.

ISSN 2063-5346
For urgent queries please contact : +918130348310

COMBINING CROP MODELS AND REMOTE SENSING FOR YIELD PREDICTION USING KNN ALGORITHM OVER K-MEANS ALGORITHM

Main Article Content

B. Bitchi Reddy, J. Chenni Kumaran
» doi: 10.31838/ecb/2023.12.sa1.326

Abstract

Aim: The combination of crop models and remote sensing to yield prediction using KNN Algorithm over KMeans Algorithm. Materials and Methods: When implementing an accurate prediction model it might not be sufficient to just consider one or two parameters. Data about Rainfall, temperature, humidity and various other factors are collected and analyzed. This analysis will be fed to the prediction model. Based on the Previous Collected Datasets, following KNN Algorithm, K-means Algorithm, the upcoming Crop Yield can be predicted with calculations. Results: By using Jupyter notebook and the previous datasets of crop yield prediction, after iterating the datasets using KNN Algorithm 93% accuracy is obtained and using K-means algorithm 86% accuracy is obtained on the other hand. Since the significance is around 0.023, there is statistically a significant difference among the study group with (p < 0.05). Conclusion: After using iterations with KNN algorithm it yields 93%(0.93) and K-means gives 86%(0.86). So it can be said that by using KNN Algorithm more Accuracy is obtained than K-means algorithm.

Article Details