Domain adaptation with transfer learning for pasture digital twins
Abstract
Domain adaptation is important in agriculture because agricultural systems have their own individual characteristics. Applying the same treatment practices (e.g., fertilization) to different systems may not have the desired effect due to those characteristics. Domain adaptation is also an inherent aspect of digital twins. In this work, we examine the potential of transfer learning for domain adaptation in pasture digital twins. We use a synthetic dataset of grassland pasture simulations to pretrain and fine-tune machine learning metamodels for nitrogen response rate prediction. We investigate the outcome in locations with diverse climates, and examine the effect on the results of including more weather and agricultural management practices data during the pretraining phase. We find that transfer learning seems promising to make the models adapt to new conditions. Moreover, our experiments show that adding more weather data on the pretraining phase has a small effect on fine-tuned model performance compared to adding more management practices. This is an interesting finding that is worth further investigation in future studies.
Download full text in pdf format
Published as:
C. Pylianidis,
M. G.J. Kallenberg,
I. N. Athanasiadis,
Domain adaptation with transfer learning for pasture digital twins,
Environmental Data Science, 3:e8,
2024, doi:10.1017/eds.2024.6.
This paper discusses domain adaptation with transfer learning to transfer field-level pasture growing knowledge between locations with diverse climates for nitrogen response rate prediction in the context of agricultural digital twins.
You might also enjoy (View all publications)
- CY-Bench: A comprehensive benchmark dataset for sub-national crop yield forecasting
- Fully automatic extraction of morphological traits from the Web: utopia or reality?
- Transdisciplinary coordination is essential for advancing agricultural modeling with machine learning