Brief description
A dataset of 6 paddocks at six sites in Queensland. Data includes paddock boundaries, point data for soil chemistry, EM38, elevation and yield (sorghum, wheat and barley). The dataset collection is includes measurements from 2005 - 2020. The collection includes raw versions of this data and versions which have been pre-processed for Machine Learning analytics.
Full description
The collection includes 6 paddocks with data including paddock boundaries, crop yield, EM38 geophysics, soil tests, elevation. The data accessible from the paddocks and has been acquired between 2005 and 2020. For machine learning pre-processing the data was converted to standard csv machine-readable format with CRS included for all measurements.Includes pre-processed paddock measurements, pre-processed Remote Sensing time-series data (Landsat, resampled to 5-m resolution using bilinear interpolation) and pre-processed climate time-series data (SILO database).. Readme metadata documents of processed files to assist for ML purposes. Measurements re-scaled and spatially aligned using ordinary block kriging method using locally estimated variograms. The value at each grid point represents an average interpolated value within a 5-m block, centred at the grid point.
Notes
Format (raw and pre-processed): Paddock boundary: shapefile; EM38: csv; Yield data: csv; Soil test data: csv; elevation: csv; satellite data: csv, climate data: csv; Readme: txt
Geographic CRS:GDA94
Includes raw and pre-processed versions.
Additional Information: readme files for raw dataset including metadata description of data labels. Yield files cleaned to remove outliers using resource: "Electromagnetic induction sensing of soil identifies constraints to the crop yields of north-eastern Australia. Soil Research 49(7) 559-571, 2011". Readme documentation for ML pre-processed input available with data files. Data dictionary, standards, vocabulary terms.
The data has been collated (raw) and processed for machine learning compliance (pre-processed) for application in the machine learning project 'Machine learning to extract maximum value from soil and crop variability - UOA2002-007RTX.'
Lineage
"Electromagnetic induction sensing of soil identifies constraints to the crop yields of north-eastern Australia. Soil Research 49(7) 559-571, 2011 (https://doi.org/10.1071/SR11199)." "Identifying the spatial variability of soil constraints using multi-year remote sensing. Field Crops Research, 2011 (https://doi.org/10.1016/j.fcr.2011.05.021)".
Delivery method
Mediated Access
This dataset is a mediated access dataset. Access to this datasets is restricted to authorised persons only. Authorised persons can access the dataset by logging in using an authentication option (e.g. UQ Authenticate, AAF, Edugain, Tuakiri or LinkedIn). The dataset creator has indicated that requests for access are possible. To request access you must first log in using any of our identity partners.
Date Submitted : 20 09 2021
Data time period: 01 01 2005 to 01 01 2020
Spatial Coverage And Location
text: Queensland
User Contributed Tags
Login to tag this record with meaningful keywords to make it easier to discover
