Interpolating turbulent heat fluxes missing from a prairie observation on the Tibetan Plateau using artificial intelligence models

<p>This paper evaluates the performances of mean diurnal variation (MDV), nonlinear regression (NR), lookup tables (LUTs), support vector regression (SVR), <span class="inline-formula"><i>k</i></span>-nearest neighbors (KNNs), gradient boosting (XGBoost), long...

Full description

Saved in:
Bibliographic Details
Main Authors: Q. Hou, Z. Gao, Z. Duan, M. Yu
Format: Article
Language:English
Published: Copernicus Publications 2025-07-01
Series:Geoscientific Model Development
Online Access:https://gmd.copernicus.org/articles/18/4625/2025/gmd-18-4625-2025.pdf
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849410902717104128
author Q. Hou
Z. Gao
Z. Gao
Z. Duan
M. Yu
author_facet Q. Hou
Z. Gao
Z. Gao
Z. Duan
M. Yu
author_sort Q. Hou
collection DOAJ
description <p>This paper evaluates the performances of mean diurnal variation (MDV), nonlinear regression (NR), lookup tables (LUTs), support vector regression (SVR), <span class="inline-formula"><i>k</i></span>-nearest neighbors (KNNs), gradient boosting (XGBoost), long short-term memory (LSTM), gated recurrent units (GRUs), and the Transformer model with a deep self-attention mechanism to interpolate the turbulent heat fluxes missing from a prairie observation on the Tibetan Plateau. Results indicated that the Transformer model outperformed the other methods that were tested. To further enhance the interpolation accuracy, a combined model of Transformer and a convolutional neural network (CNN), termed Transformer_CNN, was proposed. Herein, while Transformer focused primarily on global attention, the convolution operations in the CNN provided the model with local attention. Experimental outcomes revealed that the interpolations from Transformer_CNN surpassed the traditional single artificial intelligence model approaches. The coefficient of determination (<span class="inline-formula"><i>R</i><sup>2</sup></span>) reached 0.95 in the sensible heat flux test set and 0.90 in the latent heat flux test set, thereby confirming the applicability of the Transformer_CNN model for data interpolation of turbulent heat flux on the Tibetan Plateau. Ultimately, the turbulent heat flux observational database from 2007 to 2016 at the station was imputed using the Transformer_CNN model.</p>
format Article
id doaj-art-060a2a53e42845fe9066e8a75aab1ac2
institution Kabale University
issn 1991-959X
1991-9603
language English
publishDate 2025-07-01
publisher Copernicus Publications
record_format Article
series Geoscientific Model Development
spelling doaj-art-060a2a53e42845fe9066e8a75aab1ac22025-08-20T03:34:57ZengCopernicus PublicationsGeoscientific Model Development1991-959X1991-96032025-07-01184625464110.5194/gmd-18-4625-2025Interpolating turbulent heat fluxes missing from a prairie observation on the Tibetan Plateau using artificial intelligence modelsQ. Hou0Z. Gao1Z. Gao2Z. Duan3M. Yu4School of Atmospheric Physics, Nanjing University of Information Science and Technology, Nanjing 210044, ChinaSchool of Atmospheric Physics, Nanjing University of Information Science and Technology, Nanjing 210044, ChinaState Key Laboratory of Atmospheric Boundary Layer Physics and Atmospheric Chemistry, Institute of Atmospheric Physics, Chinese Academy of Sciences, Beijing 100029, ChinaSchool of Electrical Engineering, Nantong University, Nantong 226019, ChinaSchool of Atmospheric Physics, Nanjing University of Information Science and Technology, Nanjing 210044, China<p>This paper evaluates the performances of mean diurnal variation (MDV), nonlinear regression (NR), lookup tables (LUTs), support vector regression (SVR), <span class="inline-formula"><i>k</i></span>-nearest neighbors (KNNs), gradient boosting (XGBoost), long short-term memory (LSTM), gated recurrent units (GRUs), and the Transformer model with a deep self-attention mechanism to interpolate the turbulent heat fluxes missing from a prairie observation on the Tibetan Plateau. Results indicated that the Transformer model outperformed the other methods that were tested. To further enhance the interpolation accuracy, a combined model of Transformer and a convolutional neural network (CNN), termed Transformer_CNN, was proposed. Herein, while Transformer focused primarily on global attention, the convolution operations in the CNN provided the model with local attention. Experimental outcomes revealed that the interpolations from Transformer_CNN surpassed the traditional single artificial intelligence model approaches. The coefficient of determination (<span class="inline-formula"><i>R</i><sup>2</sup></span>) reached 0.95 in the sensible heat flux test set and 0.90 in the latent heat flux test set, thereby confirming the applicability of the Transformer_CNN model for data interpolation of turbulent heat flux on the Tibetan Plateau. Ultimately, the turbulent heat flux observational database from 2007 to 2016 at the station was imputed using the Transformer_CNN model.</p>https://gmd.copernicus.org/articles/18/4625/2025/gmd-18-4625-2025.pdf
spellingShingle Q. Hou
Z. Gao
Z. Gao
Z. Duan
M. Yu
Interpolating turbulent heat fluxes missing from a prairie observation on the Tibetan Plateau using artificial intelligence models
Geoscientific Model Development
title Interpolating turbulent heat fluxes missing from a prairie observation on the Tibetan Plateau using artificial intelligence models
title_full Interpolating turbulent heat fluxes missing from a prairie observation on the Tibetan Plateau using artificial intelligence models
title_fullStr Interpolating turbulent heat fluxes missing from a prairie observation on the Tibetan Plateau using artificial intelligence models
title_full_unstemmed Interpolating turbulent heat fluxes missing from a prairie observation on the Tibetan Plateau using artificial intelligence models
title_short Interpolating turbulent heat fluxes missing from a prairie observation on the Tibetan Plateau using artificial intelligence models
title_sort interpolating turbulent heat fluxes missing from a prairie observation on the tibetan plateau using artificial intelligence models
url https://gmd.copernicus.org/articles/18/4625/2025/gmd-18-4625-2025.pdf
work_keys_str_mv AT qhou interpolatingturbulentheatfluxesmissingfromaprairieobservationonthetibetanplateauusingartificialintelligencemodels
AT zgao interpolatingturbulentheatfluxesmissingfromaprairieobservationonthetibetanplateauusingartificialintelligencemodels
AT zgao interpolatingturbulentheatfluxesmissingfromaprairieobservationonthetibetanplateauusingartificialintelligencemodels
AT zduan interpolatingturbulentheatfluxesmissingfromaprairieobservationonthetibetanplateauusingartificialintelligencemodels
AT myu interpolatingturbulentheatfluxesmissingfromaprairieobservationonthetibetanplateauusingartificialintelligencemodels