Using Image Processing Techniques to Identify and Quantify Spatiotemporal Carbon Cycle Extremes

📅 2022-11-01
🏛️ 2022 IEEE International Conference on Data Mining Workshops (ICDMW)
📈 Citations: 2
Influential: 0
📄 PDF
🤖 AI Summary
This study addresses the critical limitations—poor temporal continuity and cross-boundary detection—in identifying carbon-cycle extreme events (STEs). We propose a novel spatiotemporal feature detection method rooted in image processing: modeling carbon flux anomalies as a 3D spatiotemporal manifold defined by local neighborhood structures, and automatically identifying contiguous, cross-regional STEs via 3D connected-component analysis. This work pioneers the integration of neighborhood-based topology and 3D connectivity into STE detection, formally defining the “spatiotemporal extreme manifold” (STE) and overcoming the constraints of conventional pixel-wise thresholding approaches. Leveraging multi-source GPP remote sensing data and Earth system model outputs, we conduct attribution analysis: among 100 detected STEs, the top contributors account for over 75% of negative carbon anomalies; STE area and intensity exhibit strong concordance with carbon loss magnitude; and climate drivers are attributed in a structurally dependent manner—revealing non-linear, spatially heterogeneous forcing mechanisms.

Technology Category

Application Category

📝 Abstract
Rising atmospheric carbon dioxide due to human activities through fossil fuel emissions and land use changes have increased climate extremes such as heat waves and droughts that have led to and are expected to increase the occurrence of carbon cycle extremes. Carbon cycle extremes represent large anomalies in the carbon cycle that are associated with gains or losses in carbon uptake. Carbon cycle extremes could be continuous in space and time and cross political boundaries. Here, we present a methodology to identify large spatiotemporal extremes (STEs) in the terrestrial carbon cycle using image processing tools for feature detection. We characterized the STE events based on neighborhood structures that are three-dimensional adjacency matrices for the detection of spatiotemporal manifolds of carbon cycle extremes. We found that the area affected and carbon loss during negative carbon cycle extremes were consistent with continuous neighborhood structures. In the gross primary production data we used, 100 carbon cycle STEs accounted for more than 75% of all the negative carbon cycle extremes. This paper presents a comparative analysis of the magnitude of carbon cycle STEs and attribution of those STEs to climate drivers as a function of neighborhood structures for two observational datasets and an Earth system model simulation.
Problem

Research questions and friction points this paper is trying to address.

Identify spatiotemporal carbon cycle extremes using image processing
Quantify carbon loss during negative carbon cycle extremes
Analyze climate drivers of carbon cycle extremes
Innovation

Methods, ideas, or system contributions that make the work stand out.

Image processing for carbon cycle extremes
3D adjacency matrices for spatiotemporal detection
Comparative analysis of climate drivers impact
🔎 Similar Papers
B
Bharat Sharma
Computational Earth Sciences Group, Oak Ridge National Laboratory, Oak Ridge, USA; Department of Civil and Environmental Engineering, Northeastern University, Boston, USA
J
J. Kumar
Environmental Sciences Division, Oak Ridge National Laboratory, Oak Ridge, USA
A
A. Ganguly
Department of Civil and Environmental Engineering, Northeastern University, Boston, USA
F
F. Hoffman
Computational Earth Sciences Group, Oak Ridge National Laboratory, Oak Ridge, USA