Study on Partial Least-Squares Regression Model of Simulating Freezing Depth Based on Particle Swarm Optimization

In order to improve fitting and forecasting precision and solve the problem that some data with less sensitivity lead to low simulation precision of partial least-squares regression (PLS for short) model, the new method of simulating freezing depth is presented according to ground temperature of different depths, air temperatures, surface temperatures and the like. Firstly, the PLS model, which is built by virtue of the ideas of principal component analysis and canonical correlation analysis, can be adopted to solve the multi-correlation among each factor effectively by extracting principal components. And the interpretation ability of each principal component to freezing depth can be obtained by assistant analysis. Meanwhile, particle swarm optimization algorithm (PSO) is adopted to optimize partial regression coefficient, and then the PLS model based on PSO can be built. Compared with traditional PLS model, the optimized model has more reliability and stability, and higher precision.

[1]  I Durán Merás,et al.  Comparison of UV derivative-spectrophotometry and partial least-squares (PLS-1) calibration for determination of methotrexate and leucovorin in biological fluids. , 2002, Analytical and bioanalytical chemistry.

[2]  Richard F. Gunst,et al.  Applied Regression Analysis , 1999, Technometrics.

[3]  Xia Zhang,et al.  Development and Testing of a Frozen Soil Parameterization for Cold Region Studies , 2007 .

[4]  Luo De-xiang.  Adaptive particle swarm optimization algorithm based on cloud theory , 2009 .

[5]  J. E. Walsh,et al.  Atmospheric response to soil-frost and snow in Alaska in March , 2004 .

[6]  Li Lin,et al.  Study on the city water resources capacity model with partial least-squares regression , 2005 .

[7]  Zhang Li.  Solutions of Multi-Objective Optimization Problems Based on Particle Swarm Optimization , 2004 .

[8]  C. Genthon,et al.  Role of soil freezing in future boreal climate change , 2004 .

[9]  Zhang Zhanyu,et al.  Multi-objective controlled drainage model based on particle swarm optimized algorithm. , 2009 .

[10]  B. Kowalski,et al.  Partial least-squares regression: a tutorial , 1986 .

[11]  A. Andricopulo,et al.  A partial least squares regression study with antioxidant flavonoid compounds , 2006 .

[12]  Jean-François Mahfouf,et al.  The representation of soil moisture freezing and its impact on the stable boundary layer , 1999 .

[13]  Wang Jing-song.  The Change Characteristics of Maximum Frozen Soil Depth of Seasonal Frozen Soil in Northwest China , 2008 .

[14]  Cheng Guo-dong.  Glaciology and Geocryology of China During the Past 40 Years: Progress and Prospects , 1999 .

[15]  I. Durán Merás,et al.  Comparison of UV derivative-spectrophotometry and partial least-squares (PLS-1) calibration for determination of methotrexate and leucovorin in biological fluids , 2002 .

[16]  Cheng Guo.  Glaciology and Geocryology of China in the Past 40 Years: Progress and Prospect , 1998 .

[17]  Lourdes Cabezas,et al.  Application of Partial Least Squares regression to predict sensory attributes of artisanal and industrial Manchego cheeses , 2006 .

[18]  Chen Zheng.  Modeling of Partial Least-Squared Regression and genetic algorithm in dam safety monitoring analysis , 2007 .

[19]  Norman R. Draper,et al.  Applied regression analysis (2. ed.) , 1981, Wiley series in probability and mathematical statistics.

[20]  Jose Crossa,et al.  Mapping QTLs and QTL × environment interaction for CIMMYT maize drought stress program using factorial regression and partial least squares methods , 2006, Theoretical and Applied Genetics.