Deep Learning Improves Planting Year Estimation of Macadamia Orchards in Australia

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.

• Publication year

  2025

• Venue

  Agriculture

• Publication date

  2025-11-11

• Fields of study

  Not labeled

• Identifiers
  DOI 10.3390/agriculture15222346
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Applied Deep Learning-Based Crop Yield Prediction: A Systematic Analysis of Current Developments and Potential Challenges

  2024cited by this paper
• High-resolution maps show that rubber causes substantial deforestation

  2023cited by this paper
• A Review of Data Augmentation Methods of Remote Sensing Image Target Recognition

  2023cited by this paper
• Pre-processing training data improves accuracy and generalisability of convolutional neural network based landscape semantic segmentation

  2023cited by this paper
• Data Augmentation techniques in time series domain: a survey and taxonomy

  2022cited by this paper
• Research on remote sensing classification of fruit trees based on Sentinel-2 multi-temporal imageries

  2022cited by this paper
• A novel framework for spatio-temporal prediction of environmental data using deep learning

  2020cited by this paper
• Macadamia Orchard Planting Year and Area Estimation at a National Scale

  2020influential reference
• Automatic mapping of planting year for tree crops with Landsat satellite time series stacks

  2019influential reference
• A Patch-Based Light Convolutional Neural Network for Land-Cover Mapping Using Landsat-8 Images

  2019cited by this paper
• Current status of Landsat program, science, and applications

  2019cited by this paper
• Deep learning based multi-temporal crop classification

  2019cited by this paper
• Improved crop forecasts for the Australian macadamia industry from ensemble models

  2019cited by this paper
• An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modeling

  2018cited by this paper
• The Harmonized Landsat and Sentinel-2 surface reflectance data set

  2018cited by this paper
• Temporal Convolutional Neural Network for the Classification of Satellite Image Time Series

  2018cited by this paper
• A comparison of resampling methods for remote sensing classification and accuracy assessment

  2018influential reference
• High-Dimensional Pixel Composites From Earth Observation Time Series

  2017cited by this paper
• Attention is All you Need

  2017cited by this paper
• Deep Learning Classification of Land Cover and Crop Types Using Remote Sensing Data

  2017cited by this paper
• Deep Residual Learning for Image Recognition

  2015cited by this paper
• Net ecosystem carbon balance of an apple orchard

  2015cited by this paper
• Learning Phrase Representations using RNN Encoder–Decoder for Statistical Machine Translation

  2014cited by this paper
• Root mean square error (RMSE) or mean absolute error (MAE)? – Arguments against avoiding RMSE in the literature

  2014cited by this paper
• Carbon Sequestration by Fruit Trees - Chinese Apple Orchards as an Example

  2012cited by this paper
• Sentinel-2: ESA's Optical High-Resolution Mission for GMES Operational Services

  2012cited by this paper
• Scikit-learn: Machine Learning in Python

  2011cited by this paper
• Biodiversity and pest management in orchard systems. A review

  2011cited by this paper
• Scale Issues in Remote Sensing: A Review on Analysis, Processing and Modeling

  2009cited by this paper
• Annual forecasting of the Australian macadamia crop - integrating tree census data with statistical climate-adjustment models.

  2006cited by this paper
• Thematic map comparison: Evaluating the statistical significance of differences in classification accuracy

  2004cited by this paper
• Status of land cover classification accuracy assessment

  2002cited by this paper
• An overview of MODIS Land data processing and product status

  2002cited by this paper
• Random Forests

  2001cited by this paper
• Measuring the quality of digital soil maps using information criteria

  2001cited by this paper
• Greedy function approximation: A gradient boosting machine.

  2001cited by this paper
• Remote sensing of chlorophyll concentration in higher plant leaves

  1998cited by this paper
• Bidirectional recurrent neural networks

  1997cited by this paper
• Long Short-Term Memory

  1997cited by this paper
• Monitoring vegetation systems in the great plains with ERTS

  1973cited by this paper

• No citing papers are available for this paper.