This is the model presented as the best-performing model to detect deforestation based on four multispectral composites in the following article: Solórzano et al., 2023. Deforestation detection using a spatio-temporal deep learning approach with synthetic aperture radar and multispectral images. ISPRS Journal of Photogrammetry and Remote Sensing 199: 87–101 [https://doi.org/10.1016/j.isprsjprs.2023.03.017](https://doi.org/10.1016/j.isprsjprs.2023.03.017). The additional Github repository containing the code to obtain this model can be found in: [https://github.com/JonathanVSV/U-netRDef](https://github.com/JonathanVSV/U-netRDef).
U-net 3D model with the highest performance (average F1-score) obtained to detect deforestation based on multispectral composites in four different periods. The three dimensions correspond to two spatial dimensions (height and width) and one temporal dimension.
