AgResearch
Browse
- No file added yet -

Location-specific vs location-agnostic machine learning metamodels for predicting pasture nitrogen response rate

Download (1.43 MB)
chapter
posted on 2023-05-03, 20:22 authored by Christos Pylianidis, Val SnowVal Snow, Dean Holzworth, Jeremy Bryant, Ioannis Athanasiadis
In this work we compare the performance of a location-specific and a location-agnostic machine learning metamodel for crop nitrogen response rate prediction. We conduct a case study for grass-only pasture in several locations in New Zealand. We generate a large dataset of APSIM simulation outputs and train machine learning models based on that data. Initially, we examine how the models perform at the location where the location-specific model was trained. We then perform the Mann–Whitney U test to see if the difference in the predictions of the two models (i.e. location-specific and location-agnostic) is significant. We expand this procedure to other locations to investigate the generalization capability of the models. We find that there is no statistically significant difference in the predictions of the two models. This is both interesting and useful because the location-agnostic model generalizes better than the location-specific model which means that it can be applied to virgin sites with similar confidence to experienced sites.

History

Rights statement

© 2021 Springer Nature Switzerland AG

Language

  • English

Does this contain Māori information or data?

  • No

Publisher

AgResearch Ltd

Journal title

Lecture Notes in Computer Science (LNCS)

ISSN

0302-9743

ISBN

9783030687809

Conference name

25th International Conference in Pattern Recognition (ICPR 2021)

Conference location

Milano, Italy

Conference start date

2021-01-10

Conference end date

2021-01-15

Citation

Pylianidis, C., Snow, V., Holzworth, D., Bryant, J., & Athanasiadis, I. N. (2021). Location-specific vs location-agnostic machine learning metamodels for predicting pasture nitrogen response rate. In Lecture Notes in Computer Science (LNCS) (Vol. 12666, pp. 45–54). Springer Nature. https://doi.org/10.1007/978-3-030-68780-9_5

Usage metrics

    Exports

    RefWorks
    BibTeX
    Ref. manager
    Endnote
    DataCite
    NLM
    DC