Research
Forecasting of Fog by using Fuzzy Interference Systems
In this study the method of fuzzy interference systems are used to evaluate fog forecasting. Input variables used in this study included the situation of fog parameters dew point, dew point spread, rate of change of dew point spread wind speed and sky coverage. The membership functions are generally trapezoids, although simpler functions such as triangles and rectangles and even delta functions are often used. The degrees of membership of the system inputs are also examined. The strength of a rule has been derived from the corresponding degrees of membership of the system inputs. Only 16 rules of the entire set of 144 would have non-zero values, or strengths. The techniques indicate some preliminary results using real data. The final system output is then calculated as the weighted average of the centroid of each membership function with the area of the enclosed set used as the weighting factor. These centroids and weighting areas of the current values were calculated to find the forecasting of fog. The result of this study would hopefully help the planners and program managers to take necessary actions and to development air, marine, and road traffic etc.
Development of Fuzzy Membership Functions and Meteorological Drought Classification as per SPI
Drought -as an environmental occurrence, is an essential part of climatic variability. Droughts are the product of keen water shortage causing severe and sometimes disastrous economic and social consequences. The Standardized Precipitation Index (SPI) provides the forecasting of drought. The SPI also detects moisture shortage more rapidly which has a reply time scale of approximately 3, 6, 12, 24, 48 months. On the other hand, fuzzy logic can be used to focus on modeling problems characterized by imprecise or ambiguous information. It also needs a complete understanding of the drought causing factors, severity classification and to interpret the drought forecasted output variables. In this study, the number of linguistic terms referred to as fuzzy sets, is assign to variable rainfall. The degree of membership (from 0 to 1) of a real valued input (SPI) to a particular fuzzy set A (ED, SD, MD, N, MW, SW, EW) is specified by a membership function ( ) A μ x . Fuzzification of linguistic variables is classified into linguistic labels by transfer membership functions for each of the variable. The drought forecasting measures in the form of fuzzy ranks were identified for each year. All the fuzzified ranks were identified for each SPI values. The fuzzified ranks were used for forecasting the drought severity class for different years. In this study the fuzzy logic based drought forecasting method using SPI can be successively used for drought analysis, forecasting and to mitigate unexpected meteorological problems.
