Radiant MLHub

A Spatio-Temporal Deep Learning-Based Crop Classification Model for Satellite Imagery

A Spatio-Temporal Deep Learning-Based Crop Classification Model for Satellite Imagery
ml-model
cnn
segmentation
supervised

First place solution for Crop Detection from Satellite Imagery competition organized by CV4A workshop at ICLR 2020. The model architecture consists of 3-layer Conv-net, Masked Features Averaging layer, 3-layer Bi-directional GRU-net and fully connected classification layer. Masked Features Averaging layer is similar to global average pooling but only averages pixels belong to crop field.

Model ID

model-cv4a-crop-detection-v1

DOI

10.34911/rdnt.h28fju

Creator

Amer, Karim

Contact

ml@radiant.earth

License

CC-BY-4.0

Applicable Temporal Extent

2019-06-06 / 2019-11-03

Publications

  • Amer, Karim, and Mohamed Elhelw. "A Spatio-Temporal Deep Learning-Based Crop Classification Model for Satellite Imagery." AGU Fall Meeting Abstracts. Vol. 2020. 2020.

Citation

Amer, K. (2022) “A Spatio-Temporal Deep Learning-Based Crop Classification Model for Satellite Imagery”, Version 1.0, Radiant MLHub. [Date Accessed] Radiant MLHub. https://doi.org/10.34911/rdnt.h28fju

Inferencing Image Example

docker pull docker.io/radiantearth/crop-detection-dl:1

Assets and Links

Inference RuntimeModel Inferencing Runtime
CheckpointFinal Model Checkpoint
Training DataTraining Data Source, Training Data Labels
Inferencing Image
docker.io/radiantearth/crop-detection-dl:1
Related MLHub DatasetCV4A Kenya Crop Type Competition Dataset

Radiant Earth Foundation

© Radiant Earth Foundation