基于贝叶斯网络的基本农田划定方法

doi:10.11849/zrzyxb.20150639

摘要/Abstract

摘要： 基本农田划定是落实耕地保护、保证粮食安全的关键问题。目前,基本农田划定的相关研究多基于对耕地适宜性条件的评价,而未涉及对耕地历史变化过程的考虑,因而不能保证划定结果适应实际区域的耕地变化趋势,导致基本农田易被占用,补划与调整频繁。论文综合考虑耕地适宜性条件与历史动态变化状况,提出了一种基于贝叶斯网络模型的基本农田划定方法。以湖北省大冶市这一典型资源型城市为实验区进行了实例研究,划定结果表明,该划定方法能在保证基本农田划定数量与质量的同时,提高其农业用途的稳定性,促进基本农田保护与经济建设、生态保护间协调发展,是一种有效的划定模型。

关键词: 贝叶斯网络, 划定模型, 基本农田

Abstract: Basic farmland protection zoning is the key issue of implementing land protection and ensuring food security. At present, most of the related studies on farmland protection zoning are based on the evaluation of the suitability of cultivated land, with no consideration of the change process of cultivated land in the past. Therefore, they cannot ensure the zoning result to adapt to the trend of cultivated land change, leading to the prime farmland being frequently occupied and adjusted. To guarantee the stability of prime farmland as well as its cultivation quality, we put forward a method of zoning farmland based on Bayesian network (BN) model in this paper, which includes both factors concerning cultivated land suitability condition and its dynamic change. With data of land use status in Daye City at two time points (1997 and 2012), the factors about suitability and changes of cultivated land are obtained. Suitability factors are used to reflect the quality of cultivated land, and the factors about changes are used to study the change disciplinarian of cultivated land. Using the basic farmland potential as the target variable, we defined the structure of the network by expert knowledge. The BN was trained by Maximum Likelihood Method with 57 085 random sample points. The results show that, only 60% farmland in Daye City remains stable from 1997 to 2012. In the three dynamic factors, the influence of building occupancy is the greatest, which accounts for 28.2%, followed by the internal adjustment, 17.4%, the influence of ecological footprint is the least, which accounts for 4.65%. The results of sensitivity analysis also indicate that building occupancy has the greatest influence on the potential value of the prime farmland, with the highest variance reduction of 26.8%. The variance reductions of the distance to the center of city (0.43%) and the center of the town (0.58%) are greater than that of the distance to the road (0.14%) or the railway (0.28%), reflecting that urban expansion has greater impact on the occupation of basic farmland than transportation construction. In natural condition factors, the influence of the distance to the water area is the minimum, which is less than 0.02%, while soil erosion has the greatest variance reduction of 0.34%. It can be deduced that soil erosion, but water, is the most important nature factor to destroy the stability of cultivated land in Daye City. Then, using the values of suitability factors in 2012, we obtained the relative potential value of each cultivated land parcel as the prime farmland through forward reasoning of the trained network, and zoned the farmland with the potential value of the target variable. The results show that, compare to traditional land evaluation method, the zoning model based on BN can improve the stability of agricultural value and ensure the quantity and quality of prime farmland. It is a new and effective model for farmland protection zoning.

Key words: Bayesian network, farmland protection, zoning model

中图分类号:

F323.211

关小东, 何建华. 基于贝叶斯网络的基本农田划定方法[J]. 自然资源学报, 2016, 31(6): 1061-1072.

GUAN Xiao-dong, HE Jian-hua. Prime Farmland Protection Zoning Based on Bayesian Network[J]. JOURNAL OF NATURAL RESOURCES, 2016, 31(6): 1061-1072.

参考文献

[1] DUKE J M, LYNCH L. Gauging support for innovative farmland preservation techniques [J]. Policy Sciences, 2007, 40(2): 123-155.
[2] CHEN R S, YE C, CAI Y L, et al. The impact of rural out-migration on land use transition in China: Past, present and trend [J]. Land Use Policy, 2014, 40: 101-110.
[3] HU R, QIU D C, XIE D T, et al. Assessing the real value of farmland in China [J]. Journal of Mountain Science, 2014, 11(5): 1218-1230.
[4] 孔祥斌, 靳京, 刘怡, 等. 基于农用地利用等别的基本农田保护区划定 [J]. 农业工程学报, 2008, 24(10): 46-51. [KONG X B, JIN J, LIU Y, et al. Method of the prime farmland protection zone based on farmland utilization grade. Transactions of the CSAE, 2008, 24(10): 46-51. ]
[5] LIU X P, LI X, TAN Z Z, et al. Zoning farmland protection under spatial constraints by integrating remote sensing, GIS and artificial immune systems [J]. International Journal of Geographical Information Science, 2011, 25(11): 1829-1848.
[6] 杨绪红, 金晓斌, 郭贝贝, 等. 基本农田调整划定方案合理性评价研究——以广东省龙门县为例 [J]. 自然资源学报, 2014, 29(2): 265-274. [YANG X H, JIN X B, GUO B B, et al. Study on the rationality of basic farmland adjustment scheme: A case study of Longmen County in Guangdong Province. Journal of Natural Resources, 2014, 29(2): 265-274. ]
[7] 董秀茹, 尤明英, 王秋兵. 基于土地评价的基本农田划定方法 [J] . 农业工程学报, 2011, 27(4): 336-339. [DONG X R, YOU M Y, WANG Q B. Demarcating method of prime farmland based on land evaluation. Transactions of the CSAE, 2011, 27(4): 336-339. ]
[8] 钟太洋, 黄贤金, 马其芳, 等. 区域人均基本农田需求面积测算模型及应用——以江苏省为例 [J]. 自然资源学报, 2006, 21(5) : 717- 726. [ZHONG T Y, HUANG X J, MA Q F, et al. Theoretical model and its application of regional per capita basic farmland area: A case study of Jiangsu Province. Journal of Natural Resources, 2006, 21(5): 717- 726. ]
[9] 罗明, 鞠正山, 张清春. 发达国家农地保护政策比较研究 [J] . 农业工程学报, 2001, 17(6): 165-168. [LUO M, JU Z S, ZHANG Q C. Comparative study on policy of farmland preservation in developed countries. Transactions of the CSAE, 2001, 17(6): 165-168. ]
[10] 钱凤魁, 王秋兵. 基于农用地分等和LESA方法的基本农田划定 [J]. 水土保持研究, 2011, 18(2): 251-255. [QIAN F K, WANG Q B. Planning method of the prime farmland based on farmland classification and LESA Method. Research of Soil and Water Conservation, 2011, 18(2): 251-255. ]
[11] 张蕾娜, 刘晓燕. 农用地分等定级成果在基本农田保护中的应用研究 [J] . 地域研究与开发, 2007, 26(4): 87-88, 115. [ZHANG L N, LIU X Y. Outcome application of agricultation land classification and graduation on the protection of prime farmland. Areal Research and Development, 2007, 26(4): 87-88, 115. ]
[12] 刘霈珈, 吴克宁, 赵华甫, 等. 基于耕地综合质量的基本农田布局优化——以河南省温县为例 [J]. 中国土地科学, 2015, 29(2): 54-59. [LIU P J, WU K N, ZHAO H F, et al. Spatial allocation optimization of prime farmland based on cultivated land comprehensive quality: A case study of Wen County, Henan Province. China Land Sciences, 2015, 29(2): 54-59. ]
[13] 聂艳, 吴西子, 于婧, 等. 基于土地评价和空间聚类的基本农田划定方法研究——以湖北省鹤峰县为例 [J]. 中国土地科学, 2013, 27(12): 39 - 46. [NIE Y, WU X Z, YU J, et al. Primary farmland zoning based on land evaluation and spatial clustering: A case of Hefeng County. China Land Sciences, 2013, 27(12): 39-46. ]
[14] 唐宽金, 郑新奇, 姚金明, 等. 基于粮食生产能力的基本农田保护区规划方法研究 [J]. 地域研究与开发, 2008, 27(6): 105-109. [TANG K J, ZHENG X Q, YAO J M, et al. Planning method for the basic farm land protection based on the potential grain productivity. Areal Research and Development, 2008, 27(6): 105-109. ]
[15] 石英, 朱德举, 程锋, 等. 属性层次模型在乡级基本农田保护区布局优化中的应用 [J]. 农业工程学报, 2006, 22(3): 27-31. [SHI Y, ZHU D J, CHENG F, et al. Attribute hierarchical model and its application to the optimal allocation of prime farmland protection areas at local level. Transactions of the CSAE, 2006, 22(3): 27-31. ]
[16] 郭贝贝, 金晓斌, 杨绪红, 等. 基于农业自然风险综合评价的高标准基本农田建设区划定方法研究 [J]. 自然资源学报, 2014, 29(3): 377-386. [GUO B B, JIN X B, YANG X H. Study on zoning approach for well-facilitated capital farmland: Based on a comprehensive assessment of agricultural natural disaster risk. Journal Natural Resources, 2014, 29(3): 377-386. ]
[17] 刘慧敏, 朱江洪. 丘陵山区高标准基本农田建设时序与模式研究 [J]. 水土保持研究, 2015, 22(2): 141-146. [LIU H M, ZHU J H. Study on time sequence and mode of high-standard prime farmland construction in the hilly and moun-tainous area. Research of Soil and Water Conservation, 2015, 22(2): 141-146. ]
[18] LI X, YEH A G O. Zoning land for agricultural protection by the integration of remote sensing, GIS, and cellular auto-mata [J]. Photogrammetric Engineering and Remote Sensing, 2001, 67: 471-477.
[19] 周尚意, 朱阿兴, 邱维理, 等. 基于GIS的农用地连片性分析及其在基本农田保护规划中的应用 [J]. 农业工程学报, 2008, 24(7): 72-77. [ZHOU S Y, ZHU A X, QIU W L, et al. GIS based connectivity analysis and its application in prime farmland protection planning. Transactions of the CSAE, 2008, 24(7): 72-77. ]
[20] RAN Z, JING L, DU Q Y, et al. Basic farmland zoning and protection under spatial constraints with a particle swarm optimization multi-objective decision model: A case study of Yicheng, China [J]. Environment and Planning B: Planning and Design, 2015, 42, doi:10.1068/b130213p.
[21] PEARL J. Probabilistic Reasoning in Intelligent Systems: Network of Plausible Inference [M]. Morgan Kaufinann, 1988: 1-86.
[22] NEWTON A, STEWART G B, DIAZ A, et al. Bayesian Belief Networks as a tool for evidence-based conservation management [J]. Journal for Nature Conservation, 2007, 15(2): 144-160.
[23] PEARL J. Causality: Models, Reasoning and Interference [M]. 2nd Edition. Cambridge: Cambridge University Press, 2009.
[24] AALDERS I. Modeling land-use decision behavior with Bayesian Belief Networks [J]. Ecology and Society, 2008, 13(1): 16.
[25] SUN Z L, MÜLLER D. A framework for modeling payments for ecosystem services with agent-based models, Bayesian Belief Networks and opinion dynamics models [J]. Environmental Modelling & Software, 2013, 45: 15-28.
[26] FRAYER J, SUN Z, MÜLLER D, et al. Analyzing the drivers of tree planting in Yunnan, China, with Bayesian networks [J]. Land Use Policy, 2014, 36: 248-258.
[27] SPIEGELHALTER D J, LAURITZEN S L. Sequential updating of conditional probabilities on directed graphical structures [J]. Networks, 1990, 20: 579-605.
[28] 慕春棣, 戴剑彬, 叶俊. 用于数据挖掘的贝叶斯网络 [J] . 软件学报, 2000, 11(5): 660-666. [MU C L, DAI J B, YE J. Bayesian network for data mining. Journal of Software, 2000, 11(5): 660-666. ]
[29] POLLINO C A, WOODBERRY O, NICHOLSON A E, et al. Parameterisation and evaluation of a Bayesian network for use in an ecological risk assessment [J]. Environmental Modelling & Software, 2007, 22: 1140-1152.