Ensemble Encoder–Decoder Models for Predicting Land Transformation

Land development is a dynamic and complex processinfluenced by a system of interconnected driving variables. Predicting such a process is important in mitigating severe climate situations and improving the resiliency of communities. Current predictive models in land transformation have not paid a se...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Pariya Pourmohammadi, Michael P. Strager, Donald A. Adjeroh
Formato: article
Lenguaje:EN
Publicado: IEEE 2021
Materias:
Acceso en línea:https://doaj.org/article/ba72a4acdabb4772a1d4a1fcf1a7a397
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
id oai:doaj.org-article:ba72a4acdabb4772a1d4a1fcf1a7a397
record_format dspace
spelling oai:doaj.org-article:ba72a4acdabb4772a1d4a1fcf1a7a3972021-11-20T00:00:19ZEnsemble Encoder–Decoder Models for Predicting Land Transformation2151-153510.1109/JSTARS.2021.3120659https://doaj.org/article/ba72a4acdabb4772a1d4a1fcf1a7a3972021-01-01T00:00:00Zhttps://ieeexplore.ieee.org/document/9580600/https://doaj.org/toc/2151-1535Land development is a dynamic and complex processinfluenced by a system of interconnected driving variables. Predicting such a process is important in mitigating severe climate situations and improving the resiliency of communities. Current predictive models in land transformation have not paid a serious attention to capturing and exploiting the interchannel relationships. Moreover, these models often have problems with generalization, which results in poor performance during testing. In this study, we use a novel multichannel data cube, constructed from socioeconomic attributes, terrain characteristics, and landscape traits, to predict land transformation in a watershed in the US. In particular, we introduce methods for projecting impervious land transformations using these data cubes, using 2-D and 3-D convolutional neural networks (CNNs) and their ensembles. We apply fusion at decision, score, and feature levels to improve the generalization ability and robustness of the proposed predictive models. Performance is assessed using the Dice coefficient, receiver operating characteristic curves, data visualization, and running time. Our study shows that the use of 2-D and 3-D CNN ensembles improved the performance of the models in terms of model stability, precision and recall, and Dice coefficient.Pariya PourmohammadiMichael P. StragerDonald A. AdjerohIEEEarticleConvolutional neural networks (CNNs)developed land expansionevidence fusionland transformation predictionOcean engineeringTC1501-1800Geophysics. Cosmic physicsQC801-809ENIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, Vol 14, Pp 11429-11438 (2021)
institution DOAJ
collection DOAJ
language EN
topic Convolutional neural networks (CNNs)
developed land expansion
evidence fusion
land transformation prediction
Ocean engineering
TC1501-1800
Geophysics. Cosmic physics
QC801-809
spellingShingle Convolutional neural networks (CNNs)
developed land expansion
evidence fusion
land transformation prediction
Ocean engineering
TC1501-1800
Geophysics. Cosmic physics
QC801-809
Pariya Pourmohammadi
Michael P. Strager
Donald A. Adjeroh
Ensemble Encoder–Decoder Models for Predicting Land Transformation
description Land development is a dynamic and complex processinfluenced by a system of interconnected driving variables. Predicting such a process is important in mitigating severe climate situations and improving the resiliency of communities. Current predictive models in land transformation have not paid a serious attention to capturing and exploiting the interchannel relationships. Moreover, these models often have problems with generalization, which results in poor performance during testing. In this study, we use a novel multichannel data cube, constructed from socioeconomic attributes, terrain characteristics, and landscape traits, to predict land transformation in a watershed in the US. In particular, we introduce methods for projecting impervious land transformations using these data cubes, using 2-D and 3-D convolutional neural networks (CNNs) and their ensembles. We apply fusion at decision, score, and feature levels to improve the generalization ability and robustness of the proposed predictive models. Performance is assessed using the Dice coefficient, receiver operating characteristic curves, data visualization, and running time. Our study shows that the use of 2-D and 3-D CNN ensembles improved the performance of the models in terms of model stability, precision and recall, and Dice coefficient.
format article
author Pariya Pourmohammadi
Michael P. Strager
Donald A. Adjeroh
author_facet Pariya Pourmohammadi
Michael P. Strager
Donald A. Adjeroh
author_sort Pariya Pourmohammadi
title Ensemble Encoder–Decoder Models for Predicting Land Transformation
title_short Ensemble Encoder–Decoder Models for Predicting Land Transformation
title_full Ensemble Encoder–Decoder Models for Predicting Land Transformation
title_fullStr Ensemble Encoder–Decoder Models for Predicting Land Transformation
title_full_unstemmed Ensemble Encoder–Decoder Models for Predicting Land Transformation
title_sort ensemble encoder–decoder models for predicting land transformation
publisher IEEE
publishDate 2021
url https://doaj.org/article/ba72a4acdabb4772a1d4a1fcf1a7a397
work_keys_str_mv AT pariyapourmohammadi ensembleencoderx2013decodermodelsforpredictinglandtransformation
AT michaelpstrager ensembleencoderx2013decodermodelsforpredictinglandtransformation
AT donaldaadjeroh ensembleencoderx2013decodermodelsforpredictinglandtransformation
_version_ 1718419860430520320