предыдущий|следующий

Remote sensing estimation of suspended sediment concentration based on Random Forest Regression Model

  • role： First author第一作者
  • Affiliation：

    Chongqing Institute of Green and Intelligent Technology, Key Laboratory of Reservoir Aquatic Environment, Chinese Academy of Sciences, Chongqing 400714, China

    University of Chinese Academy of Sciences, Beijing 100049,China

  • Email：fangxinrui15@mails.ucas.ac.cn
  • Introduction：方馨蕊，1993年生，男，硕士研究生，研究方向为环境生态。E-mail：fangxinrui15@mails.ucas.ac.cn
FANG Xinrui12,  
  • Affiliation：

    Chongqing Institute of Green and Intelligent Technology, Key Laboratory of Reservoir Aquatic Environment, Chinese Academy of Sciences, Chongqing 400714, China

WEN Zhaofei1,  
  • Affiliation：

    Chongqing Institute of Green and Intelligent Technology, Key Laboratory of Reservoir Aquatic Environment, Chinese Academy of Sciences, Chongqing 400714, China

CHEN Jilong1,  
  • role： Corresponding author通信作者
  • Affiliation：

    Chongqing Institute of Green and Intelligent Technology, Key Laboratory of Reservoir Aquatic Environment, Chinese Academy of Sciences, Chongqing 400714, China

    University of Chinese Academy of Sciences, Beijing 100049,China

  • Email：wsj@cigit.ac.cn
  • Introduction：吴胜军，1971年生，男，研究员，研究方向为地理信息工程与环境生态。E-mail：wsj@cigit.ac.cn
WU Shengjun12*,  
  • Affiliation：

    Chongqing Institute of Green and Intelligent Technology, Key Laboratory of Reservoir Aquatic Environment, Chinese Academy of Sciences, Chongqing 400714, China

HUANG Yuanyang1,  
  • Affiliation：

    Chongqing Institute of Green and Intelligent Technology, Key Laboratory of Reservoir Aquatic Environment, Chinese Academy of Sciences, Chongqing 400714, China

    University of Chinese Academy of Sciences, Beijing 100049,China

MA Maohua12

реферат

Since 2003 when the Three-Gorge Dam (TGD) was in impoundment, the dam abundantly blocks suspended sediment and cause clear water flowing through the dam, which induces scouring effect on the beds and banks of the Yangtze river below the dam.Furthermore, the altered Suspended Sediment Concentration (SSC) has adversely affected the downstream coastal environment. In this study, the random forest model was applied for SSC estimation. The model is flexible and robust, and can be used for regression analysis of ecological environment variables. Yet, its ability in estimating SSC in aquatic environment has not been fully understood. On the basis of the monitoring data of SSC and satellite remote sensing reflectance data from 2002 to 2015, this study estimated the SSC in Yichang–Chenglingji downstream reach of the TGD by constructing a non-parametric regression model using random forest. The results showed that:(1) the random forest model could effectively monitor SSC, and the correlation coefficient and prediction accuracy were significantly improved from those of other models (linear regression, support vector machine, and artificial neural network model).(2) the red band is a suitable predictor for SSC in the random forest model, but cannot be independently used for forecasting. SSC remote sensing prediction requires multivariate co-participation. (3)By using the random forest model, the average root mean square error of the seasonal division was 0.46 mg/L, and the average relative root mean square error was 12.33%. These values met the needs of high-precision SSC estimation. In conclusion, this study reveals that the season shall be considered as temporal factors to estimate SSC and then prepare for the subsequent SSC spatiotemporal inversion. Which is of great help to reveal the TGD’s downstream river sediment evolution, and understand the regional distribution of sediment and sediment variation process in the future.

ключеви́че слова́

TGD(Three Gorges Dam);downstream channel of dam;remote sensing of aquatic environment;Random Forest;remote sensing monitoring;MODIS;sediment inversion

References

  1. 1.
    Bian M, Skidmore A K, Schlerf M, Wang T J, Liu Y F, Zeng R and Fei T. 2013. Predicting foliar biochemistry of tea (Camellia sinensis) using reflectance spectra measured at powder, leaf and canopy levels. ISPRS Journal of Photogrammetry and Remote Sensing, 78: 148–156
  2. 2.
    Birth G S and McVey G R. 1968. Measuring the color of growing turf with a reflectance spectrophotometer. Agronomy Journal, 60(6): 640–643
  3. 3.
    Bowers D G, Hill P S and Braithwaite K M. 2014. The effect of particulate organic content on the remote sensing of marine suspended sediments. Remote Sensing of Environment, 144: 172–178
  4. 4.
    Breiman L. 2001. Random forests. Machine Learning, 45(1): 5–32
  5. 5.
    Cheng T W and Zhao C N. 1985. The runoff, sediment discharge and its impacts on the coastal waters of China’s major rivers. Acta Oceanologica Sinica, 7(4): 460–471
  6. 6.
    Ding L D, Wu H, Wang C J, Qin Z H and Zhang Q X. 2006. Quick recognition and mapping of Lake Water information based on MODIS image. Hydrographic Surveying and Charting, 26(6): 31–34
  7. 7.
    Fan D Q, Zhu W Q, Pan Y Z and Jiang N. 2013. Noise detection for NDVI time series based on Dixon’s test and application in data reconstruction. Journal of Remote Sensing, 17(5): 1158–1174
  8. 8.
    Fan H, Huang H J and Tang J W. 2007. Spectral signature of waters in Huanghe estuary and estimation of suspended sediment concentration from remote sensing data. Geomatics and Information Science of Wuhan University, 32(7): 601–604
  9. 9.
    Francke T, López-Tarazón J A and Schröder B. 2008. Estimation of suspended sediment concentration and yield using linear models, random forests and quantile regression forests. Hydrological Processes, 22(25): 4892–4904
  10. 10.
    Gao Z B and Duan G L. 2006. Influence of boundary condition on downstream river bed evolution of TGP. Yangtze River, 37(12): 92–94
  11. 11.
    Gong L, Zhong C H and Deng C G. 2006. Effect of suspended sand particles on growth of algae in aquatic system. Journal of Agro-Environment Science, 25(S2): 687–689
  12. 12.
    Han Z. 2004. Remote Sensing Information Extraction and Quantitative Inversion Research of Silt Tidal Flat and Suspended Sediment of Case II Waters in Coast Zone. Shanghai: East China Normal University
  13. 13.
    Ismail R, Mutanga O and Kumar L. 2010. Modeling the potential distribution of pine forests susceptible to Sirex noctilio infestations in Mpumalanga, South Africa. Transactions in GIS, 14(5): 709–726
  14. 14.
    Jiang J. 2004. A Study on Retrieval and Change Analysis of Suspended Sediment Concentration. Nanjing: Nanjing Normal University
  15. 15.
    Jiang J L, Liu X N, Liu M L and Bi X Q. 2014. Remote sensing retrieval model of sea surface salinity in Hong Kong waters based on the random forest. Marine Science Bulletin, 33(3): 333–341
  16. 16.
    Jiang L Z. 2014. Assessment of Hydrological Alteration and its Impacts on Fish Population in the Middle-Lower Yangtze River after the Impoundment of the Three Gorges Dam. Beijing: University of Chinese Academy of Sciences
  17. 17.
    Jin L, Kuang X Y, Huang H H, Qin Z N and Wang Y H. 2004. Study on the overfitting of the artificial neural network forecasting model. Acta Meteorologica Sinica, 62(1): 62–70
  18. 18.
    Li H L, Zhang Y and Jiang J. 2006. Study on the inversion model for the suspended sediment concentration in remote sensing technology. Advances in Water Science, 17(2): 242–245
  19. 19.
    Li S H and Yun C X. 2001. A study on the quantitative model of the suspended sediment concentration from the meteorological satellite imagery. Journal of Remote Sensing, 5(2): 154–160
  20. 20.
    Li Y T, Sun Z H, Deng J Y and Zhang W. 2004. Variation of sediment transport and flood disaster in the middle reach of Yangtze River. Journal of Sediment Research(2): 33–39
  21. 21.
    Li Z B. 2012. Based Support Vector Machine Retrieval Model for Ocean Suspended Solids Remote Sensing Concentration. Beijing: China University of Geosciences (Beijing)
  22. 22.
    Liang D, Guan Q S, Huang W J, Huang L S and Yang G J. 2013. Remote sensing inversion of leaf area index based on support vector machine regression in winter wheat. Transactions of the Chinese Society of Agricultural Engineering, 29(7): 117–123
  23. 23.
    Liaw A and Wiener M. 2002. Classification and regression by randomForest. R News, 2-3: 18–22
  24. 24.
    Lin C D, Zhou B, Ma Q and Jiang M X. 2014. Study on the inversion model of the suspended sediment in the middle Yangtze River based on remote sensing technology. Resources and Environment in the Yangtze Basin, 23(8): 1119–1124
  25. 25.
    Liu H Q and Huete A. 1995. A feedback based modification of the NDVI to minimize canopy background and atmospheric noise. IEEE Transactions on Geoscience and Remote Sensing, 33(2): 457–465
  26. 26.
    Liu X B, Lu J Y and Lin M S. 2006. The influence of the Three Gorges Project on the middle and lower reach of the Yangtze River//Proceedings of 2006 International Symposium on Hydropower. Kunming: China Dam Committee of China Hydropower Engineering Society, China Water Conservancy Society
  27. 27.
    Lou X L and Huang W G. 2003. An artificial Neural Network Method for detecting red tides with NOAA AVHRR imagery. Journal of Remote Sensing, 7(2): 125–130
  28. 28.
    Mei A X, Peng W L, Qin Q M and Liu H P. 2001. An Introduction to Remote Sensing. Beijing: Higher Education Press: 236-238
  29. 29.
    Miller R L and McKee B A. 2004. Using MODIS Terra 250 m imagery to map concentrations of total suspended matter in coastal waters. Remote Sensing of Environment, 93(1/2): 259–266
  30. 30.
    Novo E M L M, Steffen C A and Braga C Z F. 1991. Results of a laboratory experiment relating spectral reflectance to total suspended solids. Remote Sensing of Environment, 36(1): 61–72
  31. 31.
    Pei X Y, Zang S Y and Na X D. 2014. The introductions and rapid pretreatment of MODIS MOD13Q1 Vegetation product. Natural Science Journal of Harbin Normal University, 30(2): 65–67, 77
  32. 32.
    Prasad A M, Iverson L R and Liaw A. 2006. Newer classification and regression tree techniques: bagging and random forests for ecological prediction. Ecosystems, 9(2): 181–199
  33. 33.
    Qiao X J, He B Y, Zhang W, Li Y Z and Su Z H. 2013. MODIS-based retrieval and change analysis of suspended sediment concentration in middle Yangtze River. Resources and Environment in the Yangtze Basin, 22(8): 1090–1095
  34. 34.
    Richardson A J and Wiegand C L. 1977. Distinguishing vegetation from soil background information. Photogrammetric Engineering and Remote Sensing, 43(12): 1541–1552
  35. 35.
    Rouse J W Jr, Haas R H, Schell J A and Deering D W. 1974. Monitoring Vegetation Systems in the Great Plains with ERTS. PAPER-A20. NASA Special Publication: 309
  36. 36.
    Smith C and Croke B. 2005. Sources of uncertainty in estimating suspended sediment load//Proceedings of Symposium S1 Held During the Seventh IAHS Scientific Assembly. Foz do Igaussu, Brazil: IAHS-AISH Publication: 136-143
  37. 37.
    Stephens D and Diesing M. 2015. Towards quantitative spatial models of seabed sediment composition. PLoS One, 10(11): e0142502
  38. 38.
    Tian T, Sun C M, Liu T, Guo D D, Wang L J and Chen Y Y. 2013. Hyperspectral remote sensing and its applications in grassland and vegetation. Journal of Anhui Agricultural Sciences, 41(7): 3192–3195
  39. 39.
    Wang F, Ling Z Y, Zhou B, Song L S and Wang X. 2009. MODIS images monitoring short-period variation of estuary surface water suspended sediment concentration. Journal of Zhejiang University (Engineering Science), 43(4): 755–759
  40. 40.
    Wang Q, Shen Y P and Chen Y W. 2006. Rule extraction from support vector machines. Journal of National University of Defense Technology, 28(2): 106–110
  41. 41.
    Wang W, Yang X, Liu G, Zhou H, Ma W, Yu Y and Li Z. 2016. Random forest classification of sediments on exposed intertidal flats using ALOS-2 Quad-Polarimetric SAR data. ISPRS-International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, XLI-B8: 1191-1194 [DOI: 10.5194/isprsarchives-XLI-B8-1191-2016]
  42. 42.
    Wang X Q, Li Z, Lv P Y and Guo J S. 2007. Adsorption and desorption of phosphorus on suspended particles in the Three Gorges Area. Resources and Environment in the Yangtze Basin, 16(1): 31–36
  43. 43.
    Wang X Q, Lv P Y and Hu C S. 2006. Influence of suspended sediment in TGP reservoir on absorption of TP, TN etc. Yangtze River, 37(7): 15–17
  44. 44.
    Wang Y Y, Qi Y B, Chen Y and Xie F. 2016. Prediction of soil organic matter based on multi-resolution remote sensing data and random forest algorithm. Acta Pedologica Sinica, 53(2): 342–354
  45. 45.
    Wang Z H and Yi S Z. 2007. Comparison and research on the different index models used in water extraction by remote sensing. Science Technology and Engineering, 7(4): 534–537
  46. 46.
    Wang Z X, Liu C and Huete A. 2003. From AVHRR-NDVI to MODIS-EVI: advances in vegetation index research. Acta Ecologica Sinca, 23(5): 979–987
  47. 47.
    Wen Z F. 2017. Spatial and Seasonal Patterns of Aboveground Net Primary Productivity and Their Responses to Environmental Factors in the Drawdown Zone of the Three Gorges Reservoir, China. Chongqing: Chongqing Institute of Green and Intelligent Technology, Chinese Academy of Sciences
  48. 48.
    Wu G F, Cui L J and Ji W T. 2009. Time-series MODIS images-based retrieval and change analysis of suspended sediment concentration during flood period in Lake Poyang. Journal of Lake Sciences, 21(2): 288–297
  49. 49.
    Xie Y F, Hu Y H, Liu Z W and Xie G S. 2007. Effects of sediment resuspension on the growth of submerged plants. Acta Scientiae Circumstantiae, 27(1): 18–22
  50. 50.
    Zhai W K. 2006. Atmospheric Correction of MODIS and Analysis Space-Time Distribution Characteristics for Ocean Color in Bohai Sea. Dalian: Dalian Maritime University
  51. 51.
    Zhang H X, Guo J L, Zhu J Y and Yu J F. 2002. Multivariate Data Analysis Methods and Applications with Few Observations. Xi’an: Northwestern Polytechnical University Press: 153-154
  52. 52.
    Zhang L, Wang L L, Zhang X D, Liu S R, Sun P S and Wang T L. 2014. The basic principle of random forest and its applications in ecology: a case study of Pinus yunnanensis. Acta Ecologica Sinica, 34(3): 650–659
  53. 53.
    Zhang W. 2012. Remote Sensing Retrieval of Suspended Matters Based on Intelligent Calculation——A Case Study of Middle Yangtze River. Beijing: University of Chinese Academy of Sciences
  54. 54.
    Zhang W J, Wei L P and Qu G. 2013. The analysis of channel evolution of Jingjiang River in different types after operation of Three Gorges Project. Water Conservancy Science and Technology and Economy, 19(11): 56–59
  55. 55.
    Zimmermann A, Francke T and Elsenbeer H. 2012. Forests and erosion: Insights from a study of suspended-sediment dynamics in an overland flow-prone rainforest catchment. Journal of Hydrology, 428-429: 170–181

Читать полностью

The above content is generated by Large Model Translation. The translated content is for reference only. We do not assume any commercial or legal responsibilty for any consequences arising from the use of our website