Prediction Of Rainfall With A Machine Learning Approach
Main Article Content
Abstract
Machine Learning (ML) is a versatile method for working with complicated structures. This thesis focuses on creating a machine learning-based system for forecasting rainfall. The proposed ensemble model is provided meteorological data correlated with rainfall variables as an input. We are gathering data from IMD for this work (Indian Meteorological department). Validation and verification was carried out using ensemble learning with Support Vector Regression and Random Forest model (SVR-RF). Validation is conducted using usable measures from a meteorological department over a certain area, which aids in predicting the likelihood of rainfall. As a result, a novel solution is built to improve the system's efficiency by combining the promise of SVR-RF with the accuracy of rainfall prediction. By calculating the precipitation characteristics, the recorded data is used to forecast rainfall with continuous observations over a given area. The proposed model aids in the establishment of a partnership between rainfall variables and other similar variables, which benefits the proposed SVR-RF model's potential. Mean Absolute Error (MAE), Root Mean Square (RMS), and classification precision (day and monthly basis) are the output metrics used in the simulation. The proposed model has the ability to outperform current prediction models. The proposed model predicts rainfall effectively using a variety of measures such as temperature, precipitation, and so on. This model increases machine efficiency thus lowering error rates.
Downloads
Metrics
Article Details
Licensing
TURCOMAT publishes articles under the Creative Commons Attribution 4.0 International License (CC BY 4.0). This licensing allows for any use of the work, provided the original author(s) and source are credited, thereby facilitating the free exchange and use of research for the advancement of knowledge.
Detailed Licensing Terms
Attribution (BY): Users must give appropriate credit, provide a link to the license, and indicate if changes were made. Users may do so in any reasonable manner, but not in any way that suggests the licensor endorses them or their use.
No Additional Restrictions: Users may not apply legal terms or technological measures that legally restrict others from doing anything the license permits.