基于深度学习的湖北省土壤侵蚀空间分布

doi:10.16843/j.sswc.2022.03.015

Abstract
Figure/Table
References
Related Citation (15)

Download: PDF (1880 KB) HTML (0 KB)
Export: BibTeX | EndNote (RIS)

Abstract [Background] Regional soil erosion spatial distribution information plays an important role in ecological restoration and land use optimization decision-making, but the spatial model for its analysis and calculation is not yet mature. Deep learning method was introduced in order to establish the complex relationship between soil erosion and various factors and to obtain high-precision spatial distribution data of soil erosion intensity by using its strong computing ability and good fitting effect. The large area of coniferous forest cover in Hubei leads to serious soil erosion, which was taken as research area to verify the feasibility and efficiency of deep learning in regional soil erosion spatial distribution information acquisition.[Methods] This study introduced machine deep learning method to explore a new way to study the spatial distribution of soil erosion. The framework of UNet++ and BP neural network were constructed, and hyper-parameters were optimized on the Jupyter Notebook platform. Based on the real spatial distribution data of soil erosion in Hubei province, optimization function and loss function were used to train neurons to record the deep information of soil erosion factors. Spatial distribution data of factors were obtained by remote sensing as model input, pixel Windows were randomly extracted as training samples to calculate the spatial distribution data of soil erosion intensity grade.[Results] The results showed that the overall accuracy of the UNet++ neural network model was 95.7%, and that of the BP neural network model was 91.4%. The UNet ++ model achieved the better overall accuracy than BP neural network model. The results of BP neural network model had more "salt and pepper" phenomenon, while the results of UNet++ neural network model were difficult to find. UNet++ neural network model overcame the phenomenon of "pepper and salt" in BP model. The error distribution of UNet ++ model in each erosion intensity was relatively uniform, without obvious error aggregation phenomenon. Compared with the BP model, UNet ++ model better reflected the distribution of soil erosion.[Conclusions] It is proved that when rainfall erosivity, soil erodibility, land cover, vegetation cover, slope and topographic relief are selected as input factors, deep learning model can be used to automatically obtain spatial distribution data of soil erosion intensity accurately and quickly by computer. In addition, compared with the traditional BP neural network, the spatial distribution results of soil erosion intensity obtained by UNet++ model have higher accuracy and better effect.

Key words： soil erosion spatial distribution deep learning UNet++ BP neural network

Received: 23 January 2021

PACS:

TP391

	Service

	E-mail this article
	Add to my bookshelf
	Add to citation manager
	E-mail Alert
	RSS
	Articles by authors
	WANG Shutao
	SHI Mingchang
	CHEN Chunyang
	CHEN Jingtao

Cite this article:

WANG Shutao,SHI Mingchang,CHEN Chunyang, et al. Spatial distribution of soil erosion in Hubei province based on deep learning[J]. SSWC, 2022, 20(3): 119-125.

URL:

http://journal12.magtechjournal.com/Jweb_stbc/EN/10.16843/j.sswc.2022.03.015 OR http://journal12.magtechjournal.com/Jweb_stbc/EN/Y2022/V20/I3/119

[1]	YIN Shuiqing,ZHU Zhengyuan,WANG Li, et al. Regional soil erosion assessment based on a sample survey and geostatis[J].Hydrology and Earth System Sciences,2018,22(3):1695.
[2]	徐涛,杨勤科,赵米金.区域土壤侵蚀模型参数选择[J].水土保持研究,2005,12(6):126. XU Tao, YANG Qinke, ZHAO Mijin. Parameterization of regional soil erosion model[J].Research of Soil and Water Conservation,2005,12(6):126.
[3]	郑远攀,李广阳,李晔.深度学习在图像识别中的应用研究综述[J].计算机工程与应用,2019,55(12):20. ZHENG Yuanpan,LI Guangyang,LI Ye. Survey of application of deep learning in image recognition[J]. Computer Engineering and Applications, 2019,55(12):20.
[4]	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 Jing'an. Simulation of soil erosion intensity in the Three Gorges Reservoir Area using BP neural network[J]. Journal of Natural Resources, 2018,33(4):669.
[5]	刘秉正.渭北地区R的估算及分布[J].西北林学院学报,1993,8(2):21. LIU Bingzheng. Estimation and distribution of R in northern Weihe[J].Journal of Northwest Forestry University,1993,8(2):21.
[6]	WILLIAMS J R, JONES C A, DYKE P T.A modeling approach to determining the relationship between erosion and soil productivity[J]. Transactions of the Asae, 1984, 27(1):129.
[7]	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,2000,14(2):19. CAI Chongfa, DING Shuwen, SHI Zhihua, et al. Study of applying USLE and geographical information system IDRISI to predict soil erosion in small watershed[J].Journal of Soil and Water Conservation, 2000,14(2):19.
[8]	刘宝元,毕小刚,符素华,等.北京土壤流失方程[M].北京:科学出版社,2010:60. LIU Baoyuan, BI Xiaogang, FU Suhua, et al. Beijing soil loss equation[M]. Beijing:Science Press, 2010:60.
[9]	舒天竹,王晓红.基于3S技术的地形起伏度与区域土壤侵蚀的相关性研究[J].水土保持研究, 2017,24(4):127. SHU Tianzhu,WANG Xiaohong. Research for the correlation between relief amplitude and regional soil erosion based on 3S technology[J].Research of Soil and Water Conservation,2017,24(4):127.
[10]	靳秋桐,史明昌,张举涛,等.基于TRMM数据提取降雨侵蚀力的校正方法:以蓟运河上游地域为例[J]. 中国水土保持科学,2015,13(4):94. JIN Qiutong, SHI Mingchang, ZHANG Jutao, et al. Calibration of rainfall erosivity calculation based on TRMM data:A case study of the upriver basin of Jiyun River,North China[J].Science of Soil and Water Conservation, 2015,13(4):94.
[11]	ZHOU Z, SIDDIQUEE M, TAJBAKHSH N, et al. UNet++:A nested U-Net architecture for medical image segmentation[M]//Deep Learning in Medical Image Analysis and Multimodal Learning for Clinical Decision Support. Springer, Cham, 2018:3.
[12]	ZHAO H, GALLO O, FROSIO I,et al. Loss functions for image restoration with neural networks[J]. IEEE Transactions on Computational Imaging, 2017, 3(1):47.
[13]	KINGMA D P, BA J L. ADAM:A method for stochastic optimization[EB/OL]. Computer Science:[2019-04-20]. https://arxiv.org/abs/1412.6980.
[14]	BUSCEMA M. Back Propagation Neural Networks[J]. Substance Use & Misuse,1998,33(2):233.
[15]	刘宝元,郭索彦,李智广,等.中国水力侵蚀抽样调查[J].中国水土保持,2013(10):26. LIU Baoyuan, GUO Suoyan, LI Zhiguang,et al. Sampling survey of water erosion in China[J].Soil and Water Conservation in China,2013(10):26.
[16]	BATJES N H. Global assessment of land vulnerability to water erosion on a 1/2° by 1/2° grid[J]. Land Degradation & Development,1996,7(4):353.
[17]	刘文超,刘纪远,匡文慧.陕北地区退耕还林还草工程土壤保护效应的时空特征[J].地理学报,2019,74(9):1835. LIU Wenchao, LIU Jiyuan,KUANG Wenhui. Study of soil erosion in the southern hillside area of China based on RUSLE model[J].Acta Geographica Sinica,2019,74(9):1835.