Crop Prediction Using KNN Algorithm

Information Technology

India is generally an agricultural country. Now a days the most important emerging field in the real world is agriculture and it is main occupation and backbone to our country. Recent developments in Information Technology for agriculture field has become an interesting research area to predict the crop yield. Crop yield prediction is the methodology to predict yield of the crops using different parameters like PH, temperature, fertilizers and other atmospheric conditions are parameters. We have used combined datasets from different official government websites which includes features like crop name, area, production, temperature, rainfall, humidity and wind speed. After successfully extracting the data set, six machine learning algorithms (logistic regression, random forest, support vector machine, k-nearest neighbor, naive bayes classifier and feed forward neural network) were used to establish models. Among these machine learning models, we used K-Nearest Neighbor(K-NN) algorithm for brief analysis of crop yield. The developed model can have the accuracy of predictions more than 80%. We can further recommend which crop has to be yielded based on the season, climatic conditions and PH of the soil.

This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.