این سایت در حال حاضر پشتیبانی نمی شود و امکان دارد داده های نشریات بروز نباشند
مهندسی اکوسیستم بیابان، جلد ۱۱، شماره ۹ انگلیسی، صفحات ۴۸-۳۳
عنوان فارسی Assessing Drought Hazard Via Combined Drought Index Using Machine Learning Techniques: A Case Study of Ilam Province
چکیده فارسی مقاله 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.
کلیدواژه‌های فارسی مقاله
عنوان انگلیسی Assessing Drought Hazard Via Combined Drought Index Using Machine Learning Techniques: A Case Study of Ilam Province
چکیده انگلیسی مقاله 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.
کلیدواژه‌های انگلیسی مقاله DHI, Ilam province, MODIS
نویسندگان مقاله زاهده حیدری زادی |
faculty of Rangeland and watershed management , Gorgan university of agricultural sciences and natural resources , gorgan , iran

مجید اونق |
, Faculty of Rangeland and watershed Management, Gorgan University of Agricultural Sciences and Natural Resources, Gorgan, Iran

جوقی بایرام کمکی |
Assistant prof, Department of Watershed and Arid Zone Management, Gorgan University of Agricultural Sciences and Natural Resources (GUASNR),

نشانی اینترنتی https://deej.kashanu.ac.ir/article_114090_51259f7fedd6aa3553ddc245d3d6d324.pdf
فایل مقاله فایلی برای مقاله ذخیره نشده است
کد مقاله (doi)
زبان مقاله منتشر شده fa
موضوعات مقاله منتشر شده
نوع مقاله منتشر شده
برگشت به: صفحه اول پایگاه   |   نسخه مرتبط   |   نشریه مرتبط   |   فهرست نشریات