A review on factors influencing fog formation, classification, forecasting, detection and impacts

Lakra, Kanchan; Avishek, Kirti

doi:10.1007/s12210-022-01060-1

Cited by 25 publications

(15 citation statements)

References 277 publications

(388 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Finally, spatial aggregates of CwPS results from all features reveal that when FogNet correctly predicts both radiation and advection fog (Figures 8a,b), the strongest influential region (darkest red color) is near the target (KRAS). This is consistent with the domain knowledge which posits that the formation and dissipation of fog are controlled by local factors (Lakra and Avishek, 2022). However, non-local factors are also important.…”

Section: Discussionsupporting

confidence: 89%

“…With respect to cases when advection fog occurred (Figures 7b and 7e), note the region of 0 (weakly positive) just offshore; this pattern is typical of advection fog events along the Middle Texas coast. The condition 0 implies a downward-directed near-surface sensible heat flux to the sea, and thus a corresponding heat loss or cooling of the near-surface air temperature to the dew point temperature resulting in saturation and subsequent fog development (Huang et al, 2015; Lakra and Avishek, 2022), subject to a cloud drop-size distribution that favors the extinction of light and subsequent visibility reduction (Twomey, 1974; Koračin et al, 2014). Thus, the spatial pattern of a feature with high feature effect successfully identified an environmental condition (and associated mechanism) conducive to fog.…”

Section: Discussionmentioning

confidence: 99%

“…However, non-local factors are also important. In particular, the larger scale wind pattern can influence the intensity of marine advection fog (Lee et al, 2010; Lakra and Avishek, 2022) (which may account for the lighter-colored red over the waters in Figure 8b). The use of XAI output to confirm expert knowledge regarding the scale of fog development adds trustworthiness.…”

Section: Discussionmentioning

confidence: 99%

“…Advection and radiation fogs are associated with larger-scale subsidence/negative VVEL values (Huang et al, 2011;Yang et al, 2017;Mohan et al, 2020). Sufficient near-surface moisture (high Q surface values) is essential for fog development (Gultepe et al, 2007;Lakra and Avishek, 2022). The trustworthiness of FogNet based on feature importance XAI output is also demonstrated by the relative importance of individual features/channels or feature groups.…”

Section: Meteorological Interpretationmentioning

confidence: 99%

See 3 more Smart Citations

Aggregation strategies to improve XAI for geoscience models that use correlated, high-dimensional rasters

Krell,

Kamangir,

Collins

et al. 2023

Environ. Data Science

View full text Add to dashboard Cite

Complex machine learning architectures and high-dimensional gridded input data are increasingly used to develop high-performance geoscience models, but model complexity obfuscates their decision-making strategies. Understanding the learned patterns is useful for model improvement or scientific investigation, motivating research in eXplainable artificial intelligence (XAI) methods. XAI methods often struggle to produce meaningful explanations of correlated features. Gridded geospatial data tends to have extensive autocorrelation so it is difficult to obtain meaningful explanations of geoscience models. A recommendation is to group correlated features and explain those groups. This is becoming common when using XAI to explain tabular data. Here, we demonstrate that XAI algorithms are highly sensitive to the choice of how we group raster elements. We demonstrate that reliance on a single partition scheme yields misleading explanations. We propose comparing explanations from multiple grouping schemes to extract more accurate insights from XAI. We argue that each grouping scheme probes the model in a different way so that each asks a different question of the model. By analyzing where the explanations agree and disagree, we can learn information about the scale of the learned features. FogNet, a complex three-dimensional convolutional neural network for coastal fog prediction, is used as a case study for investigating the influence of feature grouping schemes on XAI. Our results demonstrate that careful consideration of how each grouping scheme probes the model is key to extracting insights and avoiding misleading interpretations.

show abstract

Section: Discussionsupporting

confidence: 89%

Section: Discussionmentioning

confidence: 99%

Section: Discussionmentioning

confidence: 99%

Section: Meteorological Interpretationmentioning

confidence: 99%

See 2 more Smart Citations

Aggregation strategies to improve XAI for geoscience models that use correlated, high-dimensional rasters

Krell,

Kamangir,

Collins

et al. 2023

Environ. Data Science

View full text Add to dashboard Cite

show abstract

“…ML models can help to bypass the long computation time and the current knowledge gap. ML models are very suitable for nowcasting fog (Lakra & Avishek, 2022) since they can generate a rapid forecast within seconds (Palvanov & Cho, 2019). The increasingly popular ML models offer a heuristic approach, partially circumventing the knowledge gap and the parameterization of process interactions.…”

Section: Introductionmentioning

confidence: 99%

Improving classification‐based nowcasting of radiation fog with machine learning based on filtered and preprocessed temporal data

Schütz,

Bendix

et al. 2023

Quart J Royal Meteoro Soc

View full text Add to dashboard Cite

Radiation fog nowcasting remains a complex yet critical task due to its substantial impact on traffic safety and economic activity. Current numerical weather prediction models are hindered by computational intensity and knowledge gaps regarding fog‐influencing processes. Machine‐Learning (ML) models, particularly those employing the eXtreme Gradient Boosting (XGB) algorithm, may offer a robust alternative, given their ability to learn directly from data, swiftly generate nowcasts, and manage non‐linear interrelationships among fog variables. However, unlike recurrent neural networks XGB does not inherently process temporal data, which is crucial in fog formation and dissipation. This study proposes incorporating preprocessed temporal data into the model training and applying a weighted moving‐average filter to regulate the substantial fluctuations typical in fog development. Using an ML training and evaluation scheme for time series data, we conducted an extensive bootstrapped comparison of the influence of different smoothing intensities and trend information timespans on the model performance on three levels: overall performance, fog formation and fog dissipation. The performance is checked against one benchmark and two baseline models. A significant performance improvement was noted for the station in Linden‐Leihgestern (Germany), where the initial F1 score of 0.75 (prior to smoothing and trend information incorporation) was improved to 0.82 after applying the smoothing technique and further increased to 0.88 when trend information was incorporated. The forecasting periods ranged from 60 to 240 min into the future. This study offers novel insights into the interplay of data smoothing, temporal preprocessing, and ML in advancing radiation fog nowcasting.

show abstract

Toward Understanding the Impacts of Air Pollution

Ogwu,

Imarhiagbe,

Ikhajiagbe

et al. 2024

The Handbook of Environmental Chemistry

View full text Add to dashboard Cite

A review on factors influencing fog formation, classification, forecasting, detection and impacts

Cited by 25 publications

References 277 publications

Aggregation strategies to improve XAI for geoscience models that use correlated, high-dimensional rasters

Aggregation strategies to improve XAI for geoscience models that use correlated, high-dimensional rasters

Improving classification‐based nowcasting of radiation fog with machine learning based on filtered and preprocessed temporal data

Toward Understanding the Impacts of Air Pollution

Contact Info

Product

Resources

About