Rainfall Estimation Using Transductive Learning

Precipitation is a crucial link in the hydrological cycle, and its spatial and temporal variations are enormous. A knowledge of the amount of regional rainfall is essential to the welfare of society. Rainfall can be estimated remotely, either from ground-based weather radars or from satellite. Despite the large amount of available data provided by satellites, most of them are unlabeled, and the acquisition of labeled data for a learning problem often requires a skilled human agent to manually classify training examples. In this paper we introduce the use of semi-supervised support vector machines for rainfall estimation using images obtained from visible and infrared NOAA satellite channels. The semi-supervised learners combine both labeled and unlabeled data to perform the classification task. Two experiments were performed, one involving traditional SVM and other using semi-supervised SVM (S3VM). The S3VM approach outperforms SVM in our experiments, with can be seen as a good methodology for rainfall satellite estimation, due to the large amount of unlabeled data. The accuracies obtained for SVM and S3VM were, respectively, 90.6% and 95.96%. © 2008 IEEE.4631634Bennett, K.P., Demiriz, A., Semi-supervised support vector machines (1999) Proc. of the 1998 Conf. on Advances in Neural Information Processing Systems II, pp. 368-374. , Cambridge, MA, USA, MIT PressBlum, A., Mitchell, T., Combining labeled and unlabeled data with co-training (1998) COLT' 98: Proceedings of the eleventh annual conference on Computational learning theory, pp. 92-100. , New York, NY, USA, ACM PressChapelle, O., Weston, J., Schölkopf, B., Cluster kernels for semi-supervised learning (2003) NIPS, 15. , ofde Freitas, G.M., de Ávila, A.M.H., Pinto, H.S., Papa, J.P., Classifiers evaluation for the monitoring of the agricultural areas precipitation (2007) Proceedings of the XV Brazilian Congress of AgrometeorologyFukunaga, K., Narendra, P.M., A branch and bound algorithms for computing k-nearest neighbors (1975) IEEE Trans. Computers, 24 (7), pp. 750-753Ghani, R., Combining labeled and unlabeled data for multiclass text categorization (2002) ICML '02: Proceedings of the Nineteenth International Conference on Machine Learning, pp. 187-194. , San Francisco, CA, USA, Morgan Kaufmann Publishers IncHaykin, S., (1994) Neural networks: A comprehensive foundation, , Prentice HallHuang, S.C., Huang, Y.F., Bounds on the number of hidden neurons in multilayer perceptrons (1991) IEEE Transactions on Neural Networks, 2 (1), pp. 47-55Joachims, T., Making large-scale support vector machine learning practical (1998) Advances in Kernel Methods: Support Vector Machines, , MIT Press, Cambridge, MAJoachims, T., Text categorization with support vector machines: Learning with many relevant features (1998) Proceedings of ECML-98, 10th European Conference on Machine Learning, 1398, pp. 137-142. , C. Nédellec and C. Rouveirol, editors, number, Chemnitz, DE, Springer Verlag, Heidelberg, DEKohavi, R., A study of cross-validation and bootstrap for accuracy estimation and model selection (1995) IJCAI, pp. 1137-1145J. McCullagh, K. Bluff, and E. Ebert. A neural network model for rainfall estimation. ANNES '95: Proc. of the 2nd New Zealand Two-Stream Int. Conf. on Artificial Neural Networks and Expert Systems, 00:389, 1995S. Nissen. Implementation of a fast artificial neural network library (FANN), 2003. Department of Computer Science University of Copenhagen (DIKU). Software available at http://leenissen.dk/fann/Papa, J.P., Falcão, A.X., Miranda, P.A.V., Suzuki, C.T.N., Mascarenhas, N.D.A., Design of robust pattern classifiers based on pptimum-path forests (2007) Mathematical Morphology and its Applications to Signal and Image Processing (ISMM), pp. 337-348. , MCT/INPEQi, H., Jiangang, Y., Lixia, D., Semi-supervised classification method for remote sensing images based on support vector machine (2004) Proceedings of the IEEE International Conference on Systems, Man & Cybernetics, pp. 2357-2361Umehara, S., Yamazaki, T., Sugai, Y., A precipitation estimation system based on support vector machine and neural network (2006) Electronics and Communications in Japan, 89 (3), pp. 38-47Vapnik, V.V., (1999) The Nature of Statistical Learning Theory (Information Science and Statistics), , Springer, NovemberWeston, J., Leslie, C., Zhou, D., Elisseeff, A., Noble, W., (2003) Semi-supervised protein classification using cluster kernelsZhu, X., Ghahramani, Z., (2002) Learning from labeled and unlabeled data with label propagatio