Assessing Drought Hazard Via Combined Drought Index Using Machine Learning Techniques: A Case Study of Ilam Province

نوع مقاله : مقاله پژوهشی

نویسندگان

1 faculty of Rangeland and watershed management , Gorgan university of agricultural sciences and natural resources , gorgan , iran

2 , Faculty of Rangeland and watershed Management, Gorgan University of Agricultural Sciences and Natural Resources, Gorgan, Iran

3 Assistant prof, Department of Watershed and Arid Zone Management, Gorgan University of Agricultural Sciences and Natural Resources (GUASNR),

‎ 10.22052/deej.2023.114090

چکیده

As one of the most important natural hazards worldwide, drought increases the vulnerability of the agricultural sector, raises economic loss, and threatens human life, making the characterization of drought and its hazard assessment to be of great significance. Therefore, this study used twelve various remotely sensed indices derived from Moderate Resolution Imaging Spectroradiometer (MODIS) and digital elevation model (DEM) to monitor drought throughout the 2000–2018 growing season. Moreover, the Standardized Precipitation Index (SPI) was used as reference data, with the relevant time scales ranging from 1 to 12 months. Finally, the correlation between thirteen indices and SPI in Ilam Province was modulated using three machine learning approaches, including random forest, boosted regression trees, and Cubist. The results indicated that among the three approaches mentioned above, random forest delivered the best performance (R2 = 0.88) in terms of SPI prediction. It was also found that Land Surface Temperature (LST) and Evapotranspiration (ET) had higher relative significance in terms of short-term meteorological drought, whereas Normalized Difference Vegetation Index (NDVI) and Soil Adjusted Vegetation Index (SAVI) had higher relative significance in terms of long-term meteorological drought when treated by random forest approach. In the next step, relative soil moisture, Standardized Precipitation Evapotranspiration Index (SPEI), and crop yield data were used to validate the collected data. Finally, the Drought Hazard Index (DHI) was generated based on the probability occurrences of drought using the comprehensive drought model made in the previous step. Accordingly, the results of the DHI map indicated that 65% and 18% of the study area fell under the very high and high classes of drought hazard, respectively. Overall, the results of this study provide a comprehensive method for assessing regional drought.

کلیدواژه‌ها


عنوان مقاله [English]

Assessing Drought Hazard Via Combined Drought Index Using Machine Learning Techniques: A Case Study of Ilam Province

نویسندگان [English]

  • Zahedeh Heidarizadi 1
  • Majid Ownagh 2
  • Chooghi Bairam Komaki 3
1 faculty of Rangeland and watershed management , Gorgan university of agricultural sciences and natural resources , gorgan , iran
2 , Faculty of Rangeland and watershed Management, Gorgan University of Agricultural Sciences and Natural Resources, Gorgan, Iran
3 Assistant prof, Department of Watershed and Arid Zone Management, Gorgan University of Agricultural Sciences and Natural Resources (GUASNR),
چکیده [English]

As one of the most important natural hazards worldwide, drought increases the vulnerability of the agricultural sector, raises economic loss, and threatens human life, making the characterization of drought and its hazard assessment to be of great significance. Therefore, this study used twelve various remotely sensed indices derived from Moderate Resolution Imaging Spectroradiometer (MODIS) and digital elevation model (DEM) to monitor drought throughout the 2000–2018 growing season. Moreover, the Standardized Precipitation Index (SPI) was used as reference data, with the relevant time scales ranging from 1 to 12 months. Finally, the correlation between thirteen indices and SPI in Ilam Province was modulated using three machine learning approaches, including random forest, boosted regression trees, and Cubist. The results indicated that among the three approaches mentioned above, random forest delivered the best performance (R2 = 0.88) in terms of SPI prediction. It was also found that Land Surface Temperature (LST) and Evapotranspiration (ET) had higher relative significance in terms of short-term meteorological drought, whereas Normalized Difference Vegetation Index (NDVI) and Soil Adjusted Vegetation Index (SAVI) had higher relative significance in terms of long-term meteorological drought when treated by random forest approach. In the next step, relative soil moisture, Standardized Precipitation Evapotranspiration Index (SPEI), and crop yield data were used to validate the collected data. Finally, the Drought Hazard Index (DHI) was generated based on the probability occurrences of drought using the comprehensive drought model made in the previous step. Accordingly, the results of the DHI map indicated that 65% and 18% of the study area fell under the very high and high classes of drought hazard, respectively. Overall, the results of this study provide a comprehensive method for assessing regional drought.

کلیدواژه‌ها [English]

  • DHI
  • Ilam province
  • MODIS
  1. AghaKouchak, A., Farahmand, A., Melton, F.S., Teixeira, J., Anderson, M.C., Wardlow, B.D. and Hain, C.R., 2015. Remote sensing of drought: progress, challenges and opportunities, Journal of Reviews of Geophysics. 53, 452–480.
  2. Brown, J.F., Wardlow, B.D., Tadesse, T., Hayes, M.J. and Reed, B.C. 2008. The Vegetation Drought Response Index (VegDRI): a new integrated approach for monitoring drought stress in vegetation. GIScience Remote Sens. 45 (1), 16–46.
  3. Chang, J., Li, Y., Wang, Y., Yuan, M., 2016. Copula-based drought risk assessment combined with an integrated index in the Wei River Basin. China J. Hydrol. 540, 824–834.
  4. Chang, J., Li, Y., Wang, Y. and Yuan, M., 2016. Copula-based drought risk assessment combined with an integrated index in the Wei River Basin. China J. Hydrol. 540, 824–834.
  5. Dabanli, I, 2018. Drought Risk Assessment by Using Drought Hazard and Vulnerability Indexes, Natural Hazards and Earth System. Sciences Discuss. 1–15.
  6. Dai, A, 2011. Erratum: drought under global warming: a review, Wiley Interdisciplinary Reviews: Climate Change, 2 (1), 45–65.
  7. Dutra, E., Giuseppe, F. D., Wetterhall, F. and Pappenberger, F, 2013. Seasonal forecasts of droughts in African basins using the Standardized Precipitation Index, Hydrology and Earth System Sciences, 17(6), 2359-2373. doi:10.5194/hess-17-2359-2013.
  8. Elith, J., Leathwick, J. R., & Hastie, T. (2008). A working guide to boosted regression trees. Journal of animal ecology, 77(4), 802-813. doi: 10.1111/j.1365-2656.2008.01390.x
  9. Faramarzi M, Heidarizadi Z, Mohamadi A, Heydari M. Detection of Vegetation Changes in Relation to Normalized Difference Vegetation Index (NDVI) in Semi-Arid Rangeland in Western Iran. JAST. 20 (1) :51-60.
  10. Farrokhzadeh, B, Mansouri, Sh, and Sepehari, A, 2016, determination of the correlation between vegetation indices NDVI and EVI with meteorological drought index SPI (case study: plain pastures of Golestan province), Agricultural Meteorology Journal, Volume 5, No. 2, pp. 65-56.
  11. Gao, B.-C, 1996. NDWI—a normalized difference water index for remote sensing of vegetation liquid water from space, Remote Sensing Environment (RSE). 58 (3), 257–266.
  12. Gessner, U., Naeimi, V., Klein, I., Kuenzer, C., Klein, D., and Dech, S. (2013). The relationship between precipitation anomalies and satellite-derived vegetation activity in Central Asia. Global and Planetary Change, 110, 74-87. https://doi.org/10.1016/j.gloplacha.2012.09.007.
  13. Gu, Y., Brown, J.F., Verdin, J.P. and Wardlow, B, 2007. 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, 34 (6).
  14. Huang, S., Chang, J., Leng, G., Huang, Q., 2015. Integrated index for drought assessment based on variable fuzzy set theory: a case study in the Yellow River basin. China. J. Hydrol. 527, 608–618.
  15. Huete, A. R., Post, D. F., and Jackson, R. D, 1984. Soil Spectral effects and 4-space vegetation discrimination, Journal of Remote sensing of Environment, 15:155-165.
  16. Khoshnazar, A., Corzo Perez, G.A., and Diaz, V, 2021. Spatiotemporal Drought Risk Assessment Considering Resilience and Heterogeneous Vulnerability Factors: Lempa Transboundary River Basin in The Central American Dry Corridor, Journal of Marine Science and Engineering, 9(4):386. https://doi.org/10.3390/jmse9040386
  17. Kim H, Park J, Yoo J, Kim TW, 2013, Assessment of drought hazard, vulnerability, and risk: a case study for administrative districts in South Korea. J Hydro Environ Res 9(1):28–35

doi:https://digitalcommons.unl.edu/droughtnetnews/80

  1. Kogan, F.N. 1993.United States droughts of late 1980's as seen by NOAA polar orbiting satellites. International Geoscience and Remote Sensing Symposium, 1:197-199
  2. Kouranjadi, A, Pourqasmi, H. 2018. Landslide susceptibility assessment using data mining models, case study: Chelchai watershed. Watershed Engineering and Management, 11(1), 28-42.
  3. Liaw A, Wiener M, 2002. “Classification and Regression by randomForest.” R News, 2(3), 18-22. https://CRAN.R-project.org/doc/Rnews/.
  4. Lin, Y.-C.; Kuo, E.-D.; Chi, W.-J. Analysis of Meteorological Drought Resilience and Risk Assessment of Groundwater Using Signal Analysis Method. Water Resour. Manag. 2021, 35, 179–197. [CrossRef]
  5. Luetkemeier, R.; Stein, L.; Drees, L.; Liehr, S.2017, Blended Drought Index: Integrated Drought Hazard Assessment in the Cuvelai-Basin. Climate, 5, 51. https://doi.org/10.3390/cli5030051
  6. McKee, T. B., Doesken, N. J., & Kleist, J. 1993,. The relationship of drought frequency and duration to time scales. In Proceedings of the 8th Conference on Applied Climatology (Vol. 17, No. 22, pp. 179-183).
  7. Mishra, A.K., Sivakumar, B., Singh, V.P., 2015. Drought processes, modeling, and mitigation. J. Hydrol. 526, 1–2.
  8. Mizzell, H., 2008. Improving Drought Detection in the Carolinas: Evaluation of Local, State, and Federal Drought Indicators. University of South Carolina.
  9. Nasrollahi, M, 2015. Assessment of drought hazard, vulnerability and risk (case study: Semnan province). M.Sc. thesis. Faculty of Natural Resources, University of Tehran. 104p
  10. Nasrollahi, M., Khosravi, H., Moghaddamnia, A. 2018. Assessment of drought risk index using drought hazard and vulnerability indices. Arab J Geosci 11, 606 .https://doi.org/10.1007/s12517-018-3971-y
  11. Park, S., Im, J., Jang, E., & Rhee, J. (2016). Drought assessment and monitoring through blending of multi-sensor indices using machine learning approaches for different climate regions. Agricultural and forest meteorology, 216, 157-169. Doi:https://doi.org/10.1016/j.agrformet.2015.10.011.
  12. Piao, S., Fang, J., Zhou, L., Guo, Q., Henderson, M., Ji, W. 2003. Interannual variations of monthly and seasonal normalized difference vegetation index (NDVI) in China from 1982 to 1999. Journal of Geophysical Research: Atmospheres, 108(D14). Doi:https://doi.org/10.1029/2002JD002848
  13. Poortaheri M, Eftekhari A, Kazemi N, 2013. The role of drought risk management approach in reducing social—economic vulnerability of farmers and rural regions case study: Sulduz Rural District, Azerbaijan Gharbi. Rural Res 4(1):1–12
  14. Proodhan, Foyez A., Jiahua Zhang, Fengmei Yao, Lamei Shi, Til P. Pangali Sharma, Da Zhang, Dan Cao, Minxuan Zheng, Naveed Ahmed, and Hasiba P. Mohana. 2021. "Deep Learning for Monitoring Agricultural Drought in South Asia Using Remote Sensing Data" Remote Sensing 13, no. 9: 1715. https://doi.org/10.3390/rs13091715.
  15. R Core Team, 2021. R: A language and environment for statistical computing. R Foundation for Statistical Computing, Vienna, Austria.URL https://www.R-project.org/.
  16. Rajsekhar, D., V. P. Singh, and A. K. Mishra, 2015, Integrated drought causality, hazard, and vulnerability assessment 20 for future socioeconomic scenarios: An information theory perspective. J. Geophys. Res. Atmos., 120, 6346–6378. http://doi.org/10.1002/2014JD022670 .
  17. Rhee, J., Im, J., Carbone, G.J., 2010. Monitoring agricultural drought for arid and humid regions using multi-sensor remote sensing data. Remote Sens. Environ. 114 (12), 2875–2887.
  18. Rouse, J.W., 1974. Monitoring the vernal advancement of retro gradation of natural vegetation. NASA/GSFC, Type III, Final Report, Greenbelt, MD, pp. 371.
  19. RuleQuest, 2012. http://www.rulequest.com/.
  20. Sahana, V, Mondal, A, Sreekumar, P. 2021, Drought vulnerability and risk assessment in India: Sensitivity analysis and comparison of aggregation techniques, Journal of Environmental Management, 299(113689), pages 1-10. https://doi.org/10.1016/j.jenvman.2021.113689
  21. Shahid, S., Behrawan, H., 2008. Drought risk assessment in the western part of Bangladesh. Nat. Hazards 46, 391e413.
  22. Shen, R, Huang, A, Li, B, Guo, J., 2019, Construction of a drought monitoring model using deep learning based on multi-source remote sensing data,International Journal of Applied Earth Observation and Geoinformation,Volume 79,2019,Pages 48-57,
  23. Svoboda, M., 2000. An introduction to the drought monitor. Drought Network News(1994-2001).80.
  24. United Nation Development Program (2004) Reducing disaster risk, A challenge for development. United Nation Development Program/ Bureau for Crisis Prevention and Recovery, New York. http://www. undp.org/bcpr/disred/rdr.htm.
  25. Wang, L., Qu, J.J., 2007. NMDI: A normalized multi-band drought index for monitoring soil and vegetation moisture with satellite remote sensing. Geophys. Res. Lett. 34 (20).
  26. Wardlow, B. D., Anderson, M. C., & Verdin, J. P. (Eds.). (2012). Remote sensing of drought: Innovative monitoring approaches. CRC Press
  27. Waseem, M., Ajmal, M., & Kim, T. W. 2015. Development of a new composite drought index for multivariate drought assessment. Journal of Hydrology, 527, 30-37. Doi:https://doi.org/10.1016/j.jhydrol.2015.04.044.
  28. Wilhite, D.A., Glantz, M.H., 1985. Understanding: the drought phenomenon: the role of definitions. Water Int. 10 (3), 111–120.
  29. Wilhite, D.A., Svoboda, M.D., Hayes, M.J., 2007. Understanding the complex impacts of drought: a key to enhancing drought mitigation and preparedness. Water Resour. Manage. 21 (5), 763–774.
  30. Wood, E. F., S. D. Schubert, A. W. Wood, C. D. Peters-Lidard, K. C. Mo, A. Mariotti, and R. S. Pulwarty, 2015: Prospects for Advancing Drought Understanding, Monitoring, and Prediction. J. Hydrometeor., 16, 1636–1657.
  31. Yin, J., Zhan, X., Hain, C.R., Liu, J., Anderson, M.C., 2018. A method for objectively integrating soil moisture satellite observations and model simulations toward a blended drought index. Water Resour. Res. 54. https://doi.org/10.1029/ 2017WR021959.
  32. Zhang, A., Jia, G., 2013. Monitoring meteorological drought in semiarid regions using multi-sensor microwave remote sensing data. Remote Sens. Environ. 134, 12–23. Doi:https://doi.org/10.1016/j.rse.2013.02.023