Towards more efficient agricultural practices via transformer-based crop type classification

TL;DR

This paper explores using transformer models on satellite time series data to classify crops in Mexico, aiming to improve agricultural mapping accuracy and efficiency.

Contribution

It introduces a pixel-based transformer approach for crop classification and suggests meta-learning with similar zones enhances performance.

Findings

Transformer models can classify crops from satellite data with promising accuracy.

Meta-learning with data from similar zones may improve classification results.

Preliminary results support further development of the method.

Abstract

Machine learning has great potential to increase crop production and resilience to climate change. Accurate maps of where crops are grown are a key input to a number of downstream policy and research applications. In this proposal, we present preliminary work showing that it is possible to accurately classify crops from time series derived from Sentinel 1 and 2 satellite imagery in Mexico using a pixel-based binary crop/non-crop time series transformer model. We also find preliminary evidence that meta-learning approaches supplemented with data from similar agro-ecological zones may improve model performance. Due to these promising results, we propose further development of this method with the goal of accurate multi-class crop classification in Jalisco, Mexico via meta-learning with a dataset comprising similar agro-ecological zones.