Utilizing unsupervised learning to improve sward content prediction and herbage mass estimation

TL;DR

This paper improves pasture composition and biomass estimation by applying unsupervised contrastive learning to reduce the need for labeled data, enhancing generalization across different locations.

Contribution

It introduces the use of unsupervised contrastive learning for sward content prediction and herbage mass estimation, reducing reliance on ground-truth images and improving cross-location performance.

Findings

Unsupervised contrastive learning outperforms traditional supervised methods.

Reduced need for ground-truth images in training.

Effective generalization across Danish and Irish datasets.

Abstract

Sward species composition estimation is a tedious one. Herbage must be collected in the field, manually separated into components, dried and weighed to estimate species composition. Deep learning approaches using neural networks have been used in previous work to propose faster and more cost efficient alternatives to this process by estimating the biomass information from a picture of an area of pasture alone. Deep learning approaches have, however, struggled to generalize to distant geographical locations and necessitated further data collection to retrain and perform optimally in different climates. In this work, we enhance the deep learning solution by reducing the need for ground-truthed (GT) images when training the neural network. We demonstrate how unsupervised contrastive learning can be used in the sward composition prediction problem and compare with the state-of-the-art on the publicly available GrassClover dataset collected in Denmark as well as a more recent dataset from Ireland where we tackle herbage mass and height estimation.