research by addressing the uncertainties inherent in traditional retrieval methods.

As a PhD student at East China University of Science and Technology, I visited the Image Signal Processing (ISP) group, where my research focused on machine learning, causal inference, and their applications in climate analysis.

I am a PhD student specializing in crop classification and diurnal photosynthesis monitoring. My research combines Sentinel-2 and GEDI data for crop type mapping, and utilizes FY-4A geostationary satellite observations to investigate midday photosynthetic depression and drought responses in winter wheat and maize.

In the final year of my PhD at Oxford, I developed interpretable statistical ML methodologies for climate science challenges. During my time at ISP, I advanced my work on climate model emulation and statistical downscaling using kernel methods and Gaussian processes.

When I was at ISP, in my MSc Thesis, I developed cortical image representations that are simultaneously robust to neural noise and energy efficient.

When I was at ISP, I developed machine learning algorithms for crop yield estimation using multi-scale remote sensing and climate data, focusing on anomaly detection in crop seasons and improving model interpretability.

When I was at ISP, I worked on convolutional versions of linear and nonlinear models of visual neuroscience and used those in visual prosthesis and image quality metrics.

when I was at ISP, I researched interpretable and causal feature representations, focusing on causal inference in human-biosphere systems and developing modules for interpretability and explainability in machine learning models for enhanced understanding.

When I was a PhD student at Harbin Institute of Technology, I visited ISP, where my research focused on large foundation models and the processing of hyper/multi-spectral imagery.

When I was at ISP, I worked on the development of statistical, physical, and hybrid methods to study the regional effects of climate change in the oceans (MALOC project). I had a background in Earth observation data and machine learning methods.

When I was at ISP, the main goal of my research was to develop automatic algorithms for the detection of clouds from remote sensing images. I mainly focused on the inclusion of prior knowledge and (spatial, temporal, angular) constraints in machine learning classifiers.

when I was at ISP, I worked on machine learning methods for remote sensing and earth observation data. My focus was on kernel methods and the incorporation of physical knowledge into statistical methods.

In my postdoc at the ISP group, I addressed a number of machine learning problems related to hyperspectral image processing, including graph adaptation, active learning, and advanced kernel methods.

When I was at ISP, my research work was about machine learning and its application to remote sensing, specifically in feature extraction and climate dynamics analysis. I was especially interested in soil moisture data analysis and climate teleconnections.

When I was at ISP, my PhD work included kernel-based nonlinear generalization of classical (linear) feature extraction techniques to improve classification results in remote sensing.

During my PhD, I worked on graph deep learning for air quality modelling. At ISP, my research will focus on physics-guided and graph deep learning, with a special interest in explainability and greenAI.

As ISP Coordination & Project Manager, I specialized in Remote Sensing & GIS applications for forestry, agriculture, land cover, and geospatial data quality. I collaborated with outstanding research groups and was ready for new challenges.

During my IPL visit, I focused on processing optical images using kernel and variational methods, large-scale anomaly detection methods, and digital terrain model extraction. I enjoyed collaborating with IPL researchers.

My work at the ISP group included the analysis of multi-temporal remote sensing image changes and the definition of advanced one-class classifiers.

When I was at ISP, in my MSc work, I applied accurate contrast perception models to improve Support Vector Regression in subjective domains for image coding.

When I was at ISP, my research focused on methane detection from multispectral and hyperspectral imagery. Previously, I researched machine learning for tasks such as super-resolution, domain adaptation, change detection, cloud detection, and flood segmentation.

At ISP, I built virtual worlds of controlled spatial arrangement to study the effects of occlusion, perspective, and viewpoint in 2D shape statistics.

When I was at ISP, my PhD work (best-thesis award in Physics and Maths 2003) focused on perceptual and statistical image representations for image coding and texture classification.

When I was at ISP, my interests included machine learning and signal processing, particularly deep neural networks and transfer learning, focusing on applying physical constraints to ML models for better generalization and extrapolation capabilities.

My research focuses on narrative within the digital communication framework, with a specific focus on three primary dimensions: mediations and formats, empowerment and creativity.

My research at ISP involved feature learning and dependence estimation using kernel methods and multivariate Gaussianization with applications in Earth observation.

I am working on the development of machine learning techniques to assess precursor conditions for extreme hurricane development (MALOPH project). My background is in remote sensing techniques, analysis and applications.

My background is in Theoretical Physics. These days I am working in Machine Learning and Symbolic Regression, mainly to model plant communities and ecosystem fluxes.

My research interests focus on kernel methods and the incorporation of physical knowledge in statistical methods to understand and improve Earth system modelling. My current research involves detection and attribution of climate change processes.

My field is institutional communication and I manage internal and external communications for research teams, ensuring an effective information flow. I’m interested in audiovisual representation models and their social impact.

When I was at ISP, my PhD thesis focused on developing a new family of anomaly change detection algorithms for remote sensing image processing and geoscience time series analysis.

when I was at ISP, I developed computational models of visual function based on functional Magnetic Resonance Imaging, psychophysics, and image statistics.

When I was at ISP, during my MSc work, I contributed to the development of nonlinear local-to-global Independent Component Analysis.

When I was at ISP, in my PhD, I applied advanced contrast perception models as regularization functionals to solve inverse problems such as image restoration and motion estimation and studied their connection to image statistics.

During my stay at ISP, I addressed the problem of decoding the visual signals from simulated and real neural responses.

I’ve worked with machine learning methods for crop yield estimation using climate and multi-sensor remote sensing data. My current research is now focused on the use of deep learning to upscale high resolution carbon fluxes.

My work at the ISP group included the development of target detection algorithms for remote sensing data analysis.

While I was at ISP, my research interests lay in Monte Carlo methods for Bayesian inference, focusing on the random number generation problem and computational methods for stochastic quadrature, such as rejection sampling and MCMC algorithms.

I worked with the UVERS group, conducting my PhD thesis on biophysical parameter retrieval for crop monitoring, particularly in the FP7 ERMES project, and collaborated with ISP people on GP retrieval algorithms.

While at ISP, I conducted fMRI recordings of the visual brain using synthetic and natural images. I also directed the Optometry Clinic of the Universitat de Valencia, which had a range of experimental tools for vision research.

During my stay at ISP, I used Kernel Ridge Regression for image denoising, assuming smoothness in the spatial domain.

At ISP, I worked on computational visual neuroscience, modeling the processes that take place in the brain from retinal images to extracting information from them.

My work at the ISP group included the development of semi-supervised one-class classifiers for remote sensing data classification.

While I was at ISP, I used explainable AI to understand deep neural networks, bridging physics-based and data-driven models. I also worked on integrating prior knowledge into learning through optimized penalized losses or network modifications.

While I was at ISP, my research focused on the design of deep learning models and machine attention mechanisms to be deployed in anomaly and extreme event detection in the Earth sciences.

While I was at ISP, I worked on computational neuroscience via combined fMRI and image processing techniques to better understand the mechanisms of the human vision system, which efficiently processes and extracts information from the natural world.

When I was at ISP, my background and expertise were in microwave remote sensing for soil moisture estimation and agricultural applications, including estimating crop health and soil properties.

My work at the ISP group included the development of multiinformation and divergence measures using Gaussianization transforms.

When I was at ISP, I worked on causal discovery from observational data, particularly studying climate-induced human migrations.

During my PhD years (best-MSc thesis award in Computer Science 2013) and while working at ISP, I analyzed the complexity of spatio-spectral signals for illumination-invariant Bayesian reflectance estimation and hyperspectral image coding.

When I was at ISP, I researched statistical methods for detecting and attributing climate change, focusing on extreme weather event attribution using observation analysis and climate model experiments to better understand their impacts.

I develop causal and explainable machine learning methods using Earth observations and environmental data to estimate the impact of agricultural decisions for sustainable agriculture and food security.

When I was at ISP, in my MSc thesis, I worked with a Kernel generalization of the SSIM image quality index, well-suited for application to hyperspectral images.

When I was at ISP, in my MSc thesis, I applied nonlinear models of chromatic contrast perception in wavelet domains to improve png2000.