Net ecosystem carbon exchange prediction and insightful data mining with an optimized data-matching algorithm

Net ecosystem carbon exchange (NEE) measures the carbon interchanges between the Earth’s biosphere and atmosphere. NEE datasets for two northern European sites (730 and 413 data records) incorporating twenty-two meteorological and environmental data influencing variables, collected on a daily basis...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autor principal: David A. Wood
Formato: article
Lenguaje:EN
Publicado: Elsevier 2021
Materias:
Acceso en línea:https://doaj.org/article/7618048a60d64d9f8334dd27d71da931
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
id oai:doaj.org-article:7618048a60d64d9f8334dd27d71da931
record_format dspace
spelling oai:doaj.org-article:7618048a60d64d9f8334dd27d71da9312021-12-01T04:45:57ZNet ecosystem carbon exchange prediction and insightful data mining with an optimized data-matching algorithm1470-160X10.1016/j.ecolind.2021.107426https://doaj.org/article/7618048a60d64d9f8334dd27d71da9312021-05-01T00:00:00Zhttp://www.sciencedirect.com/science/article/pii/S1470160X21000911https://doaj.org/toc/1470-160XNet ecosystem carbon exchange (NEE) measures the carbon interchanges between the Earth’s biosphere and atmosphere. NEE datasets for two northern European sites (730 and 413 data records) incorporating twenty-two meteorological and environmental data influencing variables, collected on a daily basis for years spread across the period 1997 to 2013, are evaluated by an optimized data matching machine learning algorithm to predict NEE and data mine the datasets. The model’s transparency and avoidance of regressions/hidden correlations facilitates detailed data mining of the dataset exploiting two distinct objective functions. This reveals useful insights concerning similarities and influences between specific data records. Cumulative absolute error and squared error trends of predictions enable areas of the NEE distribution, predicted to different degrees of accuracy, to be identified. Such trends also facilitate detailed comparisons of the prediction calculation of each data record. The prediction accuracy achieved by the algorithm for the UK-Gri dataset (MAE = 0.6898 gC m−2 d−1; RMSE = 0.9558; R2 = 0.8903) and the hybrid UK-Gri plus NL-Loo dataset (MAE = 0.5072 gC m−2 d−1; RMSE = 0.7746; R2 = 0.9149) substantially outperform the NEE prediction accuracies achieved by four regression-based machine learning algorithms applied to the exact set of data records.David A. WoodElsevierarticleNet ecosystem carbon exchangeEnvironmental carbon storageFeature selectionNon-regression machine learningData-matched prediction accuracyCumulative absolute error differentialsEcologyQH540-549.5ENEcological Indicators, Vol 124, Iss , Pp 107426- (2021)
institution DOAJ
collection DOAJ
language EN
topic Net ecosystem carbon exchange
Environmental carbon storage
Feature selection
Non-regression machine learning
Data-matched prediction accuracy
Cumulative absolute error differentials
Ecology
QH540-549.5
spellingShingle Net ecosystem carbon exchange
Environmental carbon storage
Feature selection
Non-regression machine learning
Data-matched prediction accuracy
Cumulative absolute error differentials
Ecology
QH540-549.5
David A. Wood
Net ecosystem carbon exchange prediction and insightful data mining with an optimized data-matching algorithm
description Net ecosystem carbon exchange (NEE) measures the carbon interchanges between the Earth’s biosphere and atmosphere. NEE datasets for two northern European sites (730 and 413 data records) incorporating twenty-two meteorological and environmental data influencing variables, collected on a daily basis for years spread across the period 1997 to 2013, are evaluated by an optimized data matching machine learning algorithm to predict NEE and data mine the datasets. The model’s transparency and avoidance of regressions/hidden correlations facilitates detailed data mining of the dataset exploiting two distinct objective functions. This reveals useful insights concerning similarities and influences between specific data records. Cumulative absolute error and squared error trends of predictions enable areas of the NEE distribution, predicted to different degrees of accuracy, to be identified. Such trends also facilitate detailed comparisons of the prediction calculation of each data record. The prediction accuracy achieved by the algorithm for the UK-Gri dataset (MAE = 0.6898 gC m−2 d−1; RMSE = 0.9558; R2 = 0.8903) and the hybrid UK-Gri plus NL-Loo dataset (MAE = 0.5072 gC m−2 d−1; RMSE = 0.7746; R2 = 0.9149) substantially outperform the NEE prediction accuracies achieved by four regression-based machine learning algorithms applied to the exact set of data records.
format article
author David A. Wood
author_facet David A. Wood
author_sort David A. Wood
title Net ecosystem carbon exchange prediction and insightful data mining with an optimized data-matching algorithm
title_short Net ecosystem carbon exchange prediction and insightful data mining with an optimized data-matching algorithm
title_full Net ecosystem carbon exchange prediction and insightful data mining with an optimized data-matching algorithm
title_fullStr Net ecosystem carbon exchange prediction and insightful data mining with an optimized data-matching algorithm
title_full_unstemmed Net ecosystem carbon exchange prediction and insightful data mining with an optimized data-matching algorithm
title_sort net ecosystem carbon exchange prediction and insightful data mining with an optimized data-matching algorithm
publisher Elsevier
publishDate 2021
url https://doaj.org/article/7618048a60d64d9f8334dd27d71da931
work_keys_str_mv AT davidawood netecosystemcarbonexchangepredictionandinsightfuldataminingwithanoptimizeddatamatchingalgorithm
_version_ 1718405780217004032