| 摘要: |
| 西部大开发促进了陕甘宁新地区经济发展，但仍存在生态资源脆弱性。本文选取陕甘宁新地区为研究对象，从经济、科技、社会、环境、自然资源、生态治理6个方面构建了农业资源可持续利用的评价指标体系，并结合2018-2020年的相关数据，利用小波-PSOSVM进行评价。结果表明：（1）小波-PSOSVM农业资源可持续评价均方误差MSE=9.4115e-05，相关系数为96.7919 %；而PSOSVM在同样的训练集以及同样的测试集下，得到的均方误差MSE、相关系数分别为：0.015339，96.7191 %。说明，小波处理后，PSOSVM预测的精度有所提高，收敛稍加快。（2）小波-SVM农业资源可持续评价均方误差MSE=20.8355，相关系数为74.7549% %；而SVM在同样的训练集以及同样的测试集下，均方误差MSE、相关系数分别为：30.9032，63.3733%，同样说明，小波处理后，SVM预测的精度提高，收敛也稍快。（3）比较小波-PSOSVM与小波-SVM，PSOSVM与SVM，得到一致的结论：PSO优化后的SVM，预测的精度提高较多，收敛也快得多。结果显示：陕甘宁新地区农业资源可持续利用评价结果，新疆位于四个地方之首，排20名，宁夏排在第27名，位于四者最位置，陕甘两地居四者中间。陕甘宁新地区在合理开发并利用农业资源的时，应转变农业生产方式，提高农业资源可持续利用水平；保护农业生态环境，平衡生态与生产建设；合理规划城镇化，推动城镇化与农业现代化协调发展。 |
| 关键词: 小波分析；微粒群算法；支持向量机；资源可持续评价 |
| DOI： |
| 分类号:S812 |
| 基金项目:国家社科后资助项目《“四化同步”的时代意蕴与现实践履》(21FKSB048) |
|
| Evaluation of sustainable utilization of agricultural resources in Shaanxi-Gansu-Ningxia-Xinjiang based on wavelet-PSOSVM |
|
WANG Chenxuan1, CHEN Li2, ZHANG Anan2
|
|
1.Anhui Agricultural University;2.Anhui University of Architecture
|
| Abstract: |
| [Background] The quick development of the new areas of Shaanxi, Gansu, and Ningxia has been aided by western development. At the same time, the area"s ecological resources look to be vulnerable. Agricultural resources are the foundation of agricultural development, and they must be used in a sustainable manner. [Methods] The sustainable utilization of agricultural resources in the Shaanxi-Gansu-Ningxia new area was evaluated using wavelet-PSOSVM in this paper. The Evaluation Index System of sustainable utilization of agricultural resources is constructed from six aspects: economy, science and technology, society, natural environment, resources, and ecological governance, and combined with related data from 2018 to 2020. [Results] The results reveal that wavelet-PSOSVM has a greater accuracy and faster convergence rate than PSOSVM when evaluating sustainable agricultural resource usage. Xinjiang rates quite high in terms of sustainable agricultural resource utilization as compared to Shaanxi, Gansu, and Ningxia. The results show that: (1) the mean square error of wavelet psosvm agricultural resources sustainable evaluation is MSE = 9.4115e-05, and the correlation coefficient is 96.7919%; psosvm"s mean square error MSE and correlation coefficient are 0.015339 and 96.7191%, respectively, under the same training and test sets. It shows that following wavelet processing, psosvm"s prediction accuracy improves and convergence speeds up marginally. (2) The mean square error of wavelet SVM agricultural resources sustainable evaluation is MSE = 20.8355, and the correlation coefficient is 74.7549%; the mean square error MSE and correlation coefficient of SVM are 30.9032 and 63.3733%, respectively, under the same training set and test set. It also demonstrates that following wavelet processing, SVM prediction accuracy improves and convergence speeds up marginally. (3) When we compare wavelet psosvm to wavelet SVM, psosvm to SVM, we get to the same conclusion: the prediction accuracy of PSO optimized SVM is significantly enhanced, and convergence is significantly faster. In short, following wavelet analysis of the index data, the training model"s complexity is reduced, the wavelet psosvm"s training time is also increased, and the prediction results are satisfactory. More scientific is the wavelet psosvm model. [Conculsions] According to the evaluation results of sustainable agricultural resource use in the Shaanxi Gansu Ningxia new area, Xinjiang is at the top of the four places, ranking 20, Ningxia is at the bottom of the four, ranking 27, and Shaanxi and Gansu are in the middle. While developing and utilizing agricultural resources in the new area of Shaanxi-Gansu-Ningxia, special attention should be devoted to protecting the agricultural ecological environment, achieving agricultural development, increasing farmers" income, and maintaining rural stability. Protecting the agricultural ecological environment and balancing ecology and production construction; Changing agricultural production modes and enhancing the level of sustainable exploitation of agricultural resources; Plan urbanization rationally and encourage the development of urbanization and agricultural modernization in tandem. In the evaluation of sustainable agricultural resource utilization, the combination of wavelet transform theory and particle swarm optimization support vector machine is conducive to enriching the theory of sustainable resource utilization and further promoting the sustainable development of agriculture in China. |
| Key words: wavelet analysis; particle swarm optimization; support vector machine; resource sustainability assessment |
