Open Access Open Access  Restricted Access Subscription Access

Meteorological Information Examination of Semi-Bone-dry Area of Karnataka Utilizing Relative Significance of Highlights and Versatile Helping classifier

Prajwala T R

Abstract


Meteorological data analysis is obtaining the information from raw data. There is vast amount of data available for weather analysis. Market needs timely and accurate data. Although the weather risk market is more dependent on high-quality data than the local or national economic needs are, the collection and storage of weather data is important because it provides an economic benefit. The semi-arid region of Karnataka namely Madikeri region is considered for data analysis. The relative importance of features is identified for analysis of rainfall data. The adaptive boosting random forest classifier is applied to generate decision rules governing the prediction of rainfall.  The data is collected from Indian Meteorological Department (IMD) for span of 12 years from 2004 to 2016. There are 4825 samples considered for the data analysis. The number of features considered for data analysis is 13 for prediction of rainfall. The validation curve and RMSE values justify the results obtained.


Full Text:

PDF

References


Indian Metrological department IMD http://dsp.imdpune.gov.in/

xiaobo zhang et.al, “Annual and Non-Monsoon Rainfall Prediction Modelling Using SVR-MLP: An Empirical Study From Odisha”, :Fourth International Conference on Computing Method- ologies and Communication, Vol 8, pp. 1302-1310,. 2020

hattopadhyay, et.al Predicting clustered weather patterns: A test case for applications of convolutional neural networks to spatio-temporal climate data. Sci Rep 10, 1317 (2020). https://doi.org/10.1038/s41598-020-57897-9,2020

Min Min , Chen Bai, et.al “Estimating Summertime Precipitation from Himawari-8 and Global Forecast System Based on Machine Learning”, IEEE transactions on geoscience and remote sensing, vol. 57, no. 5,pp.2557-2565 ,May 2019

C.P. Shabariram et.al “Rainfall Analysis and Rainstorm prediction using mapreduce framework”, International Conference on Computer Communica- tion and Informatics (ICCCI), vol34, no 7 pp.657-701,2019

Ali P.Yunusb et.al “Assessment of advanced random forest and decision tree algorithms for modeling rainfall-induced landslide susceptibility in the Izu-Oshima Volcanic Island, Japan”, Science of The Total Environment Volume 662, 20 April 2019, Pages 332-346


Refbacks

  • There are currently no refbacks.