Logo do repositório
 
Publicação

Neural network approximation based on ANFIS and Geographic Information System mapping for reliable evapotranspiration prediction in Khenchela, Algeria

2026Artigo de investigação Acesso aberto
Ver registo simples
datacite.subject.fosCiências Agrárias
dc.contributor.authorMeziani, Assia
dc.contributor.authorMega, Nabil
dc.contributor.authorMiloudi, Abdelmonen
dc.contributor.authorDuarte, A.C.
dc.contributor.authorKhechekhouche, Abderahamane
dc.date.accessioned2026-07-16T15:32:13Z
dc.date.available2026-07-16T15:32:13Z
dc.date.issued2026en_US
dc.date.updated2026-07-09T15:22:30Z
dc.description.abstractAccurate estimation of reference evapotranspiration (ET0) is critical for sustainable water resource management, irrigation scheduling, and climate adaptation in heterogeneous semi-arid regions. This study presents a streamlined neural network (NN) approximation inspired by the Adaptive Neuro-Fuzzy Inference System (ANFIS) for predicting daily ET0 in Khenchela province, northeastern Algeria. Utilizing meteorological and soil data from 2000 to 2024 at 16 representative stations (Babar (1), Babar (2), Babar (3), Baghai, Bouhmama, Chechar, Djellal, El Hamma, Kais, Khenchela, Khirane, M’sara, Remila, Tamza, Taouzient, and Zaoui), sourced from the Open-Meteo Historical Weather API, the model employs inputs including air temperature, relative humidity, precipitation, wind speed, sunshine duration, terrestrial radiation, soil temperature, and soil moisture. The NN was trained to closely approximate the FAO-56 Penman-Monteith reference ET0 values computed directly by the API. Performance evaluation yielded strong agreement across stations: R2 > 0.96, RMSE 0.22 - 0.46 mm/day, NSE > 0.95, RSR < 0.13, and Willmott’s index 0.88 - 0.93, with peak accuracy (R2 > 0.99, RMSE < 0.24 mm/day) at high-elevation sites. Spatial patterns, mapped via GIS-based inverse distance weighting interpolation, revealed pronounced topographic and aridity-driven variability, confirmed by Emberger and De Martonne indices. This computationally efficient NN offers a scalable surrogate for FAO-56 calculations in data-limited, heterogeneous environments, supporting precision irrigation, drought monitoring, and adaptive strategies in semi-arid North Africa and Mediterranean regions.eng
dc.description.versionN/A
dc.identifier.citationMEZIANI, A. [et al.] (2026) - Neural network approximation based on ANFIS and Geographic Information System mapping for reliable evapotranspiration prediction in Khenchela, Algeria. Open Access Library Journal. 13, e14974. DOI: 10.4236/oalib.1114974
dc.identifier.doi10.4236/oalib.1114974en_US
dc.identifier.issn2333-9721en_US
dc.identifier.issn2333-9705en_US
dc.identifier.slugcv-prod-5067862
dc.identifier.urihttp://hdl.handle.net/10400.11/10943
dc.language.isoeng
dc.peerreviewedyes
dc.publisherOpen Access Library Inc.
dc.rights.urihttp://creativecommons.org/licenses/by/4.0/
dc.subjectEvapotranspiration
dc.subjectNeural network
dc.subjectANFIS
dc.subjectModeling
dc.subjectKhenchela
dc.subjectAlgeria
dc.titleNeural network approximation based on ANFIS and Geographic Information System mapping for reliable evapotranspiration prediction in Khenchela, Algeriaeng
dc.typeresearch articleen_US
dspace.entity.typePublication
oaire.citation.endPage14
oaire.citation.issue03en_US
oaire.citation.startPage1
oaire.citation.titleOALiben_US
oaire.citation.volume13en_US
oaire.versionhttp://purl.org/coar/version/c_970fb48d4fbd8a85
person.familyNameCANATÁRIO DUARTE
person.givenNameANTÓNIO
person.identifier.ciencia-id0717-AB48-E1A3
person.identifier.orcid0000-0002-0319-378X
person.identifier.scopus-author-id54901177900
rcaap.cv.cienciaid0717-AB48-E1A3 | ANTÓNIO Canatário Duarte
rcaap.rightsrestrictedAccessen_US
relation.isAuthorOfPublicationff1ed167-3f68-4e2b-b092-aaa0eb28ae6b
relation.isAuthorOfPublication.latestForDiscoveryff1ed167-3f68-4e2b-b092-aaa0eb28ae6b

Ficheiros

Principais
A mostrar 1 - 1 de 1
Miniatura indisponível
Nome:
Published_Version_2026.pdf
Tamanho:
4.44 MB
Formato:
Adobe Portable Document Format
Ver/Abrir
Licença
A mostrar 1 - 1 de 1
Miniatura indisponível
Nome:
license.txt
Tamanho:
2.02 KB
Formato:
Item-specific license agreed upon to submission
Descrição:
Ver/Abrir

Coleções

ESACB - Artigos em revistas com arbitragem científica