Abstract
In this study, Urmia lake and its basin, which are vital regions in the northwest of Iran, were monitored using satellite data and modeling methods. Monthly precipitation was computed using TRMM satellite dataset. Terrestrial Water Storage (TWS), evaporation, temperature, and TWS Anomaly (TWSA) were estimated from GLDAS dataset and GRACE missions. Moreover, Jason satellite altimetry series and MODIS were used to assess the lake Water Level (WL) and area variations. These seven parameters were estimated from April 2002 to June 2019. This study adopted and evaluated four deep-learning methods based on feed-forward and recurrent architectures for data modeling, and, subsequently, predicting the water area variations. According to the obtained results, Recurrent Neural Network (RNN) and Convolutional Neural Network (CNN) models had some malfunctions in predicting lake area, while Multi-Layer Perceptron (MLP) and Long Short-Term Memory (LSTM) acquired results close to real variations of Urmia lake area. Taking Mean Absolute Error, Mean Relative Error, Root Mean Squared Error (RMSE), and correlation coefficient (r) as evaluation parameters, LSTM achieved the superior quantities, 175.07 km2, 18.87%, 231.7 km2, and 0.83, respectively. Results also indicate that LSTM is more accurate while predicting the variation of critical situations.
Zusammenfassung
Überwachung und Vorhersage zeitlicher Veränderungen im Urmia-See und seinem Einzugsgebiet unter Verwendung von Multisensor-Satellitendaten und Deep-Learning-Algorithmen In dieser Studie wurden der Urmia-See und sein Einzugsgebiet, die lebenswichtige Regionen im Nordwesten des Iran sind, mit Hilfe von Satellitendaten und Modellierungsmethoden überwacht. Der monatliche Niederschlag wurde anhand des TRMM-Satellitendatensatzes berechnet. Terrestrische Wasserspeicherung (TWS), Verdunstung, Temperatur und TWS-Anomalie (TWSA) wurden aus dem GLDAS-Datensatz und den GRACE-Missionen geschätzt. Darüber hinaus wurden Jason-Satellitenaltimetrie-Serien und MODIS verwendet, um Schwankungen des Wasserstands (WL) und der Seefläche zu bewerten. Diese sieben Parameter wurden von April 2002 bis Juni 2019 geschätzt. In dieser Studie wurden vier Deep-Learning-Methoden auf der Grundlage von Feed-Forward- und rekurrenten Architekturen für die Datenmodellierung und anschließend für die Vorhersage der Wasserflächenschwankungen verwendet und bewertet. Die Ergebnisse zeigen, dass die Modelle des rekurrenten neuronalen Netzes (RNN) und des konvolutionären neuronalen Netzes (CNN) bei der Vorhersage der Seefläche einige Fehler aufweisen, während die Modelle des mehrschichtigen Perzeptrons (MLP) und des Langzeitgedächtnisses (LSTM) Ergebnisse erzielen, die den tatsächlichen Veränderungen der Urmia-Seefläche nahe kommen. Unter Berücksichtigung des mittleren absoluten Fehlers, des mittleren relativen Fehlers, des mittleren quadratischen Fehlers (RMSE) und des Korrelationskoeffizienten (r) als Bewertungsparameter erzielte das LSTM die besten Werte: 175,07 km2, 18,87%, 231,7 km2 bzw. 0,83. Die Ergebnisse zeigen auch, dass das LSTM bei der Vorhersage der Veränderung kritischer Situationen genauer ist.
Similar content being viewed by others
References
Akbari Asanjan A, Yang T, Hsu K, Sorooshian S, Lin J, Peng Q (2018) Short-term precipitation forecast based on the PERSIANN system and LSTM recurrent neural networks. J Geophys Res Atmos 123(22):12543–512563. https://doi.org/10.1029/2018JD028375
Akhoondzadeh M (2013) A MLP neural network as an investigator of TEC time series to detect seismo-ionospheric anomalies. Adv Space Res 51(11):2048–2057. https://doi.org/10.1016/j.asr.2013.01.012
Alborzi A, Mirchi A, Moftakhari H, Mallakpour I, Alian S, Nazemi A, Hassanzadeh E, Mazdiyasni O, Ashraf S, Madani K (2018) Climate-informed environmental inflows to revive a drying lake facing meteorological and anthropogenic droughts. Environ Res Lett 13(8):084010. https://doi.org/10.1088/1748-9326/aad246
Ashrafzadeh Afshar A, Joodaki GR, Sharifi M (2016) Evaluation of groundwater resources in Iran using GRACE gravity satellite data. J Geomat Sci Technol 5(4):73–84
Bengio Y, Simard P, Frasconi P (1994) Learning long-term dependencies with gradient descent is difficult. IEEE Trans Neural Netw 5(2):157–166. https://doi.org/10.1109/72.279181
Breiman L (1996) Bagging predictors. Mach Learn 24(2):123–140. https://doi.org/10.1007/BF00058655
Chang F-J, Chen P-A, Lu Y-R, Huang E, Chang K-Y (2014) Real-time multi-step-ahead water level forecasting by recurrent neural networks for urban flood control. J Hydrol 517:836–846. https://doi.org/10.1016/j.jhydrol.2014.06.013
Chen H, Zhang W, Nie N, Guo Y (2019) Long-term groundwater storage variations estimated in the Songhua River Basin by using GRACE products, land surface models, and in-situ observations. Sci Total Environ 649:372–387. https://doi.org/10.1016/j.scitotenv.2018.08.352
Delju A, Ceylan A, Piguet E, Rebetez M (2013) Observed climate variability and change in Urmia Lake Basin, Iran. Theoret Appl Climatol 111(1–2):285–296. https://doi.org/10.1007/s00704-012-0651-9
Dietterich TG (2000) An experimental comparison of three methods for constructing ensembles of decision trees: bagging, boosting, and randomization. Mach Learn 40(2):139–157. https://doi.org/10.1023/A:1007607513941
Faraji Z, Kaviani A, Ashrafzadeh A (2017) Assessment of GRACE satellite data for estimating the groundwater level changes in Qazvin province. Ecohydrology 4(2):463–476
Feng L, Hu C, Chen X, Cai X, Tian L, Gan W (2012) Assessment of inundation changes of Poyang Lake using MODIS observations between 2000 and 2010. Remote Sens Environ 121:80–92. https://doi.org/10.1016/j.rse.2012.01.014
Feyisa GL, Meilby H, Fensholt R, Proud SR (2014) Automated water extraction index: a new technique for surface water mapping using Landsat imagery. Remote Sens Environ 140:23–35. https://doi.org/10.1016/j.rse.2013.08.029
Forootan E, Rietbroek R, Kusche J, Sharifi M, Awange J, Schmidt M, Omondi P, Famiglietti J (2014) Separation of large scale water storage patterns over Iran using GRACE, altimetry and hydrological data. Remote Sens Environ 140:580–595. https://doi.org/10.1016/j.rse.2013.09.025
Freund Y, Schapire RE (1997) A decision-theoretic generalization of on-line learning and an application to boosting. J Comput Syst Sci 55(1):119–139. https://doi.org/10.1006/jcss.1997.1504
Gamboa JCB (2017) Deep learning for time-series analysis. arXiv preprint arXiv:1701.01887
Goodfellow I, Bengio Y, Courville A (2016) Deep learning. MIT Press
Gorelick N, Hancher M, Dixon M, Ilyushchenko S, Thau D, Moore R (2017) Google earth engine: planetary-scale geospatial analysis for everyone. Remote Sens Environ 202:18–27. https://doi.org/10.1016/j.rse.2017.06.031
Graves A (2013) Generating sequences with recurrent neural networks. arXiv preprint arXiv:1308.0850
Hassanzadeh E, Zarghami M, Hassanzadeh Y (2012) Determining the main factors in declining the Urmia Lake level by using system dynamics modeling. Water Resour Manag 26(1):129–145. https://doi.org/10.1007/s11269-011-9909-8
Hochreiter S, Schmidhuber J (1997) Long short-term memory. Neural Comput 9(8):1735–1780. https://doi.org/10.1162/neco.1997.9.8.1735
Hrnjica B, Bonacci O (2019) Lake level prediction using feed forward and recurrent neural networks. Water Resour Manag 33(7):2471–2484. https://doi.org/10.1007/s11269-019-02255-2
Huffman GJ, Bolvin DT, Nelkin EJ, Wolff DB, Adler RF, Gu G, Hong Y, Bowman KP, Stocker EF (2007) The TRMM multisatellite precipitation analysis (TMPA): quasi-global, multiyear, combined-sensor precipitation estimates at fine scales. J Hydrometeorol 8(1):38–55. https://doi.org/10.1175/JHM560.1
Huffman GJ, Adler RF, Bolvin DT, Nelkin EJ (2010) The TRMM multi-satellite precipitation analysis (TMPA). In: Satellite rainfall applications for surface hydrology. Springer, pp 3–22. https://doi.org/10.1007/978-90-481-2915-7_1
Karbassi A, Bidhendi GN, Pejman A, Bidhendi ME (2010) Environmental impacts of desalination on the ecology of Lake Urmia. J Great Lakes Res 36(3):419–424. https://doi.org/10.1016/j.jglr.2010.06.004
Khazaei B, Khatami S, Alemohammad SH, Rashidi L, Wu C, Madani K, Kalantari Z, Destouni G, Aghakouchak A (2019) Climatic or regionally induced by humans? Tracing hydro-climatic and land-use changes to better understand the Lake Urmia tragedy. J Hydrol 569:203–217. https://doi.org/10.1016/j.jhydrol.2018.12.004
Landerer FW, Swenson S (2012) Accuracy of scaled GRACE terrestrial water storage estimates. Water Resour Res. https://doi.org/10.1029/2011WR011453
Li H, Mao D, Li X, Wang Z, Wang C (2019) Monitoring 40-year lake area changes of the Qaidam Basin, Tibetan Plateau, using Landsat time series. Remote Sens 11(3):343. https://doi.org/10.3390/rs11030343
Long D, Shen Y, Sun A, Hong Y, Longuevergne L, Yang Y, Li B, Chen L (2014) Drought and flood monitoring for a large karst plateau in Southwest China using extended GRACE data. Remote Sens Environ 155:145–160. https://doi.org/10.1016/j.rse.2014.08.006
Ma C, Li S, Wang A, Yang J, Chen G (2019) Altimeter observation-based Eddy Nowcasting using an improved Conv-LSTM network. Remote Sens 11(7):783. https://doi.org/10.3390/rs11070783
Ma X, Tao Z, Wang Y, Yu H, Wang Y (2015) Long short-term memory neural network for traffic speed prediction using remote microwave sensor data. Transport Res Part C Emerg Technol 54:187–197. https://doi.org/10.1016/j.trc.2015.03.014
McFeeters SK (1996) The use of the Normalized Difference Water Index (NDWI) in the delineation of open water features. Int J Remote Sens 17(7):1425–1432. https://doi.org/10.1080/01431169608948714
Mohebzadeh H (2018) Extracting AL relationship for Urmia Lake, Iran using MODIS NDVI/NDWI Indices. J Hydrogeol Hydrol Eng 7:1. of 7: 2. https://doi.org/10.4172/2325-9647.1000164
Mou L, Bruzzone L, Zhu XX (2018) Learning spectral-spatial-temporal features via a recurrent convolutional neural network for change detection in multispectral imagery. IEEE Trans Geosci Remote Sens 57(2):924–935. https://doi.org/10.1109/TGRS.2018.2863224
Okay Ahi G, Jin S (2019) Hydrologic mass changes and their implications in Mediterranean-Climate Turkey from GRACE measurements. Remote Sens 11(2):120. https://doi.org/10.3390/rs11020120
Oliveira TP, Barbar JS, Soares AS (2016) Computer network traffic prediction: a comparison between traditional and deep learning neural networks. Int J Big Data Intell 3(1):28–37. https://doi.org/10.1504/IJBDI.2016.073903
Opitz D, Maclin R (1999) Popular ensemble methods: an empirical study. J Artif Intell Res 11:169–198. https://doi.org/10.1613/jair.614
Reddy DS, Prasad PRC (2018) Prediction of vegetation dynamics using NDVI time series data and LSTM. Model Earth Syst Environ 4(1):409–419. https://doi.org/10.1007/s40808-018-0431-3
Rodell M, Houser P, Jambor U, Gottschalck J, Mitchell K, Meng C-J, Arsenault K, Cosgrove B, Radakovich J, Bosilovich M (2004) The global land data assimilation system. Bull Am Meteor Soc 85(3):381–394. https://doi.org/10.1175/BAMS-85-3-381
Rohli RV, Andrew Joyner T, Reynolds SJ, Shaw C, Vázquez JR (2015) Globally Extended Kӧppen-Geiger climate classification and temporal shifts in terrestrial climatic types. Phys Geogr 36(2):142–157. https://doi.org/10.1080/02723646.2015.1016382
Rokni K, Ahmad A, Selamat A, Hazini S (2014) Water feature extraction and change detection using multitemporal Landsat imagery. Remote Sens 6(5):4173–4189. https://doi.org/10.3390/rs6054173
Saemian P, Hosseini-Moghari S-M, Fatehi I, Shoarinezhad V, Modiri E, Tourian MJ, Tang Q, Nowak W, Bárdossy A, Sneeuw N (2021) Comprehensive evaluation of precipitation datasets over Iran. J Hydrol 603:127054. https://doi.org/10.1016/j.jhydrol.2021.127054
Sauter T, Weitzenkamp B, Schneider C (2010) Spatio-temporal prediction of snow cover in the Black Forest mountain range using remote sensing and a recurrent neural network. Int J Climatol 30(15):2330–2341. https://doi.org/10.1002/joc.2043
Sun AY (2013) Predicting groundwater level changes using GRACE data. Water Resour Res 49(9):5900–5912. https://doi.org/10.1002/wrcr.20421
Theodoridis S, Koutroumbas K (2009) Pattern recognition. Academic Press
Tourian M, Elmi O, Chen Q, Devaraju B, Roohi S, Sneeuw N (2015) A spaceborne multisensor approach to monitor the desiccation of Lake Urmia in Iran. Remote Sens Environ 156:349–360. https://doi.org/10.1016/j.rse.2014.10.006
TRMM (2011) TRMM (TMPA/3B43) Rainfall Estimate L3 1 month 0.25 degree x 0.25 degree V7. Greenbelt, MD, Goddard Earth Sciences Data and Information Services Center (GES DISC). https://doi.org/10.5067/TRMM/TMPA/MONTH/7. Accessed 15 Apr 2020
USDA (2019) Global Reservoirs/Lakes (G-REALM). Available online: http://www.pecad.fas.usda.gov/cropexplorer/global_reservoir/. Accessed 20 Sep 2019
Vaheddoost B, Aksoy H, Abghari H (2016) Prediction of water level using monthly lagged data in Lake Urmia, Iran. Water Resour Manag 30(13):4951–4967. https://doi.org/10.1007/s11269-016-1463-y
Vermote E (2015) MOD09Q1 MODIS/Terra Surface Reflectance 8-Day L3 Global 250m SIN Grid V006 N. E. L. P. DAAC. from https://doi.org/10.5067/MODIS/MOD09Q1.006. Accessed 15 Apr 2020
Vignudelli S, Scozzari A, Abileah R, Gómez-Enri J, Benveniste J, Cipollini P (2019) Water surface elevation in coastal and inland waters using satellite radar altimetry. In: Extreme hydroclimatic events and multivariate hazards in a changing environment. Elsevier, pp 87–127. https://doi.org/10.1016/B978-0-12-814899-0.00004-3
Williams RJ, Zipser D (1989) A learning algorithm for continually running fully recurrent neural networks. Neural Comput 1(2):270–280. https://doi.org/10.1162/neco.1989.1.2.270
Xu H (2006) Modification of normalised difference water index (NDWI) to enhance open water features in remotely sensed imagery. Int J Remote Sens 27(14):3025–3033. https://doi.org/10.1080/01431160600589179
Xu S, Niu R (2018) Displacement prediction of Baijiabao landslide based on empirical mode decomposition and long short-term memory neural network in Three Gorges area, China. Comput Geosci 111:87–96. https://doi.org/10.1016/j.cageo.2017.10.013
Zarghami M (2011) Effective watershed management; case study of Urmia Lake, Iran. Lake Reserv Manag 27(1):87–94. https://doi.org/10.1080/07438141.2010.541327
Zhou Z-H (2012) Ensemble methods: foundations and algorithms. CRC Press
Zhou Y, Jin S, Tenzer R, Feng J (2016) Water storage variations in the Poyang Lake Basin estimated from GRACE and satellite altimetry. Geodesy Geodyn 7(2):108–116. https://doi.org/10.1016/j.geog.2016.04.003
Zhu XX, Tuia D, Mou L, Xia G-S, Zhang L, Xu F, Fraundorfer F (2017) Deep learning in remote sensing: a comprehensive review and list of resources. IEEE Geosci Remote Sens Mag 5(4):8–36. https://doi.org/10.1109/MGRS.2017.2762307
Acknowledgements
The authors would like to acknowledge Dr. Hossein Arefi for his valuable and profound comments. We thank the following organizations for providing the data used in this work: the TRMM projects, the Global Land Data Assimilation System (GLDAS), the GRACE Project, the G-REALM project providing altimeter datasets, and MODIS project. We also thank the anonymous reviewers and the editor for their constructive suggestions and comments improving the paper substantially.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Radman, A., Akhoondzadeh, M. & Hosseiny, B. Monitoring and Predicting Temporal Changes of Urmia Lake and its Basin Using Satellite Multi-Sensor Data and Deep-Learning Algorithms. PFG 90, 319–335 (2022). https://doi.org/10.1007/s41064-022-00203-1
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s41064-022-00203-1