Читать книгу Agricultural Informatics - Группа авторов - Страница 18

There exist several statistical techniques for crop production. One of the most widely used is regression analysis [18, 19]. Regression models were developed as a technique for prediction of response variable called yield and weather, soil properties were addressed as explanatory variables [20]. Several yield forecasting models used parametric regression by taking known functional forms of the predictor variables [21]. Authors [22] described the linear regression as commonly used models for crop production. Researchers also found the use of polynomial regression models in nonlinear regression models in for agricultural applications [23]. The influence of temperature on Jowar crop was forecasted in Jowar production system. The production, minimum and maximum temperatures were the parameters of the experiment [4]. The significance was tested where 2-tailed test approach and Pearson correlation coefficients were used. The results obtained were significant at 0.01 level. Then regression analysis was carried out for yield of crop and measures of temperature. Results showed that that the Jowar yields were very less dependent on the temperature yield was highly affected by some other factors. The reduced temperature increased the yield of Jowar crops. Experiments used functional liner regression analysis to relate yield with rainfall and temperature as predictor variable [4, 24].

Correlation analysis was done taking the yield as output variable and temperature and precipitation as prediction parameters. Stepwise regression technique was used to select best predictors [4, 25]. The crop production changes with the changes in climate. This effect of changing climatic variables on crop production was studied under anticipated seasonal climate change conditions. Daily weather data was obtained from weather generator and authors used the multiple linear regression models. The parameters referencing the climate such as measures of minimum and maximum temperature, density of rainfall, humidity and precipitation rate, speed of wind and solar radiation were used for analysis. These factors were used to predict the corn yield they have results implied that climate variability significantly affects crop yields [4].

The process of identifying similar objects that are different from individuals in other groups is called Cluster analysis or clustering. Clustering finds wide usage in data analysis and many other fields such as machine learning, recognition patterns, analyzing images, retrieval of information and agriculture, etc. Clustering can be studied with several algorithms such as k-means, k-medoid, etc. K-means is most common and widely used clustering algorithm [26]. Demonstration of modified k-Means clustering algorithm in prediction of crop was done in Ref. [4]. Comparison of results for modified k-Means over k-Means and -Means++ clustering algorithms was done and it was found that the modified k-Means had the maxi-mum number of highly differentiable good quality clusters, highly correct results of crop prediction and maximum count for accuracy.

A weather forecast model was developed for classifying the metrological data. The model was based on the frequency of variables. Patterns associated to severe convective activity were identified for the task. Brazilian regions were spot for collection of features during summer of 2007. A fairly good classification performance was seen in results [27].