6533b86ffe1ef96bd12cd283
RESEARCH PRODUCT
Latent force models for earth observation time series prediction
Gustau Camps-vallsDavid LuengoManuel Campos-tabernersubject
Earth observation010504 meteorology & atmospheric sciencesSeries (mathematics)Differential equationComputer scienceMatemáticas02 engineering and technologyMissing data01 natural sciencesData-drivenData modelingsymbols.namesake0202 electrical engineering electronic engineering information engineeringsymbols020201 artificial intelligence & image processingGeologíaTime seriesGaussian processAlgorithmSimulation0105 earth and related environmental sciencesdescription
We introduce latent force models for Earth observation time series analysis. The model uses Gaussian processes and differential equations to combine data driven modelling with a physical model of the system. The LFM presented here performs multi-output structured regression, adapts to the signal characteristics, it can cope with missing data in the time series, and provides explicit latent functions that allow system analysis and evaluation. We successfully illustrate the performance in challenging scenarios of crop monitoring from space, providing time-resolved time series predictions.
| year | journal | country | edition | language |
|---|---|---|---|---|
| 2016-09-01 |