Weighted Tree-based Crop Classification Models for Imbalanced Datasets
satellite
ml-model gradient-boosting classification supervised |
Second place solution to classify crop types in agricultural fields across Northern India using multispectral observations from Sentinel-2 satellite. Ensembled weighted tree-based models "LGBM, CATBOOST, XGBOOST" with stratified k-fold cross validation, taking advantage of spatial variability around each field within different distances.
Model ID | model_ecaas_agrifieldnet_silver_v1 |
DOI | 10.34911/rdnt.qiuwp5 |
Creator | Mohammad Alasawdah |
Contact | masawdah@gmail.com |
License | CC-BY-4.0 |
Applicable Temporal Extent | 2022-01-01 / present |
Documentation
Citation
Alasawdah, M. "Weighted Tree-based Crop Classification Models for Imbalanced Datasets", Version 1.0, Radiant MLHub. [Date Accessed] Radiant MLHub <https://doi.org/10.34911/rdnt.qiuwp5>
Inferencing Image Example
docker pull docker.io/radiantearth/model_ecaas_agrifieldnet_silver:1
Assets and Links
| Inference Runtime | Model Inferencing Runtime |
| Checkpoint | Final Model Checkpoint |
| Training Data | AgriFieldNet Competition Dataset - Source Imagery, AgriFieldNet Competition Dataset - Train Labels |
| Inferencing Image | docker.io/radiantearth/model_ecaas_agrifieldnet_silver:1 |
| Related MLHub Dataset | AgriFieldNet Competition Dataset |
CONNECT
© Radiant Earth Foundation