Abstract
Weather forecasting is an important and indispensable procedure in peoples' day-to-day lives, it evaluates the alteration happening in the current condition of the atmosphere. The major goal of this project is to create a weather-based crop prediction system to predict the crops based on weather forecasting using big data analytics. In this project, the authors gather and analyze data based on temperature, rainfall, soil, seed, crop production, humidity, and wind speed to assist farmers in improving agricultural yields. The data is first preprocessed in a Python environment, and then the MapReduce framework is used to further analyze and process the massive amount of data. Second, based on MapReduce findings, k-means clustering algorithm is used to produce a mean result on the data in terms of accuracy. After that, the authors examine the link between crops, rainfall, temperature, soil, and seed type using bar graphs and scatter plots.
TopThe weather prediction can be used to enhance productivity in agricultural practices. Farmers today experience a loss for their product when they receive a higher yield from their crop but the market price for that commodity is lower. Farmers run the risk of both market price and production issues, particularly when cultivating new crops. The usage of machine learning technologies helps to solve these issues. A subset of data mining called predictive analysis forecasts probability and trends for the future. The agricultural system analyst still difficult to predict crop yield accurately using environmental, meteorological, and soil fertility parameters (Ramkar et al., 2018). The most often used factors in agricultural production prediction features are temperature, rainfall, and soil type (Sayao et al., 2020). The forecast will enable farmers to decide which crop is most suited for a given rainfall and crop price range (Zeferino et al.,2020). The goal of this strategy is to raise the crop's average yield percentage based on rainfall and temperature values.
Key Terms in this Chapter
Correlation Analysis: Correlation analysis is a statistical approach used in feature selection to assess the strength of each feature's linear connection with the target variable.
Crop Yield Prediction: It is critical in national, regional, and local decision-making since it is dependent on soil, climatic, environmental, and agricultural factors.
Elbow Method: The elbow method is a strategy for determining the number of clusters (k) to employ in a k-means clustering algorithm.
KMean Clustering: K-Means clustering is an unsupervised machine learning approach that uses characteristics to group comparable data points together.
Hadoop: Hadoop is a free and open-source software framework that allows for the distributed processing and storage of huge datasets across computer clusters by utilising basic programming methods.
Recommendation System: A recommendation system is an algorithm that suggests crops that are most appropriate to a certain person.
MapReduce algorithm: MapReduce is a programming concept and related implementation for processing and producing large data sets on a cluster using a parallel, distributed algorithm.