Spatiotemporal deep learning approach for estimating water content profiles in soil layers
Land subsidence associated with using natural groundwater resources for serving the growing population needs has been receiving extensive research attention in the literature over the past few decades. The water content fluctuation in the of subsurface soil layers significantly impacts the land subs...
Main Authors: | , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
EDP Sciences
2023-01-01
|
Series: | E3S Web of Conferences |
Subjects: | |
Online Access: | https://www.e3s-conferences.org/articles/e3sconf/pdf/2023/19/e3sconf_unsat2023_22003.pdf |
_version_ | 1797835420617146368 |
---|---|
author | Fazel Mojtahedi Farid Ghaffari Mohammad Amin Rahmati Saeed Nazari Ali Sadeghi Hamed Vanapalli Sai K. |
author_facet | Fazel Mojtahedi Farid Ghaffari Mohammad Amin Rahmati Saeed Nazari Ali Sadeghi Hamed Vanapalli Sai K. |
author_sort | Fazel Mojtahedi Farid |
collection | DOAJ |
description | Land subsidence associated with using natural groundwater resources for serving the growing population needs has been receiving extensive research attention in the literature over the past few decades. The water content fluctuation in the of subsurface soil layers significantly impacts the land subsidence. The key objective of this study is to predict changes in water content profiles in soil layers over a long period of time using a deep learning-based approach. A convolution neural network algorithm that is commonly used in Artificial Intelligence (AI) applications is modified in the present study for processing in-situ measurement water content profiles. The approach used in the proposed AI method has a distinct advantage for generating dynamic predictions based on the extracted spatiotemporal characteristics of the data. In addition, three different algorithms are compared with respect to time series prediction, including long-short-term memory (LSTM), multiple-layer perceptron (MLP) networks and autoregressive integrated moving average (ARIMA). |
first_indexed | 2024-04-09T14:52:36Z |
format | Article |
id | doaj.art-eaa6ee8053af44a7bdd853a3a9ca3ec3 |
institution | Directory Open Access Journal |
issn | 2267-1242 |
language | English |
last_indexed | 2024-04-09T14:52:36Z |
publishDate | 2023-01-01 |
publisher | EDP Sciences |
record_format | Article |
series | E3S Web of Conferences |
spelling | doaj.art-eaa6ee8053af44a7bdd853a3a9ca3ec32023-05-02T09:28:10ZengEDP SciencesE3S Web of Conferences2267-12422023-01-013822200310.1051/e3sconf/202338222003e3sconf_unsat2023_22003Spatiotemporal deep learning approach for estimating water content profiles in soil layersFazel Mojtahedi Farid0Ghaffari Mohammad Amin1Rahmati Saeed2Nazari Ali3Sadeghi Hamed4Vanapalli Sai K.5Department of Infrastructure Engineering, University of MelbourneDepartment of Civil Engineering, Sharif University of TechnologyDepartment of Civil Engineering, Sharif University of TechnologyDepartment of Civil Engineering, Sharif University of TechnologyDepartment of Civil Engineering, Sharif University of TechnologyDepartment of Civil Engineering, University of OttawaLand subsidence associated with using natural groundwater resources for serving the growing population needs has been receiving extensive research attention in the literature over the past few decades. The water content fluctuation in the of subsurface soil layers significantly impacts the land subsidence. The key objective of this study is to predict changes in water content profiles in soil layers over a long period of time using a deep learning-based approach. A convolution neural network algorithm that is commonly used in Artificial Intelligence (AI) applications is modified in the present study for processing in-situ measurement water content profiles. The approach used in the proposed AI method has a distinct advantage for generating dynamic predictions based on the extracted spatiotemporal characteristics of the data. In addition, three different algorithms are compared with respect to time series prediction, including long-short-term memory (LSTM), multiple-layer perceptron (MLP) networks and autoregressive integrated moving average (ARIMA).https://www.e3s-conferences.org/articles/e3sconf/pdf/2023/19/e3sconf_unsat2023_22003.pdfland subsidencespatiotemporal analysisdeep learning predictionwater content profiles |
spellingShingle | Fazel Mojtahedi Farid Ghaffari Mohammad Amin Rahmati Saeed Nazari Ali Sadeghi Hamed Vanapalli Sai K. Spatiotemporal deep learning approach for estimating water content profiles in soil layers E3S Web of Conferences land subsidence spatiotemporal analysis deep learning prediction water content profiles |
title | Spatiotemporal deep learning approach for estimating water content profiles in soil layers |
title_full | Spatiotemporal deep learning approach for estimating water content profiles in soil layers |
title_fullStr | Spatiotemporal deep learning approach for estimating water content profiles in soil layers |
title_full_unstemmed | Spatiotemporal deep learning approach for estimating water content profiles in soil layers |
title_short | Spatiotemporal deep learning approach for estimating water content profiles in soil layers |
title_sort | spatiotemporal deep learning approach for estimating water content profiles in soil layers |
topic | land subsidence spatiotemporal analysis deep learning prediction water content profiles |
url | https://www.e3s-conferences.org/articles/e3sconf/pdf/2023/19/e3sconf_unsat2023_22003.pdf |
work_keys_str_mv | AT fazelmojtahedifarid spatiotemporaldeeplearningapproachforestimatingwatercontentprofilesinsoillayers AT ghaffarimohammadamin spatiotemporaldeeplearningapproachforestimatingwatercontentprofilesinsoillayers AT rahmatisaeed spatiotemporaldeeplearningapproachforestimatingwatercontentprofilesinsoillayers AT nazariali spatiotemporaldeeplearningapproachforestimatingwatercontentprofilesinsoillayers AT sadeghihamed spatiotemporaldeeplearningapproachforestimatingwatercontentprofilesinsoillayers AT vanapallisaik spatiotemporaldeeplearningapproachforestimatingwatercontentprofilesinsoillayers |