Biogeochemistry-Informed Neural Network (BINN v1.0) for improving accuracy of model prediction and scientific understanding of soil organic carbon storage
Year: 2026
Type: article
Abstract: The increasing availability of large-scale observational data and the rapid development of artificial intelligence (AI) provide unprecedented opportunities to enhance our understanding of the global carbon cycle and other biogeochemical processes. However, retrieving mechanistic knowledge from these large-scale data remains a challenge. Here, we develop a Biogeochemistry-Informed Neural Network (BINN) that seamlessly integrates a vectorized process-based soil carbon cycle model (i.e., Community Land Model version 5, CLM5) into a neural network (NN) structure to examine mechanisms governing soil organic carbon (SOC) storage from big data. BINN demonstrates high accuracy in retrieving biogeochemical parameter values from synthetic data in a parameter recovery experiment. Furthermore, by incorporating Monte Carlo (MC) dropout to generate posterior distributions, we demonstrate that BINN can effectively quantify uncertainty in estimated parameters. We use BINN to predict six major processes (or components in process-based models) regulating the soil carbon cycle from 25 925 observed SOC profiles across the contiguous US and compare them with the same processes previously retrieved by a Bayesian inference-based PROcess-guided deep learning and DAta-driven modeling (PRODA) approach. The good agreement between the spatial patterns retrieved by BINN and PRODA (average correlation coefficient = 0.86) suggests that BINN's ability of capturing mechanistic knowledge is consistent with the established Bayesian-based methods. Additionally, the integration of neural networks and process-based models in BINN improves computational efficiency by more than 50 times over PRODA. We conclude that BINN is an efficient framework that harnesses the power of AI, large-scale data, and process-based modeling to understand large scale soil carbon cycle. Applying BINN to other domains of Earth system science will facilitate new scientific discoveries while improving the predictive performance of Earth system models.
Source: Geoscientific model development
Institutions: Cornell University, Nanyang Technological University
Language: English
Subfield: Soil Science
Domain: Life Sciences
SDGs: Climate action, Life on land
Open Access status: gold
Estimated APC paid: $1,725
Funders: Schmidt Futures, National Science Foundation, U.S. Department of Energy, U.S. Department of Agriculture, New York State Department of Agriculture and Markets, New York State Department of Environmental Conservation, National Institute of Food and Agriculture, College of Agriculture and Life Sciences, Cornell University, Division of Graduate Education, Division of Environmental Biology, Biological and Environmental Research, Moonshot Research and Development Program, Air Force Office of Scientific Research, Oak Ridge National Laboratory, European Office of Aerospace Research and Development
Awards: G1216388043, G1461339309, G1523888516, G1531947363, G1861088835, AGING-AWARE MANAGEMENT OF MOTORIZED ENERGY STORAGE FOR GRID
FLEXIBILITY PROVISION, NRT-HDR: Team training to develop new hardware and software applications for digital plant science across multiple scales, G2729773427, G3336938304, G3465612214, G3865373219, G4142553078, G4384255104, Collaborative Research: MRA: Harness the theoretical and data advances in solar-induced chlorophyll fluorescence to jointly partition ecosystem carbon and water fluxes, G4516736450, G5482769651, G5620962805, LTER: SEVILLETA SITE: ENVIRONMENTAL VARIABILITY AT DRYLAND ECOTONES, Collaborative Research: MRA: Constraining the continental-scale terrestrial carbon cycle using NEON data, G6478756169, G6762473753, G789101582, G7920564120, G8327808509, G8824432673
OpenAlex ID: W7170617542