Dataset Information

Water, Energy, and Carbon with Artificial Neural Networks (WECANN): A statistically-based estimate of global surface turbulent fluxes and gross primary productivity using solar-induced fluorescence.

ABSTRACT: A new global estimate of surface turbulent fluxes, latent heat flux (LE) and sensible heat flux (H), and gross primary production (GPP) is developed using a machine learning approach informed by novel remotely sensed Solar-Induced Fluorescence (SIF) and other radiative and meteorological variables. This is the first study to jointly retrieve LE, H and GPP using SIF observations. The approach uses an artificial neural network (ANN) with a target dataset generated from three independent data sources, weighted based on triple collocation (TC) algorithm. The new retrieval, named Water, Energy, and Carbon with Artificial Neural Networks (WECANN), provides estimates of LE, H and GPP from 2007 to 2015 at 1° × 1° spatial resolution and on monthly time resolution. The quality of ANN training is assessed using the target data, and the WECANN retrievals are evaluated using eddy covariance tower estimates from FLUXNET network across various climates and conditions. When compared to eddy covariance estimates, WECANN typically outperforms other products, particularly for sensible and latent heat fluxes. Analysing WECANN retrievals across three extreme drought and heatwave events demonstrates the capability of the retrievals in capturing the extent of these events. Uncertainty estimates of the retrievals are analysed and the inter-annual variability in average global and regional fluxes show the impact of distinct climatic events - such as the 2015 El Niño - on surface turbulent fluxes and GPP.

SUBMITTER: Alemohammad SH

PROVIDER: S-EPMC5744880 | biostudies-literature | 2017

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Water, Energy, and Carbon with Artificial Neural Networks (WECANN): A statistically-based estimate of global surface turbulent fluxes and gross primary productivity using solar-induced fluorescence.

Alemohammad Seyed Hamed SH Fang Bin B Konings Alexandra G AG Aires Filipe F Green Julia K JK Kolassa Jana J Miralles Diego D Prigent Catherine C Gentine Pierre P

Biogeosciences (Online) 20170920 18

A new global estimate of surface turbulent fluxes, latent heat flux (LE) and sensible heat flux (H), and gross primary production (GPP) is developed using a machine learning approach informed by novel remotely sensed Solar-Induced Fluorescence (SIF) and other radiative and meteorological variables. This is the first study to jointly retrieve LE, H and GPP using SIF observations. The approach uses an artificial neural network (ANN) with a target dataset generated from three independent data sourc ...[more]

PMID: 29290755

Similar Datasets

Project description:ObjectivesJob exposure matrices (JEMs) are important tools for estimating occupational exposures in study populations where only information on industry and occupation (I&O) are available. JEMs The objective of this work was to create JEMs for solar and artificial ultraviolet radiation (UVR) using a US standardized coding scheme.MethodsUsing U.S. Census Bureau industry and occupation codes, separate lists of I&O pairs were developed for solar and artificial UVR by a panel of Certified Industrial Hygienists who assigned exposure ratings to I&O pairs with potential exposure. Parameters for exposure included prevalence (P) and frequency (F) for solar UVR and P, F, and intensity (I) for artificial UVR. Prevalence, or percent of all workers employed in an I&O pair who were exposed, was categorically rated: 0 to <1, 1 to <20; 20 to <80, and ≥80. Frequency of exposure, defined by the number of hours per week workers were exposed, was categorically rated: 0 to <5, 5 to <20, 20 to <35, and ≥35 h per week. For artificial UVR only, intensity of exposure was assigned three ratings: low, low with rare excursions, and >low under normal conditions. Discrepant ratings were resolved via consensus.ResultsAfter excluding I&O pairs assigned P and F ratings of 0 (solar UVR) and P, F, and I ratings of 0 (artificial UVR) from the JEM, 9206 I&O pairs were rated for solar UVR and 2010 I&O pairs for artificial UVR. For solar UVR, 723 (7.9% of all rated pairs) had ratings in the highest category for P and F; this group included 45 occupations in varied industries. Construction and extraction occupations represented most of the occupations (n = 20; 44%), followed by farming, fishing, and forestry occupations (n = 6; 13%). For artificial UVR, 87 I&O pairs (4.3% of all rated pairs) had maximum ratings for P, F, and I; these comprised a single occupation (welding, soldering, and brazing workers) in diverse industries.ConclusionsJEMs for solar and artificial UVR were developed for a broad range of I&O pairs in the US population and are available for use by researchers conducting occupational epidemiological studies.

Dataset Information

Water, Energy, and Carbon with Artificial Neural Networks (WECANN): A statistically-based estimate of global surface turbulent fluxes and gross primary productivity using solar-induced fluorescence.

Publications

Water, Energy, and Carbon with Artificial Neural Networks (WECANN): A statistically-based estimate of global surface turbulent fluxes and gross primary productivity using solar-induced fluorescence.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets