Research On Matching Tree Species With Site And Growth Yield Benefit Assessment Of Plantation

China's forestry has entered an important stage of improving the quality of forest resources and transforming the development pattern.With the development of Big Data,Cloud Computing,Internet of Things and other information technology,the construction of information system of plantation management with data as the core has become an era requirement for the development of modern forestry,ecological civilization and scientific development,which makes the management process of plantation from afforestation to cutting under the scientific management system.Matching tree species with site and density control are two important contents in the process of plantation management.Among them,the biggest problem in the quantitative decision-making research of matching tree species with site is the subjectivity of experience.At the same time,due to the regional limitations and knowledge limitations of plantation cultivation experts,the cultivation knowledge is not comprehensive and difficult to obtain,which also needs to be solved.In the research of density control,many forestry workers have fragmentary experience in the research of optimal control in their operation process,and lack of new information technology means to assemble it into an effective and practical system.Therefore,it is necessary to deeply study the quantization decision of matching tree species with site and density control decision methods in plantation management,and to build the information system of plantation management based on data,so as to promote afforestation work to be carried out better.In view of this,this study took the typical plantation of Chinese fir and Masson Pine in Southern Guizhou Province as the research object,and used the continuous forest inventory data,the forest resources subcompartment data and the analytical wood data to carried out the research on matching tree species with site,density control technology and the evaluation of management income of plantation.The main research works ars as follows:(1)In the quantitative decision making research of suitable site and suitable tree in plantation management,the decision tree algorithm was used to automatically extract suitable site and suitable tree rules from a large number of data,so as to solve the problem of knowledge acquisition and update and maintenance of suitable site rules in expert system.The intelligent extraction of the suitable site rules in the afforestation design of the expert system was realized to provide theoretical basis and technical support for forestation planning and design.(2)In the density control decision-making research in plantation management,combining traditional regression and machine learning methods,relevant models were constructed in the decision model library of plantation management stand density control,mainly including the site index model,growth and harvest model,diameter structure dynamic prediction model,optimal stand density decision model,economic benefit evaluation calculation model,etc.The results showed that the prediction accuracy of machine learning in simulating stand growth and stand diameter structure was better than the traditional method,and the artificial intelligence algorithm genetic algorithm in the optimal stand density decision-making model improved the operation speed of decision-making scheme.In the calculation of economic benefits,after the increase of carbon sink income,compared with single timber economic benefits,Mean Net Present Value((MNPV))of the maximum economic benefit of Chinese fir increased by 1.36 times,and Land Expectation Value(LEV)increased by 1.42 times,and the maximum economic benefits of Masson pine increased by 1.60%(MNPV)and 5.41%(LEV)respectively.(3)Research and build related functional modules of plantation cultivation management decision support system,and realize the practical application of the above models and algorithms.Three functional modules were realized.Which were the extraction of suitable tree rules,benefit evaluation of stand growth and harvest,and intelligent design of stand management density control.