Skip to main content
ARS Home » Midwest Area » Columbia, Missouri » Cropping Systems and Water Quality Research » Research » Publications at this Location » Publication #399672
Research Project: Sustainable Intensification of Cropping Systems on Spatially Variable Landscapes and Soils

Location: Cropping Systems and Water Quality Research

Title: Evaluating deep learning methods for estimating soil carbon with in-situ near-infrared spectroscopy

Author
item Ransom, Curtis
item TIAN, FENGKAI - University Of Missouri
item VONG, CHIN NEE - University Of Missouri
item ZHOU, JIANFENG - University Of Missouri
item Sudduth, Kenneth - Ken
item Veum, Kristen
item Kitchen, Newell

Submitted to: ASA-CSSA-SSSA Annual Meeting Abstracts
Publication Type: Abstract Only
Publication Acceptance Date: 11/1/2022
Publication Date: 11/6/2022
Citation: Ransom, C.J., Tian, F., Vong, C., Zhou, J., Sudduth, K.A., Veum, K.S., Kitchen, N.R. 2022. Evaluating deep learning methods for estimating soil carbon with in-situ near-infrared spectroscopy [abstract]. ASA, CSSA, SSSA International Annual Meeting, November 6-9, 2022, Baltimore, Maryland. Available: https://scisoc.confex.com/scisoc/2022am/meetingapp.cgi/Paper/143297

Interpretive Summary:

Technical Abstract: Agricultural lands can be a sink for carbon and play an important role in offsetting carbon emissions. Current methods of measuring carbon sequestration—through repeated temporal soil samples—are costly and laborious. A promising alternative is using visible and near-infrared (VNIR) diffuse reflectance spectroscopy. However, VNIR data are complex, which requires several data processing steps and often yields inconsistent results, especially when measurements are taken in situ. Using a convolutional neural network (CNN) could bypass these steps and incorporate measurements from multiple sensors to predict three-dimensional carbon stocks. Using data previously collected (n = 1,069; from 2014 to 2020), a CNN modeling framework was developed to predict soil carbon by incorporating information from profile VNIR, soil apparent electrical conductivity, penetration resistance, and soil moisture. Results will be presented which contrast CNN vs partial least square regression.