توسعه یک روش کارآمد مبتنی بر آموزش ماشین و داده های زمینی و ماهواره ای برای پیش بینی و پهنه بندی خشکسالی کشاورزی در ایران

نوع مقاله : مقاله پژوهشی

نویسندگان

• ماهان عزیزی
• علی عباسی

گروه عمران، دانشکده مهندسی، دانشگاه فردوسی مشهد، مشهد، ایران.

10.22067/jfcei.2024.88855.1311

چکیده

خشکسالی یکی از خطرناک‌ترین وقایع طبیعی برای هر کشور به حساب می‌آید. به همین علت نظارت و پیش‌بینی این پدیده در دنیای امروز از اهمیت بسیار بالایی برخوردار است. در این پژوهش، از شاخص خشکسالی SPEI که از معروف‌ترین شاخص‌های خشکسالی به شمار می‌رود، برای پیش‌بینی خشکسالی استفاده شده است. برای محاسبه این شاخص، ترکیبی از داده‌های زمینی و سنجش از دور مورداستفاده قرار گرفته است. با توجه به وزن مختلف هر کدام از این داده‌ها در محاسبه شاخص خشکسالی، ابتدا پارامترهای مؤثر توسط روش‌های انتخاب پارامتر مؤثر مانند روش فیلتر و روش لاسو برگزیده شده و به عنوان پارامترهای ورودی مدل در نظر گرفته شدند. سپس با استفاده از 4 روش یادگیری ماشین شامل جنگل تصادفی تصحیح بایاس شده، جنگل تصادفی، ماشین بردار پشتیبان و پرسپترون چندلایه شاخص خشکسالی محاسبه شده است. برای اعتبارسنجی نتایج هر کدام از این مدل‌ها، از شاخص‌های RMSE، R2، MSE و MAE استفاده شده و سپس بر اساس مقادیر این شاخص‌ها، مدل جنگل تصادفی تصحیح بایاس شده با مقادیر R^2=0.9858 و RMSE=0.1190 برای خوشه 1 و R^2=0.9809 و RMSE=0.1375 برای خوشه 2 به عنوان مدل دارای بهترین عملکرد انتخاب شده است. در نهایت از نتایج مدل بهینه برای تهیه نقشه‌های پهنه‌بندی خشکسالی به منظور شناسایی و طبقه‌بندی مناطق مستعد به شرایط خشکسالی استفاده گردید. این نقشه‌ها می‌توانند اطلاعات ارزشمندی را در رابطه با توزیع و شدت خشکسالی در مناطق مختلف در اختیار ذینفعان و متخصصان قرار دهند.

کلیدواژه‌ها

• خشکسالی
• سنجش از دور
• یادگیری ماشین
• شاخص خشکسالی SPEI
• نقشه‌ پهنه‌بندی خشکسالی

---

عنوان مقاله [English]

Developing a Robust Data-Driven Model Based on Ground and Satellite Measured Data for Agricultural Drought Prediction in Iran

نویسندگان [English]

• Mahan Azizi
• Ali Abbasi

Department of Civil Engineering, Faculty of Engineering, Ferdowsi University of Mashhad, Mashhad, Iran

چکیده [English]

Drought is considered one of the most hazardous natural phenomena for any country. Therefore, monitoring and forecasting this phenomenon are of critical importance in today's world. To this end, the Standardized Precipitation Evapotranspiration Index (SPEI), one of the most applied drought indices, was employed for drought prediction. To calculate this index, a combination of ground-based and remote sensing data was utilized. Given the different weights of each of these data types in calculating the drought index, the most relevant parameters were first selected using feature selection methods such as the Filter method and the LASSO method and were considered as input parameters for the model. Furthermore, artificial intelligence was utilized to apply various machine learning algorithms, resulting in the development of several models. These algorithms included Bias-Corrected Random Forest, Random Forest, Support Vector Machine, and Multilayer Perceptron. To validate the results of each of these models, indices such as RMSE, R², MSE, and MAE were used. Based on the values of these indices, the Bias-Corrected Random Forest model with R² = 0.9858 and RMSE = 0.1190 for cluster 1 and R² = 0.9809 and RMSE = 0.1375 for cluster 2 was selected as the best-performing model. Finally, the results of the optimized model were used to create drought zoning maps to identify and classify areas prone to drought conditions. These maps can provide valuable information on the distribution and intensity of drought across different regions to stakeholders and experts.

کلیدواژه‌ها [English]

• Drought
• Remote sensing
• Machine learning
• SPEI drought index
• Drought maps

مراجع

[1] D. Dutta, A. Kundu, and N. R. Patel, “Predicting agricultural drought in eastern Rajasthan of India using NDVI and standardized precipitation index,” Geocarto International, vol. 28, no. 3, pp. 192–209, 2013. https://doi.org/10.1080/10106049.2012.679975

[2] N. M. Alam et al., “Evaluation of drought using SPEI drought class transitions and log-linear models for different agro-ecological regions of India,” Physics and Chemistry of the Earth, Parts A/B/C, vol. 100, pp. 31–43, 2017. https://doi.org/10.1016/j.pce.2017.02.008

[3]  W. C. Palmer, Meteorological drought, vol. 30. US Department of Commerce, Weather Bureau, 1965.

[4] T. B. McKee, N. J. Doesken, and J. Kleist, “The relationship of drought frequency and duration to time scales,” in Eighth Conference on Applied Climatology, 1993, vol. 17, no. January, pp. 17–22.

[5] S. M. Vicente-Serrano, S. Beguería, and J. I. López-Moreno, “A Multiscalar Drought Index Sensitive to Global Warming: The Standardized Precipitation Evapotranspiration Index,” Journal of Climate, vol. 23, no. 7, pp. 1696–1718, 2010. https://doi.org/10.1175/2009JCLI2909.1

[6] J. W. Rouse, R. H. Haas, J. A. Schell, and D. W. Deering, “Monitoring vegetation systems in the Great Plains with ERTS,” NASA Spec. Publ, vol. 351, no. 1, p. 309, 1974.

[7] Y. Gu, J. F. Brown, J. P. Verdin, and B. Wardlow, “A five-year analysis of MODIS NDVI and NDWI for grassland drought assessment over the central Great Plains of the United States,” Geophysical research letters, vol. 34, no. 6, 2007. https://doi.org/10.1029/2006GL029127

[8]L. Wang and J. J. Qu, “NMDI : A normalized multi-band drought index for monitoring soil and vegetation moisture with satellite remote sensing,” Geophysical research letters, vol. 34, no. July, pp. 1–5, 2007. https://doi.org/10.1029/2007GL031021

[9]  J. Rhee, J. Im, and G. J. Carbone, “Monitoring agricultural drought for arid and humid regions using multi-sensor remote sensing data,” Remote Sensing of Environment, vol. 114, no. 12, pp. 2875–2887, 2010. https://doi.org/10.1016/j.rse.2010.07.005

[10] Z. M. Yaseen, M. Ali, A. Sharafati, N. Al-Ansari, and S. Shahid, “Forecasting standardized precipitation index using data intelligence models: regional investigation of Bangladesh,” Scientific Reports, vol. 11, no. 1, p. 3435, 2021. https://doi.org/10.1038/s41598-021-82977-9

[11] M. R. Kousari, M. E. Hosseini, H. Ahani, and H. Hakimelahi, “Introducing an operational method to forecast long-term regional drought based on the application of artificial intelligence capabilities,” Theoretical and Applied Climatology, vol. 127, no. 1–2. pp. 361–380, 2017. https://doi.org/10.1007/s00704-015-1624-6

[12] M. Mokhtarzad, F. Eskandari, N. Jamshidi Vanjani, and A. Arabasadi, “Drought forecasting by ANN, ANFIS, and SVM and comparison of the models,” Environ. Earth Sci., vol. 76, no. 21, p. 729, 2017. https://doi.org/10.1007/s12665-017-7064-0

[13] A. Abbasi, K. Khalil, J. Behmanesh, and A. Shirzad, “Application of Support Vector Machine and Bayesian Network method in agricultural drought prediction,” Watershed Engineering and Management, vol. 12, no. 1, pp. 107–124, 2020. https://doi.org/10.22092/ijwmse.2019.122619.1519

[14] F. Tufaner and A. Özbeyaz, “Estimation and easy calculation of the Palmer Drought Severity Index from the meteorological data by using the advanced machine learning algorithms,” Environmental Monitoring and Assessment, vol. 192, no. 9, 2020. https://doi.org/10.1007/s10661-020-08539-0

[15] P. Feng, B. Wang, D. L. Liu, and Q. Yu, “Machine learning-based integration of remotely-sensed drought factors can improve the estimation of agricultural drought in South-Eastern Australia,” Agricultural Systems, vol. 173. pp. 303–316, 2019. https://doi.org/10.1016/j.agsy.2019.03.015

[16] M. Zoljoodi and A. Didevarasl, “Evaluation of Spatial-Temporal Variability of Drought Events in Iran Using Palmer Drought Severity Index and Its Principal Factors (through 1951-2005),” Atmospheric and Climate Sciences, vol. 03, no. 02, pp. 193–207, 2013. http://dx.doi.org/10.4236/acs.2013.32021

[17] A. Darvishi, S. Arkhi, and A. Ebrahimi, “Risk and disaster management to mitigate the effects of droughts in Iran,” in Proceeding of the Conference on Drought in Charmahal-Bakhtiari, Shahrekord, The University of Shahrekord, 2008, pp. 22–23.

[18] Iran’s Statistical Centre, “Shares and rankings of provinces based on important variables in the agricultural sector,” 2023.

[19] J. A. Hartigan and M. A. Wong, “Algorithm AS 136: A K-Means Clustering Algorithm,” Journal of the Royal Statistical Society. Series C (Applied Statistics), vol. 28, no. 1, pp. 100–108, 1979. https://doi.org/10.2307/2346830

[20] C. W. Thornthwaite, “An Approach toward a Rational Classification of Climate,” Geogr. Rev., vol. 38, no. 1, pp. 55–94, 1948. https://doi.org/10.2307/210739

[21] R. Tibshirani, “Regression Shrinkage and Selection via the Lasso,” Journal of the Royal Statistical Society: Series B (Methodological), vol. 58, no. 1, pp. 267–288, 1996. https://doi.org/10.1111/j.2517-6161.1996.tb02080.x

[22] F. Rosenblatt, Principles of neurodynamics: Perceptrons and the theory of brain mechanisms, vol. 55. Spartan books Washington, DC, 1962.

[23] A. Aghasi, M. Torbatinejad, and A. Bagherzadeh, “Modelling of rutting behavior of modified polymer asphalt mixture using artificial neural network,” Ferdowsi Civil Engineering, vol. 35, no. 3, pp. 69–88, 2022. https://doi.org/10.22067/jfcei.2022.76444.1135

[24] C. Cortes and V. Vapnik, “Support-vector networks,” Machine Learning, vol. 20, pp. 273–297, 1995. https://doi.org/10.1007/BF00994018

[25] L. Breiman, “Random Forests,” Machine Learning, vol. 45, no. 1, pp. 5–32, 2001. https://doi.org/10.1023/A:1010933404324

[26] J. Song, “Bias corrections for Random Forest in regression using residual rotation,” Journal of the Korean Statistical Society, vol. 44, no. 2, pp. 321–326, 2015. https://doi.org/10.1016/j.jkss.2015.01.003

[27]  G. Zhang and Y. Lu, “Bias-corrected random forests in regression,” Journal of Applied Statistics, vol. 39, no. 1, pp. 151–160, 2012. https://doi.org/10.1080/02664763.2011.578621

[28] Iran Meteorological Organization, “Weather data acquisition system,” Ferdowsi Civil Engineering, 2024. https://doi.org/10.22067/jfcei.2024.88855.1311

[29]  G. J. Huffman  E.F. Stocker, D.T. Bolvin, E.J. Nelkin, Jackson Tan, “GPM IMERG Final Precipitation L3 Half Hourly 0.1 degree x 0.1 degree V06.” NASA Goddard Earth Sciences Data and Information Services Cente, 2019.

[30]  Z. Wan, S. Hook, and G. Hulley, “MODIS/Terra Land Surface Temperature/Emissivity Daily L3 Global 1km SIN Grid V061.” NASA EOSDIS Land Processes Distributed Active Archive Center, 2021.

[31]  E. Vermote and R. Wolfe, “MODIS/Terra Surface Reflectance Daily L2G Global 1km and 500m SIN Grid V061.” NASA EOSDIS Land Processes Distributed Active Archive Center, 2021.

[32]  Z. Zhao, S. Xu, B. H. Kang, M. M. J. Kabir, Y. Liu, and R. Wasinger, “Investigation and improvement of multi-layer perception neural networks for credit scoring,” Expert Systems with Applications, vol. 42, no. 7, pp. 3508–3516, 2015. https://doi.org/10.1016/j.eswa.2014.12.006

[33] A. Rani, N. Kumar, J. Kumar, J. Kumar, and N. K. Sinha, “Chapter 6 - Machine learning for soil moisture assessment,” In Deep learning for sustainable agriculture, pp. 143-168, 2022. https://doi.org/10.1016/B978-0-323-85214-2.00001-X

[34] A. Afzal et al., “Response surface analysis, clustering, and random forest regression of pressure in suddenly expanded high-speed aerodynamic flows,” Aerospace Science and Technology, vol. 107, p. 106318, 2020. https://doi.org/10.1016/j.ast.2020.106318