Articles | Volume 21, issue 10
Research article
24 May 2024
Research article |  | 24 May 2024

Using automated machine learning for the upscaling of gross primary productivity

Max Gaber, Yanghui Kang, Guy Schurgers, and Trevor Keenan

Data sets

Global MODIS and FLUXNET-derived Daily Gross Primary Production, V2 (2) J. Joiner and Y. Yoshida

ERA5-Land monthly averaged data from 1950 to present J. Muñoz Sabater

A global spatially contiguous solar-induced fluorescence (CSIF) dataset using neural networks (2000-2022) Y. Zhang

Warm Winter 2020 ecosystem eddy covariance flux product for 73 stations in FLUXNET-Archive format-release 2022-1 (1.0) Warm Winter 2020 Team and ICOS Ecosystem Thematic Centre

MCD12Q1 MODIS/Terra+Aqua Land Cover Type Yearly L3 Global 500m SIN Grid V006 M. Friedl and D. Sulla-Menashe

MCD15A2H MODIS/Terra+Aqua Leaf Area Index/FPAR 8-day L4 Global 500m SIN Grid V006 R. Myneni et al.

MCD43A4 MODIS/Terra+Aqua BRDF/Albedo Nadir BRDF Adjusted Ref Daily L3 Global - 500m V006 C. Schaaf and Z. Wang

MOD11A1 MODIS/Terra Land Surface Temperature/Emissivity Daily L3 Global 1km SIN Grid V006 Z. Wan et al.

AmeriFlux AmeriFlux Management Project

Data from the ESA CCI Soil Moisture project W. Dorigo et al.

Bess_Rad Y. Ryu et al.

FLUXNET2015 dataset G. Pastorello et al.

Model code and software

AutoML for GPP upscaling v1.0 Max Gaber

Short summary
Gross primary productivity (GPP) describes the photosynthetic carbon assimilation, which plays a vital role in the carbon cycle. We can measure GPP locally, but producing larger and continuous estimates is challenging. Here, we present an approach to extrapolate GPP to a global scale using satellite imagery and automated machine learning. We benchmark different models and predictor variables and achieve an estimate that can capture 75 % of the variation in GPP.
Final-revised paper