基于DL和GKDE的松花江流域土壤侵蚀类型的概率评价研究

邢贞相; 王嘉麒; 张鸿雪; 宋健; 王轶男; 段维义; 宫铭; 黄昌丽

doi:10.13870/j.cnki.stbcxb.2024.05.012

您当前的位置：

首页 >

文章列表页 >

基于DL和GKDE的松花江流域土壤侵蚀类型的概率评价研究

更新时间：2025-02-18

- 基于DL和GKDE的松花江流域土壤侵蚀类型的概率评价研究
- Probability Evaluation Study of Soil Erosion Types in the Songhua River Basin Based on Deep Learning and Gaussian Kernel Density Estimation
- 水土保持学报 2024年38卷第5期页码：116-128
- 作者机构：
  
  1. 东北农业大学水利与土木工程学院,哈尔滨,150030
  2. 中国科学院地理科学与资源研究所,北京,100101
  3. 黑龙江省齐齐哈尔生态环境监测中心,黑龙江,齐齐哈尔,161005
- 作者简介：
  
  [ "邢贞相(1976—),男,教授,博士,主要从事农业水土资源不确定研究。E-mail:zxxing@neau.edu.cn" ]
- 基金信息：
  
  国家自然科学基金项目(51979038,52209008)
- DOI：10.13870/j.cnki.stbcxb.2024.05.012
  中图分类号： S157.1
- 纸质出版：2024
- 稿件说明：
移动端阅览
邢贞相, 王嘉麒, 张鸿雪, 等. 基于DL和GKDE的松花江流域土壤侵蚀类型的概率评价研究[J]. 水土保持学报, 2024,38(5):116-128.

XING Zhenxiang, WANG Jiaqi, ZHANG Hongxue, et al. Probability Evaluation Study of Soil Erosion Types in the Songhua River Basin Based on Deep Learning and Gaussian Kernel Density Estimation[J]. 2024, 38(5): 116-128.
邢贞相, 王嘉麒, 张鸿雪, 等. 基于DL和GKDE的松花江流域土壤侵蚀类型的概率评价研究[J]. 水土保持学报, 2024,38(5):116-128. DOI： 10.13870/j.cnki.stbcxb.2024.05.012.

XING Zhenxiang, WANG Jiaqi, ZHANG Hongxue, et al. Probability Evaluation Study of Soil Erosion Types in the Songhua River Basin Based on Deep Learning and Gaussian Kernel Density Estimation[J]. 2024, 38(5): 116-128. DOI： 10.13870/j.cnki.stbcxb.2024.05.012.

摘要

[目的] 为科学判别流域尺度土壤侵蚀类型并给出相应的发生概率。[方法] 构建基于深度学习(deeplearning

DL)的松花江流域土壤侵蚀模数(erosion modulu

EM)计算模型

并计算不同类型的侵蚀模数。以降雨、气温、风速3个侵蚀模数影响因子为随机变量

利用数值模拟和高斯核密度估计法(gaussian kernel densityestimation

GKDE)构建EM概率评价方法

给出不同土壤侵蚀强度组合的发生概率。[结果] EM计算模型验证期的R2均>0.86。流域内平均每年有74.47%发生微度水蚀与微度风蚀;12.86%的面积发生轻度及以上水蚀与微度风蚀;12.56%的面积发生轻度及以上风蚀与微度水蚀;0.11%的面积水蚀强度与风蚀强度均在轻度及以上。36个典型像元中

发生微度水蚀与微度风蚀的平均概率为57.45%;发生微度水蚀与轻度风蚀的平均概率为30.26%;发生微度水蚀与中度风蚀的平均概率为8.03%;发生轻度水蚀与微度风蚀的平均概率为2.11%;发生微度水蚀与重度风蚀的平均概率为2.08%;发生其余强度组合的平均概率在0.05%以下。[结论] 构建的松花江流域EM计算模型精度较高

揭示了松花江流域土壤侵蚀类型空间分布特征

并给出不同土壤侵蚀强度组合的发生概率

为松花江流域土壤侵蚀治理提供依据。

Abstract

[Objective] To scientifically identify the types of soil erosion at the watershed scale and give the corresponding probability of occurrence. [Methods] This study constructs a deep learning (DL)-based model for calculating soil erosion modulus in the Songhua River Basin and calculates different types of soil erosion modulus. Using three erosion modulus influencing factors

namely rainfall

air temperature and wind speed

as random variables

numerical simulation and Gaussian Kernel Density Estimation (GKDE) were used to construct the EM probability evaluation method

which gives the probability of occurrence of different combinations of soil erosion intensities. [Results] The R2 of the validation period of the EM computational models were all >0.86; 74.47% of the average annual occurrence of slight water erosion and slight wind erosion in the watershed; 12.86% of the area of slight and above water erosion and slight wind erosion; 12.56% of the area of slight and above wind erosion and slight water erosion; 0.11% of the area of water erosion strength and wind erosion intensity are both slight and above. 36 typical image elements of the 36 typical images

the average probability of occurrence of slight water erosion and slight wind erosion is 57.45%; the average probability of occurrence of slight water erosion and mild wind erosion is 30.26%; the average probability of occurrence of slight water erosion and moderate wind erosion is 8.03%; the average probability of occurrence of mild water erosion and slight wind erosion is 2.11%; the average probability of occurrence of slight water erosion and severe wind erosion is 2.08%; and the evaluations of occurrence of the remaining combinations of probabilities were all below 0.05%. [Conclusion] The calculation model of erosion modulus in the Songhua River basin constructed in this study has high accuracy

reveals the spatial distribution characteristics of soil erosion types in the Songhua River basin

and gives the probability of occurrence of different combinations of the intensity of the two types of erosion

which provides a basis for the management of soil erosion in the Songhua River basin.

关键词

Keywords

references

ZHU Y L, LI W B, WANG D Y, et al. Spatial pattern of soil erosion in relation to land use change in a rolling hilly region of Northeast China[J].Land,2022,11(8):e1253.

WANG X, ZHAO X L, ZHANG Z X, et al. Assessment of soil erosion change and its relationships with land use/cover change in China from the end of the 1980s to 2010[J].Catena,2016,137:256-268.

WANG H, YANG S L, WANG Y D, et al. Rates and causes of black soil erosion in Northeast China[J].Catena,2022,214:e106250.

左小锋,郑粉莉,张加琼,等.典型薄层黑土区前期地表风蚀作用影响坡面水蚀的研究[J].土壤学报,2021,58(5):1145-1156. ZUO X F, ZHENG F L, ZHANG J Q, et al. Study on effect of surface wind erosion on hillslope water erosion in regions of typical thin layered mollisol at early stages[J].Acta Pedologica Sinica,2021,58(5):1145-1156.

WANG S H, XU X L, HUANG L. Spatial and temporal variability of soil erosion in Northeast China from 2000 to 2020[J].Remote Sensing,2022,15(1):e225.

吴瀚逸,熊俊峰,侯渲,等.2001—2020年中国东北区域土壤水蚀数据集[J].中国科学数据,2023,8(4):283-297. WU H Y, XIONG J F, HOU X, et al. A dataset of soil water erosion of Northeast China from 2001 to 2020[J].China Scientific Data,2023,8(4):283-297.

杨严攀,田培,沈晨竹,等.基于RUSLE模型和地理探测器的鄂西南土壤侵蚀脆弱性评价[J].水土保持学报,2024,38(1):91-103. YANG Y P, TIAN P, SHEN C Z, et al. Vulnerability assessment of soil erosion in southwestern Hubei Province based on RUSLE model and geographic detector[J].Journal of Soil and Water Conservation,2024,38(1):91-103.

池金洺,于洋,冯娟龙,等.基于RUSLE模型的妫水河流域土壤侵蚀时空变化特征[J].水土保持学报,2024,38(1):70-78. CHI J M, YU Y, FENG J L, et al. Spatialand temporal variation characteristics of soil erosion in Guishui River Basin based on RUSLE[J].Journal of Soil and Water Conservation,2024,38(1):70-78.

GHOLAMI H, MOHAMMADIFAR A, GOLZARI S, et al. Using the Boruta algorithm and deep learning models for mapping land susceptibility to atmospheric dust emissions in Iran[J].Aeolian Research,2021,50:e100682.

KHOSRAVI K, REZAIE F, COOPER J R, et al. Soil water erosion susceptibility assessment using deep learning algorithms[J].Journal of Hydrology,2023,618:e129229.

郑粉莉,张加琼,刘刚,等.东北黑土区坡耕地土壤侵蚀特征与多营力复合侵蚀的研究重点[J].水土保持通报,2019,39(4):314-319. ZHENG F L, ZHANG J Q, LIU G, et al. Characteristics of soil erosion on sloping farmlands and key fields for studying compound soil erosion caused by multi-forces in mollisol region of Northeast China[J].Bulletin of Soil and Water Conservation,2019,39(4):314-319.

REZAEI M, MOHAMMADIFAR A, GHOLAMI H, et al. Mapping of the wind erodible fraction of soil by bidirectional gated recurrent unit (BiGRU) and bidirectional recurrent neural network (BiRNN) deep learning models[J].Catna,2023,223:e106953.

王善序.贝叶斯概率水文预报简介[J].水文,2001,21(5):33-34. WANG S X. Introduction to the Bayesian forecasting system[J].Hydrology,2001,21(5):33-34.

CIMUSA K L, BIGABWA B J, PRASAD P, et al. Soil erosion susceptibility mapping using ensemble machine learning models: A case study of upper Congo River sub-basin[J].Catena,2023,222:e106858.

BAG R, MONDAL I, DEHBOZORGI M, et al. Modelling and mapping of soil erosion susceptibility using machine learning in a tropical hot sub-humid environment[J].Journal of Cleaner Production,2022,364:e132428.

张光辉,杨扬,刘瑛娜,等.东北黑土区土壤侵蚀研究进展与展望[J].水土保持学报,2022,36(2):1-12. ZHANG G H, YANG Y, LIU Y N, et al. Advances and prospects of soil erosion research in the black soil region of Northeast China[J].Journal of Soil and Water Conservation,2022,36(2):1-12.

焦剑,谢云,林燕,等.东北地区融雪期径流及产沙特征分析[J].地理研究,2009,28(2):333-344. JIAO J, XIE Y, LIN Y, et al. Study on snowmelt runoff and sediment yields in Northeast China[J].Geographical Research,2009,28(2):333-344.

张晓敏,张东梅,王莉,等.降雨、积雪以及土地利用复合影响下的额尔齐斯河流域土壤侵蚀分析[J].水土保持学报,2022,36(5):104-111. ZHANG X M, ZHANG D M, WANG L, et al. Soil erosion analysis in the Irtysh River Basin under the combined effects of rainfall, snow cover and land use[J].Journal of Soil and Water Conservation,2022,36(5):104-111.

赵琴,郝晓华,王建,等.2000—2020年MODIS中国积雪物候数据集[D/OL].国家冰川冻土沙漠科学数据中心(www.ncdc.ac.cn),2021. https://cstr.cn/CSTR:11738.11.ncdc.isnow.db2519.2022. ZHAO Q, HAO X H, WANG J, et al. A dataset of snow cover phenology in China based on MODIS during 2000—2020[D/OL].National Cryosphere Desert Data Center (www.ncdc.ac.cn),2021. https://cstr.cn/CSTR:11738.11.ncdc.isnow.db2519.2022.

赵琴,郝晓华,王建,等.2000—2020年MODIS中国积雪物候数据集[J].中国科学数据,2022,7(3):60-69. ZHAO Q, HAO X H, WANG J, et al. A dataset of snow cover phenology in China based on MODIS during 2000—2020[J].China Scientific Data,2022,7(3):60-69.

YANG J, HUANG X. The 30 m annual land cover dataset and its dynamics in China from 1990 to 2019[J].Earth System Science Data,2021,13(8):3907-3925.

刘峰,张甘霖.中国高分辨率国家土壤信息网格基本属性数据集(2010—2018)[ED/OL].国家青藏高原数据中心,2021. https://doi.org/10.11666/ 00073.ver1.db. LIU F, ZHANG G L. Basic soil property dataset of high-resolution China Soil Information Grids (2010—2018)[ED/OL].National Tibetan Plateau Data Center,2021. https://dx.doi.org/10.11666/ 00073.ver1.db.

LIU F, ZHANG G L, SONG X D, et al. High-resolution and three-dimensional mapping of soil texture of China[J].Geoderma,2020,361:e114061.

巩国丽,刘纪远,邵全琴.基于RWEQ的20世纪90年代以来内蒙古锡林郭勒盟土壤风蚀研究[J].地理科学进展,2014,33(6):825-834. GONG G L, LIU J Y, SHAO Q Q. Wind erosion in Xilingol League,Inner Mongolia since the 1990s using the Revised Wind Erosion Equation[J].Progress in Geography,2014,33(6):825-834.

张天骐,柏浩钧,叶绍鹏,等.基于注意力门控膨胀卷积网络的单通道语音增强[J].电子与信息学报,2022,44(9):3277-3288. ZHANG T Q, BAI H J, YE S P, et al. Monaural speech enhancement based on attention-gate dilated convolution network[J].Journal of Electronics and Information Technology,2022,44(9):3277-3288.

HE K M, ZHANG X Y, REN S Q, et al. Deep residual learning for image recognition//2016. IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Las Vegas, NV, USA. IEEE,2016:770-778.

王红瑞,林欣,刘琼,等.基于系统聚类的北京气温变化过程遍历特征分析[J].系统工程理论与实践,2010,30(2):193-200. WANG H R, LIN X, LIU Q, et al. Ergodicity analysis based on system clustering for temperature variation process of Beijing[J].Systems Engineering-Theory and Practice,2010,30(2):193-200.

贺敬,李少林,蔡玮,等.双重不确定性预测下风电场超短期有功优化控制[J].太阳能学报,2023,44(11):270-278. HE J, LI S L, CAI W, et al. Optimal control of wind farm power based on double uncertainty prediction[J].Acta Energiae Solaris Sinica,2023,44(11):270-278.

庄琦,刘曙光,周正正.降雨数据时空精度对城市暴雨变异性及频率分析的影响[J].水科学进展,2023,34(3):398-408. ZHUANG Q, LIU S G, ZHOU Z Z. Impact of rainfall spatiotemporal resolutions on urban extreme rainfall variability and rainfall frequency analysis[J].Advances in Water Science,2023,34(3):398-408.

程媛,迟荣华, 黄少滨,等.基于非参数密度估计的不确定轨迹预测方法[J].自动化学报,2019,45(4):787-798. CHENG Y, CHI R H, HUANG S B, et al. Uncertain trajectory prediction method using non-parametric density estimation[J].Acta Automatica Sinica,2019,45(4):787-798.

浏览量

167

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

小流域土壤侵蚀模型（SWEM）

秦岭水源地生态恢复下土壤全氮分布对侵蚀的响应

人工模拟降雨下高寒区坡面径流水动力特性对砾石覆盖的响应

水力条件对不同地表粗糙度土壤分离能力的影响

三峡库区生态屏障区土壤侵蚀时空变化特征与驱动因素