Download PDFOpen PDF in browserWCP: Weather-Based Crop Yield Prediction Using Machine Learning and Big Data AnalyticsEasyChair Preprint 744311 pages•Date: February 8, 2022AbstractAgriculture is the Indian economy's backbone. Big data analytics are becoming more precise and feasible in agricultural research. Current water scarcity, uncontrollable costs owing to demand-supply imbalances, and weather instability need farmers to be prepared with smart farming techniques. Crop yields must be addressed due to unknown climate changes, limited irrigation infrastructure, soil fertility decrease, and conventional agricultural approaches. In agriculture, machine learning (ML) is used to forecast crop output. Many ML approaches such as prediction, classification, regression, and clustering anticipate agricultural production. We presented the WCP approach for predicting agricultural yields based on climatic variables in Big data analytics. The proposed study proposes a crop recommendation system that employs MapReduce and improved K-means (IKM) clustering to get computationally efficient results. The MapReduce framework may be used to build MapReduce and crop prediction based on meteorological conditions by employing Categorization, Attribute Selection, C5.0, and association algorithms. Choosing the proper method from the pool of available algorithms, on the other hand, offers a problem to the researchers in terms of the crop. This work looks at how different machine learning techniques may help estimate agricultural production. A method for predicting agricultural production using ML algorithms in the big data computing paradigm has been suggested. This report also includes a study of ML algorithms for large data analytics. Keywords: Bigdata, Weather, Crop, Prediction, Machine Learning, MapReduce, K-Means Keyphrases: BigData, Crop Prediction, K-means, MapReduce, Weather, machine learning
|