Rain is vital for environmental and human processes such as temperature regulation, vegetation growth, agriculture, power generation, domestic use, and others. However, most of the previous research has focused mainly on the prediction of the probability of occurrence of rainfall or the rain rate estimation, leaving aside the amount of rain. Most of the previous studies use information on the same spatial scale, losing important information on other scales that affect rain-related climatological processes. In this paper, we present an approximation for estimating daily rainfall using data from Meteoblue, GOES, TRMM and MODIS Vegetation indices on different spatial scales based on Bagging with Random Forest.
Valencia-Payan, C., & Corrales, J. C. (2018). A multiscale based rainfall amount prediction using multiple classifier system. In Advances in Intelligent Systems and Computing (Vol. 687, pp. 16–28). Springer Verlag. https://doi.org/10.1007/978-3-319-70187-5_2