اصلاح پیش‌بینی فرایند توفان حاره‌ای با انتخاب ویژگی‌‌‌های موثر

نوع مقاله : مقاله پژوهشی‌

نویسندگان

1 دانشگاه هرمزگان، ایران

2 موسسه ژئوفیزیک دانشگاه تهران، ایران

3 دانشکده مهندسی برق و کامپیوتر دانشگاه تهران، ایران

4 دانشکده کشاورزی و منابع طبیعی دانشگاه هرمزگان، ایران

چکیده

انتخاب ویژگی‌های مناسب برای بررسی و پیش‌بینی هر کمیت جوًی مرتبط با یک پدیده هواشناسی از قبیل وقوع توفان حاره‌ای یکی از چالش‌های اساسی شناسایی سامانه و مدل‌سازی آن است. در این تحقیق روش‌های گوناگون استخراج ویژگی از قبیل جست‌وجوی پی‌در‌پی پیشرو، پسرو، معیار همبستگی متقابل، تحلیل مولفه‌های اصلی و تحلیل عامل‌های اصلی برای استخراج کمیت‌های مرتبط با سرعت باد در ارتفاع 10 متری از سطح زمین در زمان وقوع پدیده توفان حاره‌ای اعمال شده است. در این بررسی فقط داده‌های 45 متغیر متفاوت در محدوده فعالیت توفان حاره‌ای گونو که در اوایل ماه ژوئن 2007 منطقه دریای عرب، دریای عمان و خلیج فارس را در نوردید و خسارت زیادی را به جنوب و جنوب‌شرقی ایران، شرق کشور عمان وارد ساخت پردازش ‌شده‌ است. ازآنجاکه برای استفاده از شبکه عصبی و منطق فازی نیاز به داده‌های آزمون و اعتبار‌سنجی است از داده‌های توفان حاره‌ای یمین که در اواخر ماه ژوئن همان سال در خلیج بنگال و خلیج فارس شکل گرفت درحکم داده آزمون و از داده‌های توفان حاره‌ای نرجس که در اوایل ماه مه 2008 در خلیج بنگال رخ داده بود به‌منزله داده اعتبار‌سنجی استفاده شده است. کمیت‌های انتخابی نهایی بعد از استخراج ویژگی درحکم ورودی به شبکه استنباط فازی-عصبی تطبیقی(ANFIS) که خروجی آن سرعت باد در ارتفاع 10 متری از سطح زمین است داده شد و مقدار شاخص خطا در حالت‌های متفاوت آموزش شبکه تعیین و در داخل جدولی آورده شده است.
 
 
 

کلیدواژه‌ها


عنوان مقاله [English]

Improvement the tropical cyclone forecasting process with effective features selection

نویسندگان [English]

  • Farideh Habibi 1
  • Majied Mazraeh Frahani 2
  • Behzad Moshiri 3
  • Ahmad Nohegar 4
  • Ahmad Kalhor 3
چکیده [English]

The selection of adequate features for studying and forecasting of each atmospheric quantity regarding the meteorological ‎phenomena (for example, a tropical cyclone) is one of the basic challenges in system recognition and modeling concepts.
This study uses various methods of feature extraction including sequential forward selection, sequential backward ‎selection, mutual information, principal components analysis (PCA) and principal factor analysis (PFA) to extract quantities ‎ considering the wind speed at 10 meters above surface for a tropical cyclone activity period. This work studies 45 ‎various quantities of a Guno tropical cyclone activity domain which occurred in early June 2007 over the Arabian ‎Sea, the Gulf of Fars, and the OmanSea regions which caused significant damage to the region due to storm surges. These ‎quantities were initially selected from 286 quantities of the atmosphere which were determined in the global network of 1‎ by ‎1 ‎degree under the standard conditions including standard pressure levels (1000 mb to 10 mb), surface land ‎temperature (SLT), and surface sea temperature (SST). Due to the fact that the activity of the ‎interesting phenomena (i.e. Guno tropical storm) concentrates at the low and medial troposphere, it is possible to exclude ‎quantities of the upper atmosphere.
As a rule, the employment of neural network and fuzzy logic methods requires that the data be tested and validated. As a result, the Yemyin tropical ‎cyclone data was considered as testing data (it happened exactly 8 days after the Guno storm in the west of India, and, after ‎traveling over India, then entered into the southeast of Iran and, subsequently, into the northwest of Pakistan). The Nargis tropical cyclone data which occurred in May 2008 at the Bay of Bangal was considered as validation data because there ‎is currently no valid and acceptable data regarding the history of the old Guno tropical storm which occurred in this region approximately 35 ‎years ago.‎
The features extracted from the three first methods were tested using an adaptive network-based fuzzy inference system (ANFIS) approach. ‎Of course, 44 features were considered as inputs and a speed of 10 meters of surface was considered as output. The Guno storm data was considered for ‎training the network but the Yemyin storm data was used for testing the network and the Nargis storm data was used for the purpose of network validation.
Due to the fact that the KMO parameter for all three storms was greater than 0.80, the PCA method was used with high ‎confidence for data mining. The results show that the first 18 new components of the storms Guno and Yemyin are greater ‎than the others and they include more than 95% of existing information regarding 45 variables; consequently, the remaining components can be eliminated. However, this is true for the Nargis storm with the first 20 new components.‎
The results show that the computation time of the sequential backward selection method is very high in comparison with the sequential ‎forward selection method. The results show that the corresponding accuracy for sequential backward selection is also high.
The results of an ANFIS test for a different epoch show that the features extracted from the forward selection method have ‎minimum errors within three epochs.‎
The study of coefficient components shows the basic part of the second component is related to wind speeds of 10 meters height ‎over the surface and wind speeds in the layer 30 mb above the surface. Therefore, these components can be utilized as output for neural networks and ‎fuzzy systems such as the ones used in the ANFIS method.‎
 
 

کلیدواژه‌ها [English]

  • Features selection
  • Adaptive Network-based Fuzzy Inference System (ANFIS)
  • Tropical Cyclone
  • Sequential Forward Selection (SFS)
  • Mutual Information