Student information

MSc thesis subject: Coconut mapping using Sentinel data and deep learning

The coconut palm is considered an important plant as all parts of the plant are valued at small or industrial scale. Therefore, accurate mapping and characterization of these resources is important for their proper management.

In this regard, remote sensing play an important role in mapping and monitoring due to its repeated wide area coverage. In particular, Sentinel-1 synthetic aperture radar (SAR) images offer an all weather, day and night mapping and monitoring capabilities (Mullissa et al. 2019) and Sentinel-2 images offer an unprecedented spectral capability to map and monitor above ground biomass and the land use that replaces them (Castillo et al. 2017). In the analysis domain, machine learning and deep learning methodologies offer an unprecedented accuracy in mapping and monitoring landcover and landuse (Zhang et al. 2019).

For this research we will be using Sentinel images from google earth engine and deep learning to map coconut plantations in the Congo basin. We will also use Planet data to generate the training labels and perform validation.

Objectives

  • Train a model that is able to accurately map coco plantation in the Congo basin
  • Generate a reference labels for the study area
  • Perform accuracy assessment.

Literature

  • A. G. Mullissa, C. Persello, and A. Stein, “Polsarnet: A deep fully convolutional network for polarimetric sar image classification,” IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, vol. 12, no. 12, pp. 5300–5309, Dec 2019.
  • Castillo, J.A.A.; Apan, A.A.; Maraseni, T.N.; Salmo, S.G., III. Estimation and mapping of above-ground biomass of mangrove forests and their replacement land uses in the philippines using sentinel imagery. ISPRS J. Photogramm. Remote Sens. 2017, 134, 70–85.
  • Zhang, C.; Sargent, I.; Pan, X.; Li, H.; Gardiner, A.; Hare, J.; Atkinson, P.M. Joint deep learning for land cover and land use classification. Remote Sens. Environ. 2019, 221, 173–187.

Requirements

  • Advanced Earth Observation course
  • Geo-scripting course (Good knowledge in scripting is an asset; e.g. R, python, java script)

Theme(s): Modelling & visualisation; Integrated Land Monitoring