1. erroneous;
2. see extreme value
Note: 1. Outliers may exist for two reasons: real abnormalities or incorrect measurement. If an actual abnormality, this should be notified and deserve a detailed explanation. If caused by errors, they should either be corrected or removed before creating a surface.
2. Outliers can have detrimental effects on the prediction surface including effects on semivariogram modeling and the influence of neighboring values.