IDEAS home Printed from https://ideas.repec.org/a/gam/jlands/v12y2023i7p1268-d1175919.html
   My bibliography  Save this article

Pre-Processing Training Data Improves Accuracy and Generalisability of Convolutional Neural Network Based Landscape Semantic Segmentation

Author

Listed:
  • Andrew Clark

    (Remote Sensing Research Centre, The University of Queensland, St Lucia, QLD 4072, Australia
    Applied Agricultural Remote Sensing Centre, The University of New England, Armidale, NSW 2350, Australia)

  • Stuart Phinn

    (Remote Sensing Research Centre, The University of Queensland, St Lucia, QLD 4072, Australia)

  • Peter Scarth

    (Remote Sensing Research Centre, The University of Queensland, St Lucia, QLD 4072, Australia)

Abstract

Data pre-processing for developing a generalised land use and land cover (LULC) deep learning model using earth observation data is important for the classification of a different date and/or sensor. However, it is unclear how to approach deep learning segmentation problems in earth observation data. In this paper, we trialled different methods of data preparation for Convolutional Neural Network (CNN) training and semantic segmentation of LULC features within aerial photography over the Wet Tropics and Atherton Tablelands, Queensland, Australia. This was conducted by trialling and ranking various training patch selection sampling strategies, patch and batch sizes, data augmentations and scaling and inference strategies. Our results showed: a stratified random sampling approach for producing training patches counteracted class imbalances; a smaller number of larger patches (small batch size) improves model accuracy; data augmentations and scaling are imperative in creating a generalised model able to accurately classify LULC features in imagery from a different date and sensor; and producing the output classification by averaging multiple grids of patches and three rotated versions of each patch produced a more accurate and aesthetic result. Combining the findings from the trials, we fully trained five models on the 2018 training image and applied the model to the 2015 test image. The output LULC classifications achieved an average kappa of 0.84, user accuracy of 0.81, and producer accuracy of 0.87. Future research using CNNs and earth observation data should implement the findings of this project to increase LULC model accuracy and transferability.

Suggested Citation

  • Andrew Clark & Stuart Phinn & Peter Scarth, 2023. "Pre-Processing Training Data Improves Accuracy and Generalisability of Convolutional Neural Network Based Landscape Semantic Segmentation," Land, MDPI, vol. 12(7), pages 1-25, June.
  • Handle: RePEc:gam:jlands:v:12:y:2023:i:7:p:1268-:d:1175919
    as

    Download full text from publisher

    File URL: https://www.mdpi.com/2073-445X/12/7/1268/pdf
    Download Restriction: no

    File URL: https://www.mdpi.com/2073-445X/12/7/1268/
    Download Restriction: no
    ---><---

    References listed on IDEAS

    as
    1. Xiulian Bai & Ram C. Sharma & Ryutaro Tateishi & Akihiko Kondoh & Bayaer Wuliangha & Gegen Tana, 2017. "A Detailed and High-Resolution Land Use and Land Cover Change Analysis over the Past 16 Years in the Horqin Sandy Land, Inner Mongolia," Mathematical Problems in Engineering, Hindawi, vol. 2017, pages 1-13, January.
    2. Chuanrong Zhang & Xinba Li, 2022. "Land Use and Land Cover Mapping in the Era of Big Data," Land, MDPI, vol. 11(10), pages 1-22, September.
    Full references (including those not matched with items on IDEAS)

    Most related items

    These are the items that most often cite the same works as this one and are cited by the same works as this one.

      Corrections

      All material on this site has been provided by the respective publishers and authors. You can help correct errors and omissions. When requesting a correction, please mention this item's handle: RePEc:gam:jlands:v:12:y:2023:i:7:p:1268-:d:1175919. See general information about how to correct material in RePEc.

      If you have authored this item and are not yet registered with RePEc, we encourage you to do it here. This allows to link your profile to this item. It also allows you to accept potential citations to this item that we are uncertain about.

      If CitEc recognized a bibliographic reference but did not link an item in RePEc to it, you can help with this form .

      If you know of missing items citing this one, you can help us creating those links by adding the relevant references in the same way as above, for each refering item. If you are a registered author of this item, you may also want to check the "citations" tab in your RePEc Author Service profile, as there may be some citations waiting for confirmation.

      For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: MDPI Indexing Manager (email available below). General contact details of provider: https://www.mdpi.com .

      Please note that corrections may take a couple of weeks to filter through the various RePEc services.

      IDEAS is a RePEc service. RePEc uses bibliographic data supplied by the respective publishers.