A platform for research: civil engineering, architecture and urbanism
A platform for research: civil engineering, architecture and urbanism
Combining k-nearest-neighbor models for annual peak breakup flow forecasting
https://orcid.org/0000-0003-3186-1156
AbstractIn practice, water resources managers and river forecasters often face the problem in identifying from the historical record years that show a similar pattern of weather and river conditions as the current year is following. The k-nearest neighbor (kNN) algorithm is such a type of machine learning method, where no assumptions on the dataset distributions are made, but a minimal (no explicit) training stage is required. This is especially useful in river ice forecasting where weather and river condition indicators often do not obey the typical theoretical assumptions; the complex river ice mechanisms are difficult to directly quantify. However, few applications of kNN to river ice studies have been reported. Since the predictive performance of a single kNN is limited, we combine multiple KNN models (first-level) based on different numbers of inputs which are linearly or nonlinearly correlated to annual peak breakup flow (APBF); we use both simple average methods and kNN models as combining models (second-level), and we apply the kNN-based combination models to APBF forecasting of the Smoky River at Watino, Canada. The Mahalanobis distance is chosen in kNN since neither the standardization of input variables nor the assignments of weights to variables are required. The historical breakup data at this site for the past 33years (1980 to 2012) were collected to facilitate the performance comparison of models. The results show that both training and validation performances of the combining models are substantially better than those of member models. The proposed framework can be potentially applied to various forecasting problems in water resources management practice.
HighlightsMultiple kNN models with linearly and nonlinearly correlated inputs are combined.The combining models are either a kNN model or the simple average method.The mutual information index is used to select indicators with nonlinearity.The models are applied to forecasting APBF of Smoky River at Watino, Canada.The performances of combining models are better than member models in LOOCV.
Combining k-nearest-neighbor models for annual peak breakup flow forecasting
https://orcid.org/0000-0003-3186-1156
AbstractIn practice, water resources managers and river forecasters often face the problem in identifying from the historical record years that show a similar pattern of weather and river conditions as the current year is following. The k-nearest neighbor (kNN) algorithm is such a type of machine learning method, where no assumptions on the dataset distributions are made, but a minimal (no explicit) training stage is required. This is especially useful in river ice forecasting where weather and river condition indicators often do not obey the typical theoretical assumptions; the complex river ice mechanisms are difficult to directly quantify. However, few applications of kNN to river ice studies have been reported. Since the predictive performance of a single kNN is limited, we combine multiple KNN models (first-level) based on different numbers of inputs which are linearly or nonlinearly correlated to annual peak breakup flow (APBF); we use both simple average methods and kNN models as combining models (second-level), and we apply the kNN-based combination models to APBF forecasting of the Smoky River at Watino, Canada. The Mahalanobis distance is chosen in kNN since neither the standardization of input variables nor the assignments of weights to variables are required. The historical breakup data at this site for the past 33years (1980 to 2012) were collected to facilitate the performance comparison of models. The results show that both training and validation performances of the combining models are substantially better than those of member models. The proposed framework can be potentially applied to various forecasting problems in water resources management practice.
HighlightsMultiple kNN models with linearly and nonlinearly correlated inputs are combined.The combining models are either a kNN model or the simple average method.The mutual information index is used to select indicators with nonlinearity.The models are applied to forecasting APBF of Smoky River at Watino, Canada.The performances of combining models are better than member models in LOOCV.
Combining k-nearest-neighbor models for annual peak breakup flow forecasting
https://orcid.org/0000-0003-3186-1156
AbstractIn practice, water resources managers and river forecasters often face the problem in identifying from the historical record years that show a similar pattern of weather and river conditions as the current year is following. The k-nearest neighbor (kNN) algorithm is such a type of machine learning method, where no assumptions on the dataset distributions are made, but a minimal (no explicit) training stage is required. This is especially useful in river ice forecasting where weather and river condition indicators often do not obey the typical theoretical assumptions; the complex river ice mechanisms are difficult to directly quantify. However, few applications of kNN to river ice studies have been reported. Since the predictive performance of a single kNN is limited, we combine multiple KNN models (first-level) based on different numbers of inputs which are linearly or nonlinearly correlated to annual peak breakup flow (APBF); we use both simple average methods and kNN models as combining models (second-level), and we apply the kNN-based combination models to APBF forecasting of the Smoky River at Watino, Canada. The Mahalanobis distance is chosen in kNN since neither the standardization of input variables nor the assignments of weights to variables are required. The historical breakup data at this site for the past 33years (1980 to 2012) were collected to facilitate the performance comparison of models. The results show that both training and validation performances of the combining models are substantially better than those of member models. The proposed framework can be potentially applied to various forecasting problems in water resources management practice.
HighlightsMultiple kNN models with linearly and nonlinearly correlated inputs are combined.The combining models are either a kNN model or the simple average method.The mutual information index is used to select indicators with nonlinearity.The models are applied to forecasting APBF of Smoky River at Watino, Canada.The performances of combining models are better than member models in LOOCV.
Combining k-nearest-neighbor models for annual peak breakup flow forecasting
Sun, Wei (author) / Trevor, Bernard (author)
Cold Regions, Science and Technology ; 143 ; 59-69
2017-08-21
11 pages
Article (Journal)
Electronic Resource
English
| British Library Conference Proceedings | 2005
Nearest neighbor distances in uniaxial fiber composites
| British Library Online Contents | 2004