Development and Evaluation of Machine Learning Models for Air-to-Land Temperature Conversion Using the Newly Established Kunlun Mountain Gradient Observation System

Mountainous land types are characterized by a scarcity of observational data, particularly in remote areas such as the Kunlun Mountains, where conventional Automatic Weather Stations (AWSs) typically do not record land surface temperature (LST) data. This study aims to develop and evaluate models fo...

Full description

Saved in:
Bibliographic Details
Main Authors: Yongkang Li, Qing He, Yongqiang Liu, Amina Maituerdi, Yang Yan, Jiao Tan
Format: Article
Language:English
Published: MDPI AG 2024-11-01
Series:Land
Subjects:
Online Access:https://www.mdpi.com/2073-445X/13/11/1903
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850266866649399296
author Yongkang Li
Qing He
Yongqiang Liu
Amina Maituerdi
Yang Yan
Jiao Tan
author_facet Yongkang Li
Qing He
Yongqiang Liu
Amina Maituerdi
Yang Yan
Jiao Tan
author_sort Yongkang Li
collection DOAJ
description Mountainous land types are characterized by a scarcity of observational data, particularly in remote areas such as the Kunlun Mountains, where conventional Automatic Weather Stations (AWSs) typically do not record land surface temperature (LST) data. This study aims to develop and evaluate models for converting air temperature (TA) to LST using newly established meteorological station data from the Kunlun Mountain Gradient Observation System, thereby providing time-continuous LST data for AWSs. We constructed a conceptual model to explore the relationship between 1.5 m TA and LST and instantiated it using three machine learning algorithms: Support Vector Machine (SVR), Convolutional Neural Network (CNN), and CatBoost. The results demonstrated that the CatBoost algorithm outperformed the others under complex terrain and climatic conditions, achieving a coefficient of determination (R<sup>2</sup>) of 0.997 and the lowest root mean square error (RMSE) of 0.627 °C, indicating superior robustness and accuracy. Consequently, CatBoost was selected as the optimal model. Additionally, this study analyzed the spatiotemporal distribution characteristics of cloud cover in the Kunlun Mountain region using the MOD11A1 product and assessed the uncertainties introduced by the 8-day average compositing method of the MOD11A2 product. The results revealed significant discrepancies between the monthly average LST derived from polar-orbiting satellites and the hourly composite monthly LST measured on-site or under ideal cloud-free conditions. These differences were particularly pronounced in high-altitude regions (4000 m and above), with the greatest differences occurring in winter, reaching up to 10.2 °C. These findings emphasize the importance of hourly LST calculations based on AWSs for accurately assessing the spatiotemporal characteristics of LST in the Kunlun Mountains, thus providing more precise spatiotemporal support for remote sensing applications in high-altitude regions.
format Article
id doaj-art-e166ec201c79451f91c85a6ae337a429
institution OA Journals
issn 2073-445X
language English
publishDate 2024-11-01
publisher MDPI AG
record_format Article
series Land
spelling doaj-art-e166ec201c79451f91c85a6ae337a4292025-08-20T01:54:02ZengMDPI AGLand2073-445X2024-11-011311190310.3390/land13111903Development and Evaluation of Machine Learning Models for Air-to-Land Temperature Conversion Using the Newly Established Kunlun Mountain Gradient Observation SystemYongkang Li0Qing He1Yongqiang Liu2Amina Maituerdi3Yang Yan4Jiao Tan5College of Geography and Remote Sensing Sciences, Xinjiang University, Urumqi 830052, ChinaInstitute of Desert Meteorology, China Meteorological Administration, Urumqi 830002, ChinaCollege of Geography and Remote Sensing Sciences, Xinjiang University, Urumqi 830052, ChinaXinjiang Uygur Autonomous Region Meteorological Service, Urumqi 830002, ChinaCollege of Geography and Remote Sensing Sciences, Xinjiang University, Urumqi 830052, ChinaCollege of Geography and Remote Sensing Sciences, Xinjiang University, Urumqi 830052, ChinaMountainous land types are characterized by a scarcity of observational data, particularly in remote areas such as the Kunlun Mountains, where conventional Automatic Weather Stations (AWSs) typically do not record land surface temperature (LST) data. This study aims to develop and evaluate models for converting air temperature (TA) to LST using newly established meteorological station data from the Kunlun Mountain Gradient Observation System, thereby providing time-continuous LST data for AWSs. We constructed a conceptual model to explore the relationship between 1.5 m TA and LST and instantiated it using three machine learning algorithms: Support Vector Machine (SVR), Convolutional Neural Network (CNN), and CatBoost. The results demonstrated that the CatBoost algorithm outperformed the others under complex terrain and climatic conditions, achieving a coefficient of determination (R<sup>2</sup>) of 0.997 and the lowest root mean square error (RMSE) of 0.627 °C, indicating superior robustness and accuracy. Consequently, CatBoost was selected as the optimal model. Additionally, this study analyzed the spatiotemporal distribution characteristics of cloud cover in the Kunlun Mountain region using the MOD11A1 product and assessed the uncertainties introduced by the 8-day average compositing method of the MOD11A2 product. The results revealed significant discrepancies between the monthly average LST derived from polar-orbiting satellites and the hourly composite monthly LST measured on-site or under ideal cloud-free conditions. These differences were particularly pronounced in high-altitude regions (4000 m and above), with the greatest differences occurring in winter, reaching up to 10.2 °C. These findings emphasize the importance of hourly LST calculations based on AWSs for accurately assessing the spatiotemporal characteristics of LST in the Kunlun Mountains, thus providing more precise spatiotemporal support for remote sensing applications in high-altitude regions.https://www.mdpi.com/2073-445X/13/11/1903air-to-land temperature conversionmachine learningcloud cover impactKunlun Mountain gradient observation systemmountain land
spellingShingle Yongkang Li
Qing He
Yongqiang Liu
Amina Maituerdi
Yang Yan
Jiao Tan
Development and Evaluation of Machine Learning Models for Air-to-Land Temperature Conversion Using the Newly Established Kunlun Mountain Gradient Observation System
Land
air-to-land temperature conversion
machine learning
cloud cover impact
Kunlun Mountain gradient observation system
mountain land
title Development and Evaluation of Machine Learning Models for Air-to-Land Temperature Conversion Using the Newly Established Kunlun Mountain Gradient Observation System
title_full Development and Evaluation of Machine Learning Models for Air-to-Land Temperature Conversion Using the Newly Established Kunlun Mountain Gradient Observation System
title_fullStr Development and Evaluation of Machine Learning Models for Air-to-Land Temperature Conversion Using the Newly Established Kunlun Mountain Gradient Observation System
title_full_unstemmed Development and Evaluation of Machine Learning Models for Air-to-Land Temperature Conversion Using the Newly Established Kunlun Mountain Gradient Observation System
title_short Development and Evaluation of Machine Learning Models for Air-to-Land Temperature Conversion Using the Newly Established Kunlun Mountain Gradient Observation System
title_sort development and evaluation of machine learning models for air to land temperature conversion using the newly established kunlun mountain gradient observation system
topic air-to-land temperature conversion
machine learning
cloud cover impact
Kunlun Mountain gradient observation system
mountain land
url https://www.mdpi.com/2073-445X/13/11/1903
work_keys_str_mv AT yongkangli developmentandevaluationofmachinelearningmodelsforairtolandtemperatureconversionusingthenewlyestablishedkunlunmountaingradientobservationsystem
AT qinghe developmentandevaluationofmachinelearningmodelsforairtolandtemperatureconversionusingthenewlyestablishedkunlunmountaingradientobservationsystem
AT yongqiangliu developmentandevaluationofmachinelearningmodelsforairtolandtemperatureconversionusingthenewlyestablishedkunlunmountaingradientobservationsystem
AT aminamaituerdi developmentandevaluationofmachinelearningmodelsforairtolandtemperatureconversionusingthenewlyestablishedkunlunmountaingradientobservationsystem
AT yangyan developmentandevaluationofmachinelearningmodelsforairtolandtemperatureconversionusingthenewlyestablishedkunlunmountaingradientobservationsystem
AT jiaotan developmentandevaluationofmachinelearningmodelsforairtolandtemperatureconversionusingthenewlyestablishedkunlunmountaingradientobservationsystem