"Developing Machine Learning Algorithms for spatial and spatiotemporal
data science problems"
Lecturers/topics (sorted alphabetically):
- Christian Knoth: "Introduction to Deep Learning in R for the analysis
of UAV-based remote sensing data"
- Dainius Masiliunas: "Global-scale land cover mapping using FOSS4G"
- Dainius Masiliunas: "OpenEO demo (R client)"
- Dainius Masiliunas: "Detection of breaks in time series using the
'bfast' package in R"
- Dylan Beaudette: "Algorithms for Quantitative Pedology: R packages for
working with soils data at scale"
- Dylan Beaudette: "High performance vector data analysis delivery with
- Dylan Beaudette: "Credible metrics for determining similarity,
accuracy, and precision in the context of soil type mapping"
- Edzer Pebesma: "Handling and analysing vector and raster data cubes
- Giuseppe Amatulli: "GDAL/OGR and PKTOOLS for massive raster/vector
- Hanna Meyer: "Machine learning in remote sensing applications"
- John E. Lewis: "Spatial mixed models & semiparametric regression"
- John E. Lewis: "Working with and the modelling of temporal data"
- John E. Lewis: "Using R for machine learning modelling - a coding
- Julia Wagemann: "Analysis of Big Earth Data with Jupyter Notebooks"
- Julia Wagemann: "Dashboarding with Jupyter Notebooks and Voila"
- Longzhu Shen: "Predictive modeling of nitrogen distributions in US
streams in a machine learning framework"
- Madlene Nussbaum: "Mastering machine learning for spatial prediction I
- overview and introduction in methods"
- Madlene Nussbaum: "Mastering machine learning for spatial prediction
II - model selection and interpretation, uncertainty"
- Marius Appel: "Creating and Analyzing Multi-Variable Earth Observation
Data Cubes in R"
- Meng Lu: "Assessment of global air pollution exposure"
- Paula Moraga: "Spatial modeling and interactive visualization with the
- Richard Barnes: "High-performance geocomputing for hydrological /
- Richard Barnes: "Leveraging Python, clusters, and GPUs for geocomputation"
- Richard Barnes: "Reproducible scientific analysis"
- Tim Appelhans: "mapview package tutorial"
- Tomislav Hengl: "Automated predictive mapping using Ensemble Machine
- Tomislav Hengl: "A step-by-step tutorial to optimization of
geocomputing (tiling and parallelization) with R"
- 26th of November 2019 — registrations open,
- 1st of February 2020 — registrations close,
- 16th of February 2020 — selection of candidates and invitation letters
- 12th of April 2020 — course fee payment deadline,
- 1st of May 2020 — official programme published,
- 16 August to 22 August 2020 — Summer School,
The Summer School is limited to 70 participants. In the case of higher
number of applications, candidates will be selected based on a ranking
system, which is based on: time of registration, solidarity, academic
output and contributions to the open source projects. The final
programme of the Summer School will shaped interactively.
The registrations fees for this Summer School full course fee will be in
the range 400–500 EUR (exact number will be provided in the invitation
letter). Participants from ODA countries (employed by an organization or
company in ODA-listed country) and/or full-time students (not under work
contract as University assistant or similar) have a right on reduced fee
(usually 40% lower than the full registration fee).
Summer School is organized on a cost-recovery basis. OpenGeoHub
foundation is a not-for-profit research foundation located in the
Netherlands. All lecturers are volunteers. None of the lecturers
receives any honorarium payment or is contracted by the local organizers.
Come to Wageningen the town of Life Science and improve your coding /