Successful land cover prediction can provide promising insights in the applications where manual labeling is extremely difficult. However, traditional machine learning models are plagued by temporal variation and noisy features when directly applied to land cover prediction. Moreover, these models cannot take fully advantage of the spatio-temporal relationship involved in land cover transitions. In this paper, we propose a novel spatio-temporal framework to discover the transitions among land covers and at the same time conduct classification at each time step. Based on the proposed model, we incrementally update the model parameters in the prediction process, thus to mitigate the impact of the temporal variation. Our experiments in two challenging land cover applications demonstrate the superiority of the proposed method over multiple baselines. In addition, we show the efficacy of spatio-temporal transition modeling and incremental learning through extensive analysis.
|Original language||English (US)|
|Title of host publication||Proceedings of the 17th SIAM International Conference on Data Mining, SDM 2017|
|Editors||Nitesh Chawla, Wei Wang|
|Publisher||Society for Industrial and Applied Mathematics Publications|
|Number of pages||9|
|State||Published - Jun 9 2017|
|Event||17th SIAM International Conference on Data Mining, SDM 2017 - Houston, United States|
Duration: Apr 27 2017 → Apr 29 2017
|Name||Proceedings of the 17th SIAM International Conference on Data Mining, SDM 2017|
|Other||17th SIAM International Conference on Data Mining, SDM 2017|
|Period||4/27/17 → 4/29/17|
Bibliographical noteFunding Information:
This work was funded by the NSF Awards 1029711 and 0905581, and the NASA Award NNX12AP37G. Access to computing facilities was provided by NASA Earth Exchange and Minnesota Supercomputing Institute.