Geospatial Data Mining

From Gcube Wiki
Jump to: navigation, search


Geospatial Data Mining is a set of facilities that aim to (i) compare two spatial probability\quantities distributions, (ii) retrieve spatiotemporal information from a remotely hosted geospatial layer and (iii) perform data mining on geographical layers containing environmental information. Geospatial Data Mining is included in the EcologicalEngineGeoSpatialExtension library of the gCube framework, and relies on the data mining processes contained in the EcologicalEngine library.

Overview

Geospatial processing is useful in many applications of marine sciences, including Niche Modeling, Vessels Information processing, Ecological Modeling and Biodiversity monitoring. Environmental characteristics are usually put in the format of n-dimensional vectors of real values. Such vectors must be independent in order to properly describe a phenomenon. Dependent vectors, in fact, correspond to redundant information and are not useful to automatic models. Geospatial processing includes procedures to retrieve environmental information in the format of n-dimensional vectors and the processing needed to evaluate the differences between two datasets or the degree of completeness of a single dataset. This can be essential in calculating the difference between the presence distributions of a certain species in two different years, in order to understand if the distribution is wider or narrower.

Features

The features currently supported by the Geospatial data mining facilities include:

  • Environmental layers indexing on a GeoNetwork instance, with respect to the ISO19115:2003 specifications;
  • Retrieval of environmental parameters information associated to a coordinates triple. Such information is given according to the time instants included in a layer;
  • Retrieval of environmental parameters values associates to a set of points and to a time instant;
  • Automatic simulation of values in the points in which information is not defined;
  • Management of WFS and OpenDAP based layers in seamless way to the library users.

Software

The software is available on the gCube maven repository by including the following component in the pom.xml file:

<dependency>
  <groupId>org.gcube.dataanalysis</groupId>
  <artifactId>ecological-engine-geospatial-extensions</artifactId>
  <version>1.0.0-SNAPSHOT</version>
</dependency>

An example to call the retrieval of several layers metadata which are stored on a thredds instance in a gCube based e-infrastructure:

FeaturesManager featurer = new FeaturesManager();
featurer.setScope("gcube/devsec");
List<Metadata> metadata = featurer.getAllGNInfobyText("thredds", "1");

An example to retrieve a grid of values according to a certain bounding box:

String layertitle = "temperature";
GeoIntersector intersector = new GeoIntersector("gcube/devsec", "./cfg/");
//takes the values contained in a bounding box according to the last time recorded in the layer
double[][] valuesgrid = intersector.takeLastTimeChunk(layertitle, -10, 10, -10, 10, 0,1, 1);

An example to write Metadata in ISO19115:2003 format on a GeoNetwork instance, associated to a certain parameter contained in a NetCDF file:

NetCDFMetadata metadataInserter = new NetCDFMetadata();
metadataInserter.setGeonetworkUrl("http://geoserver-dev.d4science-ii.research-infrastructures.eu/geonetwork/");
metadataInserter.setGeonetworkUser("username");
metadataInserter.setGeonetworkPwd("password");
metadataInserter.setThreddsCatalogUrl("http://thredds.research-infrastructures.eu:8080/thredds/catalog/public/netcdf/catalog.xml");
metadataInserter.setLayerUrl("http://thredds.research-infrastructures.eu:8080/thredds/dodsC/public/netcdf/04091217_ruc.nc");
metadataInserter.setTitle("temperature (04091217ruc.nc)");
//parameter name as defined in the NetCDF file
metadataInserter.setLayerName("T");
metadataInserter.setSourceFileName("04091217_ruc.nc");
metadataInserter.setAbstractField("T: temperature (degK) from 04091217ruc.nc resident on a THREDDS instance");
metadataInserter.setResolution(0.5);
metadataInserter.setXLeftLow(-180);
metadataInserter.setYLeftLow(-85.5);
metadataInserter.setXRightUpper(180);
metadataInserter.setYRightUpper(85.5);
metadataInserter.insertMetaData();

The cfg directory and the Ecological Engine GeoSpatial Extension library are accessible at this svn link: https://svn.d4science.research-infrastructures.eu/gcube/trunk/data-analysis/EcologicalEngineGeoSpatialExtension

Experiments

The complete list of environmental parameters, currently produced by the Geospatial Data Mining facilities and indexed on the D4Science e-infrastructure Geonetwork, can be found at the following link: ListofAvailableEnvironmentalParameters