Gravity Predictions in Data-Missing Areas Using Machine Learning Methods

Gravity data, comprising a key foundational dataset, are crucial for various research, including land subsidence monitoring, geological exploration, and navigational positioning. However, the collection of gravity data in specific regions is difficult because of environmental, technical, and economi...

Full description

Saved in:
Bibliographic Details
Main Authors: Yubin Liu, Yi Zhang, Qipei Pang, Sulan Liu, Shaobo Li, Xuguo Shi, Shaofeng Bian, Yunlong Wu
Format: Article
Language:English
Published: MDPI AG 2024-11-01
Series:Remote Sensing
Subjects:
Online Access:https://www.mdpi.com/2072-4292/16/22/4173
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1846152573325672448
author Yubin Liu
Yi Zhang
Qipei Pang
Sulan Liu
Shaobo Li
Xuguo Shi
Shaofeng Bian
Yunlong Wu
author_facet Yubin Liu
Yi Zhang
Qipei Pang
Sulan Liu
Shaobo Li
Xuguo Shi
Shaofeng Bian
Yunlong Wu
author_sort Yubin Liu
collection DOAJ
description Gravity data, comprising a key foundational dataset, are crucial for various research, including land subsidence monitoring, geological exploration, and navigational positioning. However, the collection of gravity data in specific regions is difficult because of environmental, technical, and economic constraints, resulting in a non-uniform distribution of the observational data. Traditionally, interpolation methods such as Kriging have been widely used to deal with data gaps; however, their predictive accuracy in regions with sparse data still needs improvement. In recent years, the rapid development of artificial intelligence has opened up a new opportunity for data prediction. In this study, utilizing the EGM2008 satellite gravity model, we conducted a comprehensive analysis of three machine learning algorithms—random forest, support vector machine, and recurrent neural network—and compared their performances against the traditional Kriging interpolation method. The results indicate that machine learning methods exhibit a marked advantage in gravity data prediction, significantly enhancing the predictive accuracy.
format Article
id doaj-art-6b6fb15635ab4551b64c0ef2e5b1d0a8
institution Kabale University
issn 2072-4292
language English
publishDate 2024-11-01
publisher MDPI AG
record_format Article
series Remote Sensing
spelling doaj-art-6b6fb15635ab4551b64c0ef2e5b1d0a82024-11-26T18:19:50ZengMDPI AGRemote Sensing2072-42922024-11-011622417310.3390/rs16224173Gravity Predictions in Data-Missing Areas Using Machine Learning MethodsYubin Liu0Yi Zhang1Qipei Pang2Sulan Liu3Shaobo Li4Xuguo Shi5Shaofeng Bian6Yunlong Wu7Key Laboratory of Geological Survey and Evaluation of Ministry of Education, China University of Geosciences, Wuhan 430074, ChinaKey Laboratory of Geological Survey and Evaluation of Ministry of Education, China University of Geosciences, Wuhan 430074, ChinaSchool of Geography and Information Engineering, China University of Geosciences, Wuhan 430074, ChinaSchool of Geography and Information Engineering, China University of Geosciences, Wuhan 430074, ChinaSchool of Geography and Information Engineering, China University of Geosciences, Wuhan 430074, ChinaSchool of Geography and Information Engineering, China University of Geosciences, Wuhan 430074, ChinaKey Laboratory of Geological Survey and Evaluation of Ministry of Education, China University of Geosciences, Wuhan 430074, ChinaSchool of Geography and Information Engineering, China University of Geosciences, Wuhan 430074, ChinaGravity data, comprising a key foundational dataset, are crucial for various research, including land subsidence monitoring, geological exploration, and navigational positioning. However, the collection of gravity data in specific regions is difficult because of environmental, technical, and economic constraints, resulting in a non-uniform distribution of the observational data. Traditionally, interpolation methods such as Kriging have been widely used to deal with data gaps; however, their predictive accuracy in regions with sparse data still needs improvement. In recent years, the rapid development of artificial intelligence has opened up a new opportunity for data prediction. In this study, utilizing the EGM2008 satellite gravity model, we conducted a comprehensive analysis of three machine learning algorithms—random forest, support vector machine, and recurrent neural network—and compared their performances against the traditional Kriging interpolation method. The results indicate that machine learning methods exhibit a marked advantage in gravity data prediction, significantly enhancing the predictive accuracy.https://www.mdpi.com/2072-4292/16/22/4173gravity data predictionmachine learningrandom forestrecurrent neural networksupport vector machine
spellingShingle Yubin Liu
Yi Zhang
Qipei Pang
Sulan Liu
Shaobo Li
Xuguo Shi
Shaofeng Bian
Yunlong Wu
Gravity Predictions in Data-Missing Areas Using Machine Learning Methods
Remote Sensing
gravity data prediction
machine learning
random forest
recurrent neural network
support vector machine
title Gravity Predictions in Data-Missing Areas Using Machine Learning Methods
title_full Gravity Predictions in Data-Missing Areas Using Machine Learning Methods
title_fullStr Gravity Predictions in Data-Missing Areas Using Machine Learning Methods
title_full_unstemmed Gravity Predictions in Data-Missing Areas Using Machine Learning Methods
title_short Gravity Predictions in Data-Missing Areas Using Machine Learning Methods
title_sort gravity predictions in data missing areas using machine learning methods
topic gravity data prediction
machine learning
random forest
recurrent neural network
support vector machine
url https://www.mdpi.com/2072-4292/16/22/4173
work_keys_str_mv AT yubinliu gravitypredictionsindatamissingareasusingmachinelearningmethods
AT yizhang gravitypredictionsindatamissingareasusingmachinelearningmethods
AT qipeipang gravitypredictionsindatamissingareasusingmachinelearningmethods
AT sulanliu gravitypredictionsindatamissingareasusingmachinelearningmethods
AT shaoboli gravitypredictionsindatamissingareasusingmachinelearningmethods
AT xuguoshi gravitypredictionsindatamissingareasusingmachinelearningmethods
AT shaofengbian gravitypredictionsindatamissingareasusingmachinelearningmethods
AT yunlongwu gravitypredictionsindatamissingareasusingmachinelearningmethods