get_st_indicator: Get a spatio-temporal indicator from neighbourhood data frame

In mrfoliveira/Evaluation-procedures-for-forecasting-with-spatio-temporal-data: Evaluation procedures for forecasting with spatio-temporal data

Description

Calculate a spatio-temporal indicator of a certain variable within a spatio-temporal neighborhood of a certain radius.

Usage

get_st_indicator(all_neib_vals, stat, radius, ind_name, var,
  time_id = "time", site_id = "site")

Arguments

all_neib_vals	a data frame containing information on observations spatio-temporal distance to neighbours and variable values at the neighbouring locations and times.
stat	the name of a function that calculates a statistic (e.g., "mean"). If the stat is "weighted.mean" then the inverse of the spatio-temporal distance is used to weight the values of observations in the spatio-temporal neighbourhood
radius	a value defining the maximum spatio-temporal distance allowed for an observation to be considered within a spatio-temporal neighbourhood
ind_name	the name of the indicator column
var	the name of the variable to summarize into an indicator
time_id	the name of the column containing time-stamps
site_id	the name of the column containing location IDs

Details

The spatio-temporal distance is defined as

D_{i,j} = d_{i,j} x α + t_{i,j} x (1-α)

where d_i,j is the spatial distance between locations, t_i,j is the temporal distance between time-stapms and α is a weighting factor. Note that radius should always be a number between zero and min(alpha, alpha-1), so the border conditions apply. Also note that if alpha is set to 1, then instead of a cone, the neighbourhood will have the shape of a cylinder.

Value

A data frame that contains a summary statistic of the values found within the spatio-temporal neighbourhood of a certain radius of each pair (location ID, time-stamp) in all_neib_vals

References

Ohashi, Orlando, and Luis Torgo. "Wind speed forecasting using spatio-temporal indicators." ECAI. 2012.

mrfoliveira/Evaluation-procedures-for-forecasting-with-spatio-temporal-data documentation built on April 11, 2021, 10:50 a.m.