Learned models : Land Cover Classification with Gaussian Processes using spatio-spectro-temporal features

Learned models (Gaussian Processes, Random Forest, Multilayer Perceptron and Lightweight Temporal Self-Attention models) for each region based on the classification data set DS-A with seed 0 (see description here). Each model is learned in an eco-climatic region. Model GP non spatial GP spatial (sum) GP spatial (product) <pre> <code>data_20210511-141111_model_20220621-155521</code></pre> <pre> <code>data_20210511-141111_model_20220411-144241</code></pre> <pre> <code>data_20210511-141111_model_20220413-162100</code></pre> Model MLP non spatial MLP spatial LTAE non spatial LTAE spatial <pre> <code>data_20210511-141111_model_20220225-142000</code></pre> <pre> <code>data_20210511-141111_model_20220312-124400</code></pre> <pre> <code>data_20210511-141111_model_20220207-123103</code></pre> <pre> <code>data_20210511-141111_model_20220208-111338</code></pre> Model RF non spatial RF spatial <pre> <code>data_20210511-141111_model_20211018-155521</code></pre> <pre> <code>data_20210511-141111_model_20211018-144241</code></pre> For further details see section VI-C of the pre-print article "Land Cover Classification with Gaussian Processes using spatio-spectro-temporal features ". This article is available here. The implementation of the models is available in the open source repository.