Characterisation of the artificial neural network CiPS for cirrus cloud remote sensing with MSG/SEVIRI

Abstract

Abstract. Cirrus clouds remain one of the key uncertainties in atmospheric research. To better understand the properties and physical processes of cirrus clouds, accurate large scale observations from satellites are required. Artificial neural networks (ANNs) have proved to be a useful tool for cirrus cloud remote sensing. Since physics is not implemented explicitly in ANNs, a thorough characterisation of the networks is necessary. In this paper the CiPS (Cirrus Properties from SEVIRI) algorithm is characterised using the space-borne lidar CALIOP. CiPS is composed of a set of ANNs for the cirrus cloud detection, opacity identification and the corresponding cloud top height, ice optical thickness and ice water path retrieval from the imager SEVIRI aboard the geostationary Meteosat Second Generation satellites. First, the retrieval accuracy is characterised with respect to different land surface types. The retrieval works best over water as well as vegetated surfaces, whereas a surface covered by permanent snow & ice or barren reduces the cirrus detection ability and increases the retrieval errors for the ice optical thickness and ice water path if the cirrus cloud is thin. Second, the retrieval accuracy is characterised with respect to the vertical arrangement of liquid, ice clouds and aerosol layers as derived from CALIOP lidar data. The CiPS retrievals show little interference from liquid water clouds and aerosol layers below an observed cirrus cloud. Only for thin cirrus clouds with an optical thickness below 0.3 or ice water path below 5.0 gm−2, a liquid water cloud vertically close or adjacent to the cirrus clearly increases the average retrieval errors for the ice optical thickness and ice water path respectively. For the cloud top height retrieval, only aerosol layers affect the retrieval error, with an increased positive bias when the cirrus is at low altitudes. Third, the CiPS retrieval error is characterised with respect to the properties of the investigated cirrus cloud (ice optical thickness and cloud top height). On average CiPS can retrieve the cirrus cloud top height with a relative error around 8 % and no bias and the ice optical thickness with a relative error around 50 % and bias around 10% for the most common combinations of cloud top height and ice optical thickness. Similarities with physically based retrieval methods are evident, which implies that even though the retrieval methods differ in the physical implementation, the retrievals behave similarly due to physical constraints. Finally, we also show that the ANN retrievals have a low sensitivity to radiometric noise in the SEVIRI observations. For optical thickness and ice water path the relative uncertainty due to noise is less than 10 % down to sub-visual cirrus. For the cloud top height retrieval the uncertainty due to noise is around 100 m for all cloud top heights.

Aviation Contrail Cirrus and Radiative Forcing Over Europe During 6 Months of COVID‐19

“…The model may overestimate OT by overestimating solar extinction, which is modeled as a function of the IFS temperature and ice water content using an empirical parameterization with about 30% uncertainty (Heymsfield et al., 2014). The CiPS cirrus OT was calibrated with space lidar observations and saturates at OT values of 3–5 (Strandgren et al., 2017b). Therefore, these deviations are within the expected range.…”

“…MSG‐SEVIRI is a 12‐channel radiometer scanning the Earth disk with 4.2‐km mean spatial surface resolution in the investigation domain. The occurrence and OT of ice clouds including contrails is derived using the Cirrus Properties from SEVIRI (CiPS) algorithm (Strandgren et al., 2017a, 2017b). The method uses a set of four neural networks trained with cloud products from the CALIOP lidar aboard CALIPSO (Winker et al., 2009).…”

Cirrus cloud retrieval with MSG/SEVIRI using artificial neural networks

“…As a next step, the CiPS retrievals will be further characterised, for example with respect to the underlying surface type and the presence of aerosol layers and liquid water clouds below the cirrus (see Strandgren et al, 2017). Constant developments and improvements of the CALIOP cirrus cloud retrievals also open the door for further improvements of CiPS.…”

“…An in-depth characterisation of CiPS with respect to (1) the relative importance of the different input variables, (2) the effect of the underlying surface type as well as underlying liquid water clouds and aerosol layers on the cirrus cloud retrieval, (3) the retrieval errors as a function of IOT and CTH combined and (4) the sensitivity to radiometric noise in the SEVIRI input data is presented in Strandgren et al (2017).…”

Evaluating cloud liquid detection against Cloudnet using cloud radar Doppler spectra in a pre-trained artificial neural network

“…The MLP structure consists of an input layer, a chosen number of hidden layers, and an output layer. Each of these layers is made up of a certain number of neurons that exchange information in a way that the output of the previous layer is used to process the output for each connected neuron in the subsequent layer according to the corresponding numeric weights assigned to each neuron-neuron connection through an activation function (Strandgren et al, 2017b). By using error back propagation introduced in Rumelhart et al (1986), the numeric weights of the neurons are adjusted in an iterative process until the squared error between the predicted (estimated) output and the known reference output data reaches its minimum.…”