Abstract
Machine learning algorithms (MLAs) are often applied to identify Land Use and Land Cover (LULC) changes, but typically to only a limited set of imagery. This leaves the consistency of MLAs performance through time poorly understood. The research objective was therefore to compare the performance of six MLAs across a time-series of Landsat imagery (1979, 1992, 2003, 2014), all processed in the same manner. Here Support Vector Machines (SVM), K-Nearest Neighbours (KNN), Random Forests (RF), Learning Vector Quantization (LVQ), Recursive Partitioning, Regression Trees (RPART) and Stochastic Gradient Boosting (GBM) were evaluated. The results demonstrated that SVM achieved higher overall accuracies and kappa coefficients, and a slightly improved fit at individual class level, than the second best classifier RF. Both classifiers clearly outperformed the other algorithms. These results suggest that SVMs (or RFs) should be prioritised when classifying time-series imagery for LULC change detection.
Original language | English |
---|---|
Title of host publication | International Geoscience and Remote Sensing Symposium (IGARSS) |
Editors | Ji Wu, Yaqiu Jin |
Publisher | IEEE, Institute of Electrical and Electronics Engineers |
Pages | 5165-5168 |
Number of pages | 4 |
Volume | 2016-November |
ISBN (Electronic) | 9781509033324 |
DOIs | |
Publication status | Published - 1 Nov 2016 |
Event | 36th IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2016 - Beijing, China Duration: 10 Jul 2016 → 15 Jul 2016 |
Conference
Conference | 36th IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2016 |
---|---|
Country/Territory | China |
City | Beijing |
Period | 10/07/16 → 15/07/16 |