2. Artificial Intelligence for tree species identification

Artificial Intelligence for tree species identification

GIMA
M-GEO
M-SE
STAMP
Staff Involved
Rosa Aguilar Bolivar
M-SE Core knowledge areas
Spatial Information Science (SIS)
Topic description

Green spaces are fundamental for the well-being of individuals and communities as they provide areas for recreation, which is essential for the quality of life in cities. The disparity in accessibility to green open spaces, those that are publicly available, is a source of inequality. For that reason, the SDG 11.7 focuses on the universal access to green open spaces. However, when allocating public green open spaces, it is crucial to carefully select (trees) species that are less allergenic to people as the increasing pollen emission volume aggravates the allergy burden in some cities.

Topic objectives and methodology

The objective of this research is to investigate the capabilities of Artificial Intelligence (AI) for tree species identification utilizing remotely sensed data and ground truth records. In particular, you will implement an AI model, Machine learning (ML) or Deep learning (DL), to predict the number and size of trees by species in a geographic area.

Data:

  • Aerial or satellite images
  • Trees datasets

Workflow

The suggested workflow of this research follows:

  1. Literature review of state-of-the-art ML/DL models for species identification
  2. Literature review on allergy burden due to pollen emission.
  3. Data acquisition
  4. Implementation of the model
  5. Assessment of model performance
  6. Critical reflection on the model and its utility

This topic requires an interest in tree species and programming skills as you will work with Jupyter Notebooks and Python. Also, there is ample room and opportunity to shape this research project in consultation with the supervisors, and we expect students who choose this topic to take initiative to do so.

References for further reading

Beloiu, M.; Heinzmann, L.; Rehush, N.; Gessler, A.; Griess, V.C. Individual Tree-Crown Detection and Species Identification in Heterogeneous Forests Using Aerial RGB Imagery and Deep Learning. Remote Sens. 2023, 15, 1463. https://doi.org/10.3390/rs15051463.

Willem W. Verstraeten, Nicolas Bruffaerts, Rostislav Kouznetsov, Letty de Weger, Mikhail Sofiev, Andy W. Delcloo. Attributing long-term changes in airborne birch and grass pollen concentrations to climate change and vegetation dynamics. Atmospheric Environment. https://doi.org/10.1016/j.atmosenv.2023.119643.

Xu, J.; Cai, Z.; Wang, T.; Liu, G.; Tang, P.; Ye, X. Exploring Spatial Distribution of Pollen Allergenic Risk Zones in Urban China. Sustainability 2016, 8, 978. https://doi.org/10.3390/su8100978

How can topic be adapted to Spatial Engineering

This topic includes:

Collecting, processing, analyzing and visualizing data, but also links to SPG with the municipality of Enschede as a stakeholder