An evaluation of unsupervised and supervised learning algorithms for clustering landscape types in the United States
Bibliographic Data
| ID | 12750705 |
|---|---|
| Authors | Jochen Wendel (Karlsruhe Institute of Technology, corresponding author), Barbara Buttenfield (0000-0001-5961-5809, University of Colorado Boulder), Lawrence V Stanislawski (0000-0002-9437-0576, United States Geological Survey) |
| Year | 2015 |
| Volume | 43 |
| Issue | 3 |
| Pages | 233-249 |
| Publication date | 2015-09-15 |
| Peer Reviewed | Yes |
| Open Access | No |
| Type | ARTICLE |
| Venue | Cartography and Geographic Information Science (JOURNAL) |
| Journal identifiers | ISSN: 1523-0406 • E-ISSN: 1545-0465 |
| Publisher | Taylor & Francis (PUBLISHER • GB) |
| DOI | 10.1080/15230406.2015.1067829 |
| OpenAlex | W1917554948 |
| Language | EN |
| References cited | 32 |
Knowledge of landscape type can inform cartographic generalization of hydrographic features, because landscape characteristics provide an important geographic context that affects variation in channel geometry, flow pattern, and network configuration. Landscape types are characterized by expansive spatial gradients, lacking abrupt changes between adjacent classes; and as having a limited number of outliers that might confound classification. The US Geological Survey (USGS) is exploring methods to automate generalization of features in the National Hydrography Data set (NHD), to associate specific sequences of processing operations and parameters with specific landscape characteristics, thus obviating manual selection of a unique processing strategy for every NHD watershed unit. A chronology of methods to delineate physiographic regions for the United States is described, including a recent maximum likelihood classification based on seven input variables. This research compares unsupervised and supervised algorithms applied to these seven input variables, to evaluate and possibly refine the recent classification. Evaluation metrics for unsupervised methods include the Davies–Bouldin index, the Silhouette index, and the Dunn index as well as quantization and topographic error metrics. Cross validation and misclassification rate analysis are used to evaluate supervised classification methods. The paper reports the comparative analysis and its impact on the selection of landscape regions. The compared solutions show problems in areas of high landscape diversity. There is some indication that additional input variables, additional classes, or more sophisticated methods can refine the existing classification
Cartographic generalization · Cartography · Cluster analysis · Data mining · Generalization · Geography · Machine learning · Outlier · Climate variability and models · Computer Science · Hydrology and Drought Analysis · Hydrology and Watershed Management Studies · Mathematics · Artificial Intelligence
An introduction to recursive partitioning
A Cluster Separation Measure
Well-Separated Clusters and Optimal Fuzzy Partitions
An Examination of Procedures for Determining the Number of Clusters in a Data Set
The Use of Multiple Measurements in Taxonomic Problems
Hierarchical Grouping to Optimize an Objective Function
Random Forests
Silhouettes
Physiographic Divisions of the United States
Physiographic Divisions of the United States
Spatial Clustering Overview and Comparison
Analysis of Properties in Land Form Geography
| Citation velocity | historical |
|---|---|
| Highly cited | No |