The content below is no longer maintained. Mathieu Gravey’s official webpage is here: https://www.mgravey.com.
KEYWORDS: multiple-point statistics, MPS simulation, remote sensing, satellite imagery, colorization, spectral enhancement, GPU-based topography point clouds completion methods, Machine Learning, Neural Network, GAN, VAE/AE.
Recent satellite imagery is a vast improvement in terms of spatial, spectral and temporal resolution over archive imagery. My Ph.D. focused on a statistical approach that reconstructs the spectrum of old satellite imagery to match quality of recent imagery. This enables the use of a single processing pipeline on a variety of different datasets acquired with diverse sensors.
Methodologically, I improve and develop new and efficient algorithms especially for pixel-based multiple-point statistics (MPS) simulations. My research develops MPS algorithms that are easier to configure and that benefits from new computing architecture, for CPUs with parallelization, multi-socket, vectorization and advance use of Xeon Phi, and for coprocessors such as GPU or FPGA. Currently, I am working on a autocalibration for MPS to enable non-expert and user-friendly utilization of these methods.
My methods are applicable, for example, for spectral enhancement, also known as colorization, of old or incomplete satellite imagery. This process can be divided into two main topics: the disaggregation, that can be seen as a deconvolution, like reconstruction of color from gray; and extrapolation, like reconstructing near infrared from color.
Aside from my research on methodology I am working through collaboration on a number of applications. First, collaborations where the method I developed is used, but more generally on any methodologies involving or requiring statistics, Machine Learning, algorithmic or intensive computation (cloud/cluster computation). From a dataset and application point of view, most of my collaborations are currently focusing on the use of remote sensed data (satellite, drone,…) in the context of quantifying changes (vegetation, land cover, snow cover, glaciers… ) in particular using Google Earth Engine to target small to large-scale studies in time (from a single moment to a complete archive) and space (from a single glacier up to worldwide studies).
After acquiring a strong foundation in mathematics and physics in “Classes Préparatoires aux Grandes Ecoles”, I completed 3 years of engineering at the Mining Engineering School of Alès, with specialization in computing (equivalent to a M.Sc.). My strong knowledge in computing and in particular in software optimization and parallelization were recognized through the Intel® Modern Code Developer Challenge 2015, where I ended Grand Prize Winner. Because of my interdisciplinary scientific fascinations and my quest for new challenges, I did my Ph.D. in earth science at the University of Lausanne in January 2016, that I finished in January 2020. Since I have the opportunities to collaborate with the IGD ( Institute of Geography ) at UNIL , on a project to quantify land cover change in Vietnam over the last 50 years.
Recently, award of SNSF early postdoc mobility, my next stop would be in Stanford University to work on Machine Learning applied for stochastic geospatial simulations.
The QuickSampling code is freely and openly available for Linux / macOS / Windows 10 and is usable form Matlab / Python3 and R on the dedicated GitHub repository. Please check the documentation for installation and basic usage.
A small selection of other interesting codes:
TrainingImagesTIFF: Training imagde for MPS, enable ready to run code in MATLAB or Python
pyDev4G2S: You want to try a new Sequential simulation algorithm, without going through the pain of managing the search of neighbors efficiently, the conflicts, multivariate situation, … pyDev4G2S will allow you to focus to the simulation of a single pixel, as an extension of the G2S framework. (Good luck 😉 , don’t hesitate to email me in case of an issue )
MatchingMapMaker: A code to measure spatial lag (and deformation) between two images, for large-scale studies (e.g., 50’000 x 50’000 pixels)
GEEex: A Google Chrome extension for Google Earth Engine to allow drag and drop upload with custom manifest, and direct Planet image transfer. (If you have any issue running it let me know, it’s sometimes hard to keep track of API changes…)
Gravey, M., & Mariethoz, G. (2020). QuickSampling v1.0: a robust and simplified pixel- based multiple-point simulation approach. Geoscientific Model Development, 13(6), 2611– 2630. DOI:10.5194/gmd-13-2611-2020
Rasera, L. G., Gravey, M., Lane, S. N., & Mariethoz, G. (2019). Downscaling Images with Trends Using Multiple-Point Statistics Simulation: An Application to Digital Elevation Models. Mathematical Geosciences, 52(2), 145–187. DOI:10.1007/s11004-019-09818-4
Benoit, L., Gourdon, A., Vallat, R., Irarrazaval, I., Gravey, M., Lehmann, B., Prasicek, G., Gräff, D., Herman, F., & Mariethoz, G. (2019). A high-resolution image time series of the Gorner Glacier – Swiss Alps – derived from repeated unmanned aerial vehicle surveys. Earth System Science Data, 11(2), 579–588. DOI:10.5194/essd-11-579-2019
Gravey, M., Rasera, L. G., & Mariethoz, G. (2019). Analogue-based colorization of remote sensing images using textural information. ISPRS Journal of Photogrammetry and Remote Sensing, 147, 242–254. DOI:10.1016/j.isprsjprs.2018.11.003
Nussbaumer, R., Mariethoz, G., Gravey, M., Gloaguen, E., & Holliger, K. (2018). Accelerating Sequential Gaussian Simulation with a constant path. Computers & Geosciences, 112, 121– 132. DOI:10.1016/j.cageo.2017.12.006
15.08.19: Gravey M., Mariethoz G., Automatic parameterization of MPS algorithms by pattern-based analysis of the training image, IAMG 2019, State College PA
06.08.19: Gravey M., Mariethoz G., A Fast Fourier Transform approach for pixel-based Multi- Point Statistics, ARD 2019, USGS-Menlo Park
05.09.18: Gravey M., Mariethoz G., A code for Quantile Sampling: a new MPS pixel-based simulation, IAMG 2018, Olomouc
15.08.18: Gravey M., Mariethoz G., Multiple-point statistics: A tool for Remote Sensing, ARD 2018, USGS-Menlo Park
05.07.18: Gravey M., Mariethoz G., Shall we use kernel weighting in multi-point statistics simulation?, geoENV 2018, Belfast
06.07.17: Gravey M., Mariethoz G., A Fast Fourier Transform approach for pixel-based Multi- Point Statistics, SpatialStat 2017, Lancaster
06.07.17: Gravey M., Mariethoz G., Enhanced classification of multi-temporal satellite images for change detection, SpatialStat 2017, Lancaster
08.09.16: Gravey M., Mariethoz G., Increasing the spectral resolution of satellite images, Geostat 2016, Valencia
19.04.16: Gravey M., Mariethoz G., Gridless, pattern-driven point cloud completion and extension, EGU, Vienna
10.04.19: Michelon A., Benoit L., Gravey M., Brauchli T., Beria H., Ceperley N., Mariethoz G., Schaefli B., The response of a headwater catchment to spatial rainfall patterns – a case study using a high-density network of high temporal resolution rain gauges, EGU 2019, Vienna.
09.04.19: Gravey M., Mariethoz G., A statistical approach to simulate hyperspectral information based on multispectral sensors, EGU 2019, Vienna.
12.12.18: Gravey M., Mariethoz G., Converting image between different satellite sensors: a statistical approach, AGU 2018, Washington D.C.
Invited presentation / lectures
17.08.18: Gravey M., Mariethoz G., MPS: from a complete error map to an automatic setting, Stanford internal prestation at SCERF Stanford
05.08.16: Gravey M., Optimization: The Art of Computing , CERN OpenLab Summer Student Lectures, CERN.
University of Lausanne,
Institute of Earth Surface Dynamics (IDYST),
Geopolis, Quartier Mouline
1015 Lausanne, Switzerland