Concept

Ontology-based data integration

Related publications (27)

ESFM - A foundation model framework for heterogeneous data integration

With increased availability of high quality diverse weather data, including reanalysis, satellite, surface stations, climate model data, the amount of data-driven foundation models (FM) in the environmental field has increased significantly over the past years with forecasting performances matching and sometimes exceeding physics-based numerical model predictions. However, most FMs are trained with one dataset or a few datasets with similar sampling and/or resolution properties. While the proposed models ac

2026

ESFM-MoE: Climate-semantic routing for Earth System Foundation Model (ESFM)

Mathieu Salzmann

Weather foundation models are increasingly expected to operate under heterogeneous and imperfect observation settings while remaining computationally scalable. Building on the Earth System Foundation Model (ESFM) setting for heterogeneous data integration, we explore how Mixture-of-Experts (MoE) can support robust and efficient learning in multi-modal weather foundation models.We introduce ESFM-MoE, an exploratory direction that combines conditional computation with climate-semantic routing, a routing princ

2026

Parallel framework for intelligent prediction of multi-site fugitive dust: Combined with DustLSTM-Trans and FedProx-Dyn

Due to the wide distribution of construction sites and data heterogeneity, single site models struggle with cross-site generalization and privacy compliance. A collaborative prediction model is needed to integrate information from multiple sites and enhance governance. Traditional time series models fail to capture short-term disturbances and long-term dependencies, and construction site data often includes abrupt changes and multi-scale dynamics. Non-Independent and Identically Distributed (Non-IID) data a

2026

A trait-informed deep learning model to map species distributions and assemblages of Swiss flora

Biodiversity models extend predictions of species assemblages beyond direct observations and play a key role in applications such as conservation planning. Yet, predicting the spatial distribution of species assemblages remains a persistent challenge in biogeography, as both abiotic constraints and biotic interactions shape community composition through complex interactions. Multi-species distribution models are promising because they can integrate information about species co-occurrence, but they remain la

2026

Hybrid integrated photonics for coherent microwave-optical transduction

Superconducting circuits are important technological tools that have found various applications, notably hypothetical future superconducting quantum computers. Scaling such systems further is, however, proving challenging because of thermal heat load and space constraints in cryostats. One way of improving the scalability of such systems would be to resort to optical fibers for controlling the circuits in cryostats, as well as mediating long-distance interaction between them while preserving quantum cohere

EPFL2026

Temporal and Relational Learning in Complex Systems for Condition Monitoring and Degradation Inference

Modern engineered systems are increasingly complex, comprising interconnected components within hierarchical structures that interact dynamically under operational and environmental influences. As these systems degrade, performance and reliability decline, with failures potentially causing severe economic and safety impacts. Robust algorithms are therefore essential for monitoring wear and performance in such environments. Machine learning has driven advances in data-driven for Prognostics and Health Manage

EPFL2025

Electro-optic Modulation in Amorphous Silicon Nitride Photonic Integrated Platforms [invited]

Electro-optic modulation is a key functionality for compact photonic integrated circuits. Linear electro-optic modulation has been lacking in amorphous photonic platforms like silicon nitride due to the absence of intrinsic second-order nonlinearities. Electrical poling by thermal or optical assistance as well as heterogeneous integration of hybrid devices is under development to unlock electro-optic capabilities on silicon nitride platforms. This paper provides an overview of methodologies reported in the

Optica Publishing Group2025

Heterogeneous van der Waals integration of single-crystalline photonic nanomembranes

Albeit the speed and energy advantages offered by silicon (Si) and silicon nitride (SiN) photonics, a single material platform, with varying intrinsic limitations, can hardly meet the ever-diversifying requirements posed for photonic integrated circuits (PICs). The heterogeneous integration of functional materials to established photonic platforms has thus gained tremendous momentum, underpinning various high-performance optoelectronic applications. However, stringent lattice-matching constraints severely h

Research Square Platform LLC2025

Homogeneous Free-Standing Nanostructures from Bulk Diamond over Millimeter Scales for Quantum Technologies

Quantum devices based on optically addressable spin qubits in diamond are promising platforms for quantum technologies such as quantum sensing and communication. Nano- and microstructuring of the diamond crystal is essential to enhance device performance, yet fabrication remains challenging and often involves trade-offs in surface quality, aspect ratio, device size, and uniformity. We tackle this hurdle with an approach producing millimeter-scale, thin (down to 70 nm), and highly parallel (< 0.35 nm/μm) mem

American Chemical Society (ACS)2025

In-depth assessment of potential new data integration into the MIP

In the scope of the Human Brain Project (SGA2), this document summarizes from the technical perspective the main challenges faced by the current Medical Informatics Platform for the integration of three new types of data: complex neuroimaging, omics, and data from wearable devices. Details are discussed up to the implementation level, considering risks, costs, and possible ethical and data privacy issues. The specific recommendations for the future development of the MIP are collected in the accompanying do

2020

Recommendations for the MIP Technical Development During SGA3

In the scope of the Human Brain Project (SGA2), this document collects the specific technical recommendations for the future development of the MIP derived from the potential integration of new types of data into the platform. This integration is discussed in detail in the accompanying document “In-depth assessment of potential new data integration into the MIP”, with component ID C2975. Here, we begin with a high-level description of the MIP architecture and of its different software components, and then w

2020

Macroecology in the age of Big Data - Where to go from here?

Recent years have seen an exponential increase in the amount of data available in all sciences and application domains. Macroecology is part of this "Big Data" trend, with a strong rise in the volume of data that we are using for our research. Here, we sum ...

2020

pyTFA and matTFA: a Python package and a Matlab toolbox for Thermodynamics-based Flux Analysis

Vassily Hatzimanikatis, Meriç Ataman, Georgios Fengos, Keng Cher Soh, Pierre Guy Rémy Salvy

Summary: pyTFA and matTFA are the first published implementations of the original TFA paper. Specifically, they include explicit formulation of Gibbs energies and metabolite concentrations, which enables straightforward integration of metabolite concentrat ...

Oxford University Press2018

Highly efficient coupling of crystalline microresonators to integrated photonic waveguides

Tobias Kippenberg, Michail Zervas, Junqiu Liu, Miles Henry Anderson, John David Jost

Crystalline optical whispering gallery mode resonators made from alkaline earth fluorides can achieve exceptionally large optical finesse, and are used in a variety of applications, from frequency stabilization and narrow linewidth lasers, to low-noise mic ...

2018

Answer validation for generic crowdsourcing tasks with minimal efforts

Karl Aberer

Crowdsourcing has been established as an essential means to scale human computation in diverse Web applications, reaching from data integration to information retrieval. Yet, crowd workers have wide-ranging levels of expertise. Large worker populations are ...

2017

Data infrastructure for medical research

While we are witnessing rapid growth in data across the sciences and in many applications, this growth is particularly remarkable in the medical domain, be it because of higher resolution instruments and diagnostic tools (e.g. MRI), new sources of structured data like activity trackers, the wide-spread use of electronic health records and many others. The sheer volume of the data is not, however, the only challenge to be faced when using medical data for research. Other crucial challenges include data heter

Emerald2017

Heterogeneous integration of lithium niobate and silicon nitride waveguides for wafer-scale photonic integrated circuits on silicon

Tobias Kippenberg, Martin Hubert Peter Pfeiffer, Michail Zervas

An ideal photonic integrated circuit for nonlinear photonic applications requires high optical nonlinearities and low loss. This work demonstrates a heterogeneous platform by bonding lithium niobate (LN) thin films onto a silicon nitride (Si3N4) waveguide ...

Optical Society of America2017

A Survey of Privacy on Data Integration

This survey is an integrated view of other surveys on privacy preserving for data integration. First, we review the database context and challenges and research questions. Second, we formulate the privacy problems for schema matching and data matching. Next, we introduce the elements of privacy models. Then, we summarize the existing privacy techniques and the analysis (proofs) of privacy guarantees. Finally, we describe the privacy frameworks and their applications.

2015

Data integration, GIS and multi-criteria decision making for the monitoring of livestock genomic resources

In 2007, FAO initiated the Global plan of action for Farm Animal Genetic Resources (FAnGR) to reduce further loss of genetic diversity in farm animals. One of the key issues mentioned is to identify endangered breeds to support conservation prioritization programs. In this context, the Swiss Federal Office for Agriculture attributed a mandate to explore the feasibility of the implementation of a monitoring concept. The report mentioned the relevance of including the geographic location of the populations mo

2014

Towards Reliable Stochastic Data-Driven Models Applied to the Energy Saving in Buildings

Nicolas Morel

We aim at the elaboration of Information Systems able to optimize energy consumption in buildings while preserving human comfort. Our focus is in the use of state-based stochastic modeling applied to temporal signals acquired from heterogeneous sources such as distributed sensors, weather web services, calendar information and user triggered events. Our general scientic objectives are: (1) global instead of local optimization of building automation sub-systems (heating, ventilation, cooling, solar shadings,

EPFL Solar Energy and Building Physics Laboratory (LESO-PB)2013

Graph Chat

Chat with Graph Search

Ask any question about EPFL courses, lectures, exercises, research, news, etc. or try the example questions below.

DISCLAIMER: The Graph Chatbot is not programmed to provide explicit or categorical answers to your questions. Rather, it transforms your questions into API requests that are distributed across the various IT services officially administered by EPFL. Its purpose is solely to collect and recommend relevant references to content that you can explore to help you answer your questions.

Related publications (27)

Heterogeneous integration of lithium niobate and silicon nitride waveguides for wafer-scale photonic integrated circuits on silicon

Tobias Kippenberg, Martin Hubert Peter Pfeiffer, Michail Zervas

Optical Society of America2017