Machine Learning Techniques to Improve Productive Planting in Agriculture Using Multi Valued Datasets and Classification Methods

Abstract

Changes in ecological factors, for example, water quality, soil quality, and contamination factors lead to illnesses in food creating plants. Distinguishing plant illness is a truly challenging errand in horticulture. Plant illnesses are likewise for the most part brought about by many impacts in farming which incorporates crossover hereditary qualities, and the plant lifetime during the disease, ecological changes like climatic changes, soil, temperature, downpour, wind, climate and so forth. The diseases might be single or blended, as indicated by the contaminations the plants illnesses spread. Early identification of plant sicknesses utilizing later advances helps the plants development. Consequently, ML strategies are utilized for right on time forecast of the illnesses. This paper is utilized to work on the exactness of distinguishing plant sicknesses utilizing the expectation of the dirt substance in the field land. In the modern era, many purposes behind agricultural plant illness because of horrible atmospheric conditions. Many reasons that impact illness in rural plants incorporate assortment/mixture hereditary qualities, the lifetime of plants at the hour of disease, climate (soil, environment), climate (temperature, wind, downpour, hail, and so on), single versus blended contaminations, and hereditary qualities of the microorganism populaces. This paper is used to improve the accuracy of detecting plant diseases using the prediction of the soil content in the field land. Because of these elements, finding of plant infections at the beginning phases can be a troublesome errand. Machine Learning (ML) classification techniques such as Naïve Bayes (NB) and Neural Network (NN) techniques were compared to develop a novel technique to improve the level of accuracy.