相关论文: Big Plastic Masses Detection using Sentinel 2 Imag…
Microlensing is the only method that can detect and measure mass of wide orbit, low mass, solar system analog exoplanets. Mass measurements of such planets would yield massive science on planet formation, exoplanet demographics, free…
Microlensing is the most promising method to study the statistical frequency of extra-solar planets orbiting typical (random) stars in the Milky Way, even those several kiloparsecs from Earth. The lensing zone corresponds to orbital…
Rotational mapping and glint are two proposed methods to directly detect liquid water on the surface of habitable exoplanets. However, false positives for both methods may prevent the unambiguous detection of exoplanet oceans. We use…
Machine learning is being widely applied to analyze satellite data with problems such as classification and feature detection. Unlike traditional image processing algorithms, geospatial applications need to convert the detected objects from…
The ANTARES Collaboration has completed in 2008 the deployment of what is currently the largest high energy neutrino detector in the Northern hemisphere. The search for cosmic neutrinos in the energy range between tens of GeV and tens of…
This paper presents an efficient object detection method from satellite imagery. Among a number of machine learning algorithms, we proposed a combination of two convolutional neural networks (CNN) aimed at high precision and high recall,…
Micro- and nanoplastics pose a growing threat to marine organisms, such as reef-building corals. Yet, our understanding of microplastic uptake, interaction with coral tissue, and incorporation into coral skeletons remains limited, mainly…
A feasibility study of microplastic detection and quantification in soil and water using resonance microwave reflectometry is carried out using artificially created samples with high volumetric concentration of microplastic with…
Mapping buildings and roads automatically with remote sensing typically requires high-resolution imagery, which is expensive to obtain and often sparsely available. In this work we demonstrate how multiple 10 m resolution Sentinel-2 images…
The pervasiveness of microplastics in global oceans is raising concern about its impacts on organisms. While quantifying its toxicity is still an open issue, sampling evidence has shown that rarely is marine microplastics found clean;…
Illegal, unreported, and unregulated (IUU) fishing poses a global threat to ocean habitats. Publicly available satellite data offered by NASA, the European Space Agency (ESA), and the U.S. Geological Survey (USGS), provide an opportunity to…
Here we develop a general statistical procedure for the analysis of finite two-dimensional (2D) patterns inspired by the analysis of heavy-ion data. The method is used in the study of publicly available data obtained by the Gaia-ESA…
Current disposal facilities for coarse-grained waste perform manual sorting of materials with heavy machinery. Large quantities of recyclable materials are lost to coarse waste, so more effective sorting processes must be developed to…
Massive amounts of unlabelled data are captured by Earth Observation (EO) satellites, with the Sentinel-2 constellation generating 1.6 TB of data daily. This makes Remote Sensing a data-rich domain well suited to Machine Learning (ML)…
Moving cameras provide multiple intensity measurements per pixel, yet often semantic segmentation, material recognition, and object recognition do not utilize this information. With basic alignment over several frames of a moving camera…
Global warming is an urgent issue that is generating catastrophic environmental changes, such as the melting of sea ice and glaciers, particularly in the polar regions. The melting pattern and retreat of polar sea ice cover is an essential…
A space telescope capable of high-contrast imaging has been recognized as the avenue toward finding terrestrial planets around nearby Sun-like stars and characterizing their potential habitability. It is thus essential to quantify the…
One of the main difficulties to analyze modern spectroscopic datasets is due to the large amount of data. For example, in atmospheric transmittance spectroscopy, the solar occultation channel (SO) of the NOMAD instrument onboard the ESA…
Deep imaging programs, such as MATLAS which has just been completed at the CFHT, allows us to study with their diffuse light the outer stellar populations around large number of galaxies. We have carried out a systematic census of their…
In the companion paper we began the task of systematically studying the detection of planets in wide orbits ($a > 1.5 R_E$) via microlensing surveys. In this paper we continue, focusing on repeating events. We find that, if all planetary…