< All algorithms
Algorithm identifier

NTD Hotspot Tool

ntd-hotspot:3

Tool for TFGH to predict prevalence and generate adaptive sampling recommendations for NTDs. Also provides the option to obtain recommendations of further survey sites to improve predictions using spatially adaptive sampling. Customized version of the generic prevalence predictor.

Specific documentation
General parameters
Outputs
Specific documentation
This section describes any differences between the customised algorithm and the general parameters described below.
  • The covariates parameter for this function is set using a drop-down list for per-country pre-generated layers, and is not set using a specific URL. These covariates include elevation (NASA SRTM), distance to inland water (worldpop.org), distance to major road (worldpop.org), annual precipitation (worldclim.org), average temperature (worldclim.org), precipitation seasonality (worldclim.org), temperature seasonality (worldclim.org) and population density in 2020 (worldpop.org).
  • The value for entropy_field is pre-set as entropy, which requires a value for exceedance_uncertainty.
Top
General parameters
Top
Outputs

if predict_to = grid

  • Produces a raster (GeoTIFF) of predicted probability of the outcome. See predict_to parameter for information on defining the resulting resolution/extent.

if predict_to = points

  • Produces a csv file of prediction_points with additional columns
  • prevalence_prediction: point prevalence prediction (i.e. best guess)
  • prevalence_bci_width: 95% prediction interval

If exceedance_threshold is defined, in addition

  • exceedance_probability: The probability that true prevalence exceeds exceedance_threshold.
  • exceedance_uncertainty: The probability that the predicted class is correct.
  • entropy: The entropy (0-1 scale) associated with each prediction. Higher entropy equates to higher uncertainty in classification.

or predict_to = polygons

  • Produces the same metrics/fields as if predicting to points. Resulting file is a GeoJSON.

If batch_size is specified, an additional column adaptively_selected with TRUE or FALSE is added, representing whether the location has been selected adaptively.