Project Background
Agriculture is the main support and the major sector of the Indian economy. The production of agronomy is far too low. low. As the demand for food is growing exponentially, the researchers, analysts, farmers, scientists, specialists and government try to place further effort and strategies to increase agricultural production to accommodate the needs. The objective of agricultural production is to achieve maximum crop yield. Initial discovery and management of complications like crop yield can help amplify return yield and ensuing profits. If regional weather patterns are influenced, large scale weather events can have a substantial effect on crop production. Crop managers can use predictions to minimize damage in critical conditions. Furthermore, these forecasts could be used to make full use of the crop forecast if the potential for favorable conditions of growth exists. Crop Yield Prediction is the methodology to predict the yield of the crops using different parameters like rainfall, temperature, fertilizers, pesticides, ph level, and other atmospheric conditions and parameters. ANN (Artificial Neural Network) is a method to predict the yield. For the purposes of this paper, ANN will be considered using zero, one and two hidden layers in this research. The ideal numbers of the different hidden layers and the numbers of units in each of the hidden layers will be determined by calculating MSEs that provide the correct or precise output. The forecast for crop yield is based on numerous types of statistics compiled and extracted. It is a fascinating method of estimating crop and the quantity of yield in an advance way before the harvest essentially takes place. Foreseeing the crop yield can be tremendously valuable for farmers. It tells them the indication of when and how to harvest crops certainly. The contribution of agricultural professionals and re- searchers in the prediction of crop yield leads to issues like nescient farmers about natural occurrence’s, the negation of personal awareness and exhaustion etc. such problems can be altered by using crop yield techniques using ANN algorithms. The main objective is to compare the output of ANN and CNN to verify whether the results in crop prediction are accurate. This paper uses crop yield prediction techniques to forecast the appropriate crop by identifying different soil parameters and atmospheric condition parameters. This paper demonstrates the ability of the artificial neural network algorithm to monitor and predict crop yields in remote areas and cities. The initiation of remote sensing data along with ANN to predict the crop is used to acquire data regularly taken from satellites orbiting around the Earth and powerful image- processing techniques like Convolutional Neural Networks is being used to predict the harvest which aptitudes increased prediction coverage and even precision. By using both ANN and CNN algorithms for crop yield predict
