Yapay Sinir Ağları ile Esenboğa Havaalanı için Sis Görüş Mesafesinin Tahmin Edilebilirliği

Abstract

Fog event affects air, land and sea transportation adversely by reducing visibility, thus causes economic loss. Besides, it has an important role in construction planning. For this reason, it is very important to predict visibility before and during fog events. In this study, fog visibility prediction was made with artificial neural networks and validations were made for Esenboğa Airport. Temperature, dew point temperature, pressure, wind speed and relative humidity, which are considered to be the most important parameters for fog occurrence, were used for 2013-2015 years to train an artificial neural network. We selected only January, February, November and December months, as those are the foggiest months for Esenboğa airport. Correlation of test part was evaluated after training. Then, whole data for 2016-2017 years (regardless of fog existence) were used for validation of the output again. As a result, we found a correlation value (R) of 0.80 for the test part of 2013-2015 years; R=0.41 and root mean square error (RMSE) of 2652m for all data of the 2016 year; and R = 0.53 and RMSE = 2464m for all data of the 2017 year. The error rate (R = 0.80) for the test part (2013-2015) was found acceptable. However, consistencies for the years 2016 and 2017, when all data were tested regardless of fog existence were found below expectations.

LSTM ve Facebook Prophet Kullanarak Brent Ham Petrol Trendinin Tahmini

“…[8] 2019 Brent oil price LSTM An et al [9] 2019 Oil price Regression-based ML Khashman and Nwulu [10] 2011 Oil price Support Vector Machines Wang et al [4] 2020 Natural gas price A hybrid data-driven model Gabralla et al [11] 2013 Oil Price ML Ishaq [12] 2020 Oil price Orange Abdullah and Zeng [13] 2010 Crude Oil Price ANN-Quantitative Olofin et al [14] 2019 Oil Price ML Guo [1] 2019 Oil Price Deep Learning and ARIMA Bristone et al [5] 2019 Oil Price LSTM Gupta and Nigam [15] 2020 Crude Oil Price ANN Abdollahi and Ebrahimi [16] 2020 Crude Oil Price ARFIMA, ANFIS, GA Chiroma et al [2] 2015 Crude Oil Price Evolutionary N.N. Model Latifoglu and Nuralan [17] 2020 Stream Flow LSTM Oğuz and Pekin [18] 2019 Fog Visibility ANN Gultepe [19] 2019 Air Pollution ML Alpay [20] 2019 USD / TRY Price LSTM Kızıloz [21] 2020 Citation Count LSTM Aguilera et al [22] 2019 Groundwater-level Prophet Weytjens et al [23] 2019 Cash flow LSTM, ARIMA, Prophet Duarte and Faerman [24] 2019 Healthcare ARIMA, Prophet Žunić et al [25] 2020 Sales Prophet Samal et al [26] 2019 Air pollution SARIMA, Prophet Borowik et al [27] 2018 Crime ARIMA, Prophet Phutela et al [28] 2020…”

A climatological study of fog in Turkey

“…Some factors such as geographic properties (e.g., proximity to moisture sources) and atmospheric factors (e.g., obvious changes in wind direction and speed, thermal instability conditions between surface and upper levels) play significant role in the rapid development of fog event on a region and makes it difficult to predict. To understand the underlying atmospheric mechanisms of fog occurrence and its predictability during short‐term, weather forecasters have performed a few local fog studies (Erturk and Prieto, 2010; Gokgoz et al ., 2014; Ezber et al ., 2018; Oğuz and Pekin, 2019). In their study, they generally combined their long‐term fog forecast experiences with meteorological products (synoptic charts, satellite, and radar products) and NWP models outputs (e.g., ECMWF, ALARO, WRF).…”

Analysis of road accidents due to obstruction in sight distance caused by foggy weather using Geographic Information System (GIS) and Artificial Neural Network (ANN) at Jumja along Thimphu-Phuentsholing Highway (Asian Highway 48)

“…Degraded road visibility has the potential to 1) catch even the experienced drivers off guard, 2) change the way that drivers behave, and 3) distort drivers' perceptions of depth, distance, and speed. Foggy weather conditions pose an immediate threat to road safety, frequently resulting in fatal road accidents (Oğuz & Pekin, 2019). All drivers, regardless of skill level, face risks when driving through fog.…”

“…The model has been trained with the following parameters as inputs: temperature, dew temperature, wind speed and direction, average sea level pressure, total cloud cover, visibility, and rainfall. They therefore came to the conclusion that the model had strong predictive ability (Oğuz & Pekin, 2019). Different research (Cools et al, 2008) evaluated how the weather affected the volume of traffic.…”