We're sorry but this page doesn't work properly without JavaScript enabled. Please enable it to continue.
Feedback

Land cover time-series data stack for Europe 2000--2019 based on LUCAS, GLAD Landsat and Spatiotemporal Ensemble Machine Learning

Formal Metadata

Title
Land cover time-series data stack for Europe 2000--2019 based on LUCAS, GLAD Landsat and Spatiotemporal Ensemble Machine Learning
Title of Series
Number of Parts
57
Author
License
CC Attribution 3.0 Germany:
You are free to use, adapt and copy, distribute and transmit the work or content in adapted or unchanged form for any legal purpose as long as the work is attributed to the author in the manner specified by the author or licensor.
Identifiers
Publisher
Release Date
Language
Producer
Production PlaceWageningen

Content Metadata

Subject Area
Genre
Abstract
Martijn Witjes is a PhD candidate at OpenGeoHub foundation. In this talk, he expounded the first results of his research on land cover time-series data stack for Europe between 2000 and 2019. The classification sees 33 different land use / land cover (LULC) classes between 2000 and 2019 using a single spatiotemporal ensemble machine learning model in a fully automated, free and open source workflow. This workflow includes harmonization and preprocessing of several high-resolution publically available covariate datasets and over five million training samples, spatial K-fold cross-validation, hyperparameter optimization, and multiple methods for LULC change analysis. Martijn also showed how the per-class probability predictions facilitated useful prediction uncertainty metrics, informed use case-tailored post-processing strategies, and enabled a novel way to quantify LULC change dynamics without relying on hard-class predictions. The results of his study suggest that the method developed by his team, enables land cover classification for subsequent years without waiting for new training data, while facilitating improved training data collection through analysing variable importance, per-class performance, and uncertainty metrics.
Keywords