Predicting Flow Velocity Affected by Seaweed Resistance Using SVM Regression
Sea water exchange is an important source of nutrient salts. Culture living beings such as kelp in a seafarming region will bring resistance to the exchange of water flows and therefore affect nutrient supplement. Study of hydrodynamic environment in marine culture zones is important for revealing water exchange conditions and guiding reasonable layout of mariculture regions. In recent years, statistical learning theories represented by Support Vector Machines (SVM) have been well developed. However, no publications are available regarding using SVM to predict marine environment elements related to hydrodynamic and combining these predicted elements with ocean models. In this paper, we use SVM regression to predict water flow velocity based on an improved hydrodynamic models with the resistance by cultivation breeding such as kelp. In particular, we use SVM regression to predict the velocity of following time points at a location with the coordinate in north-south and east-west directions. The experimental results are promising.
SVM regression POM seaweed resistance
Junyu Dong Yan Song Hui Wang Jing Zeng Zeju Wu
Department of Computer Science and Technology Ocean University of China QingDao, China School of Physical and Environmental Oceanography Ocean University of China QingDao, China School of Marine Life Sciences Ocean University of China QingDao, China School of Communication and Electronic Engineering Qingdao Technological University QingDao, China
国际会议
太原
英文
273-276
2010-10-22（万方平台首次上网日期，不代表论文的发表时间）