Open AccessExtemporize Agriculture Yield with Predictions Based on Water and Soil Properties using Multivariate Analytics and Machine Learning Algorithm
Author(s) -
V Sudha,
Shashank Mohan
Publication year - 2019
Publication title -
international journal of engineering and advanced technology
Language(s) - English
Resource type - Journals
ISSN - 2249-8958
DOI - 10.35940/ijeat.f8137.088619
Subject(s) - multivariate statistics , principal component analysis , partial least squares regression , cropping , agriculture , data analysis , multivariate analysis , computer science , yield (engineering) , agricultural engineering , statistics , machine learning , mathematics , data mining , engineering , geography , materials science , archaeology , metallurgy
Big data have rapidly developed in agriculture that increase the extensive attention of farmers to get extraordinary ideas for future crop development based on soil and water is an essential key factor of agriculture to predict data. In future farmers apply the extracts PCA (Principal component analysis) in the agriculture for crops to find best yield. The level of data is analyzed using PCA and PLS (Projection to latent structure) datasets like Crop data, Soil properties and Water properties such as Linear Regression, Multi Linear Regression, Discriminate Analysis, Partial Least Square, Least squares algorithm is used instead of Multivariate Curve Resolution. Predictive analytics can be used to make a modular decision in farming by observation of actual time data on crops, soil and water data received from different agriculture sources would contain multi-dimensions, the entire content is needed for performing analysis. Multivariate data Analysis based on Partial Least Square Programming model that identifies the cropping pattern to getting maximum yield correlated. The motive of the work is to compare various techniques which give the maximum accuracy of crop.