Development and Testing of a Decision Tree for the Forecasting of Sea Fog Along the Georgia and South Carolina Coast

Lindner, Bernhard Lee; Mohlin, Peter J.; Caulder, A. Clayton; Neuhauser, Aaron

doi:10.15191/nwajom.2018.0605

Cited by 5 publications

(3 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The average accuracy of these three approaches to forecast visibility is shown in Table XIII. This table also shows the accuracy of another study that employed a decision tree approach to forecast the occurrence of sea fog [29]. As shown in Table XIII, the fuzzy model proposed in this paper for fog occurrence was able to achieve better results than three other methods.…”

Section: Bias =mentioning

confidence: 66%

Fuzzy Inference System Framework to Prioritize the Deployment of Resources in Low Visibility Traffic Conditions

Ortega

Otero

2019

IEEE Access

View full text Add to dashboard Cite

Transportation managers and engineers are often required to make decisions regarding the use of limited resources that directly affect public safety, costs, and the overall performance of transportation systems. One important decision involves prioritizing the deployment of resources (e.g., personnel and variable signs) to low visibility areas due to fog or other environmental and road conditions. Due to the lack of proper approaches to characterize and incorporate weather and road condition parameters in the decisionmaking process, transportation managers depend mainly on personal experience to make these types of decisions. To help them prioritize the deployment of resources to low visibility areas, this research presents a fuzzy inference system (FIS) framework composed of three fuzzy systems that characterize fog occurrence, road risk conditions, and deployment of resources. Preliminary experiments to evaluate the developed fog occurrence FIS against four methods presented in the literature using data from two weather stations showed that the FIS model outperformed three of the other methods in accuracy. These results are very promising given that the other methods represent more expensive solution approaches that require large amounts of data, significant time-consuming data preparation, network architecture design tasks, and high processing power.

show abstract

Section: Bias =mentioning

confidence: 66%

Fuzzy Inference System Framework to Prioritize the Deployment of Resources in Low Visibility Traffic Conditions

Ortega

Otero

2019

IEEE Access

View full text Add to dashboard Cite

show abstract

“…Through state-of-the-art numerical models and statistical approaches such as a decision tree [5][6][7], neural network [8,9], fuzzy logic [10,11], and artificial intelligence/machine learning [12][13][14][15], the predictability of fog could be enhanced by reproducing the fogrelevant thermodynamical state of the atmosphere. Although the nowcasting (6-12 h) skill of statistical approaches for site-specific fog is reasonably satisfactory, these approaches have limited spatial resolution and depend on long-term fog field observations.…”

Section: Introductionmentioning

confidence: 99%

Operational Probabilistic Fog Prediction Based on Ensemble Forecast System: A Decision Support System for Fog

et al. 2022

View full text Add to dashboard Cite

One of the well-known challenges of fog forecasting is the high spatio-temporal variability of fog. An ensemble forecast aims to capture this variability by representing the uncertainty in the initial/lateral boundary conditions (ICs/BCs) and model physics. The present study highlights a new operational Ensemble Forecast System (EFS) developed by the Indian Institute of Tropical Meteorology (IITM), Pune, to predict the fog over the Indo-Gangetic Plain (IGP) region using the visibility (Vis) diagnostic algorithm. The EFS framework comprises the WRF model with a 4 km horizontal resolution, initialized by 21 ICs/BCs. The advantages of probabilistic fog forecasting have been demonstrated by comparing control (CNTL) and ensemble-based fog forecasts. The forecast is verified using fog observations from the Indira Gandhi International (IGI) airport during the winter months of 2020–2021 and 2021–2022. The results show that with a probability threshold of 50%, the ensemble forecasts perform better than the CNTL forecasts. The skill scores of EFS are relatively promising, with a Hit Rate of 0.95 and a Critical Success Index of 0.55; additionally, the False Alarm Rate and Missing Rate are low, with values of 0.43 and 0.04, respectively. The EFS could correctly predict more fog events (37 out of 39) compared with the CNTL forecast (31 out of 39) and shows the potential skill. Furthermore, EFS has a substantially reduced error in predicting fog onset and dissipation (mean onset and dissipation error of 1 h each) compared to the CNTL forecasts.

show abstract

“…Decision Tree Regression (DTR) [14] algorithms use a forking tree structure to classify data and can be sensitive to small changes in the training data. DTRs are very popular for classification, such as product recommendations, but may also be applied to regression predictions, including environmental forecasting [19,20]. Artificial neural networks (ANN) model complex connections between input and output data sets with a middle "hidden layer" analogous to biological neurons.…”

Section: Introductionmentioning

confidence: 99%

A Comparison of Machine Learning Methods to Forecast Tropospheric Ozone Levels in Delhi

Juarez¹,

Petersen

2021

Atmosphere

View full text Add to dashboard Cite

Ground-level ozone is a pollutant that is harmful to urban populations, particularly in developing countries where it is present in significant quantities. It greatly increases the risk of heart and lung diseases and harms agricultural crops. This study hypothesized that, as a secondary pollutant, ground-level ozone is amenable to 24 h forecasting based on measurements of weather conditions and primary pollutants such as nitrogen oxides and volatile organic compounds. We developed software to analyze hourly records of 12 air pollutants and 5 weather variables over the course of one year in Delhi, India. To determine the best predictive model, eight machine learning algorithms were tuned, trained, tested, and compared using cross-validation with hourly data for a full year. The algorithms, ranked by R2 values, were XGBoost (0.61), Random Forest (0.61), K-Nearest Neighbor Regression (0.55), Support Vector Regression (0.48), Decision Trees (0.43), AdaBoost (0.39), and linear regression (0.39). When trained by separate seasons across five years, the predictive capabilities of all models increased, with a maximum R2 of 0.75 during winter. Bidirectional Long Short-Term Memory was the least accurate model for annual training, but had some of the best predictions for seasonal training. Out of five air quality index categories, the XGBoost model was able to predict the correct category 24 h in advance 90% of the time when trained with full-year data. Separated by season, winter is considerably more predictable (97.3%), followed by post-monsoon (92.8%), monsoon (90.3%), and summer (88.9%). These results show the importance of training machine learning methods with season-specific data sets and comparing a large number of methods for specific applications.

show abstract

Development and Testing of a Decision Tree for the Forecasting of Sea Fog Along the Georgia and South Carolina Coast

Cited by 5 publications

References 28 publications

Fuzzy Inference System Framework to Prioritize the Deployment of Resources in Low Visibility Traffic Conditions

Fuzzy Inference System Framework to Prioritize the Deployment of Resources in Low Visibility Traffic Conditions

Operational Probabilistic Fog Prediction Based on Ensemble Forecast System: A Decision Support System for Fog

A Comparison of Machine Learning Methods to Forecast Tropospheric Ozone Levels in Delhi

Contact Info

Product

Resources

About