Drought Forecasting with Time Series and Machine Learning Approaches

Date

2017-12-08

Author

Evkaya, Ömer Ozan
Yozgatlıgil, Ceylan
Kestel, Sevtap Ayşe

Metadata

Show full item record

Item Usage Stats

273
views

0
downloads

As a main reason of undesired agricultural, economic and environmental damages, drought is one of the most important stochastic natural hazard having certain features. In order to manage the impacts of drought, more than 100 drought indices have been proposed for both monitoring and forecasting purposes [1], [3]. For different types of droughts, these indices have been used to understand the effects of dry periods including meteorological, agricultural and hydrological droughts in many distinct locations. In this respect, the future projections of drought indices allow the decision makers to assess certain risks of dry periods beforehand. In addition to the use of classical time series techniques for understanding the upcoming droughts, machine learning methods might be effective alternatives for forecasting the future events based on relevant drought index [2]. This study aims to identify the benefits of various methods for forecasting the future dry seasons with widely known drought indices. For that purpose, Standardized Precipitation Index (SPI), Standardized Precipitation Evapotranspiration Index (SPEI) and Reconnaissance Drought Index (RDI) have been considered over different time scales (3, 6, 9 months) to represent drought in Kulu weather station, Konya. The considered drought indices were used for forecasting the future period using both time series prediction tools and machine learning techniques. The forecast results of all methods with respect to different drought indices were examined with the data set of 1950-2010 for Kulu station. The potential benefits and limitations of various methods and drought indices were discussed in detail

Subject Keywords

Drought, Drought index, Forecast, Machine learning

URI

https://hdl.handle.net/11511/79067
http://www.turkistatistik.org/wp-content/uploads/2015/03/ISTKON10-Abstract-Book-1-min.pdf

Conference Name

10.International Statistics Congress (ISC2017), (6 - 08 Aralık 2017),

Collections

Department of Statistics, Conference / Seminar

Suggestions

OpenMETU
Core

Understanding Drought with Copula Functions: Case Study for Konya Province Evkaya, Ömer Ozan; Yozgatlıgil, Ceylan; Kestel, Sevtap Ayşe (null; 2018-10-07) Drought is one of the most drastic and complex natural phenomenon in the world, a major reason for undesired agricultural, economic and environmental damages. For this reason, the objective identification of drought and its characteristics deserve more detailed models. Most of the studies in the literature related to drought monitoring and analysis are based on special widespread quantitative drought indices. On the other hand, the generated drought indices have been derived using only one drought related p...
Drought analysis of Konya Closed Basin with the use of TMPA satellite-based precipitation data Yılmaz, Meriç (2017-01-01) Investigation of drought that has heavy sociological and economical costs to countries is very important to alleviate its adverse impacts and to take the necessary precautions. Konya Closed Basin, which has critical role in terms of agricultural yield for our country, is one of the regions where the impact of the drought is felt the most due to its semi-arid climate. For this reason, in this study, severity, duration, and impact area of drought is analyzed over Konya Closed Basin between 1998 and 2015. In t...
Gene regulation network behind drought escape, avoidance and tolerance strategies in black poplar (Populus nigra L.) Yildirim, Kubilay; Kaya, Zeki (2017-06-01) Drought is the major environmental problem limiting the productivity and survival of plant species. Here, previously identified three black poplar genotypes having contrasting response to drought were subjected to gradual soil water depletion in a pot trial to identify their physiological, morphological and antioxidation related adaptations. We also performed a microarray based transcriptome analyses on the leaves of genotypes by using Affymetrix poplar Genome Array containing 56,000 transcripts. Phenotypic...
Drought analysis using CORDEX simulations over the mediterranean climate regions of Turkey Poyraz, Anıl Yıldırım; Yücel, İsmail; Department of Civil Engineering (2018) Drought has been a significant result of climate change that causes variance on precipitation regimes. Mediterranean region is one of the hotspots of the world in this respect. Dry summers and rainy winters -the characteristic of this climate type- makes this region more vulnerable to the effects of climate change. Hence, it is important to monitor drought considering the increasing population and economic facilities in the regions that are under Mediterranean climate conditions in Turkey. This study aims t...
Flood Interaction with River Crossings: A Case Study Yanmaz, Ali Melih (null, Springer, 1994-01-01) Floods are natural hazards whose effects can deeply affect the economic and environmental equilibria of a region. Quality of life of people living in areas close to rivers depends on both the risk that a flood would occur and the reliability of flood forecast, warning and control systems. Tools for forecasting and mitigating floods have been developed through research in the recent past. Two innovations currently influence flood hazard mitigation, after many decades of lack of significant progress: they are...

Citation Formats

Ö. O. Evkaya, C. Yozgatlıgil, and S. A. Kestel, “Drought Forecasting with Time Series and Machine Learning Approaches,” presented at the 10.International Statistics Congress (ISC2017), (6 - 08 Aralık 2017), Ankara, Türkiye, 2017, Accessed: 00, 2021. [Online]. Available: https://hdl.handle.net/11511/79067.