A novel rainfall prediction method has been proposed. In the present work rainfall prediction in Southern part of West Bengal (India) has been conducted. A two-step method has been employed. Greedy forward selection algorithm is used to reduce the feature set and to find the most promising features for rainfall prediction. First, in the training phase the data is clustered by applying k-means algorithm, then for each cluster a separate Neural Network (NN) is trained. The proposed two step prediction model (Hybrid Neural Network or HNN) has been compared with MLP-FFN classifier in terms of several statistical performance measuring metrics. The data for experimental purpose is collected by Dumdum meteorological station (West Bengal, India) over the period from 1989 to 1995. The experimental results have suggested a reasonable improvement over traditional methods in predicting rainfall. The proposed HNN model outperformed the compared models by achieving 84.26% accuracy without feature selection and 89.54% accuracy with feature selection.

Rainfall prediction using hybrid neural network approach

The present work proposes a hybrid neural network based model for rainfall prediction in the Southern part of the state West Bengal of India. The hybrid model is a multistep method. Initially, the data is clustered into a reasonable number of clusters by applying fuzzy c-means algorithm, then for every cluster a separate Neural Network (NN) is trained with the data points of that cluster using well known metaheuristic Flower Pollination Algorithm (FPA). In addition, as a preprocessing phase a feature selection phase is included. Greedy forward selection algorithm is employed to find the most suitable set of features for predicting rainfall. To establish the ingenuity of the proposed hybrid prediction model (Hybrid Neural Network or HNN) has been compared with two well-known models namely multilayer perceptron feed-forward network (MLP-FFN) using different performance metrics. The data set for simulating the model is collected from Dumdum meteorological station (West Bengal, India), recorded with in the 1989 to 1995. The simulation results have revealed that the proposed model is significantly better than traditional methods in predicting rainfall.

Hybrid neural network based rainfall prediction supported by flower pollination algorithm

Prediction of humidity is one important and challenging task that needs lot of attention and study for analyzing atmospheric conditions, specially the warm weather. Advent of digital computers and development of data driven artificial intelligence approaches like Artificial Neural Networks (ANN) have helped in numerical prediction of humidity. However, very few works have been done till now in this area. The present study developed an ANN model based on the past observations of several meteorological parameters like temperature, humidity, air pressure and vapour pressure as an input for training the model. The novel architecture of the proposed model contains several multilayer perceptron network (MLP) to realize better performance. The model is enriched by analysis of several alternative models like online feature selection MLP (FSMLP) and self organizing feature map MLP (SOFM-MLP). The improvement of the performance in the prediction accuracy has been demonstrated by the selection of the appropriate features. The FSMLP is used as preprocessor to select good features. The results obtained after applying the model indicate that it is well suitable for humidity as well as warm weather prediction over large geographical areas.

Better prediction of humidity using Artificial Neural Network

Prediction of Atmospheric Pressure is one important and challenging task that needs lot of attention and study for analyzing atmospheric conditions. Advent of digital computers and development of data driven artificial intelligence approaches like Artificial Neural Networks (ANN) have helped in numerical prediction of pressure. However, very few works have been done till now in this area. The present study developed an ANN model based on the past observations of several meteorological parameters like temperature, humidity, air pressure and vapour pressure as an input for training the model. The novel architecture of the proposed model contains several multilayer perceptron network (MLP) to realize better performance. The model is enriched by analysis of alternative hybrid model of k-means clustering and MLP. The improvement of the performance in the prediction accuracy has been demonstrated by the automatic selection of the appropriate cluster
.

http://www.ijorcs.org/uploads/archive/Vol3-Issue-1-02-prediction-of-atmospheric-pressure-at-ground-level-using-artificial-neural-network.pdf

Prediction of Atmospheric Pressure at Ground Level using Artificial Neural Network

Analysis of meteorological attributes often involves the investigation of other secondary attributes which exhibit high spatial correlation with the primary attribute and among themselves. For multivariate spatial analysis, one of the major research challenges is to choose the influential secondary attributes with respect to the primary one and rank them accordingly as per their degree of influence. This research work focuses on electing the most suitable secondary attribute(s) which is/are correlated with the primary and prioritize them individually or as a group, for the corresponding spatial analysis. Time-series forecasting of the meteorological attributes has been chosen as the candidate analysis technique for the case study. A Granger causality test based approach is carried out to determine how a group of secondary time-series is statistically significant to forecast the primary. Among several meteorological attributes, the rainfall is chosen as the primary time-series, and the soil moisture, relative humidity, and land surface temperature are considered as the secondary time-series to forecast the rainfall.

Exploring spatial dependency of meteorological attributes for multivariate analysis: A granger causality test approach

In this paper a neural network based method of local rainfall prediction is proposed. This method is developed based on past observations on various atmospheric parameters such as temperature, relative humidity, vapor presser, etc. We propose a neural network model whose architecture combines several multilayer perceptron networks (MLPs) to realize better performance after capturing the seasonality effect in the atmospheric data. We also demonstrate that the use of appropriate features can further improve the performance in prediction accuracy. These observations inspired us to use a feature selection MLP, FSMLP, (instead of MLP) which can select good features on-line while learning the prediction task. The FSMLP is used as a preprocessor to select good features. The combined use of FSMLP and SOFM-MLP results in a network system that uses only very few inputs but can produce good prediction.

Bimal Dutta

Papers

A connectionist model for rainfall prediction