برآورد زیست توده گندم زمستانه (Triticum aestivum L.) با استفاده از مدل‌های رگرسیون خطی چندگانه، شبکه عصبی مصنوعی و داده‌های سنجش از دور

نوع مقاله : مقاله پژوهشی

نویسندگان

1 دانشجوی دکتری ، زراعت/دانشکده کشاورزی/ دانشگاه شهرکرد/شهرکرد/ایران

2 دانشیار ، خاکشناسی، دانشکده کشاورزی، دانشگاه شهرکرد، ایران

3 دانشیار ، گروه زراعت، دانشکده کشاورزی، دانشگاه شهرکرد، ایران

چکیده

سابقه و هدف: زیست‌توده ارتباط حیاتی بین مصرف انرژی خورشیدی و عملکرد گیاه را فراهم می‌کند، بنابراین برآورد صحیح آن برای پایش دقیق رشد محصول و پیش‌بینی عملکرد بسیار مهم است و به مدیران کشاورزی برای بهبود مدیریت زمین‌های زراعی کمک می‌کند. در چند دهه اخیر، سنجش از دور به عنوان ابزاری برای تخمین پارامترهای بیوفیزیکی گیاه به صورت گسترده مورد استفاده قرار گرفته است. توانایی فناوری سنجش از دور برای تخمین زیست‌توده گیاهی امید بخش، سریع، دوره‌ای و غیرمخرب است. بدین منظور، این تحقیق با هدف کاربرد فناوری سنجش از دور و مقایسه دو مدل آماری رگرسیون خطی چندگانه و شبکه عصبی مصنوعی برای برآورد زیست‌توده گندم زمستانه در شهرستان شهرکرد، استان چهارمحال و بختیاری در سال 1396 انجام شد.
مواد و روش‌ها: در این پژوهش به منظور برآورد زیست‌توده گیاه گندم به وسیله تصاویر ماهواره لندست 8، هشت مزرعه زیر کشت گندم زمستانه با مساحت بین 10 تا 60 هکتار در سراسر شهرستان شهرکرد، در نظر گرفته شد. سپس موقعیت 120 واحد نمونه-برداری به صورت تصادفی در مزارع مورد مطالعه توسط GPS تعیین گردید. واحدهای نمونه‌برداری به صورت مربع‌های 30×30 متری مطابق با پیکسل‌های لندست بود. هر یک از این واحدها، شامل 5 پلات 25/0 مترمربعی در چهار گوشه و مرکز مربع می‌باشد. درطی فصل رشد در تاریخ‌های 31 فروردین (20 آوریل)، 1 خرداد (22 می)، 2 تیر (23 ژوئن) و 3 مرداد (25 ژولای) سال 1396 همزمان با عبور ماهواره لندست 8 به مزارع مراجعه و نمونه‌برداری انجام گردید. جمع‌آوری داده‌های میدانی شامل زیست‌توده اندام هوایی و شمارش تعداد بوته‌ها در هر پلات بود. سپس نمونه‌ها به آزمایشگاه منتقل گردیده و آون خشک و وزن شدند. همزمان داده-های مربوط به سنجش از دور ماهواره لندست 8 در این تاریخ‌ها به دست آمد و شاخص‌های گیاهی به کمک باندهای ماهواره‌ای محاسبه شد. در این بررسی زیست‌توده گندم با استفاده از 25 شاخص گیاهی و دو روش رگرسیون خطی چند متغیره و شبکه عصبی مصنوعی (Artificial Neural Network, ANN) برآورد شد. مدل شبکه عصبی مصنوعی پرسپترون با چندلایه (پیش‌خور) طراحی شد و کارایی آن با نتایج مدل رگرسیون خطی چند متغیره مقایسه گردید. اعتبارسنجی و آزمون مدل ها و مقایسه نتایج این دو مدل با استفاده از آماره‌هایی نظیر ضریب تبیین (R2)، شاخص جذر میانگین مربعات خطا (RMSE)، و میانگین خطا (ME) انجام گرفت.
یافته‌ها: نتایج نشان داد که مدل شبکه عصبی مصنوعی با 83/0=R2 و g/m2 91/53=RMSE برای داده‌های آموزش و 85/0=R2 و g/m2 74/46=RMSE برای داده‌های آزمون و مدل رگرسیون خطی چند متغیره با 78/0=R2 و g/m2 68/65=RMSE زیست‌توده را برآورد کرده‌اند. در روش رگرسیون خطی چند متغیره، شاخص‌های EVI، CIgreen، PSRI، CRI، VARI و GNDVI به ترتیب مؤثرترین شاخص در تخمین میزان زیست‌توده محصول بودند. شاخص‌های GI، SAVI، ARVI، CRI، EVI، NDWI، MSR و NDVI به ترتیب بیشترین حساسیت را در رابطه با زیست‌توده گندم در مدل شبکه عصبی مصنوعی داشتند.
نتیجه‌گیری: یافته‌های پژوهش حاضر نشان داد که با بهره‌گیری از تصاویر ماهواره‌ای و توسعه مدل‌های آماری پارامتری و غیرپارامتری امکان برآورد زیست‌توده گندم زمستانه در منطقه مورد مطالعه وجود دارد. همچنین روش شبکه عصبی مصنوعی نسبت به روش رگرسیون خطی چندگانه صحت پیش‌بینی بهتری دارد و لذا استفاده از این روش به عنوان یک رهیافت مناسب در برآورد زیست‌توده گندم زمستانه پیشنهاد می‌شود.

کلیدواژه‌ها

عنوان مقاله [English]

Estimation of above-ground biomass of winter wheat (Triticum aestivum L.) using multiple linear regression, artificial neural network models remote sensing data

نویسندگان [English]

  • Maryam Soltanian 1
  • Mehdi Naderi Khorasgani 2
  • Ali Tadayyon 3
1 Agronomy Department, Faculty of Agriculture, Shahrekord University, Shahrekord, IRAN
2 Pedology Department, Faculty of Agriculture, Shahrekord University, Shahrekord, IRAN.
3 Agronomy Department, Faculty of Agriculture, Shahrekord University, Shahrekord, IRAN
چکیده [English]

Background and objectives: Above-ground biomass (AGB) provides a vital link between solar energy consumption and crop yield, so accurate estimation of biomass is very important for accurate monitoring of crop growth and yield prediction and helps agricultural managers to improve crop management. In recent decades, remote sensing has been widely used as a tool to estimate crop biophysical parameters. The potentials of remote sensing techniques promise fast, periodical, and non-destructive estimation of above-ground biomass. For this purpose, this study was conducted with the aim of applying remote sensing technology and comparing two statistical models of multiple linear regression and artificial neural network to estimate winter wheat biomass in Shahrekord County, Chaharmahal and Bakhtiari province in 2017.
Materials and methods: In this study, in order to estimate the wheat biomass by Landsat 8 satellite images, eight fields under winter wheat cultivation with an area between 10 to 60 hectares throughout Shahrekord County were considered. Then the location of 120 sampling units was randomly determined by GPS. Samples units were taken as 30 × 30 m squares according to Landsat pixels. Each of these units includes 5 plots of 0.25 m2 in four corners and the center of the square. During the growing season, on 20th April, 22nd May, 23rd June, and 25th July 2017, at the same time the satellite passes, sampling was carried out on farms. Field data collection included above-ground biomass and counting the number of plants per plot. Then the samples were transferred to the laboratory and dried and weighed. At the same time, data from Landsat 8 satellite remote sensing were obtained at these dates, and vegetation indices were calculated using satellite bands. In this study, wheat biomass was estimated using 25 vegetation indices and multivariate linear regression (MLR) and artificial neural network methods (ANN). Multilayer perceptron artificial neural network model (feed-forward) was designed and its performance was compared with multivariate linear regression model. To construct and validate the model and compare the results of these two models, statistics such as coefficient of determination (R2), root mean square error index (RMSE) and mean error (ME) were used.
Results: The results showed that the ANN model with R2=0.83 and RMSE=53.91 g/m2 for training data and R2=0.85 and RMSE=46.74 g/m2 for test data and multivariate linear regression model with R2=0.78 and RMSE=65.68 g/m2 estimated biomass. In multivariate linear regression, EVI, CIgreen, PSRI, CRI, VARI, and GNDVI indices are the most effective indices for estimating crop biomass, respectively. GI, SAVI, ARVI, CRI, EVI, NDWI, MSR, and NDVI indices were the most sensitive to wheat biomass in ANN model, respectively.
Conclusion: The findings of the present study showed that the use of satellite images and developing parametric and non-parametric statistical models helps to estimate winter wheat biomass in the study area. Also, the artificial neural network method has better predictive accuracy than the multiple linear regression method. Therefore, the use of this method as a suitable approach in estimating winter wheat biomass is suggested.

کلیدواژه‌ها [English]

  • : Artificial Neural Network
  • Biomass
  • Remote Sensing
  • Vegetation Index
  • Wheat

مراجع

  1.   Ali, I., Greifeneder, F., Stamenkovic, J., Neumann, M., and Notarnicola, C. 2015. Review of machine learning approaches for biomass and soil moisture retrievals from remote sensing data. Remote Sens. 7: 12. 16398-16421.

    1. Atzberger, C., Darvishzadeh, R., Immitzer, M., Schlerf, M., Skidmore, A., and le Maire, G. 2015. Comparative analysis of different retrieval methods for mapping grassland leaf area index using airborne imaging spectroscopy. Int. J. Appl. Earth Obs. Geoinf. 43: 19-31.
    2. Atzberger, C., Guérif, M., Baret, F., and Werner, W. 2010. Comparative analysis of three chemometric techniques for the spectroradiometric assessment of canopy chlorophyll content in winter wheat. Comput. Electron. Agric. 73: 2. 165-173.
    3. Ayoubi, S., and Sahrawat, K.L. 2011. Comparing multivariate regression and artificial neural network to predict barley production from soil characteristics in northern Iran. Arch. Agron. Soil Sci. 57: 5. 549-565.
    4. Berger, K., Atzberger, C., Danner, M., D’Urso, G., Mauser, W., Vuolo, F., and Hank, T. 2018. Evaluation of the PROSAIL model capabilities for future hyperspectral model environments: a review study. Remote Sens. https://doi.org/10.3390/rs10010085
    5. Bolton, D.K., and Friedl, M.A. 2013. Forecasting crop yield using remotely sensed vegetation indices and crop phenology metrics. Agric. For. Meteorol. 173: 74-84.
    6. Broge, N.H., and Leblanc, E. 2000. Comparing predictive power and stability of broadband and hyperspectral vegetation indices for estimation of green leaf area index and canopy chlorophyll density. Remote Sens. Environ. 76: 2. 156-172.
    7. Chen, J.M. 1996. Evaluation of vegetation indices and modified simple ratio for boreal applications. Can. J. Remote. Sens. 22: 3. 229-242.
    8. Chen, P., Haboudane, D., Tremblay, N., Wang, J., Vigneault, P., and Li, B. 2010. New spectral indicator assessing the efficiency of crop nitrogen treatment in corn and wheat. Remote Sens. Environ. 114: 1987-1997.
    9. Cheng, T., Song, R., Li, D., Zhou, K., Zheng, H., Yao, X., Tian, Y., Cao, W., and Zhu, Y. 2017. Spectroscopic estimation of biomass in canopy components of paddy rice using dry matter and chlorophyll indices. Remote Sens. 9: 319.
    10. Cilia, C., Panigada, C., Rossini, M., Meroni, M., Busetto, L., Amaducci, S., Boschetti, M., Picchi, V., and Colombo, R. 2014. Nitrogen status assessment for variable rate fertilization in maize through hyperspectral imagery. Remote Sens. 6: 7. 6549-6565.
    11. Clevers, J.G.P.W. 1986. The application of a vegetation index in correcting the infrared reflectance for soil background. Int. Arch. Photogramm. Rem. Sens., Balkema, Rotterdam, Boston 26: 221-226.
    12. Clevers, J.G.P.W., van der Heijden, G.W.A.M., Verzakov, S., and Schaepman, M.E. 2007. Estimating grassland biomass using SVM band shaving of hyperspectral data. Photogramm Eng. Remote Sens. 73: 10. 1141-1148.
    13. Du, Y., Wang, J., Liu, Z., and Lin, Y. 2019. Estimation and multiscale transformation of aboveground biomass: an hgsu-oriented approach based on multisource data. IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens. 12: 7. 2388-2396.
    14. Feret, J.B., Gitelson, A.A., Noble, S.D., and Jacquemoud, S. 2017. PROSPECT-D: towards modeling leaf optical properties through a complete lifecycle. Remote Sens. Environ. 193: 204-215.
    15. Gao, B. 1996. NDWI-A normalized difference water index for remote sensing of vegetation liquid water from space. Remote Sens. Environ. 58: 257-266.
    16. Gao, S., Niu, Z., Huang, N., and Hou, X.H. 2013. Estimating the leaf area index, height and biomass of maize using HJ-1 and RADARSAT-2. Int. J. Appl. Earth Obs. Geoinf. 24: 1-8.
    17. Gilles, L., Mariehelene, J., and Francois, G. 2008. Diagnosis tool for plant and crop N status in vegetative stage. Eur. J. Agron. 28: 4. 614-624.
    18. Gitelson, A. 2004. Wide dynamic range vegetation index for remote quantification of biophysical characteristics of vegetation. J. Plant Physiol. 161: 2. 165-173.
    19. Gitelson, A.A., Gritz, Y., and Merzlyak, M.N. 2003a. Relationships between leaf chlorophyll content and spectral reflectance and algorithms for non-destructivechlorophyll assessment in higher plant leaves. J. Plant Physiol. 160: 3. 271-282.
    20. Gitelson, A.A., Kaufman, Y.J., Stark, R., and Rundquist, D. 2002a. Novel algorithms for remote estimation of vegetation fraction. Remote Sens. Environ. 80: 1. 76-87.
    21. Gitelson, A.A., Vina, A., Arkebauer, T.J., Rundquist, D.C., Keydan, G.P., and Leavitt, B. 2003b. Remote estimation of leaf area index and green leaf biomass in maize canopies. Geophys. Res. Lett. 30: 5. 1248.
    22. Gitelson, A.A., Zur, Y., Chivkunova, O.B., and Merzlyak, M.N. 2002b Assessing carotenoid content in plant leaves with reflectance spectroscopy. Photochem. Photobiol. 75: 3. 272-281.
    23. Gnyp, M.L., Bareth, G., Li, F., Lenz-Wiedemann, V.I.S. Koppe, W., Miao, Y., Hennig, S.D., Jia, L., Laudien, R., Chen, X., and Zhang, F. 2014a. Development and implementation of a multiscale biomass modelusing hyperspectral vegetation indices for winter wheat in the NorthChina Plain. Int. J. Earth Obs. Geoinf. 33: 232-242.
    24. Gnyp, M.L., Miao, Y.X., Yuan, F., Ustin, S.L., Yu, K., Yao, Y.K., Huang, S.Y., and Bareth, G. 2014b. Hyperspectral canopy sensing of paddy rice aboveground biomass at different growth stages. Field Crops Res. 155: 42-55.
    25. Goel, N.S., and Qin, W.H. 1994. Influences of canopy architecture on relationships between various vegetation indices and LAI and FPAR: a computer simulation. Remote Sens. Reviews 10: 4. 309-347.
    26. Haboudane, D., Miller, J.R., Tremblay, N., Zarco-Tejada, P.J., and Dextraze, L. 2002. Integration of hyperspectral vegetation indices for prediction of crop chlorophyll content for application to precision agriculture. Remote Sens. Environ. 81: 2-3. 416-426.
    27. Huang, J., Sedano, F., Huang, Y., Ma, H., Li, X., Liang, S., Tian, L., Zhang, X., Fan, J., and Wu, W. 2016. Assimilating a synthetic Kalman filter leaf area index series into the WOFOST model to improve regional winter wheat yield estimation. Agric. For. Meteorol. 216: 188-202.
    28. Huete, A., Didan, K., Miura, T., Rodriguez, E.P., Gao, X., and Ferreira, L.G. 2002. Overview of the radiometric and biophysical performance of the MODIS vegetation indices. Remote Sens. Environ. 83: 195-213.
    29. Huete, A.R. 1988. A soil-adjusted vegetation index (SAVI). Remote Sens. Environ. 25: 3. 295-309.
    30. Huete, A.R., Liu, H.Q., Batchily, K., and Leeuwen, W. 1997. A comparison of vegetation indices over a global set of TM images for EOS-MODIS. Remote Sens. Environ. 59: 3. 440-451.
    31. Jacquemoud, S., Verhoef, W., Baret, F., Bacour, C., Zarco-Tejada, P.J., Asner, G.P., François, C., and Ustin, S.L. 2009. PROSPECT + SAIL models: a review of use for vegetation characterization. Remote Sens. Environ. 113: S56-S66.
    32. Jin, X.L., Yang, G.J., Xu, X.G., Yang, H., Feng, H.K., Li, Z.H., Shen, J.X., Zhao, C.J., and Lan, Y.B. 2015. Combined multi-temporal optical and radar parameters for estimating LAI and biomass in winter wheat using HJ and RADARSAR-2 data. Remote Sens. 7: 10. 13251-13272.
    33. Kaufman, Y.J. and Tanre, D. 1992. Atmospherically Resistant Vegetation Index (ARVI) for EOS- MODIS. IEEE Trans Geosci Remote Sens. 30: 2. 261-270.
    34. Kross, A., McNairn, H., Lapen, D., Sunohara, M., and Champagne, C. 2015. Assessment of RapidEye vegetation indices for estimation of leaf area index and biomass in corn and soybean crops. Int. J. Appl. Earth Obs. Geoinf. 34:1. 235-248.
    35. Kumar, L. and Mutanga, O. 2017. Remote sensing of above-ground biomass. Remote Sens. 9. 935.
    36. Liu, Y., Liu, S., Li, J., Guo, X., Wang, S., and Lu, J. 2019. Estimating biomass of winter oilseed rape using vegetation indices and texture metrics derived from UAV multispectral images. Comput. Electron. Agric. 166: 105026.
    37. Lobell, D.B. 2013. The use of satellite data for crop yield gap analysis. Field Crops Res. 143: 56-64.
    38. Lu, D. 2006. The potential and challenge of remote sensing-based biomass estimation. Int. J. Remote Sens. 27: 7. 1297-1328.
    39. Marshall, M., and Thenkabail, P. 2015. Developing in situ non-destructive estimates of crop biomass to address issues of scale in remote sensing. Remote Sens. 7: 1. 808-835.
    40. Merzlyak, M.N., Gitelson, A.A., Chivkunova, O.B., and Rakitin, Y.R. 1999. Non-destructive optical detection of pigment changes during leaf senescence and fruit ripening. Physiol. Plant. 106: 135-141.
    41. Mosleh Ghahfarokhi, Z. 2016. Soil digital mapping, land suitability and optimization cultivation model for major products plains of Shahrekord. PhD thesis pedology, Faculty of Agriculture, University of Shahrekord, Iran. (In Persian)
    42. Padilla, F.L.M., Maas, S.J., González-Dugo, M.P., Mansilla, F., Rajan, N., Gavilán, P., and Domínguez, J. 2012. Monitoring regional wheat yield in Southern Spain using the GRAMI model and satellite imagery. Field Crops Res. 130: 145-154.
    43. Paltridge, G., and Barber, J. 1988. Monitoring grassland dryness and fire potential in Australia with NOAA/AVHRR data. Remote Sens. Environ. 25: 3. 381-394.
    44. Pearson, R.L., and Miller, L.D. 1972. Remote mapping of standing crop biomass for estimation of the productivity of the shortgrass prairie. Remote Sens. Environ. 8: 1348-1355.
    45. Penuelas, J., Baret, F., and Filella, I. 1995. Semi-empirical indices to assess carotenoids/chlorophyll-a ratio from leaf spectral reflectance. Photosynthetica. 31: 2. 221-230.
    46. Prabhakara, K., Hively, W.D., and McCarty, G.W. 2015. Evaluating the relationship between biomass, percent groundcover and remote sensing indices across six winter cover crop fields in Maryland, United States. Int. J. Appl. Earth Obs. Geoinf. 39: 88-102.
    47. Qi, J., Chehbouni, A., Huete, A.R., Kerr, Y.H., and Sorooshian, S. 1994. A modified soil adjusted vegetation index. Remote Sens. Environ. 48: 2. 119-126.
    48. Ren, H. and Feng, G. 2014. Are soil-adjusted vegetation indices better than soil-unadjusted vegetation indices for above-ground green biomass estimation in arid and semi-arid grasslands? Br. Grassl. Soc. 70: 4. 611-619.
    49. Rondeaux, G., Steven, M., and Baret, F. 1996. Optimization of soil- adjusted vegetation indices. Remote Sens. Environ. 55: 2. 95-107.
    50. Roujean, J.L., and Breon, F.M. 1995. Estimating PAR absorbed by vegetation from bidirectional reflectance measurements. Remote Sens. Environ. 51: 3. 375-384.
    51. Rouse, J.W., Haas, R.H., Schell, J.A., and Deering, D.W., 1974. Monitoring vegetation systems in the great plains with ERTS. Third ERTS Symposium, NASA SP. 351: 309-317.
    52. Sayago, S., and Bocco, M. 2018. Crop yield estimation using satellite images: comparison of linear and non-linear models. Agriscientia. 35: 1-9.
    53. Shirani, H. 2017. Artificial neural networks with an application in agricultural and natural resource sciences. Vali-e-Asr University of Rafsanjan Press. 320 p. (In Persian)
    54. Tucker, C.J. 1979. Red and photographic infrared linear combinations for monitoring vegetation. Remote Sens. Environ. 8:2. 127-150.
    55. Wang, D.C., Wang, J.H., Jin, N., Wang, Q., Li. C.J., Huang, J.F., Wang, Y., and Huang, F. 2008. ANN-based wheat biomass estimation using canopy hyperspectral vegetation indices. Trans. CSAE 24: 196-201.
    56. Wang, L., Zhou, X., Zhu, X., Dong, Z., and Guo, W. 2016. Estimation of biomass in wheat using random forest regression algorithm and remote sensing data. Crop J. 4: 3. 212-219.
    57. Yue, J., Feng, H., Yang, G., and Li, Z. 2018. A comparison of regression techniques for estimation of above-ground winter wheat biomass using near-surface spectroscopy. Remote Sens. https://doi.org/10.3390/rs10010066
    58. Yue, J., Yang, G., Li, C., Li, Z., Wang, Y., Feng, H., and Xu, B. 2017. Estimation of winter wheat above-ground biomass using unmanned aerial vehicle-based snapshot hyperspectral sensor and crop height improved models. Remote Sens. 9: 7. 708.
    59. Yue, J., Yang, G., Tian, Q., Feng, H., Xu, K., and Zhou, C. 2019. Estimate of winter-wheat above-ground biomass based on UAV ultrahighground-resolution image textures and vegetation indices. ISPRS J. Photogramm. Remote Sens. 150: 4. 226-244.
    60. Zarco-Tejada, P.J., Miller, J.R., Mohammed, G.H., Noland, T.L., and Sampson, P.H., 1999. Optical Indices as Bioindicators of Forest Condition from Hyperspectral CASI data. 19th Symposium of the European Association of Remote Sensing Laboratories (EARSeL).
مجله تولید گیاهان زراعی
دوره 13، شماره 3
آذر 1399
صفحه 179-196

فایل ها

هم رسانی

ارجاع به این مقاله

آمار