Читать книгу Agricultural Informatics - Группа авторов - Страница 17

Decision trees are the supervised learning techniques used in machine learning. The Decision Tree model is comprised of nodes, branches, leaf, terminal value, payoff distribution, rollback and certain equivalent and method. Decision trees have three variants of nodes and two variants of branches. Square is used to represent one of the decision points. The decision node is a point of choice for the tree. The decision nodes extend decision branches. Each node toward the end of the tree is called terminal node. There is an associated value associated with terminal node commonly referred to as payoff, outcome value. The terminal value is the measure of sequences of decisions or the resultant of the scenario in the tree. The construction of Decision tree algorithm is a two-step process that includes growth of tree and pruning. In the growth step the large decision tree is created, reduced and overfitting is removed. The second step does the tree pruning to reach a decision. The classification tree used for decision making is the obtained pruned tree [13].

Prediction is influenced by various factors in agricultural explorations [14]. Variables associated with agronomics, application of nitrogen and weed control were used for machine learning and decision tree for yield forecasting and development of yield mapping. Both decision trees and ANN were implemented and results showed that greater accuracies were obtained from ANN results.

Authors [15] modeled productivity of soybean using decision trees. Data for climate in Bhopal district was collected for since 1984 to 2003 considering the climatic factors of evaporation, minimum and maximum temperature, humidity, and rainfall. The factors were studied for the production of soybean crop. Interactive Dichotomizer3 (ID3) algorithm was implemented on data. ID technique is based on information and two assumptions. Relative humidity was found to be a major parameter that affected soybean crop yield. Few rules were generated that helped know the lowest and highest prediction of soybean. The only one limitation of the model was that, the amount of yield production cannot be predicted [4, 16], as shown in Figure 1.3.

The vast climatic diversity of India impacts the agricultural production in several parts of the country. Convenient decisions can be made by the farmers and policy inventors if the production can be forecasted in advance.

Figure 1.3 Decision tree structure for crop details prediction [4].

Crop Advisor is one of the advancement in this area. It is a user friendly webpage that identified the impact of weather parameters on the yield of crops. Crop Advisor implements C4.5 algorithm. The most effective parameter of the climate on the yields of specified crops in selected region of Madhya Pradesh was ascertained using C4.5. There is boom in cloud based decision and support system for agriculture these days. There exists a Decision support and Automation system (DSAS) to assist farmers and growers. Users of the application have controls for different features in web portal. There are different stages in DSAS. DSAS provides farmer with real time data via interconnection of several devices. The farmer had right to monitor the real time data and control the machine through software. Few another systems like spray controller will spray defined amount of pesticide in fields, irrigation controller manage irrigation and fertilizer controller takes care of fertilizer. The data to DSAS is given by different sensors of climate and soil [17].