Mapping Invasive Plants

Mapping Invasive Plants

Mapping Invasive Plants with Drones and Satellite Images

This project is currently Active

With the help of high resolution drone and satellite images, we created maps of the distribution and density of several invasive plant species in the humid zone of the different islands in the archipelago. This information is important to be able to plan control actions of those species that negatively affect the native species. In addition, it also helps to identify high priority conservation areas for the protection of endangered plant and animal species.

The most invasive plant species in the humid zone of the Galapagos islands are blackberry (Rubus niveus), guava (Psidium guajava), Cuban cedar (Cedrela odorata), elephant grass (Pennisetum purpureum) and quinine (Cinchona pubescens). The distributions of these species were determined using satellite images by ground-truthing colour profiles, using drone images of areas with known vegetation types. The resulting maps for the Galapagos National Park area allow us to estimate the cover of these species with an accuracy of 80-90%.

Our Research Team

Heinke Jäger

Principal Investigator

Heinke started working at CDRS in 1998, first on the introduced quinine tree ( Cinchona pubescens ) and then on rare and endangered plant species. After receiving her PhD from Technical University...

Read More

Carolina Carrión

Investigator

Other collaborators: Jorge Luis Rentería, Daniel Orellana (Universidad de Cuenca), Marcelo Loyola (field assistant).

Project Details

Invasive plant species can alter the composition, structure and functioning of terrestrial ecosystems1, especially in a place with fragile ecosystems, such as the Galapagos Archipelago2. To support the conservation of Galapagos and to optimize resources for the management of these invasive plants, we need to know where they are and their abundance. Therefore, we are creating high resolution maps of invasive plant species in the humid zone of several islands in Galapagos. To achieve this, we are using remote sensing tools, such as satellite images and drones, which enable us to cover large areas of difficult access3,4.

Video on the mapping of invasive plants in Galapagos.

How did we do it?

We mixed a bit of fun flying drones in the fresh air of the Galapagos highlands with many cups of coffee, as we worked on programming tasks behind the computer, to arrive at the perfect recipe for the mapping of invasive plants.

Left: WorldView-2 multispectral satellite image. Right: Drone photography captured with a DJI Inspire 1 drone. Invasive species at the visitor site “Los Gemelos”, Santa Cruz are in red, purple and pink. Map elaborated by: Carolina Carrión, CDF.

For the mapping we are using cutting-edge technology. Our main resources are aerial photos captured with drones (DJI Inspire 1 and Mavic Pro) and satellite images with very high resolution (WorldView-2), donated by the DigitalGlobe Foundation, through Brown University. The photos captured by drones are very detailed, which allow us to visually identify and delineate the plant species present in our sampling area. While the WorldView-2 satellite images have a lower resolution than the drone photos, their potential lies in the fact that they cover the entire study area and are multispectral5,6. This means that they have eight color channels (instead of four as the Google Earth satellite images). Among those eight spectral channels, there are some which cover the infrared range, which is very useful for characterizing plant species with different concentrations of chlorophyll. Combining the information captured with the drone with the color information in the satellite image, we train a statistical model called “Random Forest”7. This model identifies a species based on its color characteristics and then extrapolates this information to the entire satellite image. This way, an approximation of the spatial distribution and abundance of each species is being attained.

Diagram of the applied methodology
Diagram of the applied methodology. Based on the photos captured with the drone, individual species are identified and delineated. The delineated shapes are then applied to the multispectral satellite image. A classification model based on the color characteristics of each species is created. This model will then be applied to the entire satellite image. Map elaborated by: Carolina Carrión, CDF.

What have we achieved?

We have created maps of the distribution of the most dominant invasive plants in the humid zone of the Santa Cruz island: blackberry (Rubus niveus), guava (Psidium guajava) and Cuban cedar (Cedrela odorata). We are currently working on the maps for the islands of Floreana and Santiago, applying the same method. These maps also form a baseline to be able to determine the changes in the distribution of these invasive species in the future. We hope that this information will help the Galapagos National Park Directorate (GNPD) effectively plan management actions for invasive plants and thus contribute to the conservation of the unique species of Galapagos.

Our main goal is to have maps of the distribution and abundance of the invasive plant species in order to support conservation efforts in Galapagos.

Our results

Distribution of invasive species in the humid zone of Santa Cruz Island within the protected area:

Results map
Map elaborated by: Carolina Carrión, CDF.

Keywords: Invasive species, Maps, Drone, UAV, Satellite Imagery, Multispectral, WorldView-2

Bibliographical References

  1. Vilà, M., Espinar, J.L., Hejda, M. et al. (2011). Ecological impacts of invasive alien plants: A meta-analysis of their effects on species, communities and ecosystems. Ecol Lett., 14(7), 702-708. doi:10.1111/j.1461-0248.2011.01628.x
  2. Toral-Granda, M.V., Causton, C.E., Jäger, H. et al. (2017). Alien species pathways to the Galapagos Islands, Ecuador. PLoS One, 12(9), e0184379. doi:10.1371/journal.pone.0184379
  3. Alvarez-Taboada, F., Paredes, C. y Julián-Pelaz, J. (2017). Mapping of the invasive species Hakea sericea using Unmanned Aerial Vehicle (UAV) and WorldView-2 imagery and an object-oriented approach. Remote Sens., 9(9), 913. doi:10.3390/rs9090913
  4. Asner, G.P., Knapp, D.E., Kennedy-Bowdoin, T. et al. (2008). Invasive species detection in Hawaiian rainforests using airborne imaging spectroscopy and LiDAR. Remote Sens Environ.;112(5):1942-1955. doi:10.1016/j.rse.2007.11.016
  5. Laliberte, A.S., Goforth, M.A., Steele, C.M. y Rango, A. (2011). Multispectral remote sensing from unmanned aircraft: Image processing workflows and applications for rangeland environments. Remote Sens.;3(11):2529-2551. doi:10.3390/rs3112529
  6. Immitzer, M., Atzberger, C. y Koukal, T. (2012). Tree species classification with Random forest using very high spatial resolution 8-band worldView-2 satellite data. Remote Sens., 4(9), 2661-2693. doi:10.3390/rs4092661
  7. Liaw, A. y Wiener, M. (2002). Classification and regression by randomForest. R news 2002, 2, 18–22.

Partners

The “Charles Darwin Foundation for the Galapagos Islands”, in French “Fondation Charles Darwin pour les îles Galapagos”, Association International sans but lucratif (“AISBL”), has its registered office located at Drève du Pieuré 19, 1160 Brussels, and is registered under the trade registry of Brussels under the number 0409.359.103.

© 2018 Charles Darwin Foundation. All rights reserved.