The Statistical Pattern Recognition of the Weather Conditions Based on the Gray-Scale of Image

The Statistical Pattern Recognition of the Weather Conditions Based on the Gray-Scale of Image

Li-ling Peng (Kunming University of Science and Technology, China) and Xiao-rong Gan (Kunming University of Science and Technology, China)
Copyright: © 2012 |Pages: 10
DOI: 10.4018/jaec.2012070105
OnDemand PDF Download:
$30.00
List Price: $37.50

Abstract

In this paper, gray-scale of various types of cloud images collected over the Kunming Area were analyzed based on statistical theory and methods in order to achieve recognition of the pattern of the weather conditions. The results show that there are remarkable differences in normal distribution on the gray-scale histogram and the recurrence plot for different weather conditions. It is shown that the gray-scale method is simple, feasible, timely, reliable, and accurate. That would provide theoretical support and methods for meteorological and other related departments.
Article Preview

1. Introduction

Weather forecast is an important reference for people’s life because of the close correlation between weather phenomena and development of society economic (meteorological program in CCTV with first audience rating), and the meteorological prediction has become the new hot spot for international scientific community (Jiao, Gong, & Zhou, 2006). Usually there are the situation forecast and element forecast for the weather forecast: situation forecast is the basis of element forecasting, and the situation forecast focus on changes of appearance, disappearance, move, and intensity of various weather systems within a period of time in future, while the element forecast focus on changes of temperatures, wind, clouds, precipitation and weather phenomena in moments in future. Means of situation forecast include numerical prediction and weather map which also has experienced extrapolation, similar situation, statistical data and physical analysis. Elements forecast methods are mainly experience forecast, statistical forecast and the power of statistical forecast (Sun & Zhang, 2005).

Overall, weather forecast have developed to a new era when a variety of the latest achievements of science and technology and methods are applied synthetically based on the platform of man-machine interactive processing system and the numerical weather prediction from the traditional semi-empirical theory of qualitative methods of the climate theory, mathematical statistics and forecaster’ experience; and the way of forecasting gradually shifts to the in-depth consideration of the inherent laws of atmospheric motion from the external phenomena of atmosphere (Qiu, 2000). More specifically speaking, the kinematic method and extrapolation method, the most popular weather forecast technology 50 years ago, had followed the style of the Bergen School. Since the operational model of numerical weather forecast appeared, the national meteorological centers gradually adopted the numerical power and probabilistic forecasts in order to guide the weather situation or element prediction after 6 ~ 12 hours (Zeng, 1979). Before 1966,people like Zeng, Chou, and Zhou Xiaoping have made many contributions to the development of the numerical techniques, initialization and mode (Chen & Xue, 2004; Zeng, 2002). Afterwards, scientists had a lot of research on the predictability of the various types of weather phenomena. Lorenz (1963) proposed that the atmosphere is a chaotic system and probability concepts should be adopted to forecast weather change. His “attractor” research has been widely used in the field of fluid mechanics. An important theoretical foundation was provided by Lorenz for numerical statistics (MOS), probability statistics forecast and numerical ensemble prediction. However, it was found that a tiny error in initial conditions would enlarge with the proliferation of larger scales in many trials of the modes. Besides, with the wide application of computer, synoptic meteorology had changed gradually from description by artistic experience of weather phenomena and process to analysis of dynamic and thermodynamic diagnostic in order to incorporate synoptic meteorology and atmospheric dynamics. By the 20th century, the grid points of the mode in two-dimensional (z, y) has increased from 102×102 to 103×103 with the development of large-capacity and high-speed computers. Undoubtedly, development of these technologies is great power for data collection, exchange, processing of numerical weather prediction, weather, climate, ocean observing and other areas atmospheric science. In addition, the World Meteorological Organization (WMO) is embarked on a Global Weather Observing System Research and Predictability experiment (THORPEX) for 10 years (Shapiro & Thorpe, 2004), further enrich results achieved from the ensemble forecasting and adaptive observation to improve dynamical prediction and probabilistic forecasts of disastrous weather and rainfall.

Complete Article List

Search this Journal:
Reset
Open Access Articles: Forthcoming
Volume 8: 4 Issues (2017): 3 Released, 1 Forthcoming
Volume 7: 4 Issues (2016)
Volume 6: 4 Issues (2015)
Volume 5: 4 Issues (2014)
Volume 4: 4 Issues (2013)
Volume 3: 4 Issues (2012)
Volume 2: 4 Issues (2011)
Volume 1: 4 Issues (2010)
View Complete Journal Contents Listing