کاربرد دو تکنیک داده‌کاوی برای تهیه نقشه پراکنش مکانی کربن آلی خاک (مطالعه موردی: کرانه شرقی دریاچه ارومیه)

نوع مقاله : مقالات پژوهشی

نویسندگان

• امین موسوی ¹
• فرزین شهبازی ¹
• شاهین اوستان ¹
• علی اصغر جعفرزاده ¹
• بودیمن میناسنی ²

¹ دانشگاه تبریز

² استرالیا

https://doi.org/10.22067/jsw.v34i3.84154

چکیده

در این پژوهش، از دو مدل جنگل تصادفی و کیوبیست به عنوان یکی از پرکاربردترین تکنیک­های نوین داده­کاوی برای تهیه نقشه رقومی کربن آلی خاک در ساحل شرقی دریاچه ارومیه استفاده شد. بدین منظور با استفاده از روش نمونه­برداری تصادفی مرتب شده در منطقه­ای به وسعت 500 کیلومتر­مربع تعداد 131 نمونه خاک سطحی (عمق 10-0 سانتی­متری) و از دوسایت جداگانه برداشت شد. متغیرهای کمکی مورداستفاده در این تحقیق شامل شش باند مستقل برگرفته از تصویر OLI ماهواره لندست 8 (باندهای 2 تا 7)، تجزیه به مؤلفه­های اصلی (PCA) باندها و همچنین تعداد 14 شاخص­ ترکیبی مربوط به تیرماه سال 1396می­باشد. نتایج پیش­بینی مدل در مرحله آزمون (25 درصد داده­ها) نشان داد که مدل جنگل تصادفی با مقادیر (89/0 R2 =، 16/0RMSE = و 01/0ME =) صحت و کارایی بالاتری نسبت به مدل کیوبیست (85/0 R2 =، 21/0RMSE = و 03/0ME =) دارد. همچنین نتایج رتبه­بندی اهمیت متغیرهای کمکی برای پیش­بینی کربن آلی خاک نشان داد که پارامترهای شاخص مرئی مقاومت اتمسفریک (VARI)، شاخص گیاهی نرمال شده (NDVI)، شاخص سنگی شده آهک دو (CRI2) و شاخص سنگی شده آهک یک (CRI1) دارای بیشترین تأثیر و شاخص گچ (GI)­ و برخی باند­های مستقل از جمله باند 5 (B5) و باند 3 (B3) اهمیت کمتری نسبت به سایر شاخص­ها دارند. به­طور کلی نتایج نشان داد که مدل جنگل تصادفی در مقایسه با مدل کیوبیست به نحو مطلوبی قادر به مدل­سازی و پیش­بینی پراکنش مکانی کربن آلی خاک در منطقه مورد مطالعه بوده است.

کلیدواژه‌ها

• جنگل تصادفی
• کیوبیست
• متغیرهای کمکی
• مدل‌سازی
• نقشه‌برداری رقومی

عنوان مقاله [English]

Application of Two Data Mining Techniques for Mapping the Spatial Distribution of Soil Organic Carbon (Case Study: East Shore of Urmia Lake)

نویسندگان [English]

• A. Mousavi ¹
• F. Shahabzi ¹
• Sh. Oustan ¹
• A.A. Jafarzadeh ¹
• B. Minasny ²

¹ Tabriz University

² Australia

چکیده [English]

Introduction: Soils are considered as one of the most important parameters to be achieved the sustainable agriculture at any place in the world. Additionally, the digital environment needs to have a soil continuous maps at local and regional scales. However, such information are always not available at the required scale and mapping with high accuracy. Digital soil mapping (DSM) is a key for quantifying and assessing the variation of soil properties such as organic carbon (OC) especially in un-sampled and scarcely sampled areas. Using remotely sensed indices as an important auxiliary information relevant to the study area and data mining techniques were the pathway to create digital maps. Previous studies showed that digital elevation model (DEM) and remotely sensed data are the most commonly useful ancillary data for soil organic carbon prediction. the importance of DEM and derivative data in soil spatial modelling, it was not carried out in our research because there were no sharp differences in relief, and climate for that matter, across the study area. This research aims to investigate the spatial distribution of soil organic carbon (SOC) in a study area in north-western Iran using 21 remotely sensed indices as well as two data mining techniques namely Random Forests (RF) and Cubist.
Materials and Methods: This study was performed on the east shore of Urmia Lake located in the east Azerbaijan province, Iran. The area extension is about 500 km2. Based on the synoptic meteorological station report, the average annual precipitation and temperature of the study area is 345.37 mm and 10.83°C, respectively. Soil moisture and temperature regimes are Xeric and Mesic, respectively. Using stratified random soil sampling method, 131 soil samples (for the depth of 0-10 cm) were collected. Soil organic carbon (SOC) were then measured. The next step was to gather a suite of auxiliary data or environmental covariates thought to be useful (and available) for predicting SOC within a DSM framework for the region studied. Then, a number of remotely sensed imagery scenes from the Landsat 8-OLI acquired were collected in July 2017. The RF and Cubist models were applied to establish a relationship between soil organic carbon and auxiliary data. Both reflectance of the individual bands and indices derived from combinations of the individual bands were used. Fourteen spectral indices relevant to four types of data including: i) vegetation and soil; ii) water; iii) landscape; and iv) geology were gathered. Three different statistics was used for evaluating the performance of model in predicting SOC, namely the coefficient of determination (R2), mean error or bias (ME) and root mean square error (RMSE).
Results and Discussion: The results of the descriptive statistics of determined and calculated SOC for 131 soil samples showed that the mean and median values for SOC were 2.52% and 2.11%, respectively. Also, the CVs was recorded 57.94%. Minimum and maximum recorded values for SOC were 0.83% and 5.22%, respectively. The contents of SOC was left-skewed in the data set. The RF model prediction was quite good with calibration (R2= 0.89, MSE = 0.16 and ME = 0.01). While, in the Cubist calibration data set, the Valve of RMSE and ME were increased (R2= 0.85, MSE = 0.21 and ME = 0.03). In terms of R2, The RF model showed the higher value (0.89) compared with the Cubist model (0.85) for the validation dataset. Generally, the remote sensing (RS) spectral indices can successfully predict various SOC across the study area. The covariate importance rankings showed that VARI­, NDVI­, CRI2 and CRI1 were the four important covariates to predict SOC in the study area. Accordingly, the changes in SOC over space were not uniform across the study area and also it means that the study area is very dynamic and evolved over time.
Conclusion: The results of this study showed that although variables and auxiliary data had different importance in predicting the distribution of SOC, in general it can be found by modelling the relationship between them and SOC through the model. The results revealed that the RF model was suitable for the target variable. Accordingly, the auxiliary variables had different importance in predicting the spatial distribution of SOC. Remote sensing imagery, particularly those encompassing the combined indices played an important role in the prediction of SOC. The obtained results also indicated that the Visible Atmospherically Resistant Index (VARI) and Normalized Difference Vegetation Index (NDVI) were important to predict SOC. The current study revealed that DSM using important environmental covariates can be successfully used in Iran which there is no sufficient soil databases. This research also provided a pathway to start further works in the future such as DSM relevant to the soil erosion, soil ripening, trace elements and so on.

کلیدواژه‌ها [English]

• Cubist
• Digital soil mapping
• Environmental covariates
• Modelling
• random forest

مراجع

1- Adhikari K., Hartemink A.E., Minasny B., Bou Kheir R., and Greve M.B. 2014. Digital mapping of soil organic carbon contents and stocks in Denmark. PLoS One 9(8):1-13.

2- Ayoubi S., Shahri A.P., Karchegani P.M., and Sahrawat K.L. 2011. Application of artificial neural network (ANN) to predict soil organic matter using remote sensing data in two ecosystems. In Tech Publication 181-196.

3- Azarnivand H., Joneidi H., Zare Chahooki M.A., and Maddah Arefi H. 2011. Investigation of the effects of some ecological factors on carbon sequestration in Artemisia sieberi rangelands of Semnan province. Journal of Range and Watershed Management 64(1): 107-127. (In Persian with English abstract)

4- Banaei M.H. 1998. Soil moisture and temperature regime map of Iran. Soil and Water Research Institute. Ministry of Agriculture, Tehran, Iran.

5- Bernoux M., Carvalho M.C.S., Volkoff B., and Cerri C.C. 2002. Brazil’s soil carbon stocks. Soil Sciences Society American Journal 66(3): 888-896.

6- Bicheldey T.K., and Latushkina E. 2010. Biogass emission prognosis at the landfills. International Journal of Environmental Science and Technology 7(4): 623-628.

7- Boettinger J.L., Ramsey R.D., Bodily J.M., Cole N.J., Kienast-Brown S., Nield S.J., Saunders A.M., and Stum A.K. 2008. Landsat spectral data for digital soil mapping, in: Hartemink A.E., McBratney A.B., and Mendonca-Santos M. (eds.) Digital Soil Mapping with Limited Data. Springer, Dordrecht. p. 193-203.

8- Bonfatti B., Hartemink A.E., Giasson E., Tornquist C.G., and Adhikari K. 2016. Digital mapping of soil carbon in a viticultural region of Southern Brazil. Catena 261: 204-221.

9- Brahim N., Blavet D., Gallali T., and Bernoux M. 2011. Application of structural equation modeling for assessing relationships between organic carbon and soil properties in semiarid Mediterranean region. International Journal of Environmental Science and Technology 8(2): 305-320.

10- Breiman L. 2001. Random forests. Machine Learning 45: 5-32.

11- Brungard C.W. 2009. Alternative Sampling and Analysis Methods for Digital Soil Mapping in Southwestern Utah. Thesis for Master of Science, Utah State University, USA.

12- Brungard C.W., Boettinger J.L., Duniway M.C., Wills S.A., and Edwards T.C. 2015. Jr. Machine learning for predicting soil classes in three semi-arid landscapes. Geoderma 239-240: 68-83.

13- Carlson T., Gillies R., and Perry E. 1994. A method to make use of thermal infrared temperature and NDVI measurements to infer surface soil water content and fractional vegetation cover. Remote Sensing Reviews 9: 1-2.161-173.

14- Celik I. 2005. Land-use Effects on Organic Matter and Physical Properties of Soil in a Southern Mediterranean Highland of Turkey. Soil and Tillage Research 83: 270-277.

15- Chitsaz V. 1999. Investigation of Soil Salinity and Alkalinity Map in Isfahan East Area Using Digital Data. M.Sc. Degree in Desertification, Faculty of Natural Resources, Isfahan University of Technology.

16- Christensen B.T. 1996. Carbon in primary and secondary organomineral complexes. In structure and organic matter storage in agricultural soils in: Cater, M.R.; Stewart, B.A., (eds.) 97-165. CRC Press, Boca Raton.

17- Dai P.F., Qigang Z., Zhiqiang L.V., Xuemei W., and Gangcai L. 2014. Spatial prediction of soil organic matter content integrating artificial neural network and ordinary kriging in Tibetan Plateau. Ecological Indicators 45: 184-194.

18- Fang X., Xue Z.J., Li B.C., and An S.S. 2012. Soil organic carbon distribution in relation to land use and its storage in a small watershed of the Loess Plateau, China. Catena 88: 6-13.

19- Garcia-Pausas J., Casals P., Camarero L., Huguet C., Sebastia M.T., Thompson R., and Romanya J. 2007. Soil organic carbon storage in mountain grasslands of the Pyrenees: effects of climate and topography. Biogeochemistry 82: 279-289.

20- Gilabert M.A., Gonzalez-Piqueras J., Garcia-Haro F.J., and Melia J. 2002. A generalized soil adjusted vegetation index. Remote Sensing of Environment 82: 303-310.

21- Gitelson A.A., Kaufman Y.J., Stark R., and Rundquist D. 2002. Novel algorithms for remote estimation of vegetation fraction. Remote Sensing of Environment 80: 76-87.

22- Grimm R., Behrens T., Märker M., and Elsenbeer H. 2008. Soil organic carbon concentrations and stocks on Barro Colorado Island—digital soil mapping using random forests analysis. Geoderma 146: 102-113.

23- Haese R.R., Wallmann K., Dahmke A., Kretzmann U., Muller P.J., and Schulz H.D. 1997. Iron species determination to investigate early diagenetic reactivity in marine sediments. Geochimica et Cosmochimica Acta 61: 63-72.

24- Hengl T., Heuvelink G.B., Kempen B., Leenaars J.G., Walsh M.G., Shepherd K.D., Sila A., MacMillan R.A., de Jesus J.M., Tamene L., and Tondoh, J.E. 2015. Mapping soil properties of Africa at 250 m resolution: random forests significantly improve current predictions. PLoS One10: 1-26.

25- Hengl T., Toomanian N., Reuter H.I., and Malakouti M.J. 2007. Methods to interpolate soil categorical variables from profile observations: Lessons from Iran. Geoderma 140(4): 417-427.

26- Holmes G., Hall M., and Frank E. 1999. Generating rule sets from model trees. In: Foo N. (ed.) Advanced Topics in Artificial Intelligence. Lecture Notes in Artificial Intelligence, 1-12.

27- Hontoria C., Rodr´ ıguez-Murillo J.C., and Saa A. 1999. Relationships between soil organic carbon and site characteristics in Peninsular Spain. Soil Science Society of America Journal 63(3): 614-621.

28- IRIMO, 2012. Islamic Republic of Iran Meteorological Organization.

29- Koutika L.S., Chone T., Andreux F., Burtin G., and Cerri C.C. 1999. Factors influencing carbon decomposition of topsoils from the Brazilian Amazon Basin. Biology and Fertility of Soils 28(4): 436-438.

30- Kumar S., Lal R., and Liu D. 2012. A geographically weighted regression kriging approach for mapping soil organic carbon stock. Geoderma 189-190: 627-634.

31- LieB M., Glaser B., and Huwe B. 2012. Uncertainty in the spatial prediction of soil texture comparison of regression tree and random forest models. Groderma 170: 70-79.

32- Liu F., Zhang G., Sun Y., ZhaoY., and Li D. 2013. Mapping the Three-Dimensional Distribution of Soil Organic Matter across a Subtropical Hilly Landscape. Soil Science Society America Journal 77: 1241-1253.

33- Luoto M., and Hjort J. 2005. Evaluation of current statistical approaches for predictive geomorphological mapping. Geomorphology 67: 299-315.

34- McBratney A.B., Mendoça Santos M.L., and Minasny B. 2003. On digital soil mapping. Geoderma 117: 3-52.

35- McBratney A.B., Stockmann U., Angers D., Minasny B., and Field D. 2014. Challenges for Soil Organic Carbon Research. In Alfred E. Hartemink, Kevin McSweeney (eds.) Soil Carbon, p. 3-16. Cham: Springer.

36 Metternicht G.I., and Zinck J.A. 2003. Remote sensing of soil salinity: potentials and constraints. Remote Sensing of Environment 85: 1-20.

37- Moonjun R., Farshad A., Shrestha D.P., and Vaiphasa C. 2010. Artificial Neural Network and Decision Tree in Predictive Soil Mapping of Hoi Num Rin Sub-Watershed, Thailand. In: Boettinger J.L. Howell D.W. Moore A.C Hartemink A.E and Kienast-Brown S. (eds.) Digital Soil Mapping, Progress in Soil Science 2, p. 151- 164.

38- Nelson D.W., and Sommers L.E. 1996. Total Carbon, Organic Carbon, and Organic Matter. p. 961-1010. In: Sparks D.L. (ed.), Methods of Soil Analysis. Chemical Methods. Part 3. The American Society of Agronomy and Soil Science Society of America, Madison, Wisconsin.

39- Nobakht A., Pourmajidian M., Hojjati S.M., and Fallah A. 2011. A comparison of soil carbon sequestration in hardwood and softwood monocultures (Case study: Dehmian forest management plan, Mazandaran). Iranian Journal of Forest 3(1): 13-23. (In Persian with English abstract)

40- Pahlavan-Rad M.R., Toomanian N., Khormali F., Brungard C.W., Komaki C.B., and Bogaert P. 2014. Updating soil survey maps using random forest and conditioned Latin hypercube sampling in the loess derived soils of northern Iran. Geoderma 232-234: 97-106.

41- Palm C., Sanchez P., Ahamed S., and Awiti A. 2007. Soils: A contemporary perspective. Annual Review of Environment and Resources 32: 99-129.

42- Parks S.A., Dillon G.K., and Miller C. 2014. A new metric for quantifying burn severity: the relativized burn ratio. Remote Sensing 6: 1827-1844.

43- Paustian K., Levine E., Post W.M., and Ryzhova I.M. 1997. The use of models to integrate information and understanding of soil C at the regional scale. Geoderma 79(1-4): 227-260.

44- 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): 181-19.

45- Qi J., Chehbouni A.R., Kerr Y.H., and Sorooshian S. 1994. A Modified Soil Adjusted Vegetation Index. Remote Sensing of Environment 48: 119-126.

46- R Development Core Team. 2015. R: a language and environment for statistical computing. R. Foundation for Statistical Computing, Vienna, Austria. Available at http://www.informaworld.com/contentUa/V.24-2-2004/article9.htm (visited 5 September 2010).

47- Randall E.W., Mahieu D.S., Powlson D.S., and Christensen B.T. 1995. Fertilization effects on organic matter in physically fractionated soils as studied by 13C NMR: results from two long-term field experiments. European Journal of Soil Science 46(4): 449-459.

48- Shahbazi F., Hughes P., McBratney A., Minasny B., and Malone B. 2019a. Evaluating the spatial and vertical distribution of agriculturally important nutrients-nitrogen, phosphorous and boron-in North West Iran. Catena 173: 71-82.

49- Shahbazi F., McBratney A., Malone B., Oustan S., and Minasny B. 2019b. Retrospective monitoring of the spatial variability of crystalline iron in soils of the east shore of Urmia Lake, Iran using remotely sensed data and digital maps. Geoderma 337: 1196-1207.

50- Shahrabi M. 1994. The report of 1:250000 scale geological map of Urmia. Publication of Geological survey and Mineral Exploration Organization of Iran.

51- Sindayihebura A., Ottoy S., Dondeyne S., Meirvenne M.V., and Orshoven J.V. 2017. Comparing digital soil mapping techniques for organic carbon and clay content: Case study in Burundi's central plateaus. Catena 156: 161-175.

52- Skakun R.S., Wulder M.A., and Franklin S.E. 2003. Sensitivity of the thematic mapper enhanced wetness difference index to detect mountain pine beetle red-attack damage. Remote Sensing of Environment 86: 433-443.

53- Smith C.A.S., Daneshfar B., and Frank G. 2012. Use of weights of evidence statistics to define inference rules to disaggregate soil survey maps. p. 215-220. In: Minasny B., Malone B.P., and McBratney A. (eds.) Digital Soil Assessments and Beyond: Proceedings of the 5th Global Workshop on Digital Soil Mapping. CRC Press, Sydney.

54- Sreenivas K., Dadhwal V.K., Kumar S., Sri Harsha G., Mitran T., Sujatha G., Janaki Rama Suresh G., Fyzee M.A., and Ravisankar T. 2016. Digital organic and inorganic carbon mapping of India. Geoderma 269: 160-173.

55- Stoorvogel J.J., Kempen, B., Heuvelink, G.B.M., and de Bruin S. 2009. Implementation and evaluation of existing knowledge for digital soil mapping in Senegal. Geoderma 149: 169-170.

56- Taghizadeh-Mehrjardi R., Nabiollahi K., and Kerry R. 2016. Digital mapping of soil organic carbon at multiple depths using different data mining techniques in Baneh region, Iran. Geoderma 266: 98-110.

57- Triantifilis J., Earl N.Y., and Gibbs I.D. 2012. Digital soil-classmapping across the Edgeroi district using numerical clustering and gamma-ray spectrometry data. p. 187-191. In: Minasny B., Malone B.P., and McBratney A. (eds.) Digital Soil Assessments and Beyond: Proceedings of the 5th Global Workshop on Digital Soil Mapping, CRC Press, Sydney.

58- Van Zijl G.M., le Roux P.A.L., and Smith A.B. 2012. Rapid soil mapping under restrictive conditions in Tete, Mozambique. p. 335-339. In: Minasny B. Malone B.P. and McBratney A. (eds.) Digital Soil Assessments and Beyond: Proceedings of the 5th Global Workshop on Digital Soil Mapping. CRC Press, Sydney.

59- Varamesh S., Hosseini S.M., Abdi N., and Akbarinia M. 2010. Increment of soil carbon sequestration due to forestation and its relation with some physical and chemical factors of soil. Iranian Journal of Forest 2(1): 25-35. (In Persian with English abstract)

60- Vasques G.M., Grunwald S., and Sickman J.O. 2008. Comparison of multivariate methods for inferential modeling of soil carbon using visible/near-infrared spectra. Geoderma 146: 14-25.

61- Vaysse K., and Lagacherie K. 2015. Evaluating Digital Soil Mapping approaches for mapping GlobalSoilMap soil properties from legacy data in Languedoc- Roussillon (France). Geoderma Regional 4: 20-30.

62- Were K., Bui D.T., Dick Q.B., and Singh B.R. 2015. A comparative assessment of support vector regression, artificial neural networks, and random forests for predicting and mapping soil organic carbon stocks across an Afromontane landscape. Ecological Indicators 52: 394-403.

63- Xu, H. 2006. Modification of normalised difference water index (NDWI) to enhance open water features in remotely sensed imagery. International Journal of Remote Sensing 27: 3025-3033.

64- Zhang S., Huang Y., Shen C., Ye H., and Du Y. 2012. Spatial prediction of soil organic matter using terrain indices and categorical variables as auxiliary information. Geoderma 171: 35-43.