Climatic data values have become very important to predict climate phenomena or to evaluate historical data which give support for decision makers, especially in agriculture. To ensure the quality of these data is crucial. In the process of collecting data at meteorological stations, some errors may occur and data inconsistencies be generated. This paper presents an approach that uses statistical and geostatistical techniques to identify incorrect and suspicious data and estimate new values to fill gaps and errors. In this research, a spatial database was used to implement these techniques (statistical and geostatistical) and to test and evaluate the climatic data. To evaluate these techniques temperature data set provided by meteorological stations located in Paraná State, were used. As a result, these techniques have proved to be suitable to identify basic errors and historical errors. The spatial validation showed a poor performance by overestimating the amount of incorrect data. Kriging, Inverse of Distance Weighting and Linear Regression estimation techniques showed similar performance in the present error analysis.
gap �filling; meteorological data; statistics; geostatistics; data quality control; spatial database
