Spectral-spatial multi-feature classification of remote sensing big data based on a random forest classifier for land cover mapping
- 671 Downloads
Supplementary information, such as multi-temporal spectral data and textural features, has the potential to improve land cover classification accuracy. However, given the larger volumes of remote sensing data, it is difficult to utilize all the features of remote sensing big data having different times and spatial resolutions. Inefficiency is also a large problem when dealing with large area land cover mapping. In this study, a new mode of incorporating spatial and temporal dependencies in a complex region employing the random forests (RFs) classifier was utilized. To map land covers, spring and autumn spectral images and their spectral indexes, textural features obtained from Landsat 5 were selected, and an importance measure variable was used to reduce the data’s dimension. In addition to randomly selecting the variable, we used random sampling to furthest decrease the generalization error in RF. The results showed that utilizing random sampling, multi-temporal spectral image and texture features, the classification of the Wuhan urban agglomeration, China, using RF performed well. The RF algorithm yielded an overall accuracy of 89.2% and a Kappa statistic of 0.8522, indicating high model performance. In addition, the variable importance measures demonstrated that the type of textural features was extremely important for intra-class separability. The RF model has transitivity. The algorithm can be extended by choosing a set of appropriate features for signature extension over large areas or in time-series of Landsat imagery. Land cover mapping might be more economical and efficient if no-cost imagery is used.
KeywordsLand cover mapping Random forests (RFs) Random sampling Spectral features Temporal features Textural features Feature selection (FS) Wuhan urban agglomeration
This research has been supported by the National Research Program on Global Changes and Adaptation: Rapid production method of large scale global change products (2016YFA0600302) and by National Ecological Environment Change Assessment by Remote Sensing Survey Project 2000–2010 (STSN-10-03) Grants.
- 5.Zhang, X.M., He, G.J., Wang, M.M., Zhang, Z.M., Jiao, W.L., Peng, Y., Wang, G.Z., Liu, H.C., Long, T.F.: Eco-environmental assessment and analysis of Tonglvshan mining area in Daye City, Hubei Province based on spatiotemporal methodology. In: 2015 International Workshop on Spatiotemporal Computing. ISPRS Annals of the Photogrammetry, Fairfax, VA, USA, pp. 211–215 (2015)Google Scholar
- 26.Zhu, Z., Gallant, A., Woodcock, C., Pengra, B., Olofsson, P., Loveland, T., Jin, S., Dahal, D., Yang, L., Auch, R.: Optimizing selection of training and auxiliary data for operational land cover classification for the LCMAP initiative. ISPRS J. Photogramm. Remote Sens. 122, 206–221 (2016)CrossRefGoogle Scholar
- 30.Rouse, J., Haas, R., Schell, J., Deering, D.: Monitoring vegetation systems in the great plains with ERTS. Third ERTS Symposium, NASA, pp. 309–317 (1973)Google Scholar
- 31.Haboudane, D., Miller, J.R., Pattey, E., Zarco-Tejada, P.J., Strachan, I.B.: Hyperspectral vegetation indices and novel algorithms for predicting green LAI of crop canopies: modeling and validation in the context of precision agriculture. Remote Sens. Environ. 90, 337–352 (2004)CrossRefGoogle Scholar