Assessing the Generalization of Machine Learning-Based Slope Failure Prediction to New Geographic Extents
Autor: | Shannon Marie Maynard, Kurt Donaldson, Maneesh Sharma, Caleb M. Malay, J. Steven Kite, Aaron E. Maxwell |
---|---|
Jazyk: | angličtina |
Rok vydání: | 2021 |
Předmět: |
LiDAR
010504 meteorology & atmospheric sciences Geography Planning and Development spatial predictive modeling 0211 other engineering and technologies Terrain light detection and ranging 02 engineering and technology Machine learning computer.software_genre 01 natural sciences Cohen's kappa Earth and Planetary Sciences (miscellaneous) Computers in Earth Sciences generalization 021101 geological & geomatics engineering 0105 earth and related environmental sciences Mathematics landslides Geography (General) Receiver operating characteristic business.industry digital terrain analysis Probabilistic logic slope failures Spatial heterogeneity Random forest Lidar machine learning G1-922 Artificial intelligence F1 score business computer random forest |
Zdroj: | ISPRS International Journal of Geo-Information, Vol 10, Iss 293, p 293 (2021) ISPRS International Journal of Geo-Information Volume 10 Issue 5 |
ISSN: | 2220-9964 |
Popis: | Slope failure probabilistic models generated using random forest (RF) machine learning (ML), manually interpreted incident points, and light detection and ranging (LiDAR) digital terrain variables are assessed for predicting and generalizing to new geographic extents. Specifically, models for four Major Land Resource Areas (MLRAs) in the state of West Virginia in the United States (US) were created. All region-specific models were then used to predict withheld validation data within all four MLRAs. For all validation datasets, the model trained using data from the same MLRA provided the highest reported overall accuracy (OA), Kappa statistic, F1 Score, area under the receiver operating characteristic curve (AUC ROC), and area under the precision-recall curve (AUC PR). However, the model from the same MLRA as the validation dataset did not always provide the highest precision, recall, and/or specificity, suggesting that models extrapolated to new geographic extents tend to either overpredict or underpredict the land area of slope failure occurrence whereas they offer a better balance between omission and commission error within the region in which they were trained. This study highlights the value of developing region-specific inventories, models, and high resolution and detailed digital elevation data, since models may not generalize well to new geographic extents, potentially resulting from spatial heterogeneity in landscape and/or slope failure characteristics. |
Databáze: | OpenAIRE |
Externí odkaz: |