This paper proposes the discriminant analysis on land grading after analyzing the common methods and discussing the Fisher’s discriminant in detail. Actually this method deduces the dimension from multi to single, th...This paper proposes the discriminant analysis on land grading after analyzing the common methods and discussing the Fisher’s discriminant in detail. Actually this method deduces the dimension from multi to single, thus it makes the feature vectors in n \|dimension change to a scalar, and use this scalar to classify samples. This paper illustrates the result by giving an example of the residential land grading by the discriminant analysis.展开更多
With the increasing requirement for the protection of arable land, monitor- ing the grades of arable land quality is becoming more important, which can accu- rately and fully reflect the current situation and developm...With the increasing requirement for the protection of arable land, monitor- ing the grades of arable land quality is becoming more important, which can accu- rately and fully reflect the current situation and development trends of arable land quality. It is also an important measure for protecting the quality of arable land. in the present study, the distribution and changes of arable lands of different gradient types and grades in Lingchuan County, Guangxi Zhuang Autonomous Region in 2015 were monitored and evaluated, to analyze the trends and reasons for the changes in the quality and productivity of arable lands, and to provide references for dynamic monitoring of the quality of arable land.展开更多
With the classifi cation data covering American land-use/land-cover (LUCC) with 30 m resolu tion from the project of National Land Cover Data (NLCD), we normalize d them and made their resolution changed into 1 km ...With the classifi cation data covering American land-use/land-cover (LUCC) with 30 m resolu tion from the project of National Land Cover Data (NLCD), we normalize d them and made their resolution changed into 1 km ×1 km, created the data of American land-use grade and analyzed the spatial distribution and featur es of American LUCC as well as the influence of population and altit ude on the land-use grade in light of methods of sampling analysis a nd correlation study. Based on the analysis, we concluded that forestr y and grassland, accounting for 71.24% of the whole country, has taken the main part of American land cover, and besides, construction and arable land has occupied 19.22% of the total land, the rest of land cover types, including water area, wetland and underdeveloped land, is 9. 54% of the country's total. The developing potential of American land resources is enormous with less destroyed and disturbed ecological environment. Although, in some sense, the population and altitude influence the sp atial variation of American land-use grade respectively, the influence of spatial variation of altitude and population density on that of la nd-use grade is not significanct.展开更多
文摘This paper proposes the discriminant analysis on land grading after analyzing the common methods and discussing the Fisher’s discriminant in detail. Actually this method deduces the dimension from multi to single, thus it makes the feature vectors in n \|dimension change to a scalar, and use this scalar to classify samples. This paper illustrates the result by giving an example of the residential land grading by the discriminant analysis.
文摘With the increasing requirement for the protection of arable land, monitor- ing the grades of arable land quality is becoming more important, which can accu- rately and fully reflect the current situation and development trends of arable land quality. It is also an important measure for protecting the quality of arable land. in the present study, the distribution and changes of arable lands of different gradient types and grades in Lingchuan County, Guangxi Zhuang Autonomous Region in 2015 were monitored and evaluated, to analyze the trends and reasons for the changes in the quality and productivity of arable lands, and to provide references for dynamic monitoring of the quality of arable land.
基金National Natural Science Foundation of China, No. 90202002.
文摘With the classifi cation data covering American land-use/land-cover (LUCC) with 30 m resolu tion from the project of National Land Cover Data (NLCD), we normalize d them and made their resolution changed into 1 km ×1 km, created the data of American land-use grade and analyzed the spatial distribution and featur es of American LUCC as well as the influence of population and altit ude on the land-use grade in light of methods of sampling analysis a nd correlation study. Based on the analysis, we concluded that forestr y and grassland, accounting for 71.24% of the whole country, has taken the main part of American land cover, and besides, construction and arable land has occupied 19.22% of the total land, the rest of land cover types, including water area, wetland and underdeveloped land, is 9. 54% of the country's total. The developing potential of American land resources is enormous with less destroyed and disturbed ecological environment. Although, in some sense, the population and altitude influence the sp atial variation of American land-use grade respectively, the influence of spatial variation of altitude and population density on that of la nd-use grade is not significanct.
