Science Journal of Environmental Research, Volume
2013, September 2013
© Author(s) 2013. This work is distributed under the Creative Commons Attribution 3.0 License.
On A Generalization of a Dynamic Reconstruction-Method for Gap Filling in Daily Temperature Datasets From Weather Networks
Gianmarco Tardivo and Antonio Berti
University of Padua. Department of Agriculture, Food, Natural Resources, Animals, and Environment (DAFNAE).
Viale Dell'Universitą, 16. Legnaro (Padova)-Italy.
Accepted 29 July, 2013; Available Online 1 September 2013
Research in the environmental sciences often makes use of database provided by measuring instruments. Lack of detections or false readings are some important and natural drawbacks of their use.The finding of methods to solve these problems is required to improve the quality of the data and the analysis carried out with them.A dynamic method to fill in the missing values of a dataset, from a network of automatic temperature sensors, was just presented in the international literature.The aim of this paper is to suggest a way to improve this method and generalize it in some of its procedures.
Keywords:reconstructing method; weather network; daily temperature; neural networks; regression trees