کاربست روش شبکه‌های عصبی در پیش‌بینی دمای سطح زمین، با استفاده از تصاویر حرارتی مادیس

نوع مقاله : علمی - پژوهشی

نویسندگان

1 استادیار مؤسسۀ ژئوفیزیک، دانشگاه تهران

2 استادیار دانشکده مهندسی صنایع و سیستم‌های مدیریت، دانشگاه صنعتی امیرکبیر، تهران

3 دانشجوی کارشناسی‌ارشد مهندسی دانش و علوم تصمیم، دانشگاه علوم اقتصادی، تهران

چکیده

در این مطالعه، مدلی ترکیبی از شبکه‌های عصبی ماژولار و پردازش تصاویر مادیس برای محاسبۀ دمای سطح زمین، در منطقه‌ای شامل شهر تهران، ارائه شده است. در این مدل، داده‌های تصاویر حرارتی با تکیه بر ویژگی‌های دمای درخشندگی در باندهای حرارتی 31 و 32 میکرومترسنجندۀ مادیس، به‌منزلۀ ورودی در شبکه‎های عصبی ماژولار به‌کار رفته و روش جدیدی براساس ترکیبی از شبکۀ عصبی نگاشت خودسازمانده و الگوریتم بهینه‌سازی تجمع ذرات پیشنهاد شد. نتایج به‌دست‌آمده نشان می‌دهد استفاده از این الگوریتم سبب توزیع مناسب داده‌های ورودی شبکه‌های عصبی می‌شود. در آخر، نتایج نهایی با مدل‌های شبکه‌های عصبی با آموزش و ساختار غیرماژولار نیز مقایسه شده است. نتایج این مقایسه نشان می‌دهد که زمان آموزش مدل در پیش‌بینی دمای سطح زمین کاهش، و دقت مدل افزایش یافته است. اختلاف کم بین مقادیر پیش‎بینی‌شده و مقادیر واقعی دما در منطقه نشان می‌دهد که دما با دقت مناسبی در این مدل پیش‌بینی شده است، به‌طوری‌که میانگین خطای مدل ترکیبی مقدار 0081/0 و درصد خطای مطلق نیز 59/10 است. 

کلیدواژه‌ها


عنوان مقاله [English]

Application of Neural Networks for Land Surface Temperature Forecasting Using MODIS Images

نویسندگان [English]

  • F Taghavi 1
  • A Ahmadi 2
  • Z Zargaran 3
1 Assistant Prof., Institute of Geophysics, University of Tehran
2 Assistant prof., Institute of Industrial Engineering and Management Systems, Amirkabir University of Technology
3 M.Sc. Student, University of Economic Sciences
چکیده [English]

In this study, a combined model of modular networks and satellite image processing and optimization algorithms to forecast land surface temperature in  an area  including city of Tehran is presented. Calculating the LST has been done based on brightness temperature features in 31 and 32 MODIS channels. Thus, brightness temperature data related to these images is fed to neural network and values of land surface temperature are recovered as the output of the network. In this way,after obtaining the optimal structure obtained for networks they are trained and their weights are extracted. Then by applying a neural network with a modular structure and clustering algorithms, training will be also modular. Decomposition of the networks and after that  combining the results to get the final forecast  makes the performance of the modular network more effective. As a result , a new approach based on the combination of neural network or self-organizing map and particle swarm optimization algorithms is proposed. The results showed that using PSO algorithm causes appropriate distribution of cluster of SOM method and using satellite images improved performance of the proposed model. Finally, results are compared with training neural network models and non-modular structure. The results of this comparison show that model-training time in predicting the land surface temperature is decreased and the accuracy of model increased. The little difference between the predicted values and actual (real) values of temperature in the region shows that this model could predict the temperature accuraetly, so that, in this hybrid model Mean Square Errors (MSE) and Mean Absolute Percentage Error (MAPE) are 0.0081 and 10.59 respectively.

کلیدواژه‌ها [English]

  • MODIS Images
  • Modular Neural Networks
  • Surface temperature
  1. تقوی، ف.، اولاد، ا.، صفرراد، ط.، ایران‌نژاد، پ.، 1392، تشخیص و پایش توفان گردوغبار غرب ایران با استفاده از تکنیک‌های سنجش از دور، مجلۀ فیزیک زمین و فضا، دورۀ 39، شمارۀ 3، صص. 96-83.
  2. سایت تصاویر سنجندۀ مادیس، 2010.
  3. rapidfire.sci.gsfc.nasa.gov/realtime
  4. شکیبا، ع.، ضیائیان فیروزآبادی، پ.، عاشورلو، د.، نامداری، سودابه.، 1388، تحلیل رابطۀ کاربری و پوشش اراضی و جزایر حرارتی شهر تهران با استفاده از داده‌هایETM+ ، سنجش از دور و GIS ایران، سال اول، شمارۀ 1،صص. 56-39.
  5. علوی‌پناه، س.ک.، 1382، کاربرد سنجش از دور در علوم زمین (علوم خاک)، تهران، انتشارات دانشگاه تهران.
  6. Anderson, M.C., Norman, J.M., Kustas, W.P., Houborg, R., Starks, P.J & Agam, N., 2008, A Thermal-Based Remote Sensing Technique for Routine Mapping of Land-Surface Carbon, Water and Energy Fluxes from Field to Regional Scales, Remote Sensing of Environment, Vol. 112, No. 12, PP. 4227-4241.
  7. Auda, G.K. & Kamel, M., 1999, Modular Neural Networks: A Survey, International Journal of Neural Systems, Vol. 9, Issue 2, PP. 129-151.
  8. Behbahani, S.M.R., Rahimikhoob, A. & Nazarifar, M.H., 2009, Comparison of Some Split-Window Algorithms to Estimate Land Surface Temperature from AVHRR Data in South eastern Tehran, Iran: Desert, Vol. 14, No. 2, PP, 157-161.
  9. Bodri, L.C. & Cermak, V., 2000, Prediction of Extreme Precipitation Using a Neural Network: Application to Summer Flood Occurrence in Moravia, Advances Eng. Software, Vol. 31, No. 5, PP. 311-321.
  10. Dell’Acqua, F.G. & Gamba, P., 2003, Pyramidal Rain Field Decomposition Using Radial Basis Function Neural Networks for Tracking and Forecasting Purposes, IEEE Trans, on Geoscience and Remote Sensing, Vol. 41, No. 4, PP. 853-862.
  11. Hall, T.H., 1998, Precipitation Forecasting Using a Neural Network, Weather and Forecasting, Vol. 14, PP. 338-345.
  12. Hayati, M.M. & Mohebi, Z., 2007, Temperature Forecasting Based on Neural Network, World Applied Sciences, Vol. 2, No. 6, PP. 613-620.
  13. Hierarchical Data Format, HDF: http://www. hdfgroup.org/ HDF-FAQ.html
  14. Hung, N.Q., Babel, M.S., Weesakul, S. & Tripathi, N.K., 2009, An Artificial Neural Network Model for Rainfall Forecasting in Bangkok, Thailand, Hydrol. Earth Syst. Sci, Vol. 13, No. 8, PP. 1413-1425.
  15. Jaruszewicz, M.M. & Madziuk, J., 2002, Application of PCA Method to Weather Prediction Task, IEEE, Neural Information Processing, Vol. 5, PP. 2359-2363.
  16. Jimenez, D., 1998, Dynamically Weighted Ensemble Neural Networks for Classification, Neura Networks, Vol. 1, PP. 753-756.
  17. Kalnay, E., 2003, Atmospheric Modeling, Data Assimilation and Predictability, Cambridge University Press.
  18. Karray, F.O. & de Silva, C., 2004, Soft Computing and Intelligent Systems Design, Harlow, England: Pearson Education Limited.
  19. Karnieli, A., Agam, N., Pinker, R.T., Anderson, M., Imhoff, M.L. & Gutman, G.G., 2010,
  20. Use of NDVI and Land Surface Temperature for Drought Assessment, Merits and Limitations,
  21. Journal of Climate, Vol. 23, No. 3, PP. 618-633.
  22. Kustas, W. & Anderson, M., 2009, Advances in Thermal Infrared Remote Sensing for
  23. Land Surface Modeling, Agricultural and Forest Meteorology, Vol. 149, Issue 12, PP. 2071-2081.
  24. Kattekola, S., 2010, Weather Radar Image Based Forecasting Using Joint Series Prediction, Thesis, University of New Orleans .
  25. Knorr, W.P., Ioannis, P., George, P. & Nadine, G., 2011, Combined Use of Weather Forecasting and Satellite Remote Sensing Information for Fire Risk, Fire and Fire Impact Monitoring, Computational Ecology and Software, Vol.1, No. 2, PP.112-120.
  26. Li, Z.L., Tang, B.H., Wu, H., Ren, H., Yan, G., Wan, ZH., Trigo, I.F. & Sobrino, J.A., 2013, Satellite-Derived Land Surface Tempera-ture: Current Status and Perspectives, Remote Sensing of Environment, Vol. 131, PP. 14-37.
  27. Liu, C.X. & Zhang, C.F., 2010, Cluster Algorithm Based on Hybrid SOM and PSO, Communications Technology.
  28. Luk, K.C., Ball, J.E. & Sharma, A., 2007, An Application of Artificial Neural Networks for Rainfall Forecasting, Modelling and Simulation Society of Australia and New Zealand.
  29. Lynch, P., 2006, The Emergence of Scientific Weather Forecasting, Cambridge University Press.
  30. Maqsood, I.R., Riaz, M. & Abraham, Kh., 2004, An Ensemble of Neural Networks for Weather Forecasting, Neural Comput & Applic, Vol. 13, No. 2, PP. 112-122.
  31. Mas, J.F. & Flores, J.J, 2008, The Application of Artificial Neural Networks to the Analysis of Remotely Sensed Data, International Journal of Remote Sensing, Vol. 29, No. 3, PP. 617-663.
  32. Mendoza, O.M., Melin, P. & Castillo, O., 2009, Interval Type-2 Fuzzy Logic and Modular Neural Networks for Face Recognition Applications, Applied Soft Computing, Vol. 9, No. 4, PP. 1377-1387.
  33. Nowlan, S.J. & Hinton, G.E., 1990, Evaluation of Adaptive Mixtures of Competing Experts, Neural Information Processing Systems, PP. 774-780.
  34. O’Neill, M.B. & Brabazon, A., 2006, Self-Organizing Swarm (SOSwarm): A Particle Swarm Algorithm for Unsupervised Learning, IEEE, Evolutionary Computation, PP. 634-639.
  35. Otsuka, K.H., Horikoshi, T., Suzuki, S. & Kojima, H., 2000, Memory-Based Forecasting for Weather Image Patterns, Artificial Intelligence, PP. 330-336.
  36. Paras, S.M., Mathur, S., Kumar, A. & Chandra, M., 2007, A Feature Based Neural Network Model for Weather Forecasting, World Academy of Science, Engineering and Technology, Vol. 34, PP. 66-73.
  37. Peres, L.F., Carlos, C. & DaCamara,2013, Land Surface Temperature and Emissivity Estimation Based on the Two-Temperature Method: Sensitivity Analysis Using Simulated MSG/SEVIRI Data, Remote Sensing of Environment, Vol. 91, No. 3, PP. 377-389.
  38. Prata, A J., Caselles, V., Coll, C., Sobrino, J.A. & Ottle, C., 1995, Thermal Remote Sensing of Land Surface Temperature from Satellites, Current Status and Future Prospects, Remote Sensing Reviews, Vol. 12, Issue 3-4, PP. 175-224.
  39. Price, J.C., 1983, Estimating Surface Temperatures from Satellite Thermal Infrared Data: A Simple Formulation for the Atmospheric Effect, Remote Sensing of Environment, Vol. 13, PP. 353-361.
  40. ______, 1984, Land Surface Temperature Measurements from the Split Window Channels of the NOAA 7 AVHRR, Journal of Geophysical Research, Vol. 89, Issue D5 , PP. 7231-7237.
  41. Principe, J.C., Euliano, N.R. & Lefebvre, W.C., 2000, Neural and Adaptive Systems, New York, John Wiley and Sons.
  42. Radhika, Y.S. & Shashi, M., 2009, Atmospheric Temperature Prediction Using Support Vector Machines, International Journal of Computer Theory and Engineering, Vol. 1, No. 1, PP. 55-58.
  43. Salby, M.L., 1996, Fundamentals of Atmospheric Physics, International Geophysics series, Elsevier.
  44. Santhanam, T.S. & Subhajini, A.C., 2011, An Efficient Weather Forecasting System using Radial Basis Function Neural Network, Computer Science, Vol. 7, Issue 7, PP. 962-966.
  45. Santhosh Baboo, S. & Shereef, I.K., 2010, An Efficient Weather Forecasting System Using Artificial Neural Network, Environmental Science and Development, Vol. 1, No. 4, PP. 321-326.
  46. Santurette, P. & Georgiev, C., 2005, Weather Analysis and Forecasting: Applying Satellite Water Vapor Imagery and Potential Vorticity Analysis, Elsevier Academic Press.
  47. Shank, D.B., Hoogenboom, G. & McClendon, R.W., 2008, Dewpoint Temperature Prediction Using Artificial Neural Networks, J. Appl. Meteor. Climatol, Vol. 47, PP. 1757-1769
  48. Sharma, A.O. & Omlin, Ch.W., 2008, Determining Cluster Boundaries Using Particle Swarm Optimization, World Academy of Science, Engineering and Technology, Vol. 2, No. 10, PP. 1106-1110.
  49. Sobrino, J.A. & Romaguera, M., 2004, Land Surface Temperature Retrieval from MSG1-SEVIRI Data, Remote Sensing of Environment, Vol. 92, PP. 247-254.
  50. Sohrabinia, M., Zawar-Reza, P., Rack, W., 2015, Spatio-Temporal Analysis of the Relationship between LST from MODIS and Air Temperature in New Zealand, Theor. Appl. Climatol., Vol. 119, Issue 3., PP. 567-583.
  51. Su, M.B. & Basu, M., 2001, Gating Improves Neural Network Performance, Neural Networks, Vol. 3, PP. 2159-2164.
  52. Taghavi,F. & Neyestani, A., 2011, Short Range Temperature Forecast Verification of WRF Model over Iran, Abstract Proceedings of XXV IUGG General Assembly, Earth on the Edge, Science for a Sustainable Planet Melbourne, Australia, www.iugg.com
  53. Taylor, J.B. & Buizza, R., 2002, Neural Network Load Forecasting with Weather Ensemble Predictions, IEEE Trans. on Power Systems, Vol. 17, No. 3, PP. 626-632.
  54. Xiao, X.D., Dow, E.R., Eberhart, R., Miled, Z.B. & Oppelt, R.J., 2003(a), Gene-Clustering Using Self-Organizing Maps and Particle Swarm, IEEE International Parallel and Distributed Processing Symposium, PP. 22-26.,
  55. _________, 2004(b), A Hybrid Self-Organizing Maps and Particle Swarm Optimization Approach: Concurrency and Computation, Practice and Experience, Vol. 16, No. 9, PP. 895-915.
  56. Xu, J., Rugg, S., Byerle, L. & Liu, Z., 2009, Weather Forecasts by the WRF-ARW Model with the GSI Data Assimilation System in the Complex Terrain Areas of Southwest Asia: Weather and Forecasting, Vol. 24, No. 4, PP. 987-1008.
  57. Yaiprasert, C.J., Jaroensutasinee, K. & Jaroensutasinee, M., 2007, The Pixel Value Data Approach for Rainfall Forecasting Based on GOES-9 Satellite Image Sequence Analysis, Engineering & Technolog, Vol. 36, P. 186.
  58. Zargaran, Z., Ahmadi, A., Mohebi, A. & Taghavi, F., 2014, Hybrid Model for Weather Forecasting Using Ensemble of Neural Networks and Mutual Information, IEEE International Geoscience and Remote Sensing symposium, Quebec , July 13-18, Academy of Science, Engineering and Technology, 186-191,www.igarss2014.org.