Emulators are regression models that are able to approximate the processing of an RTM, although at a fraction of the computational cost. To enable emulation of an RTM, the first step involves building a statistically-based representation (i.e. an emulator) of the RTM from a set of training data points derived from runs of the actual RTM. The second stage uses the emulator built in the first step to compute the output that otherwise would be generated by the RTM. The Emulator toolbox is foreseen to open new opportunities in the use of advanced RTMs, in which both consistent physical assumptions and data-driven machine learning algorithms live together.
ARTMO’s Emulator toolbox v.1.16.
The Emulator toolbox is based on machine learning regression regression algorithms (MLRAs) coming from the simple Regression toolbox, (simpleR).
Currently, the following MLRAs are implemented. When aiming to emulated multiple spectral bands, it is recommended to use together with a dimensionality reduction method (e.g. PCA):
- Random Forest (TreeBagger)
- Regression tree (LS boosting)
- Multioutput support vector regression
- Support Vector Regression - Matlab
- Extreme Learning Machine
- Kernel ridge Regression
- Canonical Correlation Forests
- Gaussian Processes Regression
- Gaussian Processes Regression - Matlab
- Multioutput Gaussian Processes Regression
- Gaussian Processes Regression
In short, the Emulator toolbox enables:
- To apply and evaluate multiple MLRAs according to customized training strategies, e.g. with different noise and train/validation partitioning.
- Data can either come from ARTMO-RTMs or coming from external LUTs imported as text file.
- The MLRAs are evaluated on their emulator capacities using RMSE goodness-of-fit statistics.
- The best performing MLRA can then function as emulator. Its performance can be tested against the original RTM.
- Emulators can approximate RTMs and generate LUTs at a tremendous gain in processing speed.