میزان همخوانی نقشه‌های حاصل از روش‌های یادگیری ماشین و تخمینگر کریجینگ در پایش شوری بخشی از اراضی حاشیه‌ای پلایای سیرجان، استان کرمان

نوع مقاله : مقاله پژوهشی

نویسندگان

1 دانش‌آموخته مقطع کارشناسی‌ارشد گروه علوم و مهندسی خاک، دانشکده کشاورزی، دانشگاه ولی‌عصر رفسنجان

2 استادیار بخش تحقیقات خاک و آب، مرکز تحقیقات و آموزش کشاورزی و منابع طبیعی استان چهارمحال و بختیاری، سازمان تحقیقات، آموزش و ترویج

3 استاد گروه علوم و مهندسی خاک، دانشکده کشاورزی، دانشگاه ولی عصر رفسنجان، رفسنجان، ایران

چکیده

تصاویر ماهواره‌ای و رویکردهای سنجش از دور، ابزار مهمی برای ارزیابی، نقشه‌برداری و مدیریت اراضی شور در مناطق مختلف جهان به‌شمار می‌آیند. هدف اصلی از مطالعه حاضر، بررسی میزان همخوانی نقشه­های حاصل از روش­های یادگیری ماشین و تخمینگر کریجینگ  برای پایش شوری بخشی از خاک‌های حاشیهی پلایای سیرجان در دو فصل زمستان و تابستان با استفاده از دو منبع داده سنجش از دور (لندست 8 و سنتینل 2)  می­باشد. 90 نمونه خاک سطحی (صفر تا 30 سانتی­متر) در قالب یک الگوی نمونه­برداری شبکه­ای منظم با فواصل 750 متر برداشت شد. برخی از مهمترین ویژگی­های فیزیکی و شیمیایی آن­ها با استفاده از روش­های استاندارد اندازه­گیری شد. همچنین پس از انجام تصحیح‌های رادیومتریکی و اتمسفری بر روی تصاویر ماهواره­ای مزبور، علاوه بر باندهای اصلی، از 13 شاخص­ طیفی (شاخص شوری) به­منظور تخمین شوری خاک با استفاده از مدل­های شبکه عصبی مصنوعی، درخت تصمیم، جنگل تصادفی و ماشین ­بردار پشتیبان استفاده شد. به‌علاوه، نقشه‌های کریجینگ شوری خاک برای هر دو زمان گفته‌شده ترسیم شدند. نتایج نشان داد که ماهواره سنتینل 2 نسبت به  داده‌های ماهواره لندست 8، از صحت بالاتری (ضریب تبیین 87/0 در مقابل 72/0) برای پیش‌بینی تغییرات شوری در منطقه مورد مطالعه برخوردار بود. علاوه بر این، بهترین نتایج برای برآورد قابلیت هدایت الکتریکی عصاره اشباع خاک در فصل­ زمستان با استفاده از تصاویر سنتینل 2 و مدل شبکه عصبی مصنوعی (R2=0.77, RMSE%=27.1 ) و در فصل تابستان بر اساس تصاویر ماهواره سنتینل 2 و مدل جنگل تصادفی (R2=0.87, RMSE%=17.4 ) برای منطقه مطالعاتی به دست آمدند. از ­بین شاخص‌های شوری مورد مطالعه، شاخص VSSI به­عنوان مؤثرترین شاخص برای برآورد شوری خاک منطقه انتخاب شد. نتایج همچنین نشان داد که نقشه‌های قابلیت هدایت الکتریکی عصاره اشباع خاک حاصل از دو روش از میزان همخوانی زیاد و صحت عمومی بالای 80 درصد برخوردار بودند؛ با این حال، تغییر فصل و نوع ماهواره بر میزان تطابق‌پذیری نقشه‌های به­دست آمده اثرگذار بود.

کلیدواژه‌ها

موضوعات

عنوان مقاله [English]

The Matching Rate of Maps Obtained by Machine Learning Methods and Kriging Estimator in Salinity Monitoring of a Part of the Marginal Lands of Sirjan Playa, Kerman Province

نویسندگان [English]

  • Mojdeh Golestani 1
  • zohreh mosleh 2
  • Isa Esfandiarpour Boroujeni 3
  • Hossein Shirani 3
1 MSc Student of Soil Science Department, College of Agriculture, Vali-e-Asr University of Rafsanjan, Rafsanjan, Iran
2 Assistant Prof. of Soil and Water Research Department, Chaharmahal and Bakhtiari Agricultural and Natural Resources Research and Education Center, Agricultural Research, Education and Extension Organization (AREEO), Shahrekord, Iran te
3 Professor of Soil Science, Department of Soil Science, Faculty of Agriculture, Vali-e-Asr University of Rafsanjan, Rafsanjan, Iran
چکیده [English]

Satellite images and remote sensing approaches are important tools for evaluating, mapping, and managing saline lands in different world regions. The main aim of the present study was to investigate the degree of concordance between maps obtained by machine learning methods and kriging estimator about salinity monitoring of a part of the soils of marginal lands of Sirjan Playa in two seasons, i.e., winter and summer, using two remote sensing data sources, i.e., Landsat 8 and Sentinel 2. Ninety surface soil samples (zero to 30 cm) were collected as a regular grid sampling pattern with 750 meters intervals. Some of their most important physical and chemical characteristics were determined using standard measurement methods. After performing radiometric and atmospheric corrections on mentioned satellite images, in addition to the main bands, 13 salinity indices were used to estimate soil salinity using artificial neural network, decision tree, random forest, and support vector machine models. Besides, kriging maps of soil salinity were drawn for both mentioned times. Results showed a higher performance (R2 =0.87 versus= 0.72) of Sentinel-2 than Landsat-8 in predicting soil salinity.  Moreover, results confirmed that the ANN model developed by Sentinel-2A image had the highest performance (R2 =0.77, RMSE% =27.1) to predict ECe in the winter season. Furthermore, RF presents the lowest error (R2 =0.87, RMSE% =17.4) for prediction ECe during the summer season. Among the studied salinity indices, VSSI index was also selected as the most effective index to estimate soil salinity of region. The results also showed that ECe maps obtained by two methods had a high level of concordance and an overal accuracy of over 80%; however, the change of season and type of satellite affectedthe compatibility of the maps.

کلیدواژه‌ها [English]

  • Sentinel 2
  • Salinity index
  • Kriging
  • Landsat 8
  • Modeling

مراجع

Abbasnejad A., Shahidasht A. 2013. Vulnerability of Sirjan plain due to aquifer over abstraction. Geography and territorial spatial arrangent, 3 (7): 85-96.
Abdul-Qadir A. M. H., and Benni T. J. 2010. Monitoring and evaluation of soil salinity in term of spectral response using Landsat images and GIS in Mesopotamian plain/Iraq. Journal of Iraqi Desert Studies, 2 (2): 19-32.
Abulaiti A., Nurmemet I., Muhetaer N., Xiao S. and Zhao J. 2022. Monitoring of soil salinization in the Keriya Oasis based on deep learning with PALSAR-2 and Landsat-8 datasets. Sustainability, 14 (5): 2666-2675.
Afrasinei G. M., Melis M. T., Buttau C., Bradd J. M., Arras C. and Ghiglieri G. 2017. Assessment of remote sensing-based classification methods for change detection of salt-affected areas (Biskra area, Algeria). Journal of Applied Remote Sensing, 11(1): 160-185.
Akhzari D., Asadi Meyabadi A. 2016. Soil salinity map preparation using spectral analysis of OLI sensor and field data (Case study: Southern parts of Malayer plain). RS & GIS for Natural Resources, 7 (2): 87-100.
Alamdar S., Ghazban F. and Zarei A. 2023. Efficiency of Machine Learning Algorithms in Soil Salinity Detection Using LANDSAT-8 Oli Imagery. ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences, 10:  49-55.
Alexakis D. D., Daliakopoulos I. N., Panagea I. S. and Tsanis I. K. 2018. Assessing soil salinity using World View-2 multispectral images in Timpaki, Crete, Greece. Geocarto International, 33(4): 321-338.
Alison L. E. and Moodie C. D. 1965. Carbonate. In: C. A., Black et al. (Eds.), Methods of soil analysis. Part II. Soil Science Society of America and American Society of Agronomy, Madison, pp. 1379-1396.
Aksoy S., Yildirim A., Gorji T., Hamzehpour N., Tanik A. and Sertel E. 2022. Assessing the performance of machine learning algorithms for soil salinity mapping in Google Earth Engine platform using Sentinel-2A and Landsat-8 OLI data. Advances in Space Research, 69: 1072–1086.
Akramkhanov, A. 2005. The spatial distribution of soil salinity: detection and prediction. Ph.D dissertation, ZEF Ecology and Development, Cuvillier Verlag, Göttingen, Germany.
Allbed A. and Kumar L. 2013. Soil salinity mapping and monitoring in arid and semi-arid regions using remote sensing technology: a review. Advances in Remote Sensing, 2 (4): 373-385.
Avdan U., Kucuk Matci D., Kaplan G., Yigit Avdan Z., Erdem F., Demirtas I. and Mızık E.T. 2021. Evaluating the atmospheric correction impact on Landsat 8 and Sentinel-2 data for soil salinity determination. Geodetski List, 75(3): 225-240.
Bagheri Bodaghabadi M., Martinez-Casasnovas J. A., Salehi M. H., Mohammadi J., Esfandiarpoor Borujeni I., Toomanian N. and Gandomkar A. 2015. Digital soil mapping using artificial neural networks and terrain-related attributes. Pedosphere, 25: 580–591.
Bouyoucos G. J. 1951. A recalibration of hydrometer method for making mechanical analysis of soil. Agronomy, 43: 434-438.
Byrt T., Bishop J. and Carling J. B. 1993. Bias, prevalence and kappa. Journal of Clinical Epidemiology, 46: 423- 429.
Cambardella C.A., Moorman T.B., Novak J.M., Parkin T.B., Karlen D.L., Turco R.F. and Konopka A.E. 1994. Field‐scale variability of soil properties in central Iowa soils. Soil science society of America journal, 58(5): 1501-1511.
Chen Y., Qiu Y., Zhang Z., Zhang J., Chen C., Han J. and Liu D. 2020. Estimating salt content of vegetated soil at different depths with Sentinel-2 data. PeerJ, 8: e10585.
Congalton R. C. and Green K. 2009. Assessing the Accuracy of Remotely Sensed Data: Principles and Practices. 3nd Ed. CRC Press, Taylor and Francis Group, London, New York, 348p.
Davis E., Wang C. and Dow K. 2019. Comparing Sentinel-2 MSI and Landsat 8 OLI in soil salinity detection: A case study of agricultural lands in coastal North Carolina. International Journal of Remote Sensing, 40 (16): 6134-6153.
Day J.H. 1983. The Canadian Soil Information System (CanSIS). Manual for Describing Soils in the Field. Agriculture Canada Expert committee on soil survey.Branch, Ottawa, Ontario, 175p.
Ding J. and Yu D. 2014. Monitoring and evaluating spatial variability of soil salinity in dry and wet seasons in the Werigan-Kuqa Oasis, China, using remote sensing and electromagnetic induction instruments. Geoderma, 235: 316–322.
Duan Z., Wang X. and Sun L. 2022. Monitoring and mapping of soil salinity on the exposed seabed of the Aral sea, Central Asia. Water, 14 (9): 1438.
Elhag M. 2016. Evaluation of different soil salinity mapping using remote sensing techniques in arid ecosystems, Saudi Arabia. Journal of Sensors, 2016: 1-8.
Fan X., Weng Y. and Tao J. 2016. Towards decadal soil salinity mapping using Landsat time series data. International Journal of Applied Earth Observation and Geoinformation, 52: 32-41.
Farahmand N. and Sadeghi V. 2020. Estimating soil salinity in the dried lake bed of Urmialake using optical Sentinel-2 images and nonlinear regression models. Journal of the Indian Society of Remote Sensing, 48 (4): 675-687.
Fathizadeh H., Ardakani M. A. H., Sodaiezadeh H., Kerry R. and Taghizadeh-Mehrjardi R. 2020. Investigation of the spatial and temporal variation of soil salinity using random forests in the central desert of Iran. Geoderma, 365: 114233.
Feng J., Ding J. and Wei W. 2019. Soil salinization monitoring based on Radar data. Remote Sensing for Land and Resources, 1: 195-203.
Jiang H., Rusuli Y., Amuti T. and He Q. 2019. Quantitative assessment of soil salinity using multi-source remote sensing data based on the support vector machine and artificial neural network. International Journal of Remote Sensing, 40 (1): 284-306.
Gorji T., Sertel E. and Tanik A. 2017. Monitoring soil salinity via remote sensing technology under data scarce conditions: A case study from Turkey. Ecological Indicators, 74: 384-391.
Gorji T., Yildirim A., Hamzehpour N., Tanik A. and Sertel E. 2020. Soil salinity analysis of Urmia Lake Basin using Landsat-8 OLI and Sentinel-2A based spectral indices and electrical conductivity measurements. Ecological Indicators, 112: 106173.
Gopalakrishnan T. and Kumar L. 2020. Modeling and mapping of soil salinity and its impact on paddy lands in Jaffna Peninsula, Sri Lanka. Sustainability, 12(20): 8317.
Grunwald S. 2009. Multi-criteria characterization of recent digital soil mapping and modeling approaches. Geoderma, 152(3-4): 195-207.
He Y., Zhang Z., Xiang R., Ding B., Du R., Yin H., Chen Y. and Ba Y. 2023. Monitoring salinity in bare soil based on Sentinel-1/2 image fusion and machine learning. Infrared Physics & Technology, 104656.
Hesse P. R. 1976. Particle size distribution in gypsic soils. Plant and Soil, 44 (1):  241-247.
Huang X., Cao Y. and Li J. 2020. An automatic change detection method for monitoring newly constructed building areas using time-series multi-view high-resolution optical satellite images. Remote Sensing of Environment, 244: 111802.
Ivushkin K., Bartholomeus H., Bregt A. K., Pulatov A., Kempen B. and De Sousa L. 2019a. Global mapping of soil salinity change. Remote Sensing of Environment, 231: 111260.
Ivushkin K., Bartholomeus H., Bregt A. K., Pulatov A., Franceschini M. H., Kramer H. and Finkers R. 2019b. UAV based soil salinity assessment of cropland. Geoderma, 338: 502-512.
Kazemi Garajeh M., Blaschke T., Hossein Haghi V., Weng Q., Valizadeh Kamran K. and Li Z. 2022. A comparison between Sentinel-2 and Landsat 8 OLI satellite images for soil salinity distribution mapping using a deep learning convolutional neural network. Canadian Journal of Remote Sensing, 48 (3): 452-468.
Khajehzadeh M., Afzali S. F., Honarbakhsh A. and Ingram B. 2022. Remote sensing and GIS-based modeling for predicting soil salinity at the watershed scale in a semi-arid region of southern Iran. Arabian Journal of Geosciences, 15 (5): 1-10.
Khaleghi R., Behmanesh J., Azad N. 2017. Prediction of Soil Salinity Using Multivariable Regression on the Basis of Extracted Indices from Landsat 8 Satellite (Case study: Urmia). Applied Soil Research, 7 (1): 108-120.
Kim-Anh N., Liou Y. A., Tran H. P., Hoang P. P. and Thanh-Hung N. 2020. Soil salinity assessment by using near-infrared channel and Vegetation Soil Salinity Index derived from Landsat 8 OLI data: a case study in the Tra Vinh Province, Mekong Delta, Vietnam. Progress in Earth and Planetary Science, 7 (1): 1-16.
Klute A. 1986. Methods of soil analysis. Part I. Physical and mineralogical methods. Soil Science Society of America, Madison, WI. 687-734.
Krinsley, D.B., 1970. A geomorphological and paleoclimatological study of the playas of Iran, first ed. Geological Survey U.S. Department of Interior, Washington D.C, 180p.
Kumar S., Gautam G. and Saha S. K. 2015. Hyperspectral remote sensing data derivedspectral indices in characterizing salt-affected soils: a case study ofIndo-Gangetic plains of India. Environmental Earth Sciences, 73 (7): 3299–3308.
Lanyon L. E. and Heald W. R. 1982. Magnesium, Calcium, Strontium and Barium. In: A. L., Page et al. (Eds), Methods of soil Analysis. Part II. Soil Science Society of America and American Society of Agronomy, Madison, pp. 247-260.
 Masoud A. A., Koike K., Atwia M. G.,  El-Horiny M. M. and Gemail K. S. 2019. Mapping soil salinity using spectral mixture analysis of landsat 8 OLI images to identify factors influencing salinization in an arid region. International Journal of Applied Earth Observation and Geoinformation, 83: 101944.
Mehrabi M., Hamzeh S., Alavipanah S.K., Kiavarz M., Ziaee R. 2019. Estimating soil moisture using remotely sensed data and surface energy balance system. Journal of Watershed Engineering and Management, 11 (3): 759-770.
Mohamed E. S., Saleh A. M., Belal A. B. and Gad A. 2018. Application of near-infrared reflectance for quantitative assessment of soil properties. The Egyptian Journal of Remote Sensing and Space Science, 21(1): 1-14.
Morgan R. S., El-Hady M. A. and Rahim I. S. 2018. Soil salinity mapping utilizing sentinel-2 and neural networks. Indian Journal of Agricultural Research, 52 (5): 524-529.
Nelson R. E., Klameth L. C. and Nettleton W. D. 1978. Determining soil gypsum content and expressing properties of gypsiferous soils. Soil Science Society of America Journal, 42 (4), 659-661.
Neyestani M., Farpoor M.H., 2014. Genesis, clay mineralogy and micromorphology of saline-gypsiferous soils in Kheirabad playa, Sirjan. Arid Biome Scientific and Research Journal, 4 (1): 65- 77.
Noroozi A.A., Abkar A., Damizadeh M., Arasto B. 2018. Iranian Journal of Range and Desert Research, 26 (1): 117- 130.
Nurmemet I., Sagan V., Ding J. L., Halik Ü., Abliz A. and Yakup Z. 2018. A WFS-SVM model for soil salinity mapping in keriya oasis, Northwestern china using polarimetric decomposition and fully PolSAR data. Remote Sensing, 10 (4): 598-609.
Oster J.D. and Sposito G. 1980. The Gapon coefficient and the exchangeable sodium percentage‐sodium adsorption ratio relation. Soil Science Society of America Journal, 44 (2): 258-260.
Park H. M. 2008. Univariate Analysis and Normality Test using SAS, Stata and SPSS. The University Information Technology Services (UITS) Center for Statistical and Mathematical Computing, Indiana University, 41.
Peng J., Biswas A., Jiang Q., Zhao R., Hu J., Hu B. and Shi Z. 2019. Estimating soil salinity from remote sensing and terrain data in southern Xinjiang Province, China. Geoderma, 337: 1309-1319.
Richards L. A. 1954. Diagnosis and Improvement of Saline-Alkali Soils. USDA Hand Book, Washington DC, USA, 166p.
Robinson T. P. and Metternicht G. 2006. Testing the performance of spatial interpolation techniques for mapping soil properties. Computers and Electronics in Agriculture, 50 (2): 97-108.
Rossiter D. G. and Loza A. V. 2010. Technical note: Analyzing land cover change with logistic regression in R. ITC, Enschede, the Netherlands.
Sahbeni G. 2021. Soil salinity mapping using Landsat 8 OLI data and regression modeling in the Great Hungarian Plain. SN Applied Sciences, 3 (5): 1-13.
Seifi M., Ahmadi A., Neyshabouri M. R., Taghizadeh-Mehrjardi R. and Bahrami H. A. 2020. Remote and Vis-NIR spectra sensing potential for soil salinization estimation in the eastern coast of Urmia hyper saline lake, Iran. Remote Sensing Applications: Society and Environment, 20: 100398.
Sidike A., Zhao S. and Wen Y. 2014. Estimating soil salinity in Pingluo County of China using QuickBird data and soil reflectance spectra. International Journal of Applied Earth Observation and Geoinformation, 26: 156-175.
Shahmoradi S, Ghaffarian Malmiri H.R., Sharifi Pichoon M. 2021. Modeling and Mapping of Soil Salinity and Moisture Using Spectral and Radar Remote Sensing. Applied Soil Research, 10 (3): 43-65.
Taghizadeh Mehrjardi R., KhademiH, Khayamim F., Zeraatpisheh M., Heung B. and Scholten T. 2022. A Comparison of model averaging techniques to predict the spatial distribution of soil properties. Remote Sensing, 14 (3): 472-481.
Tran T. V., Tran D. X., Myint S. W., Huang C. Y., Pham H. V., Luu T. H. and Vo T. M. 2019. Examining spatiotemporal salinity dynamics in the Mekong River Delta using Landsat time series imagery and a spatial regression approach. Science of the total environment, 687: 1087-1097.
Vasques G. M., Grunwald S. and Harris W. G. 2010. Spectroscopic models of soil organic carbon in Florida, USA. Journal of Environmental Quality, 39 (3): 923-934.
Wang J., Ding J., Yu D., Ma X., Zhang Z., Ge X., Teng D., Li X., Liang J., Lizaga I. and Chen X. 2019. Capability of Sentinel-2 MSI data for monitoring and mapping of soil salinity in dry and wet seasons in the Ebinur Lake region, Xinjiang, China. Geoderma, 353: 172-187.
Wang J., Ding J., Yu D., Teng D., He B., Chen X., Ge X., Zhang Z., Wang Y., Yang X., Shi T. and Su F. 2020. Machine learning-based detection of soil salinity in an arid desert region, Northwest China: A comparison between Landsat-8 OLI and Sentinel-2 MS. Science of the Total Environment, 707: 136092.
Wang J., Peng J., Li H., Yin C., Liu W., Wang T. and Zhang H. 2021. Soil salinity mapping using machine learning algorithms with the Sentinel-2 MSI in arid areas. China. Remote Sensing, 13 (2):305.
Wilding L. 1985. Spatial variability: its documentation, accommodation and implication to soil surveys. In: Nielsen, D. R. and Bouma, J. (Eds.). Soil Spatial Variability, Proc. of a workshop of ISSS and SSA. Pudoc Wageningen, the Netherlands: Centre for Agriculture. Publishing and Documentation, pp. 166‐189.
Yahiaoui I., Bradaï A., Douaoui A. and Abdennour M. A. 2021. Performance of random forest and buffer analysis of Sentinel-2 data for modelling soil salinity in the Lower-Cheliff plain (Algeria). International Journal of Remote Sensing, 42 (1): 148-171.
Yimer A. M., Sodango T. H. and Abi Assefa S. 2022. Analysis and modeling of soil salinity using Sentinel-2A and Landsat-8 images in the Afambo irrigated area, Afar Region, Ethiopia. Search Life-Sciences Literature, Preprints.org; DOI: 10.20944/preprints202204.0250.v1.
Zarei A., Hasanlou M. and Mahdianpari M. 2021. A comparison of machine learning models for soil salinity estimation using multi-spectral earth observation data. ISPRS Annals of the Photogrammetry. Remote Sensing and Spatial Information Sciences, 3: 257-263.

فایل ها

سابقه مقاله

  • تاریخ دریافت: 02 شهریور 1402
  • تاریخ بازنگری: 18 آذر 1402
  • تاریخ پذیرش: 28 آذر 1402

هم رسانی

ارجاع به این مقاله

آمار