Recommending Environmental Big Data Using Semantically Guided Machine Learning - Large Scale and Big Data: Processing and Management - page 479

15.4.2.2 Processing BOM-SILO Time Series
The Long Paddock SILO database is operated by the Queensland Climate Change
Centre of Excellence (QCCCE) within the Department of Science, Information
Technology, Innovation, and the Arts (DSITIA). Data is based on all 4760 Australian
Bureau of Meteorology (BOM) weather stations. SILO contains Australian climate
data from “1889 to yesterday,” in a number of ready-to-use formats, suitable for
research and climate applications. Data files were available in .txt format. Web data
adaptor were able to download data files automatically through HTTP access from
the SILO server, extract all relevant text information from these files using a dedi-
cated batch processor, and finally converted them into numeric time series. Sixteen
attributes measured daily are extracted from downloaded patched point SILO file
which are namely, maximum temperature (°C), minimum temperature (°C), rainfall
(mm), evaporation (mm), radiation (MJ/m 2 ), vapor pressure (hPa), relative humid-
ity at maximum temperature (%), relative humidity at minimum temperature (%),
FAO56 potential evapotranspiration (mm), Morton evaporation over shallow lakes
(mm), Morton potential evapotranspiration over land (mm), Morton actual evapo-
transpiration over land (mm), Morton wet environment areal evapotranspiration over
land (mm), a comparison between measure class A pan evaporation, and synthetic
pan evaporation (mm), class A evaporation (used post-1970) followed by synthetic
pan evaporation (pre-1970) (mm), and mean sea level pressure (hPa). Figure 15.7
shows the graphical representation of some of the SILO variables for Tullochgorum,
Tasmania, during the period including December 2010 to June 2012.

FIGURE 15.7 Time series data from SILO.