Estimating cloud base height from Himawari-8 based on a random forest algorithm

Tan, Zhonghui; Huo, Juan; Ma, Shuo; Han, Dejun; Wang, Xin; Hu, Shensen; Yan, Wei

doi:10.1080/01431161.2020.1854891

Cited by 20 publications

(14 citation statements)

References 39 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The RF method is well-suited for capturing complex or nonlinear relationships between predictors and predictands. As mentioned earlier, this statistical or ML-based algorithm has been already proven successful in retrieving CTH and CBH (Min et al, 2020;Tan et al, 2020).…”

Section: Random-forest-based Cloud-base Height Estimation Algorithmmentioning

confidence: 95%

Technical note: Applicability of physics-based and machine-learning-based algorithms of geostationary satellite in retrieving the diurnal cycle of cloud base height

Wang,

Min,

et al. 2024

Preprint

View full text Add to dashboard Cite

Abstract. Four distinct retrieval algorithms, comprising two physics-based and two machine-learning (ML) approaches, have been developed to retrieve cloud base height (CBH) and its diurnal cycle from Himawari-8 geostationary satellite observations. Validations have been conducted using the joint CloudSat/CALIOP (Cloud-Aerosol Lidar with Orthogonal Polarization) CBH products in 2017, ensuring independent assessments. Results show that the two ML-based algorithms exhibit markedly superior performance (with a correlation coefficient of R > 0.91 and an absolute bias of approximately 0.8 km) compared to the two physics-based algorithms. However, validations based on CBH data from the ground-based lidar at the Lijiang station in Yunnan province and the cloud radar at the Nanjiao station in Beijing, China, explicitly present contradictory outcomes (R < 0.60). An identifiable issue arises with significant underestimations in the retrieved CBH by both ML-based algorithms, leading to an inability to capture the diurnal cycle characteristics of CBH. The strong consistence observed between CBH derived from ML-based algorithms and the spaceborne active sensor may be attributed to utilizing the same dataset for training and validation, sourced from the CloudSat/CALIOP products. In contrast, the CBH derived from the optimal physics-based algorithm demonstrates the good agreement in diurnal variations of CBH with ground-based lidar/cloud radar observations during the daytime (with an R value of approximately 0.7). Therefore, the findings in this investigation from ground-based observations advocate for the more reliable and adaptable nature of physics-based algorithms in retrieving CBH from geostationary satellite measurements. Nevertheless, under ideal conditions, with an ample dataset of spaceborne cloud profiling radar observations encompassing the entire day for training purposes, the ML-based algorithms may hold promise in still delivering accurate CBH outputs.

show abstract

Section: Random-forest-based Cloud-base Height Estimation Algorithmmentioning

confidence: 95%

Technical note: Applicability of physics-based and machine-learning-based algorithms of geostationary satellite in retrieving the diurnal cycle of cloud base height

Wang,

Min,

et al. 2024

Preprint

View full text Add to dashboard Cite

show abstract

“…In this case, the regression model is built automatically on the available set of synchronous active and passive CBH measurements. This approach was first implemented in [9] on the basis of the multi-layer perceptron, and then developed in [10] by using the XGBoost algorithm and simplified considerably in [11] by applying Kohonen self-organizing neural networks.…”

Section: Introductionmentioning

confidence: 99%

“…In [9][10][11], CBH recovery algorithms provide estimate of the average bias of this parameter 0.2... 0.3 km relative to its reference values with a standard deviation of 0.9-1.7 km. Such results are considered satisfactory according to NOAA NESDIS recommendations taking into account the fact that the determination of the CBH is carried out indirectly.…”

Section: Introductionmentioning

confidence: 99%

Base height estimation for multi-layer clouds from passive remote sensing data

Skorokhodov,

Kuryanovich

2023

29th International Symposium on Atmospheric and Ocean Optics: Atmospheric Physics

View full text Add to dashboard Cite

We present the results of testing the algorithm of cloud-base height (CBH) estimation to determine this parameter for multi-layer clouds from data of passive remote sensing by MODIS spectroradiometer (Aqua satellite). Episodes of observations of two-and three-layer clouds over Western Siberia in summer time for the period from 2010 to 2015 were considered mainly with the following parameters: optical thickness less than 20, distance between the layers more than 1 km, and multi-layer flag value greater than 3. Sampling was based on the results of remote sensing by CALIOP lidar (CALIPSO satellite) and CPR radar (CloudSat satellite). The most repeated combinations of clouds in different levels observed simultaneously as part of multi-layer clouds were determined. The results of CBH estimation for multi-layer clouds and their statistical analysis are discussed. We found that the algorithm generally gives underestimated values of the CBH relative to the overlying level and overestimated values in comparison to the underlying. The perspective ways for development of this work are given.

show abstract

“…Li et al [18] developed a deep-learning-based cloud detection and classification algorithm, achieving cloud detection, cloud phase classification and multi-layer cloud detection from multi-spectral observed radiances and simulated clear-sky radiances using deep neural networks (DNNs). Among these machine learning algorithms, the random forest algorithm is considered appropriate for cloud detection classification due to its advantages of fast training, no overfitting, the lack of a need to reduce dimensionality and its relatively simple parameter settings [19][20][21][22].…”

Section: Introductionmentioning

confidence: 99%

All-Day Cloud Classification via a Random Forest Algorithm Based on Satellite Data from CloudSat and Himawari-8

Wang,

Hu,

Ding

et al. 2023

Atmosphere

View full text Add to dashboard Cite

It remains challenging to accurately classify complicated clouds owing to the various types of clouds and their distribution on multiple layers. In this paper, multi-band radiation information from the geostationary satellite Himawari-8 and the cloud classification product of the polar orbit satellite CloudSat from June to September 2018 are investigated. Based on sample sets matched by two types of satellite data, a random forest (RF) algorithm was applied to train a model, and a retrieval method was developed for cloud classification. With the use of this method, the sample sets were inverted and classified as clear sky, low clouds, middle clouds, thin cirrus, thick cirrus, multi-layer clouds and deep convection (cumulonimbus) clouds. The results indicate that the average accuracy for all cloud types during the day is 88.4%, and misclassifications mainly occur between low and middle clouds, thick cirrus clouds and cumulonimbus clouds. The average accuracy is 79.1% at night, with more misclassifications occurring between middle clouds, multi-layer clouds and cumulonimbus clouds. Moreover, Typhoon Muifa from 2022 was selected as a sample case, and the cloud type (CLT) product of an FY-4A satellite was used to examine the classification method. In the cloud system of Typhoon Muifa, a cumulonimbus area classified using the method corresponded well with a mesoscale convective system (MCS). Compared to the FY-4A CLT product, the classifications of ice-type (thick cirrus) and multi-layer clouds are effective, and the location, shape and size of these two varieties of cloud are similar.

show abstract

Estimating cloud base height from Himawari-8 based on a random forest algorithm

Cited by 20 publications

References 39 publications

Technical note: Applicability of physics-based and machine-learning-based algorithms of geostationary satellite in retrieving the diurnal cycle of cloud base height

Technical note: Applicability of physics-based and machine-learning-based algorithms of geostationary satellite in retrieving the diurnal cycle of cloud base height

Base height estimation for multi-layer clouds from passive remote sensing data

All-Day Cloud Classification via a Random Forest Algorithm Based on Satellite Data from CloudSat and Himawari-8

Contact Info

Product

Resources

About