The Migratory Modelling Experiment (MM) lets you investigate how the potential distribution of your species might change throughout the year. This experiment runs a Species Distribution Modelling experiment for subsets of your species occurrence data. For each subset you can choose a different set of climate and environmental variables. All subsets will be run using the same algorithm. Read more about Species Distribution Modelling here.

How to run an MM in the BCCVL

  • At the top of the page click on the Experiments tab. 
  • Under the primary experiments heading click on Migratory Modelling Experiment

Step 1: Description tab

  • Enter the name for your experiment in the first box (e.g. Summer vs winter distribution of Monarch butterfly in Australia). 
  • (optional) You can also add a description of your experiment in the box below if you want to convey more information. Some researchers use this box to record their research question or hypotheses for later referral.
  • Click Next.

Step 2: Occurrences tab

Note: only species occurrence datasets that include a column labeled 'month' will appear in the dataset search in this experiment type.

  • Select your pre-loaded species occurrence dataset by clicking the Select A Dataset button. Note: If you click this and you have no loaded species occurrence datasets you will need to visit the dataset page and import or upload the required data.
  • In the pop-up box select the dataset you wish to use in your MM. Click Select
  • (optional) You can visualise your occurrence data by clicking the green eye icon.
  • Click Next.

Step 3: Absences tab

You have two options for adding absence data

  • Uploaded true absence data: If you have your own absence data with a column labeled 'month' with the same input values as the 'month' column in your occurrence data, you can select this for your experiment as follows:
    • Select Yes under the question whether you have true absence data.
    • Click the Select A Dataset button that appears.
    • In the pop-up box select the pre-loaded absence dataset you wish to use in your MM. Click Select
    • (optional) You can visualise your absence data by clicking the green eye icon. 
    • Click Next.
  • Pseudo-absence data: The BCCVL can randomly generate pseudo-absence or background (if using Maxent as algorithm) points for your experiment.
    • Select No under the question whether you have true absence data.
    • You can change the pseudo-absence generation settings (absence-presence ratio and strategy) or the background generation settings (number of background points). By default the generation will be random throughout the geographic extent of the area selected in the constraints tab, with a 1:1 ratio of absence:presence data. All subsets in the experiment will be modelled with the same settings.
    • Click Next.

Step 4: Subsets & Environmental Data tab

  • Click the Add Subset button.
  • Search for the climate/environmental data that you want to use for your first subset  by entering search terms to filter for required datasets or browse through by scrolling. NB. For this experiment type, monthly datasets can be very useful. To find these, untick the Summary datasets (long term) tickbox first, and then select the Monthly datasets.
  • Once you have found the dataset/s you are looking for select them and click Select Layers
  • Select the layers in the dataset that you want to use in your model in the blue box.
  • On the right sight, add a Title for the subset, and indicate which values in the 'month' column should be used for this subset. NB. The values in the 'month' column need to be numbers but can represent other periods than months (e.g. 1 = winter, 2 = summer, or 1 = breeding, 2 = feeding).
  • You can add more subsets by clicking the Add Subset button.
  • For each subset you can choose a different set of climate/environmental variables.
  • Once you have selected all your environmental and climate layers for each of the subsets click Next.

Step 5: Constraints tab

On this tab you can select the area in which to train your model. This means that only the occurrence records from the constrained area are used, and pseudo-absence or background points are only generated in this area. 

The default constraint is the convex hull (= minimum polygon) around all occurrence records. This convex hull will be generated for each subset separately, although the blue outline on the map shows the convex hull around all records in the MM occurrence dataset. The green box indicates the area of the selected environmental/climate variables. If this area is smaller than the convex hull, the model will only be trained in that area. The different constraint options are:

  • Use Convex Hull
    • You can add a buffer around the convex hull by nominating a distance in km and click Add Offset. The buffer will be added on the map.
  • Select constraints by pre-defined region
    • Select one of the region types that are currently available in the BCCVL: Australian States and Territories, Local Government Areas, National Resource Management Regions, IBRA 7 regions, River Regions, Drainage Divisions Level 1 or 2, Marine Ecoregions of the World, Integrated Marine and Coastal Regionalisation of Australia (IMCRA4) Provincial or Meso-scale Bioregions.
    • Find the region of your interest in the drop down menu. You can select multiple regions.
    • Click Add To Map.
    • You can also add a buffer around the pre-defined region constraints.
  • Use Environmental Envelope
    • This is the geographic extent of where all selected climate/environmental datasets overlap.
  • Draw constraints on Map
    • Click Draw On Map to draw a shape on the map to which the model will be constrained.
  • Upload Shapefile 
    • Select a shapefile from your computer to use as the constraint.

Note that the model will be trained on the selected area, and the results will include a predicted distribution map for the constrained area, as well as a projection to the geographic extent of your environmental/climate layers.

Step 6: Algorithms tab

  • Select the algorithm you would like to use to calibrate your model. For the MM experiment, you can only choose one algorithm to run your experiment. Don't know which one to select? Look up detailed information of each algorithm under Algorithm Information (SDMs)  which you can quickly get to by clicking the Read more button under the "i" icon behind each algorithm.
  • (optional) Configuration (Note: each subset will be modelled with the same algorithm configuration settings):
    • The settings selected on the Absence tab will automatically be loaded here, but you can change this again if needed. 
    • Other configuration options are available for most algorithms. These options can be changed by changing the value or make a different selection from the drop down menu. The configuration options are currently set to the standard default values of the R packages. More information about each configuration option can be found on the support page for that particular algorithm under Algorithm Information (SDMs).
  • Click Next.

Note: The BCCVL currently provides 17 different algorithms. Choosing what algorithm best suits your experiment and data or selecting the optimal configuration options can be confusing. For further information on each algorithm and the configuration options click on the title of the algorithm you want to explore under Algorithm Information (SDMs).

Step 7: Run tab

  • Ensure you are happy with your experiment design.
  • If all tabs are green then your experiment is ready to go.
  • Click Start Experiment.
  • If any of your tabs are red, revisit it and ensure you have filled in each component correctly.

A log file will now be sent to our virtual machines where your experiment will be run. You will receive an email when your results are ready to view. This can be done from the Experiments page. For now, sit back and relax, grab a coffee, or do some other work without being hampered by a slower computer that is running heavy models in the background.