Environmental Science
6 years ago

SVM outperforms Bayesian algorithms in predicting landslide susceptibility zones in India

1 view
Geocarto International
A comparison of Support Vector Machines and Bayesian algorithms for landslide susceptibility modelling
Binh Thai Pham, Indra Prakash, Khabat Khosravi, Kamran Chapi, Phan Trọng Trịnh, Trinh Quoc Ngo, Seyed Vali Hosseini, Dieu Tien Bui

Paper Summary

The article compares different methods for predicting landslides in a specific area in India. They used historical landslide data and various factors to create models. The results show that Support Vector Machines (SVM) had the best prediction accuracy, followed by Naïve Bayes Tree (NBT), Decision Table Naïve Bayes (DTNB), Bayes network (BN), and Naïve Bayes (NB). This means SVM is a reliable model for assessing landslide risk.

Related papers

Theme background image
Computer Science
a year ago

PLN Customer Sentiment Analysis Reveals Public Frustration with Service Quality

Data Mining
Multimedia Learning
Expert Systems Development
Theme background image
Computer Science
a year ago

Boosting accuracy in text classification with Support Vector Machine outperforms other models

Multi-label Classification
Phishing Detection
Machine Learning
Theme background image
Environmental Science
3 years ago

Machine Learning Boosts Abu Dhabi Drinking Water Quality Monitoring Accuracy

Quality Monitoring
Wastewater Monitoring
Hydrological Modeling