Geographical Transferability of Pretrained K-Means Clustering–Artificial Neural Network Model for Disaggregation of Rainfall Data in an Indian Monsoon Climate

Abstract

High temporal resolution rainfall data are among the most demanded resources for water resource engineers. In modern times, this need has only multiplied day by day due to the need for training large parameter-heavy models for the prediction of climatic features, analysis of extreme rainfall, etc. However, the availability of such high temporal resolution data is low, which can cause hindrances in research or development projects in several regions. It is therefore imperative to find newer and better models for the disaggregation of rainfall data from lower to higher temporal resolutions, such as a model that uses deep learning neural networks. The main issue with such a model is the requirement for historical rainfall data at different time scales for training, testing, and validating prior to use in practical scenarios, data that may not always be available for all regions necessary. In this paper, an attempt has been to test the accuracy and applicability of pretrained models for the purpose of disaggregating rainfall in other geographical locations, thus reducing the requirement for historical rainfall data for training and validation purposes. A large data set comprising rainfall data from 68 rain gauge stations across the Indian subcontinent has been used to test models pretrained using rainfall data from seven major stations in India (Bikaner, Chennai, Cherrapunji, Delhi, Kolkata, Mumbai, and Mangalore). The pretrained models are tested in their ability to conserve extreme rainfall characteristics by comparing intensity–duration–frequency (IDF) curves generated from observed and disaggregated rainfall, further which the errors in these IDF curves are used to generate heatmaps for the country using the inverse distance weighted interpolation method. At the end of this paper, a map is provided that covers the entire country of study, detailing that a pretrained model can be used for a certain region based on its accuracy of disaggregation and proximity to the city of pretraining data.