Reconstructed Solar‐Induced Fluorescence: A Machine Learning Vegetation Product Based on MODIS Surface Reflectance to Reproduce GOME‐2 Solar‐Induced Fluorescence

Autor: Gentine, P., Alemohammad, S. H.
Rok vydání: 2018
Předmět:
Solar‐induced fluorescence
010504 meteorology & atmospheric sciences
media_common.quotation_subject
0211 other engineering and technologies
Eddy covariance
Irradiance
02 engineering and technology
Biogeosciences
Machine learning
computer.software_genre
Hydrology and Land Surface Studies
01 natural sciences
Biogeochemical Kinetics and Reaction Modeling
Remote Sensing
Oceanography: Biological and Chemical
Paleoceanography
Research Letter
Global Change
Photosynthesis
Absorption (electromagnetic radiation)
Planetary Sciences: Solid Surface Planets
021101 geological & geomatics engineering
0105 earth and related environmental sciences
media_common
business.industry
Vegetation
Biogeochemistry
Fluorescence
Research Letters
Geophysics
MODIS
Photosynthetically active radiation
Sky
General Earth and Planetary Sciences
Environmental science
Artificial intelligence
Moderate-resolution imaging spectroradiometer
Cryosphere
business
Biogeochemical Cycles
Processes
and Modeling
computer
Zdroj: Geophysical Research Letters
ISSN: 1944-8007
0094-8276
DOI: 10.1002/2017gl076294
Popis: Solar‐induced fluorescence (SIF) observations from space have resulted in major advancements in estimating gross primary productivity (GPP). However, current SIF observations remain spatially coarse, infrequent, and noisy. Here we develop a machine learning approach using surface reflectances from Moderate Resolution Imaging Spectroradiometer (MODIS) channels to reproduce SIF normalized by clear sky surface irradiance from the Global Ozone Monitoring Experiment‐2 (GOME‐2). The resulting product is a proxy for ecosystem photosynthetically active radiation absorbed by chlorophyll (fAPARCh). Multiplying this new product with a MODIS estimate of photosynthetically active radiation provides a new MODIS‐only reconstruction of SIF called Reconstructed SIF (RSIF). RSIF exhibits much higher seasonal and interannual correlation than the original SIF when compared with eddy covariance estimates of GPP and two reference global GPP products, especially in dry and cold regions. RSIF also reproduces intense productivity regions such as the U.S. Corn Belt contrary to typical vegetation indices and similarly to SIF.
Key Points A new machine learning‐based vegetation product, Reconstructed Solar‐Induced Fluorescence (RSIF), is developed using visible and near‐infrared MODIS channelsRSIF improves SIF with better correlation with in situ eddy covariance and remote sensing‐based photosynthesis and lower noiseRSIF has high spatial resolution and a long record and does not saturate, unlike optical vegetation indices
Databáze: OpenAIRE
Externí odkaz: