Prediction of soil erosion evolution in counties in the loess hilly region based on ANN-CA model
ZHAO Jintao1,2, MA Yixue3, SHI Yun1, HAO Shanshan1, MA Xiaoyan1
1. Collegeof Geography and Planning, Ningxia University, 750021, Yinchuan, China; 2. Yellow River Institute of Hydraulic Research, Yellow River Conservancy Commission, 450003, Zhengzhou, China; 3. China University of Geosciences, 100083, Beijing, China
Abstract：[Background] With destroying the ecological environment and affecting the regional environmental carrying capacity, soil erosion has become one of the important issues restricting the sustainable development of society. Pengyang county is located in the second sub-region of the Loess Hilly and Gully Region, and is a key control area for soil erosion in the country. After years of vigorous management, the ecological environment has been effectively improved. In order to consolidate the management results, accurate soil erosion prediction results are the scientific basis for reasonable prevention of soil erosion.[Methods] Three phases of remote sensing images, DEM, and daily rainfall were used as basic datain 2000, 2008, and 2015, meanwhile soil erosion was calculated based on GIS and RUSLE models and the analysis area was quantified and characteristics of annual spatiotemporal distributionin 2000-2015. An ANN-CA model was constructed using an artificial neural network coupled with a cellular automaton and the six soil erosion factors R, K, C, P, L, and S were invoked as model input variables. The soil erosion intensity level was the initial state of the cell which made a prediction of soil erosion in Pengyang country in 2025.[Results] 1) Overall situation of soil erosion in Pengyang country from 2000 to 2015 indicated a positive trend. The area of erosion above the grade strong decreased by 652.81 km2 and high-grade erosion gradually shifted to low-grade. 2) The accuracy of soil erosion intensity simulation results in 2015 was ranked as follows:slight > light > medium > ultra strong > severe > strong, the overall accuracy was 7.9%, the Kappa coefficient was 0.82 and the prediction accuracy was high. 3) Soil erosion in Pengyang county in 2025 would be mainly slight and light with areas of 1 366.67 km2 and 7 486.61 km2, accounting for 84.69% of the total area. The area above the strong is only 2.69 km2, accounting for 1.1% of the total area which has improved further with compared with 2015. Erosion above the strong mainly occurred in Mengyuan and Xinjitown so that the construction of soil erosion conservation measures could be enhanced in this area to prevent soil erosion.[Conculsions] The research results illuminate that the ANN-CA model has significantly self-learning ability and spatial dynamic simulation function which are universal in regional soil erosion prediction.
赵金涛, 马逸雪, 石云, 郝姗姗, 马小燕. 基于ANN-CA模型的黄土丘陵区县域土壤侵蚀演变预测[J]. 中国水土保持科学, 2021, 19(6): 60-68.
ZHAO Jintao, MA Yixue, SHI Yun, HAO Shanshan, MA Xiaoyan. Prediction of soil erosion evolution in counties in the loess hilly region based on ANN-CA model. SSWC, 2021, 19(6): 60-68.
QIAO Yuliang,Q Yun. Fast soil erosion investigation and dynamic analysis in the Loess Plateau of China by using information composite technique[J]. Advances in Space Research, 2002, 29(1):85.
[2]
HESSEL R. Consequences of hyperconcentrated flow for process-based soil erosion modelling on the Chinese Loess Plateau[J]. Earth Surface Processes and Landforms:the Journal of the British Geomorphological Research Group, 2006, 31(9):1100.
[3]
GHOBADI M,TAHERABADI S,GHOBADI M, et al. Antioxidant capacity, photosynthetic characteristics and water relations of sunflower (Helianthus annuus L.) cultivars in response to drought stress[J]. Industrial Crops and Products, 2013, 50:29.
[4]
D'AMBROSIO D,DIGREGORIO S,GABRIELE S, et al. A cellular automata model for soil erosion by water[J]. Physics and Chemistry of the Earth, Part B:Hydrology, Oceans and Atmosphere, 2001, 26(1):33.
[5]
张芳, 汤国安, 曹敏, 等. 基于ANN-CA模型的黄土小流域正负地形演化模拟[J]. 地理与地理信息科学, 2013, 29(1):28. ZHANG Fang, TANG Guoan, CAO Min, et al.Simulation of positive and negative terrain evolution in loess small watershed based on ANN-CA model[J]. Geography and Geo-Information Science, 2013, 29(1):28.
[6]
张美美, 张荣群, 郝晋珉, 等. 基于ANN-CA的银川平原湿地景观演化驱动力情景模拟分析[J]. 地球信息科学学报, 2014, 16(3):418. ZHANG Meimei, ZHANG Rongqun, HAO Jinmin, et al.Scenario simulation analysis of driving forces of Yinchuan plain wetland landscape evolution based on ANN-CA[J]. Journal of Geo-Information Science, 2014, 16(3):418.
[7]
YAN Jianzhuo,XU Zongbao,YU Yongchuan, et al. Application of a hybrid optimized bp network model to estimate water quality parameters of Beihai lake in Beijing[J]. Applied Sciences, 2019, 9(9):1863.
[8]
刘荣增, 陆文涛, 杜力卿. 基于ANN-CA模型的郑州城市空间拓展研究[J]. 城市发展研究, 2019, 26(12):49. LIU Rongzeng, LU Wentao, DU Liqing. Research on urban space expansion of Zhengzhou based on ANN-CA model[J]. Urban Studies, 2019, 26(12):49.
[9]
李旭青, 李龙, 庄连英, 等. 基于小波变换和BP神经网络的水稻冠层重金属含量反演[J]. 农业机械学报, 2019, 50(6):226. LI Xuqing, LI Long, ZHUANG Lianying, et al. Inversion of heavy metal content in rice canopy based on wavelet transform and BP neural network[J]. Transactions of the CSAM, 2019, 50(6):226.
[10]
ZHAO Jumin,TIAN Hao,LI Dengao. Channel prediction based on BP neural network for backscatter communication networks[J]. Sensors, 2020, 20(1):300.
[11]
曹敏, 史照良. 基于遗传神经网络获取元胞自动机的转换规则[J]. 测绘通报, 2010(3):24. CAO Min, SHI Zhaoliang. Acquisition of cellular automata conversion rules based on genetic neural network[J]. Bulletin of Surveying and Mapping, 2010(3):24.
[12]
刘婷, 邵景安. 基于BP神经网络的三峡库区土壤侵蚀强度模拟[J]. 自然资源学报, 2018, 33(4):669. LIU Ting, SHAO Jingan. Simulation of soil erosion intensity in the Three Gorges Reservoir area based on BP neural network[J]. Journal of Natural Resources, 2018, 33(4):669.
[13]
林晨, 周生路, 吴绍华. 基于优化GeoCA模型的土壤侵蚀时空变化模拟——以福建省长汀县为例[J]. 地理科学进展, 2012, 31(7):911. LIN Chen, ZHOU Shenglu, WU Shaohua. Simulation of spatiotemporal changes in soil erosion based on the optimized GeoCA model:Taking Changting county, Fujian province as an example[J]. Progress in Geography, 2012, 31(7):911.
[14]
郝姗姗, 李梦华, 马永强, 等. 黄土丘陵区土壤侵蚀因子敏感性分析[J]. 中国水土保持科学, 2019, 17(2):77. HAO Shanshan, LI Menghua, MA Yongqiang, et al. Sensitivity analysis of soil erosion factors in loess hilly region[J]. Science of Soil and Water Conservation, 2019, 17(2):77.
[15]
李传华, 潘竟虎. 基于神经网络和GeoCA的土壤侵蚀预测模拟——以庆城县水土保持世行二期贷款项目区为例[J]. 土壤通报, 2009, 40(4):902. LI Chuanhua, PAN Jinghu. Simulation of soil erosion prediction based on neural network and GeoCA:Taking Qingchengcounty soil and water conservation world bank phase II loan project area as an Example[J]. Chinese Journal of Soil Science, 2009, 40(4):902.
[16]
董婷婷, 左丽君, 张增祥. 基于ANN-CA模型的土壤侵蚀时空演化分析[J]. 地球信息科学学报, 2009, 11(1):132. DONG Tingting, ZUO Lijun, ZHANG Zengxiang. Analysis of the temporal and spatial evolution of soil erosion based on ANN-CA model[J]. Journal of Geo-Information Science, 2009, 11(1):132.
[17]
李芳. 基于CA和ANN的土壤侵蚀时空演化模拟[D]. 长沙:湖南师范大学, 2010. LI Fang. Simulation of temporal and spatial evolution of soil erosion based on CA and ANN[D]. Changsha:Hunan Normal University, 2010.
[18]
郑丽丹. 基于ANN-CA的南方红壤区土壤侵蚀时空格局及演化模拟[D]. 福州:福建师范大学, 2012. ZHENG Lidan. Spatial-temporal pattern and evolution simulation of soil erosion in southern red soil region based on ANN-CA[D]. Fuzhou:Fujian Normal University, 2012.
[19]
石云. 基于景观格局变化的黄土丘陵沟壑区生态恢复评价与分析[D]. 银川:宁夏大学, 2016. SHI Yun. Evaluation and analysis of ecological restoration in loess hilly and gully regions based on changes in landscape pattern[D]. Yinchuan:Ningxia University, 2016.
[20]
虎维军, 文志强, 杨晓辉, 等. 彭阳县水土保持生态建设的主要做法与经验[J]. 中国水土保持, 2010(8):56. HU Weijun, WEN Zhiqiang, YANG Xiaohui, et al. Main practices and experiences of soil and water conservation and ecological construction in Pengyangcounty[J]. Soil and Water Conservation in China, 2010(8):56.
[21]
WILLIAMS J R,RENARD K G,DYKE P T. EPIC:a new method for assessing erosion's effect on soil productivity[J]. Journal of Soil and Water Conservation, 1983, 38(5):381.
[22]
汪邦稳, 杨勤科, 刘志红, 等. 基于DEM和GIS的修正通用土壤流失方程地形因子值的提取[J]. 中国水土保持科学, 2007,5(2):18. WANG Bangwen, YANG Qinke, LIU Zhihong, et al. Extraction of terrain factor values of modified general soil loss equation based on DEM and GIS[J]. Science of Soil and Water Conservation, 2007,5(2):18.
[23]
江忠善, 郑粉莉. 坡面水蚀预报模型研究[J]. 水土保持学报, 2004,18(1):66. JIANG Zhongshan, ZHENG Fenli. Research on slope water erosion forecast model[J]. Journal of Soil and Water Conservation, 2004,18(1):66.
[24]
符素华, 刘宝元, 周贵云, 等. 坡长坡度因子计算工具[J]. 中国水土保持科学, 2015, 13(5):105. FU Suhua, LIU Baoyuan, ZHOU Guiyun, et al. Calculation tool for slope length and slope factor[J]. Science of Soil and Water Conservation, 2015, 13(5):105.
[25]
蔡崇法, 丁树文, 史志华, 等. 应用USLE模型与地理信息系统IDRISI预测小流域土壤侵蚀量的研究[J]. 水土保持学报, 2000,18(2):19. CAI Chongfa, DING Shuwen, SHI Zhihua, et al. Application of USLE model and geographic information system IDRISI to predict the amount of soil erosion in a small watershed[J]. Journal of Soil and Water Conservation, 2000,14(2):19.
[26]
冯强, 赵文武. USLE/RUSLE中植被覆盖与管理因子研究进展[J]. 生态学报, 2014, 34(16):4461. FENG Qiang, ZHAO Wenwu. Research progress of vegetation cover and management factors in USLE/RUSLE[J]. Acta Ecologica Sinica, 2014, 34(16):4461.
[27]
章文波, 谢云, 刘宝元. 利用日雨量计算降雨侵蚀力的方法研究[J]. 地理科学, 2002,22(6):705. ZHANG Wenbo, XIE Yun, LIU Baoyuan. Research on the method of calculating rainfall erosivity using daily rainfall[J]. Scientia Geographica Sinica, 2002,22(6):705.
[28]
陈楠, 王钦敏, 汤国安, 等. 基于BP神经网络自动提取沟谷研究[J]. 中国水土保持科学, 2006,4(5):30. CHEN Nan, WANG Qinmin, TANG Guoan, et al. Research on automatic extraction of valleys based on BP neural network[J]. Science of Soil and Water Conservation, 2006,4(5):30.
[29]
杨冉冉, 徐涵秋, 林娜, 等. 基于RUSLE的福建省长汀县河田盆地区土壤侵蚀定量研究[J]. 生态学报, 2013, 33(10):2974. YANG Ranran, XU Hanqiu, LIN Na, et al. Quantitative study on soil erosion in Hetian basin of Changting county, Fujian province based on RUSLE[J]. Acta Ecologica Sinica, 2013, 33(10):2974.
[30]
赵明伟, 汤国安, 李发源, 等. 基于BP神经网络的陕北黄土高原侵蚀产沙影响因子显著性研究[J]. 水土保持通报, 2012, 32(1):5. ZHAO Mingwei, TANG Guoan, LI Fayuan, et al. Significance of factors affecting erosion and sediment yield in the Loess Plateau of northern Shaanxi based on BP neural network[J]. Bulletin of Soil and Water Conservation, 2012, 32(1):5.
2021, Vol. 19 
