Ensemble fine tuned multi layer perceptron for predictive analysis of weather patterns and rainfall forecasting from satellite data (Record no. 22712)

MARC details
000 -LEADER
fixed length control field a
003 - CONTROL NUMBER IDENTIFIER
control field OSt
005 - DATE AND TIME OF LATEST TRANSACTION
control field 20250424142651.0
008 - FIXED-LENGTH DATA ELEMENTS--GENERAL INFORMATION
fixed length control field 250424b xxu||||| |||| 00| 0 eng d
040 ## - CATALOGING SOURCE
Original cataloging agency AIKTC-KRRC
Transcribing agency AIKTC-KRRC
100 ## - MAIN ENTRY--PERSONAL NAME
9 (RLIN) 25981
Author Surana, Amruta V.
245 ## - TITLE STATEMENT
Title Ensemble fine tuned multi layer perceptron for predictive analysis of weather patterns and rainfall forecasting from satellite data
250 ## - EDITION STATEMENT
Volume, Issue number Vol.15(2), Oct
260 ## - PUBLICATION, DISTRIBUTION, ETC.
Place of publication, distribution, etc. Chennai
Name of publisher, distributor, etc. ICT Academy
Year 2024
300 ## - PHYSICAL DESCRIPTION
Pagination 3491-3496p.
520 ## - SUMMARY, ETC.
Summary, etc. The accurate prediction of weather patterns and rainfall forecasting is<br/>critical for various sectors, including agriculture, disaster<br/>management, and water resource planning. Traditional models often<br/>struggle to capture the complex interactions between atmospheric<br/>variables, particularly when integrating diverse types of satellite data<br/>(binary, categorical, and numerical). To address this challenge, an<br/>ensemble fine-tuned multi-layer perceptron (MLP) model is developed,<br/>combining the strengths of multiple machine learning techniques for<br/>more robust predictions. The primary problem is the difficulty in<br/>handling mixed data types while maintaining high prediction accuracy.<br/>Satellite data, including binary indicators (e.g., cloud presence),<br/>categorical features (e.g., cloud types), and numerical variables (e.g.,<br/>temperature, humidity, and wind speed), provide rich information but<br/>require specialized processing for effective forecasting. The proposed<br/>method involves fine-tuning an ensemble of MLP models with<br/>backpropagation, dropout regularization, and batch normalization to<br/>reduce overfitting and enhance generalization. The ensemble<br/>integrates predictions from individual MLP models, each trained on<br/>different subsets of features (binary, categorical, numerical). This<br/>technique allows the model to leverage complementary strengths and<br/>produce more accurate rainfall forecasts. Satellite data is preprocessed<br/>and normalized before training, and categorical variables are one-hot<br/>encoded to ensure compatibility with the MLP architecture. Results<br/>from testing on historical satellite weather datasets demonstrate<br/>significant improvements in forecast accuracy. The ensemble MLP<br/>achieved an accuracy of 91.3%, with a precision of 90.7%, recall of<br/>89.5%, and an F1-score of 90.1%. The model performed exceptionally<br/>well in identifying critical rainfall events, reducing false positives by<br/>12% compared to traditional models.
650 #0 - SUBJECT ADDED ENTRY--TOPICAL TERM
9 (RLIN) 4622
Topical term or geographic name entry element Computer Engineering
700 ## - ADDED ENTRY--PERSONAL NAME
9 (RLIN) 25982
Co-Author Pawar, Suvarna Eknath
773 0# - HOST ITEM ENTRY
Title ICTACT Journal on Soft Computing (IJSC)
Place, publisher, and date of publication Chennai ICT Academy
856 ## - ELECTRONIC LOCATION AND ACCESS
URL https://ictactjournals.in/paper/IJSC_Vol_15_Iss_2_Paper_3_3491_3496.pdf
Link text Click here
942 ## - ADDED ENTRY ELEMENTS (KOHA)
Source of classification or shelving scheme Dewey Decimal Classification
Koha item type Articles Abstract Database
Holdings
Withdrawn status Lost status Source of classification or shelving scheme Damaged status Not for loan Home library Current library Shelving location Date acquired Total Checkouts Barcode Date last seen Price effective from Koha item type
    Dewey Decimal Classification     School of Engineering & Technology School of Engineering & Technology Archieval Section 24/04/2025   2025-0661 24/04/2025 24/04/2025 Articles Abstract Database
Unique Visitors hit counter Total Page Views free counter
Implemented and Maintained by AIKTC-KRRC (Central Library).
For any Suggestions/Query Contact to library or Email: librarian@aiktc.ac.in | Ph:+91 22 27481247
Website/OPAC best viewed in Mozilla Browser in 1366X768 Resolution.