 |
| Titel |
Assessment of hydrological and seasonal controls over the nitrate flushing from a forested watershed using a data mining technique |
| VerfasserIn |
S. Rusjan, M. Mikoš  |
| Medientyp |
Artikel
|
| Sprache |
Englisch
|
| ISSN |
1027-5606
|
| Digitales Dokument |
URL |
| Erschienen |
In: Hydrology and Earth System Sciences ; 12, no. 2 ; Nr. 12, no. 2 (2008-04-01), S.645-656 |
| Datensatznummer |
250010583
|
| Publikation (Nr.) |
 copernicus.org/hess-12-645-2008.pdf |
|
|
|
|
|
| Zusammenfassung |
| A data mining, regression tree algorithm M5 was used to review the role of
mutual hydrological and seasonal settings which control the streamwater
nitrate flushing during hydrological events within a forested watershed in
the southwestern part of Slovenia, characterized by distinctive flushing,
almost torrential hydrological regime. The basis for the research was an
extensive dataset of continuous, high frequency measurements of seasonal
meteorological conditions, watershed hydrological responses and streamwater
nitrate concentrations. The dataset contained 16 recorded hydrographs
occurring in different seasonal and hydrological conditions. Based on
predefined regression tree pruning criteria, a comprehensible regression
tree model was obtained in the sense of the domain knowledge, which was able
to adequately describe most of the streamwater nitrate concentration
variations (RMSE=1.02 mg/l-N; r=0.91). The attributes which were found to be
the most descriptive in the sense of streamwater nitrate concentrations were
the antecedent precipitation index (API) and air temperatures in the preceding
periods. The model was most successful in describing streamwater
concentrations in the range 1–4 mg/l-N, covering large proportion of the
dataset. The model performance was little worse in the periods of high
streamwater nitrate concentration peaks during the summer hydrographs (up to
7 mg/l-N) but poor during the autumn hydrograph (up to 14 mg/l-N) related to
highly variable hydrological conditions, which would require a less robust
regression tree model based on the extended dataset. |
| |
|
| Teil von |
|
|
|
|
|
|
|
|