Weather Forecasting using Incremental K-means Clustering

Clustering is a powerful tool which has been used in several forecasting works, such as time series forecasting, real time storm detection, flood forecasting and so on. In this paper, a generic methodology for weather forecasting is proposed by the help of incremental K-means clustering algorithm. Weather forecasting plays an important role in day to day applications.Weather forecasting of this paper is done based on the incremental air pollution database of west Bengal in the years of 2009 and 2010. This paper generally uses typical K-means clustering on the main air pollution database and a list of weather category will be developed based on the maximum mean values of the clusters.Now when the new data are coming, the incremental K-means is used to group those data into those clusters whose weather category has been already defined. Thus it builds up a strategy to predict the weather of the upcoming data of the upcoming days. This forecasting database is totally based on the weather of west Bengal and this forecasting methodology is developed to mitigating the impacts of air pollutions and launch focused modeling computations for prediction and forecasts of weather events. Here accuracy of this approach is also measured.

💡 Research Summary

This paper proposes a general methodology for weather forecasting using incremental K-means clustering algorithm, focusing on the air pollution database of West Bengal from 2009 to 2010. The core approach involves initial clustering based on typical K-means applied to the main air pollution dataset and developing a list of weather categories based on maximum mean values of clusters.

When new data arrives, incremental K-means is employed to assign these data points into predefined weather category clusters. This strategy builds up an effective way to predict upcoming weather conditions for subsequent days. The forecasting database is entirely based on the weather patterns in West Bengal and aims at mitigating the impacts of air pollution while enabling focused modeling computations for predicting weather events.

The incremental K-means algorithm works by initially forming clusters from existing data sets, then assigning new incoming data points into the most suitable pre-existing cluster without reprocessing all previous data. This approach is advantageous as it allows for real-time data processing and quick response times, reducing computational costs compared to traditional K-means which processes all data points at once.

The paper measures the accuracy of this method, evaluating its effectiveness in actual weather prediction scenarios. However, since the study focuses on a specific region (West Bengal), further research is needed to understand how it performs under different climatic conditions or geographical locations.

Incremental K-means clustering can be applied beyond just weather forecasting and is particularly useful for real-time data processing where quick responses are necessary. This method offers more efficient and effective results compared to traditional clustering approaches, making it a notable advancement in the field of predictive analytics and environmental monitoring.