Upgrade to Pro — share decks privately, control downloads, hide ads and more …

Roland Rodde- Vegetation management for powerlines with remote sensing data

Roland Rodde- Vegetation management for powerlines with remote sensing data

Growing vegetation causes risks to overhead powerlines. Therefore vegetation needs to be cut in a corridor near these powerlines. We developed a solution to support the risk assessment and the planning of future clearings based on satellite images and helicopter based Lidar data. In this talk I will give an overview on the different data sources, the models and algorithms we apply and how we implemented the solution in Azure.

MunichDataGeeks

April 26, 2023
Tweet

More Decks by MunichDataGeeks

Other Decks in Science

Transcript

  1. Vegetation management for powerlines
    with remote sensing data
    Datageeks Meetup March 2023
    Dr. Roland Rodde

    View full-size slide

  2. 2
    Agenda
    Project motivation and setup
    I
    Satellite images and Lidar data
    II
    Modelling and usage of data
    III
    IV
    V
    V
    Architecture
    IV

    View full-size slide

  3. Project motivation
    4
    Vegetation can grow into the powerlines from below or fall into the the powerlines from the sides.
    This can lead to outages. Therefore the vegetation near to the powerlines has to be monitored

    View full-size slide

  4. Project goals
    5

    View full-size slide

  5. One project team
    6
    - Jose Moreno Ortega
    - Roland Rodde
    - Martin Cleven
    - Stefan Bietz
    - Anders Richter
    - Christer Friberg
    - Cecilia Pihl
    - Nils Näsström
    - Anton Westholm
    - Wilhelm Rosendahl
    - Alejandro Ruete
    - Jonas Josefsson
    - Louise Westerberg
    - Tobias Dannerstedt
    - Anders Vannfält
    - Johan Höök

    View full-size slide

  6. Product development
    7
    Agile development: mixture of
    Kanban and Scrum, Sprints of 3
    weeks
    Different workstreams: Frontend/UI,
    GIS systems, Ecological corridor
    management, Data processing and
    ML
    Quality standards: Unit testing of
    code, peer reviews before code
    acceptance
    Toolset: Jira (Task management),
    Confluence (documentation), Gitlab
    (source code management)

    View full-size slide

  7. 8
    Agenda
    Project motivation and setup
    I
    Satellite images and Lidar data
    II
    Modelling and usage of data
    III
    IV
    V
    V
    Architecture
    IV

    View full-size slide

  8. High resolution satellite images
    9
    Satellite images can be tasked
    for areas of interest
    Skysat image constellation
    operated by planet
    A full set of APIs is available to
    do the tasking, track the tasking
    and to obtain the image data
    Time to delivery mainly
    dependent on weather
    conditions and satellite orbits

    View full-size slide

  9. Planets image processing chain
    10

    View full-size slide

  10. Example data
    11

    View full-size slide

  11. What is Lidar data?
    12

    View full-size slide

  12. How do we obtain the Lidar data?
    13

    View full-size slide

  13. Lidar data example
    14
    Short demo of lidar data

    View full-size slide

  14. 15
    Agenda
    Project motivation and setup
    I
    Satellite images and Lidar data
    II
    Modelling and usage of data
    III
    IV
    V
    V
    Architecture
    IV

    View full-size slide

  15. Generating training data set
    Preprocessing of satellite images
    16
    Tiling Cloud cover removal
    Selection of tiles
    with ground truth
    Split of dataset
    Input
    Train Test Validation

    View full-size slide

  16. Generating training data set
    Generating ground truth from Lidar data
    17
    Reprojection of
    lidar data
    Map projection of
    heights
    Map projection of
    lidar classes
    Creation of
    segmentation classes
    Tiling of segmentation
    images
    Split of dataset
    Input
    Train Test Validation

    View full-size slide

  17. Semantic segmentation model
    18
    DeeplabV3 model for
    semantic segmentation
    Resnet101 backbone
    Model is pretrained on COCO
    train2017 dataset
    Can be easily obtained
    through torchvision library
    Transfer learning is done to
    adapt model parameters to
    task at hand

    View full-size slide

  18. Model training
    19
    • We use cross entropy loss as loss function
    • As our groundtruth data contains a lot of
    missing data, we ignore these pixels in loss
    calculation
    • We use a learning rate scheduler to adapt
    learning rate during training (exponential decay)
    • Adam is used as optimiser
    • To increase the diversity of the training dataset
    we apply image augmentations on the training
    images (Rotations, flips, distortion of colours)
    • Early stopping done after model does not improve
    over several epochs
    • Dataset pretty balanced, no need for class weights
    • Hyperparameter tuning was apllied to find the
    best set of hyperparameters (learning rate,
    learning rate scheduler, image augmentation
    probabilities, …)

    View full-size slide

  19. Model evaluation
    20
    Our main metric is IoU (Intersection over Union)
    Groundtruth Prediction
    Red IoU: 5 / (5 + 2 + 1) = 0.63
    Blue IoU: 4 / (4 + 1 + 2) = 0.57
    Mean IoU: Mean of class IoU = 0.6
    We also log the best and worst performing tiles
    to get an idea for model improvements

    View full-size slide

  20. Generating heightmaps
    21
    Height normalised Lidar
    Input Determine DTM Resolution binning
    Quantile based height
    Output

    View full-size slide

  21. Generating growth maps
    22
    Height map date 1 (2015) Height map date 2 (2019) Weather data (temperature
    and precipitation)
    Growthmap

    View full-size slide

  22. Calculating risks
    23
    Growth Model HeightMap1
    GrowthMap
    PowerLine
    Risk Model
    Based on the initial heightmap, the GrowthMap will be used to estimate the future height for each pixel. These pixel will be associated with a risk value,
    which will be projected into points with a equidistant distance along a line in the centre of the corridor. Based on the accumulated risk for each point,
    areas in need of clearing are identified which will be assumed cleared and used as feedback to future years
    risk_year
    interpolation_distance
    Projected Risk
    HeightMap0
    Cut down of high risk areas

    View full-size slide

  23. 24
    Agenda
    Project motivation and setup
    I
    Satellite images and Lidar data
    II
    Modelling and usage of data
    III
    IV
    V
    V
    Architecture
    IV

    View full-size slide

  24. Azure architecture
    25

    View full-size slide

  25. Python environment
    26
    rasterio

    View full-size slide

  26. Scaling and rollout
    27

    View full-size slide

  27. Thank you for your attention!

    View full-size slide