A Hybrid Approach for Fog Retrieval Based on a Combination of Satellite and Ground Truth Data

Abstract

Fog has a substantial influence on various ecosystems and it impacts economy, traffic systems and human life in many ways. In order to be able to deal with the large number of influence factors, a spatially explicit high-resoluted data set of fog frequency distribution is needed. In this study, a hybrid approach for fog retrieval based on Meteosat Second Generation (MSG) data and ground truth data is presented. The method is based on a random forest (RF) machine learning model that is trained with cloud base altitude (CBA) observations from Meteorological Aviation Routine Weather Reports (METAR) as well as synoptic weather observations (SYNOP). Fog is assumed where the model predicts CBA values below a dynamically derived threshold above the terrain elevation. Cross validation results show good accordance with observation data with a mean absolute error of 298 m in CBA values and an average Heidke Skill Score of 0.58 for fog occurrence. Using this technique, a 10 year fog baseline climatology with a temporal resolution of 15 min was derived for Europe for the period from 2006 to 2015. Spatial and temporal variations in fog frequency are analyzed. Highest average fog occurrences are observed in mountainous regions with maxima in spring and summer. Plains and lowlands show less overall fog occurrence but strong positive anomalies in autumn and winter.

First fully diurnal fog and low cloud satellite detection reveals life cycle in the Namib

“…As previous studies (e.g., Cermak and Knutti, 2009;Lee et al, 2011;Egli et al, 2016;Nilo et al, 2018) have shown, geostationary satellites have the potential to draw a spatiotemporally coherent picture of the occurrence of fog and low clouds (FLCs). However, information on FLCs from satellites is typically inferred using separate daytime (e.g., Bendix et al, 2006;Cermak andBendix, 2008, 2011;Nilo et al, 2018) and night-time (e.g., Ellrod, 1995;Cermak and Bendix, 2007) algorithms, disrupting our view of fog development at a critical time of its life cycle, as typically, shortwave radiative heating starts the dissipation of fog shortly after sunrise (Tardif and Rasmussen, 2007;Haeffelin et al, 2010;Waersted et al, 2017). This break in retrieval techniques has thus limited the applicability of satellite-based FLC observations for the analysis of entire fog life cycles.…”

Mapping and Understanding Patterns of Air Quality Using Satellite Data and Machine Learning

“…It employs the station altitude and subtracts the mean altitude of surrounding pixels in its vicinity. Positive values indicate a summit position, whereas negative values indicate a valley position (Egli et al, 2018). Again, a window size of 20 km was chosen.…”

Fast Cloud Segmentation Using Convolutional Neural Networks

“…Machine learning methods such as random forests [23] are increasingly being applied to remote sensing tasks including cloud classification. Similar to the threshold based approaches, methods such as support vector machines (SVM) [24] and random forests (RF) [8] focus on classification of individual pixels. They are available as ready-to-use methods [25] and are also used to derive cloud-related products such as rainfall retrievals [26].…”

“…Methods relying only on spatial properties are developed [29] or adapted from other domains [30]. Spatial information in the form of handcrafted texture features are also used for machine learning approaches such as RF [8]. However, identifying and handcrafting relevant spatial features is a cumbersome and time-consuming task.…”

“…However, spatial structures and dynamics contain important information, e.g., the surface structure of clouds is particularly meaningful. Therefore, spatial statistics about the closer environment (3 × 3 pixel) of each pixel are often used, e.g., rodograms and/or 2D-variograms [8]. Nevertheless, these statistics represent only a small part of the available spatial information, and they do not take into account the spatial relationships and dynamics in larger areas and scales.…”