ENM resolution mix - single run version

Created: 2014-11-18 17:11:07 Last updated: 2015-04-04 21:24:11

Download Workflow

Single run version of the workflow for comparing results of two kinds of ecological niche models: one using only low resolution layers and the other using a random mix of low and high resolution layers. Users select the study region and the environmental variables considered to be the main drivers of a virtual species niche. The workflow is all based on the ENM components, which use the openModeller Web Service (OMWS). After getting initial parameters from the user, the workflow generates a random virtual niche. A random threshold within a given prevalence range is then used to separate suitable from unsuitable areas, from where random training and testing points are sampled. Training points are used to generate the models and independent testing points are used for external tests measuring the AUC. This is a simplified version of the workflow http://www.myexperiment.org/workflows/4535 since it doesn't include experiment replication to check if one of the two types of model performs significantly better than the other. This workflow goes through all steps a single time, but it also includes model projection for illustration purposes.

Preview

Download as scalable diagram (SVG)

Run

Run this Workflow in the Taverna Workbench...

Option 1:

Copy and paste this link into File > 'Open workflow location...'
http://www.myexperiment.org/workflows/4536/download?version=6
[ More Info Expand ]

Workflow Components

Authors (1)

Titles (1)

Descriptions (1)

Dependencies (0)

Inputs (6)

Name	Description
max_virtual_niche_prevalence	Maximum virtual niche prevalence (proportion of suitable area in the native range).
min_virtual_niche_prevalence	Minimum virtual niche prevalence (proportion of suitable area in the native range).
num_testing_points	Number of points to be used for testing (an equal number will be used for presences and absences).
max_number_training_points	Maximum number of training points to be used when creating models for the virtual species. The real number will be a random value between minimum and maximum.
min_number_training_points	Minimum number of training points to be used when creating models for the virtual species. The real number will be a random value between minimum and maximum.
num_background_points	Number of background points

Processors (26)

Name	Type	Description
convert_points_xml_to_csv	component	Component convert_points_xml_to_csv
convert_points_xml_to_csv_2	component	Component convert_points_xml_to_csv
convert_points_xml_to_csv_3	component	Component convert_points_xml_to_csv
convert_points_xml_to_csv_4	component	Component convert_points_xml_to_csv
create_model_with_low_resolution_layers	component	Component create_model
create_model_with_mixed_resolution_layers	component	Component create_model
define_random_number_of_training_points	beanshell	Script int my_min_points = Integer.parseInt(min_points); int my_max_points = Integer.parseInt(max_points); num_points = my_min_points + (int)(Math.random()*(my_max_points-my_min_points));
define_random_testing_points	component	Component select_random_points_based_on_threshold
define_random_training_points	component	Component select_random_points_based_on_threshold
extract_low_resolution_auc	component	Component extract_auc
extract_mixed_resolution_auc	component	Component extract_auc
maxent_parameters	stringconstant	Value
mix_layers_randomly	workflow
test_model_with_low_resolution_layers	component	Component test_model
test_model_with_mixed_resolution_layers	component	Component test_model
generate_acceptable_virtual_niche	workflow
define_frequently_used_constants	component	Component define_frequently_used_constants
get_last_iteration_result	beanshell	Script int last_pos = point_list.size()-1; random_proportion = random_proportion_list.get(last_pos); point = point_list.get(last_pos); threshold = threshold_list.get(last_pos); model_xml = model_xml_list.get(last_pos); model_values = model_values_list.get(last_pos);
choose_layers_and_mask	workflow
merge_all_layers	beanshell	Script all_layers = high_resolution_layers + "\n" + low_resolution_layers;
sample_background_points	component	Randomly sample background points on the specified mask using the intersection between all environmental layers (high and low resolution). Points are returned in the absences port. Component sample_points
GreyTiff100	stringconstant	Value GreyTiff100
project_model_with_low_resolution_layers	component	Component project_model
Get_Image_From_URL_2	localworker	Script if ((url == void) \|\| (url == null)) { throw new RuntimeException("The url must be specified"); } URL inputURL = null; if (base != void) { inputURL = new URL(new URL(base), url); } else { inputURL = new URL(url); } int bytesRead = 0; int totalBytesRead = 0; InputStream is = inputURL.openStream(); ByteArrayOutputStream os = new ByteArrayOutputStream(); byte[] buffer = new byte[2048]; while (true) { bytesRead = is.read(buffer); if (bytesRead == -1) { break; } os.write(buffer, 0, bytesRead); } image = os.toByteArray(); is.close(); os.close();
project_model_with_mixed_resolution_layers	component	Component project_model
Get_Image_From_URL_1	localworker	Script if ((url == void) \|\| (url == null)) { throw new RuntimeException("The url must be specified"); } URL inputURL = null; if (base != void) { inputURL = new URL(new URL(base), url); } else { inputURL = new URL(url); } int bytesRead = 0; int totalBytesRead = 0; InputStream is = inputURL.openStream(); ByteArrayOutputStream os = new ByteArrayOutputStream(); byte[] buffer = new byte[2048]; while (true) { bytesRead = is.read(buffer); if (bytesRead == -1) { break; } os.write(buffer, 0, bytesRead); } image = os.toByteArray(); is.close(); os.close();

Beanshells (6)

Name	Inputs	Outputs
define_random_number_of_training_points	min_points max_points	num_points
get_last_iteration_result	random_proportion_list point_list threshold_list model_xml_list model_values_list	random_proportion point threshold model_xml model_values
merge_all_layers	high_resolution_layers low_resolution_layers	all_layers
suggest_random_suitable_threshold	model_values min_prevalence max_prevalence	threshold proportion
empty_list		empty_list
mix_layers	low_resolution_layers high_resolution_layers	mixed_resolution_layers

Outputs (12)

Name	Description
origin_point
model_xml
suitability_threshold
low_resolution_auc
mixed_resolution_auc
num_training_points
training_points_csv
testing_presence_points_csv
testing_absence_points_csv
prevalence
low_resolution_projection
mixed_resolution_projection

Datalinks (109)

Source	Sink
define_random_training_points:presences_xml	convert_points_xml_to_csv:points_xml
define_frequently_used_constants:label	convert_points_xml_to_csv:species_label
define_random_testing_points:presence_points_xml	convert_points_xml_to_csv_2:points_xml
define_frequently_used_constants:label	convert_points_xml_to_csv_2:species_label
define_random_testing_points:absence_points_xml	convert_points_xml_to_csv_3:points_xml
define_frequently_used_constants:label	convert_points_xml_to_csv_3:species_label
generate_acceptable_virtual_niche:point	convert_points_xml_to_csv_4:points_xml
define_frequently_used_constants:label	convert_points_xml_to_csv_4:species_label
maxent_parameters:value	create_model_with_low_resolution_layers:algorithm_xml
define_random_training_points:presences_xml	create_model_with_low_resolution_layers:presence_points_xml
define_frequently_used_constants:latlong_wgs84	create_model_with_low_resolution_layers:srs
define_frequently_used_constants:label	create_model_with_low_resolution_layers:species_label
define_frequently_used_constants:no	create_model_with_low_resolution_layers:environmentally_unique
define_frequently_used_constants:empty_string	create_model_with_low_resolution_layers:absence_points_xml
define_frequently_used_constants:no	create_model_with_low_resolution_layers:spatially_unique
choose_layers_and_mask:mask_id	create_model_with_low_resolution_layers:mask_id
choose_layers_and_mask:low_resolution_layers_ids	create_model_with_low_resolution_layers:layers_ids
maxent_parameters:value	create_model_with_mixed_resolution_layers:algorithm_xml
define_random_training_points:presences_xml	create_model_with_mixed_resolution_layers:presence_points_xml
define_frequently_used_constants:label	create_model_with_mixed_resolution_layers:species_label
define_frequently_used_constants:latlong_wgs84	create_model_with_mixed_resolution_layers:srs
define_frequently_used_constants:no	create_model_with_mixed_resolution_layers:environmentally_unique
define_frequently_used_constants:empty_string	create_model_with_mixed_resolution_layers:absence_points_xml
define_frequently_used_constants:no	create_model_with_mixed_resolution_layers:spatially_unique
choose_layers_and_mask:mask_id	create_model_with_mixed_resolution_layers:mask_id
mix_layers_randomly:mixed_resolution_layers	create_model_with_mixed_resolution_layers:layers_ids
max_number_training_points	define_random_number_of_training_points:max_points
min_number_training_points	define_random_number_of_training_points:min_points
num_testing_points	define_random_testing_points:num_presences
num_testing_points	define_random_testing_points:num_absences
get_last_iteration_result:threshold	define_random_testing_points:threshold
generate_acceptable_virtual_niche:model_values	define_random_testing_points:model_values
sample_background_points:absence_points_xml	define_random_testing_points:points_xml
define_random_number_of_training_points:num_points	define_random_training_points:num_presences
define_frequently_used_constants:0	define_random_training_points:num_absences
get_last_iteration_result:threshold	define_random_training_points:threshold
generate_acceptable_virtual_niche:model_values	define_random_training_points:model_values
sample_background_points:absence_points_xml	define_random_training_points:points_xml
test_model_with_low_resolution_layers:statistics_xml	extract_low_resolution_auc:statistics_xml
test_model_with_mixed_resolution_layers:statistics_xml	extract_mixed_resolution_auc:statistics_xml
choose_layers_and_mask:high_resolution_layers_ids	mix_layers_randomly:high_resolution_layers
choose_layers_and_mask:low_resolution_layers_ids	mix_layers_randomly:low_resolution_layers
create_model_with_low_resolution_layers:model_xml	test_model_with_low_resolution_layers:model_xml
define_random_testing_points:absence_points_xml	test_model_with_low_resolution_layers:absence_points_xml
define_random_testing_points:presence_points_xml	test_model_with_low_resolution_layers:presence_points_xml
define_frequently_used_constants:latlong_wgs84	test_model_with_low_resolution_layers:srs
define_frequently_used_constants:label	test_model_with_low_resolution_layers:species_label
define_frequently_used_constants:0	test_model_with_low_resolution_layers:num_background_points
define_frequently_used_constants:no	test_model_with_low_resolution_layers:calculate_matrix
define_frequently_used_constants:yes	test_model_with_low_resolution_layers:calculate_roc
define_frequently_used_constants:0_5	test_model_with_low_resolution_layers:threshold
choose_layers_and_mask:mask_id	test_model_with_low_resolution_layers:mask_id
choose_layers_and_mask:low_resolution_layers_ids	test_model_with_low_resolution_layers:layers_ids
create_model_with_mixed_resolution_layers:model_xml	test_model_with_mixed_resolution_layers:model_xml
define_random_testing_points:presence_points_xml	test_model_with_mixed_resolution_layers:presence_points_xml
define_random_testing_points:absence_points_xml	test_model_with_mixed_resolution_layers:absence_points_xml
define_frequently_used_constants:latlong_wgs84	test_model_with_mixed_resolution_layers:srs
define_frequently_used_constants:label	test_model_with_mixed_resolution_layers:species_label
define_frequently_used_constants:0	test_model_with_mixed_resolution_layers:num_background_points
define_frequently_used_constants:no	test_model_with_mixed_resolution_layers:calculate_matrix
define_frequently_used_constants:yes	test_model_with_mixed_resolution_layers:calculate_roc
define_frequently_used_constants:0_5	test_model_with_mixed_resolution_layers:threshold
choose_layers_and_mask:mask_id	test_model_with_mixed_resolution_layers:mask_id
mix_layers_randomly:mixed_resolution_layers	test_model_with_mixed_resolution_layers:layers_ids
min_virtual_niche_prevalence	generate_acceptable_virtual_niche:min_prevalence
max_virtual_niche_prevalence	generate_acceptable_virtual_niche:max_prevalence
choose_layers_and_mask:mask_id	generate_acceptable_virtual_niche:mask_id
sample_background_points:absence_points_xml	generate_acceptable_virtual_niche:background_points
merge_all_layers:all_layers	generate_acceptable_virtual_niche:all_layers
choose_layers_and_mask:high_resolution_layers_ids	generate_acceptable_virtual_niche:high_resolution_layers
generate_acceptable_virtual_niche:point	get_last_iteration_result:point_list
generate_acceptable_virtual_niche:random_proportion	get_last_iteration_result:random_proportion_list
generate_acceptable_virtual_niche:threshold	get_last_iteration_result:threshold_list
generate_acceptable_virtual_niche:model_xml	get_last_iteration_result:model_xml_list
generate_acceptable_virtual_niche:model_values	get_last_iteration_result:model_values_list
choose_layers_and_mask:low_resolution_layers_ids	merge_all_layers:low_resolution_layers
choose_layers_and_mask:high_resolution_layers_ids	merge_all_layers:high_resolution_layers
choose_layers_and_mask:mask_id	sample_background_points:mask_id
num_background_points	sample_background_points:num_points
define_frequently_used_constants:no	sample_background_points:environmentally_unique
define_frequently_used_constants:no	sample_background_points:spatially_unique
define_frequently_used_constants:label	sample_background_points:species_label
define_frequently_used_constants:1	sample_background_points:proportion_of_absences
merge_all_layers:all_layers	sample_background_points:layers_ids
define_frequently_used_constants:no	sample_background_points:return_environmental_data
GreyTiff100:value	project_model_with_low_resolution_layers:output_format
choose_layers_and_mask:mask_id	project_model_with_low_resolution_layers:mask_id
define_frequently_used_constants:0_5	project_model_with_low_resolution_layers:cell_statistics_threshold
create_model_with_low_resolution_layers:model_xml	project_model_with_low_resolution_layers:model_xml
choose_layers_and_mask:low_resolution_layers_ids	project_model_with_low_resolution_layers:layers_ids
project_model_with_low_resolution_layers:raster_url	Get_Image_From_URL_2:url
GreyTiff100:value	project_model_with_mixed_resolution_layers:output_format
choose_layers_and_mask:mask_id	project_model_with_mixed_resolution_layers:mask_id
define_frequently_used_constants:0_5	project_model_with_mixed_resolution_layers:cell_statistics_threshold
create_model_with_mixed_resolution_layers:model_xml	project_model_with_mixed_resolution_layers:model_xml
mix_layers_randomly:mixed_resolution_layers	project_model_with_mixed_resolution_layers:layers_ids
project_model_with_mixed_resolution_layers:raster_url	Get_Image_From_URL_1:url
convert_points_xml_to_csv_4:points_csv	origin_point
generate_acceptable_virtual_niche:model_xml	model_xml
get_last_iteration_result:threshold	suitability_threshold
extract_low_resolution_auc:auc	low_resolution_auc
extract_mixed_resolution_auc:auc	mixed_resolution_auc
define_random_number_of_training_points:num_points	num_training_points
convert_points_xml_to_csv:points_csv	training_points_csv
convert_points_xml_to_csv_2:points_csv	testing_presence_points_csv
convert_points_xml_to_csv_3:points_csv	testing_absence_points_csv
generate_acceptable_virtual_niche:random_proportion	prevalence
Get_Image_From_URL_2:image	low_resolution_projection
Get_Image_From_URL_1:image	mixed_resolution_projection

Coordinations (13)

Controller	Target
define_random_testing_points	test_model_with_low_resolution_layers
merge_all_layers	sample_background_points
choose_layers_and_mask	merge_all_layers
create_model_with_low_resolution_layers	project_model_with_low_resolution_layers
sample_background_points	generate_acceptable_virtual_niche
generate_acceptable_virtual_niche	get_last_iteration_result
create_model_with_mixed_resolution_layers	test_model_with_mixed_resolution_layers
define_random_testing_points	test_model_with_mixed_resolution_layers
create_model_with_mixed_resolution_layers	project_model_with_mixed_resolution_layers
define_random_training_points	create_model_with_low_resolution_layers
create_model_with_low_resolution_layers	test_model_with_low_resolution_layers
get_last_iteration_result	define_random_training_points
get_last_iteration_result	define_random_testing_points

Information Workflow Type

Taverna 2

Information Uploader

Renato De Giovanni

Information License

All versions of this Workflow are licensed under:

Information Version 6 (latest) (of 6)

Information Credits (2)

(People/Groups)

Information Attributions (0)

(Workflows/Files)

None

Information Tags (0)

None

Log in to add Tags

Information Shared with Groups (1)

BioVeL internal

Information Featured In Packs (0)

None

Log in to add to one of your Packs

Information Attributed By (0)

(Workflows/Files)

None

Information Favourited By (0)

No one

Information Statistics

3858 viewings

1286 downloads

[ see breakdown ]

Citations (0)

None

Version History

In chronological order:

ENM resolution mix - single run version

Created by Renato De Giovanni on Tuesday 18 November 2014 17:11:02 (UTC)
ENM resolution mix - single run version

Created by Renato De Giovanni on Wednesday 19 November 2014 11:39:03 (UTC)

Revision comment:

Upgraded some of the components.
ENM resolution mix - single run version

Created by Renato De Giovanni on Thursday 04 December 2014 16:20:03 (UTC)

Revision comment:

Updated components versions.
ENM resolution mix - single run version

Created by Renato De Giovanni on Friday 05 December 2014 17:41:15 (UTC)

Revision comment:

Fix bug in threshold calculation.
ENM resolution mix - single run version

Created by Renato De Giovanni on Tuesday 09 December 2014 20:32:36 (UTC)

Revision comment:

Updated samplePoints component and removed unnecessary loop feedback.
ENM resolution mix - single run version

Created by Renato De Giovanni on Saturday 04 April 2015 21:24:11 (UTC)

Revision comment:

Upgraded interaction components to use github pages.

Reviews (0)

No reviews yet

Be the first to review!

Comments (0)

View Timeline

No comments yet

Log in to make a comment

Other workflows that use similar services (0)

There are no workflows in myExperiment that use similar services to this Workflow.

ENM resolution mix - single run version

Preview

Run

Run this Workflow in the Taverna Workbench...

Workflow Components

Component

Component

Component

Component

Component

Component

Script

Component

Component

Component

Component

Value

Component

Component

Component

Script

Script

Component

Value

Component

Script

Component

Script

Reviews (0)

Comments (0)

Other workflows that use similar services (0)