Spatiotemporal Comparative Analysis of Dry/Wet Phenomenon of the Rainy Period Using Artificial Neural Networks and Markov Chains
The work presented in this paper is a spatiotemporal analysis of the dry/wet phenomenon of the rainy period in northern Algeria to predict the drought. To that end, we implemented artificial neural networks (ANN) to analyze the behavior of processes. For a comparative study, we also analyzed the beh...
Gespeichert in:
Veröffentlicht in: | Journal of the Indian Society of Remote Sensing 2023-07, Vol.51 (7), p.1409-1425 |
---|---|
Hauptverfasser: | , , , , |
Format: | Artikel |
Sprache: | eng |
Schlagworte: | |
Online-Zugang: | Volltext |
Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
container_end_page | 1425 |
---|---|
container_issue | 7 |
container_start_page | 1409 |
container_title | Journal of the Indian Society of Remote Sensing |
container_volume | 51 |
creator | Hamdad, Sadjia Lazri, Mourad Mohia, Yacine Labadi, Karim Ameur, Soltane |
description | The work presented in this paper is a spatiotemporal analysis of the dry/wet phenomenon of the rainy period in northern Algeria to predict the drought. To that end, we implemented artificial neural networks (ANN) to analyze the behavior of processes. For a comparative study, we also analyzed the behavior of the dry/wet phenomenon of the rainy period using Markov chains (MC). The dry/wet phenomenon is divided into 9 categories obtained according to the values of SPI (Standard Precipitation Index). The database is built from satellite estimates of precipitation rates over a period from 1985 to 2021. To assess the performance of the two methods, short-term predictions were determined and compared to actual satellite data. The evaluation parameters used show that the predictions obtained correspond to real data for both the Markov chain method and the neural network method. We then predicted the long-term dry/wet phenomenon, from 2022 to 2050. The long-term prediction results of the dry/wet phenomenon performed by ANN and MC are compared to the simulations given by the coupled multi-model inter-comparison project version 6 (CMIP6) under scenarios, shared socioeconomic pathways SSP126. The overall orientation is identical for the three models (ANN, MC and CMIP6). Indeed, the prediction results performed by the three models indicate that areas representing dry surfaces are gaining ground at the expense of wetlands with a slight difference. |
doi_str_mv | 10.1007/s12524-023-01720-1 |
format | Article |
fullrecord | <record><control><sourceid>proquest_cross</sourceid><recordid>TN_cdi_proquest_journals_2840647058</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2840647058</sourcerecordid><originalsourceid>FETCH-LOGICAL-c270t-bd1d114f13182aae6316247558f23c73ff9a9f208d32f7ee6037187b6ce7c18c3</originalsourceid><addsrcrecordid>eNp9kEtLAzEUhYMoWKt_wFXAdWweM5PpstQn1Adq0V1IZ5I2bWcyJmlldv50047gzsXlXg7nHLgfAOcEXxKM-cATmtIEYcoQJpxiRA5ADw95ghjG2WG8aZqiLMMfx-DE-2UUk5TQHvh-bWQwNqiqsU6u4dhWjXRR2io4quW69cZDq-GVawfvKsDnhaptFafeqWGh4Is0dQuflTO2hFNv6jkcuWC0KUzse1Qbt1_hy7qVh7Iu4YN0K7uF40VM-lNwpOXaq7Pf3QfTm-u38R2aPN3ej0cTVFCOA5qVpCQk0YSRnEqpMkYymvA0zTVlBWdaD-VQU5yXjGquVIYZJzmfZYXiBckL1gcXXW_j7OdG-SCWduPih17QPIk4OE7z6KKdq3DWe6e0aJyppGsFwWJHWnSkRSQt9qQFiSHWhXw013Pl_qr_Sf0Agj2B9Q</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2840647058</pqid></control><display><type>article</type><title>Spatiotemporal Comparative Analysis of Dry/Wet Phenomenon of the Rainy Period Using Artificial Neural Networks and Markov Chains</title><source>SpringerNature Journals</source><creator>Hamdad, Sadjia ; Lazri, Mourad ; Mohia, Yacine ; Labadi, Karim ; Ameur, Soltane</creator><creatorcontrib>Hamdad, Sadjia ; Lazri, Mourad ; Mohia, Yacine ; Labadi, Karim ; Ameur, Soltane</creatorcontrib><description>The work presented in this paper is a spatiotemporal analysis of the dry/wet phenomenon of the rainy period in northern Algeria to predict the drought. To that end, we implemented artificial neural networks (ANN) to analyze the behavior of processes. For a comparative study, we also analyzed the behavior of the dry/wet phenomenon of the rainy period using Markov chains (MC). The dry/wet phenomenon is divided into 9 categories obtained according to the values of SPI (Standard Precipitation Index). The database is built from satellite estimates of precipitation rates over a period from 1985 to 2021. To assess the performance of the two methods, short-term predictions were determined and compared to actual satellite data. The evaluation parameters used show that the predictions obtained correspond to real data for both the Markov chain method and the neural network method. We then predicted the long-term dry/wet phenomenon, from 2022 to 2050. The long-term prediction results of the dry/wet phenomenon performed by ANN and MC are compared to the simulations given by the coupled multi-model inter-comparison project version 6 (CMIP6) under scenarios, shared socioeconomic pathways SSP126. The overall orientation is identical for the three models (ANN, MC and CMIP6). Indeed, the prediction results performed by the three models indicate that areas representing dry surfaces are gaining ground at the expense of wetlands with a slight difference.</description><identifier>ISSN: 0255-660X</identifier><identifier>EISSN: 0974-3006</identifier><identifier>DOI: 10.1007/s12524-023-01720-1</identifier><language>eng</language><publisher>New Delhi: Springer India</publisher><subject>Artificial neural networks ; Comparative studies ; Drought ; Earth and Environmental Science ; Earth Sciences ; Markov analysis ; Markov chains ; Neural networks ; Performance assessment ; Rainfall ; Remote Sensing/Photogrammetry ; Review Article</subject><ispartof>Journal of the Indian Society of Remote Sensing, 2023-07, Vol.51 (7), p.1409-1425</ispartof><rights>Indian Society of Remote Sensing 2023. Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.</rights><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed><cites>FETCH-LOGICAL-c270t-bd1d114f13182aae6316247558f23c73ff9a9f208d32f7ee6037187b6ce7c18c3</cites><orcidid>0000-0003-2145-1823</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktopdf>$$Uhttps://link.springer.com/content/pdf/10.1007/s12524-023-01720-1$$EPDF$$P50$$Gspringer$$H</linktopdf><linktohtml>$$Uhttps://link.springer.com/10.1007/s12524-023-01720-1$$EHTML$$P50$$Gspringer$$H</linktohtml><link.rule.ids>314,780,784,27924,27925,41488,42557,51319</link.rule.ids></links><search><creatorcontrib>Hamdad, Sadjia</creatorcontrib><creatorcontrib>Lazri, Mourad</creatorcontrib><creatorcontrib>Mohia, Yacine</creatorcontrib><creatorcontrib>Labadi, Karim</creatorcontrib><creatorcontrib>Ameur, Soltane</creatorcontrib><title>Spatiotemporal Comparative Analysis of Dry/Wet Phenomenon of the Rainy Period Using Artificial Neural Networks and Markov Chains</title><title>Journal of the Indian Society of Remote Sensing</title><addtitle>J Indian Soc Remote Sens</addtitle><description>The work presented in this paper is a spatiotemporal analysis of the dry/wet phenomenon of the rainy period in northern Algeria to predict the drought. To that end, we implemented artificial neural networks (ANN) to analyze the behavior of processes. For a comparative study, we also analyzed the behavior of the dry/wet phenomenon of the rainy period using Markov chains (MC). The dry/wet phenomenon is divided into 9 categories obtained according to the values of SPI (Standard Precipitation Index). The database is built from satellite estimates of precipitation rates over a period from 1985 to 2021. To assess the performance of the two methods, short-term predictions were determined and compared to actual satellite data. The evaluation parameters used show that the predictions obtained correspond to real data for both the Markov chain method and the neural network method. We then predicted the long-term dry/wet phenomenon, from 2022 to 2050. The long-term prediction results of the dry/wet phenomenon performed by ANN and MC are compared to the simulations given by the coupled multi-model inter-comparison project version 6 (CMIP6) under scenarios, shared socioeconomic pathways SSP126. The overall orientation is identical for the three models (ANN, MC and CMIP6). Indeed, the prediction results performed by the three models indicate that areas representing dry surfaces are gaining ground at the expense of wetlands with a slight difference.</description><subject>Artificial neural networks</subject><subject>Comparative studies</subject><subject>Drought</subject><subject>Earth and Environmental Science</subject><subject>Earth Sciences</subject><subject>Markov analysis</subject><subject>Markov chains</subject><subject>Neural networks</subject><subject>Performance assessment</subject><subject>Rainfall</subject><subject>Remote Sensing/Photogrammetry</subject><subject>Review Article</subject><issn>0255-660X</issn><issn>0974-3006</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2023</creationdate><recordtype>article</recordtype><recordid>eNp9kEtLAzEUhYMoWKt_wFXAdWweM5PpstQn1Adq0V1IZ5I2bWcyJmlldv50047gzsXlXg7nHLgfAOcEXxKM-cATmtIEYcoQJpxiRA5ADw95ghjG2WG8aZqiLMMfx-DE-2UUk5TQHvh-bWQwNqiqsU6u4dhWjXRR2io4quW69cZDq-GVawfvKsDnhaptFafeqWGh4Is0dQuflTO2hFNv6jkcuWC0KUzse1Qbt1_hy7qVh7Iu4YN0K7uF40VM-lNwpOXaq7Pf3QfTm-u38R2aPN3ej0cTVFCOA5qVpCQk0YSRnEqpMkYymvA0zTVlBWdaD-VQU5yXjGquVIYZJzmfZYXiBckL1gcXXW_j7OdG-SCWduPih17QPIk4OE7z6KKdq3DWe6e0aJyppGsFwWJHWnSkRSQt9qQFiSHWhXw013Pl_qr_Sf0Agj2B9Q</recordid><startdate>20230701</startdate><enddate>20230701</enddate><creator>Hamdad, Sadjia</creator><creator>Lazri, Mourad</creator><creator>Mohia, Yacine</creator><creator>Labadi, Karim</creator><creator>Ameur, Soltane</creator><general>Springer India</general><general>Springer Nature B.V</general><scope>AAYXX</scope><scope>CITATION</scope><orcidid>https://orcid.org/0000-0003-2145-1823</orcidid></search><sort><creationdate>20230701</creationdate><title>Spatiotemporal Comparative Analysis of Dry/Wet Phenomenon of the Rainy Period Using Artificial Neural Networks and Markov Chains</title><author>Hamdad, Sadjia ; Lazri, Mourad ; Mohia, Yacine ; Labadi, Karim ; Ameur, Soltane</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c270t-bd1d114f13182aae6316247558f23c73ff9a9f208d32f7ee6037187b6ce7c18c3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2023</creationdate><topic>Artificial neural networks</topic><topic>Comparative studies</topic><topic>Drought</topic><topic>Earth and Environmental Science</topic><topic>Earth Sciences</topic><topic>Markov analysis</topic><topic>Markov chains</topic><topic>Neural networks</topic><topic>Performance assessment</topic><topic>Rainfall</topic><topic>Remote Sensing/Photogrammetry</topic><topic>Review Article</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Hamdad, Sadjia</creatorcontrib><creatorcontrib>Lazri, Mourad</creatorcontrib><creatorcontrib>Mohia, Yacine</creatorcontrib><creatorcontrib>Labadi, Karim</creatorcontrib><creatorcontrib>Ameur, Soltane</creatorcontrib><collection>CrossRef</collection><jtitle>Journal of the Indian Society of Remote Sensing</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Hamdad, Sadjia</au><au>Lazri, Mourad</au><au>Mohia, Yacine</au><au>Labadi, Karim</au><au>Ameur, Soltane</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Spatiotemporal Comparative Analysis of Dry/Wet Phenomenon of the Rainy Period Using Artificial Neural Networks and Markov Chains</atitle><jtitle>Journal of the Indian Society of Remote Sensing</jtitle><stitle>J Indian Soc Remote Sens</stitle><date>2023-07-01</date><risdate>2023</risdate><volume>51</volume><issue>7</issue><spage>1409</spage><epage>1425</epage><pages>1409-1425</pages><issn>0255-660X</issn><eissn>0974-3006</eissn><abstract>The work presented in this paper is a spatiotemporal analysis of the dry/wet phenomenon of the rainy period in northern Algeria to predict the drought. To that end, we implemented artificial neural networks (ANN) to analyze the behavior of processes. For a comparative study, we also analyzed the behavior of the dry/wet phenomenon of the rainy period using Markov chains (MC). The dry/wet phenomenon is divided into 9 categories obtained according to the values of SPI (Standard Precipitation Index). The database is built from satellite estimates of precipitation rates over a period from 1985 to 2021. To assess the performance of the two methods, short-term predictions were determined and compared to actual satellite data. The evaluation parameters used show that the predictions obtained correspond to real data for both the Markov chain method and the neural network method. We then predicted the long-term dry/wet phenomenon, from 2022 to 2050. The long-term prediction results of the dry/wet phenomenon performed by ANN and MC are compared to the simulations given by the coupled multi-model inter-comparison project version 6 (CMIP6) under scenarios, shared socioeconomic pathways SSP126. The overall orientation is identical for the three models (ANN, MC and CMIP6). Indeed, the prediction results performed by the three models indicate that areas representing dry surfaces are gaining ground at the expense of wetlands with a slight difference.</abstract><cop>New Delhi</cop><pub>Springer India</pub><doi>10.1007/s12524-023-01720-1</doi><tpages>17</tpages><orcidid>https://orcid.org/0000-0003-2145-1823</orcidid></addata></record> |
fulltext | fulltext |
identifier | ISSN: 0255-660X |
ispartof | Journal of the Indian Society of Remote Sensing, 2023-07, Vol.51 (7), p.1409-1425 |
issn | 0255-660X 0974-3006 |
language | eng |
recordid | cdi_proquest_journals_2840647058 |
source | SpringerNature Journals |
subjects | Artificial neural networks Comparative studies Drought Earth and Environmental Science Earth Sciences Markov analysis Markov chains Neural networks Performance assessment Rainfall Remote Sensing/Photogrammetry Review Article |
title | Spatiotemporal Comparative Analysis of Dry/Wet Phenomenon of the Rainy Period Using Artificial Neural Networks and Markov Chains |
url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-25T11%3A16%3A28IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_cross&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Spatiotemporal%20Comparative%20Analysis%20of%20Dry/Wet%20Phenomenon%20of%20the%20Rainy%20Period%20Using%20Artificial%20Neural%20Networks%20and%20Markov%20Chains&rft.jtitle=Journal%20of%20the%20Indian%20Society%20of%20Remote%20Sensing&rft.au=Hamdad,%20Sadjia&rft.date=2023-07-01&rft.volume=51&rft.issue=7&rft.spage=1409&rft.epage=1425&rft.pages=1409-1425&rft.issn=0255-660X&rft.eissn=0974-3006&rft_id=info:doi/10.1007/s12524-023-01720-1&rft_dat=%3Cproquest_cross%3E2840647058%3C/proquest_cross%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2840647058&rft_id=info:pmid/&rfr_iscdi=true |