Deep Learning Improves Planting Year Estimation of Macadamia Orchards in Australia

Title
Deep Learning Improves Planting Year Estimation of Macadamia Orchards in Australia
Publication Date
2025-11-02
Author(s)
Clark, Andrew
( author )
OrcID: https://orcid.org/0000-0002-5309-6910
Email: aclar200@une.edu.au
UNE Id une-id:aclar200
Brinkhoff, James
( author )
OrcID: https://orcid.org/0000-0002-0721-2458
Email: jbrinkho@une.edu.au
UNE Id une-id:jbrinkho
Robson, Andrew
( author )
OrcID: https://orcid.org/0000-0001-5762-8980
Email: arobson7@une.edu.au
UNE Id une-id:arobson7
Shephard, Craig
( author )
OrcID: https://orcid.org/0000-0002-4726-0665
Email: cshepha2@une.edu.au
UNE Id une-id:cshepha2
Type of document
Journal Article
Language
en
Entity Type
Publication
Publisher
MDPI AG
Place of publication
Switzerland
DOI
10.3390/agriculture15222346
UNE publication id
une:1959.11/71674
Abstract

Deep learning reduced macadamia planting year error at a national scale, achieving a pixel-level Mean Absolute Error (MAE) of 1.2 years and outperforming a vegetation index threshold baseline (MAE 1.6 years) and tree-based models—Random Forest (RF; MAE 3.02 years) and Gradient Boosted Trees (GBT; MAE 2.9 years). Using Digital Earth Australia Landsat annual geomedians (1988–2023) and block-level, industry-supplied planting year data, models were trained and evaluated at the pixel level under a strict Leave-One-Region-Out cross-validation (LOROCV) protocol; a secondary block-level random split (80/10/10) is reported only to illustrate the more optimistic setting, where shared regional conditions yield lower errors (0.6–0.7 years). Predictions reconstruct planting year retrospectively from the full historical record rather than providing real-time forecasts. The final model was then applied to all Australian Tree Crop Map (ATCM) macadamia orchard polygons to produce wall-to-wall planting year estimates. The approach enables fine-grained mapping of planting patterns to support yield forecasting, resource allocation, and industry planning. Results indicate that sequence-based deep models capture informative temporal dynamics beyond thresholding and conventional machine learning baselines, while remaining constrained by regional and temporal data sparsity. The framework is scalable and transferable, offering a pathway to planting year mapping for other perennial crops and to more resilient, data-driven agricultural decision-making.

Link
Citation
Agriculture, 15(22), p. 1-27
ISSN
2077-0472
Start page
1
End page
27
Rights
Attribution 4.0 International

Files:

NameSizeformatDescriptionLink