METHOD FOR PREDICTING RAINFALL TRENDS

Abstract

ABSTRACT A method (100) for predicting rainfall trends, the method (100) comprising the steps of collecting historical rainfall and environmental data from a target geographic region, pre-processing the collected data to compensate for missing values, normalize features and remove outliers, applying non-parametric statistical tests to identify long-term rainfall trends and seasonal variations and generating an aggregated rainfall prediction output by stacking the long-term rainfall trends and seasonal variations using machine learning based meta-model. <>

Specification

Description:FIELD OF THE DISCLOSURE
[0001] This invention generally relates to a field of predicting rainfall trends and in particular relates to a method for predicting rainfall trends in a geographical area.
BACKGROUND

[0002] The subject matter discussed in the background section should not be assumed to be prior art merely as a result of its mention in the background section. Similarly, a problem mentioned in the background section or associated with the subject matter of the background section should not be assumed to have been previously recognized in the prior art. The subject matter in the background section merely represents different approaches, which in and of themselves may also correspond to implementations of the claimed technology.
[0003] Rainfall prediction plays a crucial role in supporting agriculture, disaster management, and water resource planning. In regions where the economy and local infrastructure rely heavily on accurate rainfall data, such as in agricultural zones, precise prediction methods , Claims:1. A method (100) for predicting rainfall trends, the method (100) comprising the steps of:
collecting historical rainfall and environmental data from a target geographic region;
pre-processing the collected data to compensate for missing values, normalize features and remove outliers;
applying non-parametric statistical tests to identify long-term rainfall trends and seasonal variations; and
generating an aggregated rainfall prediction output by stacking the long-term rainfall trends and seasonal variations using machine learning based meta-model.

2. The method (100) as claimed in claim 1, further comprising evaluating the meta-model's performance using metrics to assess prediction accuracy and reliability, wherein the metrics include Mean Absolute Error (MAE), Mean Squared Error (MSE), Root Mean Squared Error (RMSE), and R² score.

3. The method (100) as claimed in claim 1, further comprising visualising the collected data through time-series graph and heat-maps to analyse spatial and temporal distribut

Documents