Scientific- Research Quarterly of Geographical Data (SEPEHR)

Scientific- Research Quarterly of Geographical Data (SEPEHR)

The Comparison of ARIMA and Neural Network methods for Modeling and Monitoring of Drought Using Remote Sensing Time Series Data (Case Study: City of Arak)

Document Type : Research Paper

Authors
Mohammad Mahdi Khoshgoftar 1
Mehdi Akhoondzadeh Hanzaei 2
Iman Khosravi 3
1 Young researchers and elite club, Khomein Branch, Islamic Azad University, Khomein, Iran
2 Remote sensing division, Surveying and geomatics engineering department, University College of Engineering, University of Tehran, Tehran, Iran
3 Ph.D Candidate in remote sensing division, Surveying and geomatics engineering department, University College of Engineering, University of Tehran, Tehran, Iran
10.22131/sepehr.2019.35646
Abstract
Introduction
Drought is a critical climate condition affecting many places on Earth. Drought severity is often measured using a combination of different variables including rainfall, temperature, humidity, wind, soil moisture, and steam flow. During the last decades, Iran has suffered from drought conditions and it may suffer more in future. The frequent occurrence of drought in Iran is mainly due to lack of sufficient precipitation and improper water management system. Drought is often categorized into three types: meteorological, agricultural, and hydrological. There are various methods for measuring and quantifying drought severity. The most commonly used ones are Palmer Drought Severity Index (PDSI) and Standardized Precipitation Index (SPI). Remotely sensed data can also be used for monitoring drought condition. The most widely used ones are Normalized Difference Vegetation Index (NDVI), Land Surface Temperature (LST), Vegetation Condition Index (VCI), Temperature Vegetation Index (TVX) and NDVI deviation Index (DEV). Neural Network (NN) and Autoregressive Integrated Moving Average (ARIMA) are two of the most widely applied methods for modeling and monitoring drought severity indices.
In this paper, monthly time series data (2000 to 2014) of three remotely sensed indices (i.e., NDVI, VCI, and TVX) and one meteorological index (i.e., SPI) were applied for modeling drought severity. In addition, the NN and ARIMA were developed for modeling these indices.
 
Materials & Methods
Data used in this paper were the time series of NDVI, VCI, TVX, and SPI. The study area in this paper was Arak, center of Markazi province. It has cold and wet winters with warm and dry summers. ARIMA and NN were employed for modeling indices.
ARIMA model is generally derived from three basic time series models: Autoregressive (AR), Moving Average (MA), and Autoregressive Moving Average (ARMA). These basic models are used with static time series, i.e., they have constant mean and covariance in relation to time.
Usually, NN method has three layers. The first layer or the input layer introduces data to network. Input data is processed in the second layer or the hidden layer. Finally, the output layer produces the results of the input data. In this paper, single hidden layer feed forward network, which is the most widely utilized NN form, was employed for modeling indices.
 
Results & Discussion
After implementing NN and ARIMA models on the time series data, the performance of the models was evaluated using Mean Absolute Error (MAE) and Root Mean Square Error (RMSE). The RMSE obtained by NN and used for modeling NDVI, VCI, TVX, and SPI indices of Arak were 0.1944, 0.2191, 0.1295, and 0.2990, respectively. In addition, RMSE obtained from ARMIA, and used for modeling these indices were 0.0770, 37.2318, 0.2658, and 1.3370. In another experiment, the correlation between remotely sensed indices and SPI was studied. Among the remotely sensed indices, TVX shows the most powerful correlation with SPI.
 
Conclusion
In the present study, drought condition in the central region of Markazi province was studied during the 2000 to 2014 period. We used the time series of remotely sensed data (such as LST and NDVI) and meteorological data (such as SPI). Then TVX, VCI, and DEV indices were extracted from NDVI and LST data. NN and ARIMA were applied for modeling time series data. Based on the findings, it is concluded that NN is more successful and efficient than ARIMA for this study area. In addition, TVX, which is built based on NDVI and LST, had the most powerful correlation with SPI. This issue implies that both vegetation index and temperature index had an important role in modeling and monitoring drought condition.
 
Keywords
Neural network
ARIMA
Standardized precipitation index
Normalized Difference Vegetation Index (NDVI)
Vegetation Condition Index (VCI) and Temperature-Vegetation Index (TVX)
1. آخوندزاده، م.؛ (1384). تهیه نقشه‌های حرارتی سطح زمین با استفاده از تصاویر MODIS. پایان‌نامه کارشناسی ارشد، دانشگاه تهران، پردیس دانشکده‌های فنی، گروه مهندسی نقشه‌برداری.
2. ابریشم‌چی، ا.؛ مهدیخانی، ح.؛ تجریشی، م.؛ (1385). توسعه مدل تلفیقی غیرخطی پیش‌بینی خشکسالی مبتنی بر شبکه عصبی مصنوعی و تبدیلات موجک، مطالعه موردی: زیر حوضه سد زاینده رود. دومین کنفرانس مدیریت منابع آب، اصفهان، دانشگاه صنعتی اصفهان، انجمن علوم و مهندسی منابع آب ایران.
3. جلیلی، ش.؛ مرید، س.؛ ضیائیان فیروزآبادی، پ.؛ (1387). مقایسه عملکرد شاخص‌های ماهواره‌ای و هواشناسی در پایش خشکسالی. مجله تحقیقات آب و خاک ایران، دوره 39، ش 1، ص 149-139.
4. جویباری، ی.؛ (1393). تهیه نقشه ضریب گسیل و دما با استفاده از تصاویر ماهواره لندست-8. پایان‌نامه کارشناسی ارشد، دانشگاه تهران، پردیس دانشکده‌های فنی، گروه مهندسی نقشه برداری.
5. سلیمانی، ع.؛ (1389). تحلیل خطرپذیری خشکسالی. پایان‌نامه کارشناسی ارشد، دانشگاه تهران، پردیس دانشکده‌های فنی، گروه نقشه برداری.
6. کارآموز، م.؛ رسولی، ک.؛ نظیف، س.؛ (1385). تدوین ترکیبی خشکسالی با استفاده از شبکه‌های عصبی. دومین کنفرانس مدیریت منابع آب، اصفهان، دانشگاه صنعتی اصفهان، انجمن علوم و مهندسی منابع آب ایران.
7. محمودی کهن، ف.؛ (1389). مطالعه قابلیت شاخص‌های گیاهی ماهواره‌ای در پیش‌بینی و آشکارسازی خشکسالی. پایان‌نامه کارشناسی ارشد، دانشگاه تحصیلات تکمیلی صنعتی کرمان، دانشکده عمران و نقشه‌برداری، گروه سنجش از دور.
8. Barua, S.; Perera, B.J.C.; Ng, A.W.M. and Tran, D.; (2010). “Drought Forecasting Using an Aggregated Drought Index and Artificial Neural Networks”, Journal of Water and Climate Change, Vol 1, pp 193–206.
9. Bhuiyan, C.; Singh, R.P. and Kogan, F.N.; (2006). “Monitoring Drought Dynamics in the Aravalli Region (India) Using Different Indices Based on Ground and Remote Sensing Data,” Int’l J. Applied Earth Observation and Geoinformation, vol. 8, pp. 289-302.
10. Box, G.E.P. and Jenkins, G.M.; (1976). “Time Series Analysis: Forecasting and Control”, Holden-Day, San Francisco, 525 pp.
11.Dastorani, M.T. Afkhami, H. and Borroni, B.; (2011). “Application of Artificial Neural Networks on Drought Prediction in Yazd (Central Iran)”, Desert, Vol 16, pp 39–48.
12. Durdu, O.F.; (2010). “Application of Linear Stochastic Models for Drought Forecasting in the Buyuk Menderes River Basin, Western Turkey”. Stochastic Environmental Research and Risk Assessment, Vol 24, pp 1145–1162.
13. Fernandez, C.; Vega, J.A.; Fonturbel, T. and Jimenez, E.; (2008). “Streamflow Drought Time Series Forecasting: a Case Study in a Small Watershed in North West Spain”. Stochastic Environmental Research and Risk Assessment, Vol 23, pp 1063–1070.
14. Fernando, D.A.K. and Jayawardena, A.W.; (1994). “Generation and forecasting of monsoon rainfall data”, in: Proceedings of the 20th WEDC Conference, Colombo, Sri Lanka, pp 310–313.
15. Han, P.; Wang, P.X.; Zhang, S.Y. and Zhu, D.H.; (2010). “Drought forecasting based on the remote sensing data using ARIMA models”, Mathematical and Computer Modelling, Vol 51, pp 1398–1403.
16. Han, P.; Wang, P.; Tian, M.; Zhang, S. and Liu, J.; (2013). “Application of the ARIMA Models in Drought Forecasting Using the Standardized Precipitation Index”, IFIP International Federation for Information Processing, Vol 392, pp. 352–358.
17. Hopfner, C. and Scherer, D.; (2011). “Analysis of Vegetation and Land Cover Dynamics in North-Western Morocco during the Last Decade Using Modis NDVI Time Series Data,” Biogeosciences, vol. 8, pp. 3359-3373.
18. Hu, W.B.; Tong, S.L.; Mengersen, K. and Connell, D.; (2007). “Weather variability and the incidence of cryptosporidiosis: Comparison of time series Poisson regression and SARIMA models”, Annals Epidemiology, Vol 17, pp 679–688.
19. Jalili, M.; Gharibshah, J.; Ghavami, S.M.; Beheshtifar, M.R. and Farshi, R.; (2014). “Nationwide Prediction of Drought Conditions in Iran Based on Remote Sensing Data”, IEEE Transactions on Computers, Vol 63, No 1, pp:90-101. 
20. Jain, S.K.; Keshri, R.; Goswami, A. and Sarkar, A.; (2010). “Application of Meteorological and Vegetation Indices for Evaluation of Drought Impact: A Case Study for Rajasthan, India,” Natural Hazards, vol. 54, pp. 643-656.
21. Keskin, M.E.; Terzi, O.; Taylan, E.D. and Kucukyaman, D.; (2011). “Meteorological Drought Analysis Using Artificial Neural Networks”, Scientific Research and Essays, Vol 6, pp 4469–4477.
22. Kinyanjui, M.J.; (2011). “NDVI-Based Vegetation Monitoring in Mau Forest Complex, Kenya,” African J. Ecology, vol. 49, pp. 165-174.
23. Kriegler F.J.; Malila W.A.; Nalepka R.F. and Richardson W.; (1969). “Preprocessing transformations and their effects on multispectral recognition”, in: Proceedings of the Sixth International 
24. Kogan, F.N.; (1997). “Global Drought Watch From Space”, Bull. Am. Met. Soc., Vol 78, pp 621-636.
25. Lambin, E.F. and Ehrlich, D.; (1996). “The surface temperature-vegetation index for land cover and land cover change analysis”. International Journal of Remote Sensing, Vol 17, pp 463–487.
26. Li, B. and Tao, S.; (2002). “Relations between AVHRR NDVI and Ecoclimatic Parameters in China,” Int’l J. Remote Sensing, vol. 23, pp. 989-999.
27. Lotsch, A.; Friedl, M.A. and Anderson, B.T.; (2003). “Coupled Vegetation-Precipitation Variability Observed from Satellite and Climate Records,” Geophysical Research Letters, vol. 30, pp. 1774-1777.
28. McKee, T. B.; Doesken, N.J. and Kleist, J.; (1995). “Drought monitoring with multiple time scales”. Ninth Conference on Applied Climatology, American Meteorological Society, Dallas TX, pp.233-236.
29. McKee, T. B., Doesken, N.J. and Kleist, J.; (1993). “The relationship of drought frequency and duration of time scales”. Eighth Conference on Applied Climatology, American Meteorological Society, Anaheim CA, pp.179-186.
30. Mishra, A.K.; Desai, V.R.; (2006). “Drought Forecasting Using Feed-Forward Recursive Neural Network”, Ecological Modelling, Vol 198, pp 127–138.
31. Modarres, R.; (2006). “Streamflow drought time series forecasting”, Stochastic Environmental Research and Risk Assessment, Vol 21, pp 223–233.
32. Orhan, O.; Ekercin, S. and Dadaser-Celik, F.; (2014). “Use of Landsat Land Surface Temperature and Vegetation Indices for Monitoring Drought in the Salt Lake Basin Area, Turkey”. The Scientific World Journal, Vol 2014.
33. Rouse, J. W.; Haas, R.H.; Schell, J. A. and Deering, D.W.; (1973). :Monitoring vegetation systems in the Great Plains with ERTS”, Third ERTS Symposium, NASA SP-351 I, pp 309-317.
34. Rulinda, C.M.; (2007). “Mining Drought from Remote Sensing Images”, MSc thesis, Geo-information Science and Earth Observation.
35. Rulinda, C.M.; Dilo, A.; Bijker, W. and Steina, A.; (2012). “Characterising and Quantifying Vegetative Drought in East Africa Using Fuzzy Modelling and NDVI Data,” J. Arid Environments, vol. 78, pp. 169-178.
36. Sharma, A.; (2006). “Spatial Data Mining for Drought Monitoring: An Approach Using temporal NDVI and Rainfall Relationship”, MSc thesis, Geo-information Science and Earth Observation.
37. Tucker, C.J. and Choudhury, B.J.; (1987). “Satellite Remote Sensing of Drought Conditions,” Remote Sensing of Environment, vol. 23, pp. 243-251, 1987.
38. Weerts, A.H.; Schellekens, J. and Weiland, F.S.; (2010). “Real-Time Geospatial Data Handling and Forecasting: Examples from Delft-FEWS Forecasting Platform/System,” IEEE J. Selected Topics in Applied Earth Observations and Remote Sensing, vol. 3, no. 3, pp. 386-394.
39. Yurekli, K.; Kurunc, K. and Ozturk, F.; (2005). “Application of linear stochastic models to monthly flow data of Kelkit stream”, Ecological Modeling, Vol 183,pp 67–75.
40. Zhang, G.P.; (2003). “Time series forecasting using a hybrid ARIMA and neural network model”, Neurocomputing, Vol 50,pp 159–175.