Deep Learning on High Spatial and Temporal Cadence Satellite Imagery for Field Boundary Delineation

Abstract

Agriculture field boundary information is vital in crop health monitoring, food security efforts, and precision agriculture. In countries like Denmark and the Netherlands field parcel information is available whereas Pakistan lacks such datasets.Denmark field boundary data for year 2018 was selected for the training of the model. Satellite imagery of four dates was downloaded and preprocessed to capture crop dynamics on the ground. Semantic segmentation architectures were used to train the models on the imagery, and results were assessed using metrics such as Intersection over Union(IoU) and f1-scores.The results show that UNet architecture with SENet154 backbone performs better than other architecture-backbone combinations. In terms of dates of imagery, data from 27th July achieved a higher IoU score. The method of providing input mask to the model had the most impact on the metrics and resulted in a 35% increase in IoU. Temporal stacking of multi-date satellite imagery proved to be an effective way of increasing information content for boundary delineation and improved the IoU by 6.5% in comparison to a single-date model. The final temporal stacked model had an IoU score of around 0.72.The trained model was able to delineate boundaries and showed good results in comparison to the available ground truth. The results of transfer learning to new areas suggest that there is potential in using such techniques, but further factors need to be considered to improve the metrics.