Abstract
This paper aims to reveal the appropriate amount of training data for accurately and quickly building a support vector regression (SVR) model for micrometeorological data prediction. SVR is derived from statistical learning theory and can be used to predict a quantity in the future based on training that uses past data. Although SVR is superior to traditional learning algorithms such as the artificial neural network (ANN), it is difficult to choose the most suitable amount of training data to build the appropriate SVR model for micrometeorological data prediction. The challenge of this paper is to reveal the periodic characteristics of micrometeorological data in Japan and determine the appropriate amount of training data to build the SVR model. By selecting the appropriate amount of training data, it is possible to improve both prediction accuracy and calculation time. When predicting air temperature in Sapporo, the prediction error was reduced by 0.1°C and the calculation time was reduced by 98.7% using the appropriate amount of training data.
Highlights
Some kinds of sensor network-based agricultural support systems that enable users to monitor and control the environment in greenhouse horticulture or fields have been studied and developed [1,2,3,4,5,6]
Micrometeorological data is defined as meteorological data that is affected by the surface of the earth, for example, air temperature, relative humidity, amount of CO2, and soil moisture
The algorithms cannot avoid becoming stuck in a local optimum, which can lead to a sub-optimal solution [15]
Summary
Some kinds of sensor network-based agricultural support systems that enable users to monitor and control the environment in greenhouse horticulture or fields have been studied and developed [1,2,3,4,5,6]. Model predictive control (MPC) in industry is an effective means to deal with multivariable constrained control problems, a key issue for controlling the environment appropriately is how to develop a precise prediction model for micrometeorological data. Classical statistical procedures as well as artificial neural networks (ANNs) have already been applied for predicting micrometeorological data [7,8,9,10,11,12,13,14]. ANNs are useful alternatives to traditional statistical modeling in many scientific disciplines. They are composed of a large number of possible non-linear functions, or neurons, each with several parameters that are fitted to data through a computationally intensive training process. The network has to be optimized by considering, for example, how many neurons and hidden layers would be necessary, what kind of activation functions would be appropriate, and how to connect the neurons with each other to form a network
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
