Diurnal heat-flux data were partitioned into daytime and nighttime, and positive and negative fractions.
These data were partitioned randomly into two sets, for training and testing.
Distinct diel patterns of CH4 flux were observed when the data were partitioned into different cropping periods (pre-planting, growth, and fallow).
In both cases, key structures with data were partitioned from common chemistry by dividing them into individual new PDFs for conversion.
Two spectral regions (675 1180 and 3400-3600/cm) were selected and the data were partitioned into training and test subsets applying the Kennard-Stone design.
To test the predictability of the arrest outcome, data were partitioned into a training set containing approximately 80% of the cohort and a test set containing the remaining 20%.
To develop the models, data were partitioned into different subsets: training (70%), validation (15%), and testing (15%), and the tuned forecasting models with near global optimum solutions were applied and evaluated at multiple horizons: short-term (i.e., weekends, working days, whole weeks, and public holidays), and long-term (monthly).
For each cross validation iteration, the data were partitioned into training and test sets.
Data were partitioned if different models were identified for individual data sets before combination.
Data were partitioned by manually editing the XML file and by applying the respective best-fitting models and parameters [53].
Typically, data were reported at the level of the "site" but at some sites data were partitioned to the level of "colony" or "sub-colony".
