GBRT-Based Estimation of Terrestrial Latent Heat Flux in the Haihe River Basin from Satellite and Reanalysis Datasets

Wang, Lu; Zhang, Yuhu; Yao, Yunjun; Xiao, Zhiqiang; Shang, Ke; Guo, Xihong; Yang, Junming; Xue, Shuhui; Wang, Jie

doi:10.3390/rs13061054

“…Its basic idea is to build a new tree that corrects the error of the previous tree by combining multiple decision trees and using the residual and gradient information between the trees. The regression model of GBDT has been widely applied in various domains (Asadollah et al., 2022; Ding et al., 2016; Hrisko et al., 2021; Wang et al., 2021). In this study, a GBDT‐based regression model is used for data training and transformation.…”

Section: Calibration Model Based On Machine Learningmentioning

confidence: 99%

Measurement and Calibration of EMF: A Study Using Phone and GBDT for Mobile Communication Signals

Zeng,

Chen,

Ji

et al. 2024

Radio Science

1

0

View full text Add to dashboard Cite

Electromagnetic exposure caused by mobile communication signals has always been a cause of concern. Due to the cost and inconvenience of professional measurement equipment, researchers have turned to smartphone APPs to study and assess the electric field strength caused by mobile communication signals. However, existing cell phone‐based measurements have two weaknesses. First, no system architecture suitable for large‐scale crowdsourced testing has been proposed. Second, since smartphone sensors cannot measure electric field strength directly, existing methods for converting the received signal power of the phone and electric field strength have errors of more than 5 dB. This paper proposes a measurement and calibration method for electric field strength of mobile communication signals based on a smartphone app and gradient boosting decision tree (GBDT). This method consists of a downlink signal acquisition system based on an APP and a calibration model based on GBDT to convert received signal power into electric field strength. The experimental results show that the proposed model achieves a R2 score of 0.93 and a MAE of 0.97 dB. Compared with the existing methods, our method improves the calibration accuracy by 4 dB, enabling large‐scale, low‐cost, and high‐precision direct measurement of the electric field strength of mobile communication signals.

show abstract

“…Machine learning has already been tested for the estimation of surface turbulent Ćuxes outside the polar regions with a successful outcome (e.g. Pelliccioni et al, 1999;Qin et al, 2005a,b;Wang et al, 2017;Safa et al, 2018;Xu et al, 2018;Leufen and Schädler, 2019;Wang et al, 2021). In recent studies, machine-learning parametrizations have been developed which can accurately estimate turbulent Ćuxes observed at measurement towers (McCandless et al, 2022;Wulfmeyer et al, 2022), and the properties of such parametrizations investigated in large-eddy simulations (Muĳoz-Esparza et al, 2022).…”

Section: Introductionmentioning

confidence: 99%

Reducing parametrization errors for polar surface turbulent fluxes using machine learning

Cummins

¹

,

Guémas

²

,

Blein

³

et al. 2023

Preprint

View full text Add to dashboard Cite

Turbulent exchanges between sea ice and atmosphere are known to influence the melting rate of sea ice, the development of atmospheric circulation anomalies and, potentially, teleconnections between the Arctic and non-polar regions. Large model errors remain in the parametrization of turbulent heat fluxes over sea ice in climate models, resulting in significant uncertainties in projections of future climate. Fluxes are typically calculated using bulk formulae, based on Monin-Obukhov similarity theory, which have shown particular limitations in polar regions. Parametrizations developed specifically for polar conditions (e.g. representing form drag from ridges or melt ponds in sea ice) rely on sparse observations and thus may not be universally applicable. In this study, new data-driven parametrizations have been developed for surface turbulent fluxes of momentum, sensible heat and latent heat in the Arctic. Machine learning has already been used outside the polar regions to provide accurate and computationally inexpensive estimates of surface turbulent fluxes. To investigate the feasibility of this approach in the Arctic, we have fitted neural network models to a reference dataset (SHEBA). Predictive performance has been tested using data from other observational campaigns. For momentum and sensible heat, performance of the neural networks is found to be comparable to, and in some cases substantially better than, that of state-of-the-art bulk formulations. These results offer an efficient alternative to the traditional bulk approach in cases where the latter fails, and can serve to inform further physically based developments.

show abstract

“…However, they did not apply tower data and did not perform comparisons with MOST or BRN. Momentum and sensible heat fluxes were not studied either; the same limitations apply to the latent heat flux predictions by Wang et al (2017); Xu et al (2018); Wang et al (2021). Safa et al (2018) investigated sensible and latent heat fluxes with a multilayer perceptron (MLP) as the ML method including sensitivity analyses based on multiyear data sets of fluxes and L-A variables over maize.…”

Section: Introductionmentioning

confidence: 99%

Estimation of the Surface Fluxes for Heat and Momentum in Unstable Conditions with Machine Learning and Similarity Approaches for the LAFE Data Set

Wulfmeyer

¹

,

Pineda

²

,

Otte

³

et al. 2022

Boundary-Layer Meteorol

View full text Add to dashboard Cite

Measurements of three flux towers operated during the land atmosphere feedback experiment (LAFE) are used to investigate relationships between surface fluxes and variables of the land–atmosphere system. We study these relations by means of two machine learning (ML) techniques: multilayer perceptrons (MLP) and extreme gradient boosting (XGB). We compare their flux derivation performance with Monin–Obukhov similarity theory (MOST) and a similarity relationship using the bulk Richardson number (BRN). The ML approaches outperform MOST and BRN. Best agreement with the observations is achieved for the friction velocity. For the sensible heat flux and even more so for the latent heat flux, MOST and BRN deviate from the observations while MLP and XGB yield more accurate predictions. Using MOST and BRN for latent heat flux, the root mean square errors (RMSE) are 107 Wm$$^{-2}$$ - 2 and 121 Wm$$^{-2}$$ - 2 , respectively, as well as the intercepts of the regression lines are $$\approx 110$$ ≈ 110 Wm$$^{-2}$$ - 2 . For the ML methods, the RMSEs reduce to 31 Wm$$^{-2}$$ - 2 for MLP and 33 Wm$$^{-2}$$ - 2 for XGB as well as the intercepts to just 4 Wm$$^{-2}$$ - 2 for MLP and $$-1$$ - 1 Wm$$^{-2}$$ - 2 for XGB with slopes of the regression lines close to 1, respectively. These results indicate significant deficiencies of MOST and BRN, particularly for the derivation of the latent heat flux. In fact, in contrast to the established theories, feature importance weighting demonstrates that the ML methods base their improved derivations on net radiation, the incoming and outgoing shortwave radiations, the air temperature gradient, and the available water contents, but not on the water vapor gradient. The results imply that further studies of surface fluxes and other turbulent variables with ML techniques provide great promise for deriving advanced flux parameterizations and their implementation in land–atmosphere system models.

show abstract

GBRT-Based Estimation of Terrestrial Latent Heat Flux in the Haihe River Basin from Satellite and Reanalysis Datasets

Cited by 19 publications

References 68 publications

Measurement and Calibration of EMF: A Study Using Phone and GBDT for Mobile Communication Signals

Measurement and Calibration of EMF: A Study Using Phone and GBDT for Mobile Communication Signals

Reducing parametrization errors for polar surface turbulent fluxes using machine learning

Estimation of the Surface Fluxes for Heat and Momentum in Unstable Conditions with Machine Learning and Similarity Approaches for the LAFE Data Set

Contact Info

Product

Resources

About