Early Prediction of Extreme Rainfall Events: A Deep Learning Approach
Prediction of heavy rainfall is an extremely important problem in the field of meteorology as it has a great impact on the life and economy of people. Every year many people in different parts of the world suffer from the severe consequences of heavy rain
- PDF / 1,023,775 Bytes
- 14 Pages / 439.37 x 666.142 pts Page_size
- 6 Downloads / 213 Views
Department of Computer Science and Engineering, Indian Institute of Technology, Kharagpur, India [email protected], {sudeshna,pabitra}@cse.iitkgp.ernet.in 2 Department of Civil Engineering, Indian Institute of Technology, Bombay, India [email protected]
Abstract. Prediction of heavy rainfall is an extremely important problem in the field of meteorology as it has a great impact on the life and economy of people. Every year many people in different parts of the world suffer from the severe consequences of heavy rainfall like flood, spread of diseases, etc. We have proposed a model based on deep neural network to predict extreme rainfall from the previous climatic parameters. Our model comprising of a stacked auto-encoder has been tested for Mumbai and Kolkata, India, and found to be capable of predicting heavy rainfall events over both these regions. The model is able to predict extreme rainfall events 6 to 48 h before their occurrence. However it also predicts several false positives. We compare our results with other methods and find our method doing much better than the other methods used in literature. Predicting heavy rainfall 1 to 2 days earlier is a difficult task and such an early prediction can help in avoiding a lot of damages. This is where we find that our model can give a promising solution. Compared to the conventional methods used, our method reduces the number of false alarms; on further analysis of our results we find that in many cases false alarm has been raised when there has been rainfall in the surrounding regions. Thus our model generates warning for heavy rain in surrounding regions as well. Keywords: Machine learning
1
· Deep learning · Stacked auto-encoder
Introduction
Early prediction of heavy rainfall has always been a challenge in the field of weather forecasting. Early rainfall alert helps in relocating the population which could be affected, operating the flood control systems effectively, preparing the disaster mitigation team, etc. which minimizes the social and economic losses. This problem has become even more challenging with changing climatic patterns. According to [7] extreme rainfall events are expected to increase in changing climate. Therefore a proper scientific understanding of the rainfall extremes has become very important for correct prediction. Every year some metropolitan c Springer International Publishing Switzerland 2016 P. Perner (Ed.): ICDM 2016, LNAI 9728, pp. 154–167, 2016. DOI: 10.1007/978-3-319-41561-1 12
Early Prediction of Extreme Rainfall Events: A Deep Learning Approach
155
cities in India specially Mumbai and Kolkata experience very heavy rainfall during monsoon which brings life to a standstill in these places. Both these regions are urbanised and have high population of people living here, this makes it extremely difficult to take preparatory measures like relocation, rainfall alert broadcasting, etc. for high rainfall in a short notice like in 6 h or even less. Currently, weather prediction is mainly based on numerical weather prediction (NW
Data Loading...
