Consiglio Nazionale delle Ricerche

Tipo di prodottoArticolo in rivista
TitoloImproving surface roughness lengths estimation using machine learning algorithms
Anno di pubblicazione2020
Autore/iXiaolong Hu, Liangsheng Shia, Lin Lin, Vincenzo Magliulo
Affiliazioni autoriState Key Laboratory of Water Resources and Hydropower Engineering Sciences, Wuhan University, Wuhan, Hubei 430072, China Institute for Agriculture and Forestry Systems in the Mediterranean, National Research Council, Napoli, Italy
Autori CNR e affiliazioni
  • inglese
AbstractSurface roughness lengths, including the aerodynamic roughness length (z0m) and the thermodynamic roughness length (z0h, represented by excess resistance kB-1), are crucial parameters in the accurate simulation of surface turbulent fluxes. However, considerable uncertainties exist in physically-based surface roughness lengths models, due to insufficient knowledge of the physical mechanisms of them. In this study, we attempt to overcome this issue by establishing the data-driven surface roughness lengths models, which is based on global observations from the FLUXNET2015 dataset and Moderate Resolution Imaging Spectroradiometer (MODIS). Four machine learning algorithms, including random forest (RF), single hidden layer artificial neural network (ANN), multilayer perceptron (MLP), deep belief network (DBN) are explored. A large number of data from 45 flux tower sites (as many as 44662 daily z0m and 583484 half-hour kB-1 observations) are utilized to train and test the data-driven models. Our results show that the data-driven models surprisingly achieve significantly improved estimation of surface roughness lengths and turbulent fluxes than physical models, which indicated the model inadequacy of physical models. The RF-driven models achieve the best results. The MLP and DBN-driven models of higher complexity are slightly superior to ANN-driven models, but exhibit unstable performance. The RF and ANN accurately reproduce the unimodal function relationship between leaf area index and z0m, thus demonstrating that the machine learning methods can extract physical rules from vast numbers of observations. In contrast, the MLP and DBN fail to capture this relationship, possibly because of too complicated architecture. It implies that a suitable complexity of machine learning algorithm is critical to excavate true physical mechanism. To the best of our knowledge, this study firstly demonstrate that machine learning technique can contribute to highly accurate estimation of surface turbulent fluxes by building data-driven surface roughness lengths models.
Lingua abstractinglese
Altro abstract-
Lingua altro abstract-
Pagine da-
Pagine a-
Pagine totali17
RivistaAgricultural and forest meteorology (Print)
Attiva dal 1984
Editore: Elsevier - New York ;
Paese di pubblicazione: Paesi Bassi
Lingua: inglese
ISSN: 0168-1923
Titolo chiave: Agricultural and forest meteorology (Print)
Titolo proprio: Agricultural and forest meteorology. (Print)
Titolo abbreviato: Agric. for. meteorol. (Print)
Numero volume della rivista287
Fascicolo della rivista107956
Verificato da refereeSì: Internazionale
Stato della pubblicazionePublished version
Indicizzazione (in banche dati controllate)
  • Scopus (Codice:2-s2.0-85081017828)
  • ISI Web of Science (WOS) (Codice:000531095900029)
Parole chiaveSurface roughness lengths; Machine learning; FLUXNET2015 dataset; MODIS
Link (URL, URI)
Titolo parallelo-
Scadenza embargo-
Data di accettazione02/03/2020
Note/Altre informazionisottomesso: 22 settembre 2019
Strutture CNR
  • ISAFoM — Istituto per i sistemi agricoli e forestali del mediterraneo
Moduli/Attività/Sottoprogetti CNR
  • AG.P04.038.001 : Scambi di massa e di energia dei sistemi naturali e antropici con l'atmosfera
Progetti Europei
xiaolong (documento privato )
Tipo documento: application/pdf