An official website of the United States government
Abstract Global climate models (GCMs), typically run at ∼100-km resolution, capture large-scale environmental conditions but cannot resolve convection and cloud processes at kilometer scales. Convection-permitting models offer higher-resolution simulations that explicitly simulate convection but are computationally expensive and impractical for large ensemble runs. This study explores machine learning (ML) as a bridge between these approaches. We train simple, pixel-based neural networks to predict convective cloud fraction from environmental variables produced by a regional convection-permitting model. The ML models achieve promising results, with structural similarity index measure (SSIM) values exceeding 0.8, capturing the diurnal cycle and orographic convection without explicit temporal or spatial coordinates as input. Model performance declines when fewer input features are used or specific regions are excluded, underscoring the role of diverse physical mechanisms in convective cloud activity. These results demonstrate the potential of ML as both a tool for scientific discovery and a proof of concept that relatively simple model architectures can elucidate relationships between convective cloud characteristics and large-scale environmental controls. The proposed pixel-based approach is computationally inexpensive and is well suited as a diagnostic framework for analyzing GCM and reanalysis datasets rather than as a forecasting system. Unlike convolutional neural networks, which depend on the spatial structure and grid size, the pixel-based model treats each grid point independently, enabling value-to-value mapping independent of spatial context. This design facilitates cross-model and cross-scenario applicability and supports generalization across diverse environmental regimes, providing an efficient pathway for linking coarse-resolution environmental conditions to subgrid-scale convective features in a changing climate. Significance StatementUnderstanding how clouds and storms form is critical for predicting severe weather in a changing climate. However, current climate models struggle to capture small-scale cloud features due to their coarse resolution. Our research shows that machine learning, trained on detailed weather simulations, can successfully predict where the most storms occur based on larger-scale environmental patterns. This approach bridges the gap between what climate models can resolve and the finer details of clouds that matter most for impacts like severe weather. By combining high-resolution simulations and machine learning, our work offers a powerful new way to better understand storms in both current and future climate.
more »
« less
Knowledge-guided machine learning can improve carbon cycle quantification in agroecosystems
Abstract Accurate and cost-effective quantification of the carbon cycle for agroecosystems at decision-relevant scales is critical to mitigating climate change and ensuring sustainable food production. However, conventional process-based or data-driven modeling approaches alone have large prediction uncertainties due to the complex biogeochemical processes to model and the lack of observations to constrain many key state and flux variables. Here we propose a Knowledge-Guided Machine Learning (KGML) framework that addresses the above challenges by integrating knowledge embedded in a process-based model, high-resolution remote sensing observations, and machine learning (ML) techniques. Using the U.S. Corn Belt as a testbed, we demonstrate that KGML can outperform conventional process-based and black-box ML models in quantifying carbon cycle dynamics. Our high-resolution approach quantitatively reveals 86% more spatial detail of soil organic carbon changes than conventional coarse-resolution approaches. Moreover, we outline a protocol for improving KGML via various paths, which can be generalized to develop hybrid models to better predict complex earth system dynamics.
more »
« less
- PAR ID:
- 10503419
- Publisher / Repository:
- Nature
- Date Published:
- Journal Name:
- Nature Communications
- Volume:
- 15
- Issue:
- 1
- ISSN:
- 2041-1723
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Measurement of methane fluxes (FCH4) from natural systems, such as wetlands, has lagged far behind carbon dioxide fluxes. Short and fragmented wetland FCH4data limit our ability to assess its long‐term dynamics and potential climate feedbacks. Extrapolating short‐term FCH4records to recent decades remains challenging for both process‐based models and data‐driven machine learning (ML) approaches. Here, we develop a knowledge‐guided ML framework that integrates eddy covariance (EC) FCH4observations, field warming experiments, and biogeochemical knowledge to reconstruct the long‐term FCH4budgets and trends. Focusing on the 11 longest EC monitoring sites in the AmeriFlux network, we found considerable variability in multi‐decadal trends of wetland FCH4, with increases up to 14% per decade from 2000 to 2024. We also found that the strength of these increasing trends declines from high to low latitudes, highlighting the vulnerability of northern wetlands. This work presents novel and robust reconstructions of long‐term wetland FCH4, offering critical benchmark datasets for bottom‐up ecosystem models and advancing fundamental understanding of wetland biogeochemistry.more » « less
-
Abstract Sea surface height observations provided by satellite altimetry since 1993 show a rising rate (3.4 mm yr−1) for global mean sea level. While on average, sea level has risen 10 cm over the last 30 years, there is considerable regional variation in the sea level change. Through this work, we predict sea level trends 30 years into the future at a 2° spatial resolution and investigate the future patterns of the sea level change. We show the potential of machine learning (ML) in this challenging application of long-term sea level forecasting over the global ocean. Our approach incorporates sea level data from both altimeter observations and climate model simulations. We develop a supervised learning framework using fully connected neural networks (FCNNs) that can predict the sea level trend based on climate model projections. Alongside this, our method provides uncertainty estimates associated with the ML prediction. We also show the effectiveness of partitioning our spatial dataset and learning a dedicated ML model for each segmented region. We compare two partitioning strategies: one achieved using domain knowledge and the other employing spectral clustering. Our results demonstrate that segmenting the spatial dataset with spectral clustering improves the ML predictions. Significance StatementLong-term projections are needed to help coastal communities adapt to sea level rise. Forecasting multidecadal sea level change is a complex problem. In this paper, we show the promise of machine learning in producing such forecasts 30 years in advance and over the global ocean. Continued improvements in prediction skills that build on this work will be vital in sea level rise adaptation efforts.more » « less
-
Laser beam powder bed fusion (LB-PBF) is a widely-used metal additive manufacturing process due to its high potential for fabrication flexibility and quality. Its process and performance optimization are key to improving product quality and promote further adoption of LB-PBF. In this article, the state-of-the-art machine learning (ML) applications for process and performance optimization in LB-PBF are reviewed. In these applications, ML is used to model the process-structure–property relationships in a data-driven way and optimize process parameters for high-quality fabrication. We review these applications in terms of their modeled relationships by ML (e.g., process—structure, process—property, or structure—property) and categorize the ML algorithms into interpretable ML, conventional ML, and deep ML according to interpretability and accuracy. This way may be particularly useful for practitioners as a comprehensive reference for selecting the ML algorithms according to the particular needs. It is observed that of the three types of ML above, conventional ML has been applied in process and performance optimization the most due to its balanced performance in terms of model accuracy and interpretability. To explore the power of ML in discovering new knowledge and insights, interpretation with additional steps is often needed for complex models arising from conventional ML and deep ML, such as model-agnostic methods or sensitivity analysis. In the future, enhancing the interpretability of ML, standardizing a systemic procedure for ML, and developing a collaborative platform to share data and findings will be critical to promote the integration of ML in LB-PBF applications on a large scale.more » « less
-
Forest ecosystems play a critical role in the Earth system as major carbon sinks that are essential for carbon neutralization and climate change mitigation. However, the Earth has undergone significant deforestation and forest degradation, and the remaining forested areas are also facing increasing pressures from socioeconomic factors and climate change, potentially pushing them towards tipping points.Responding to the grand challenge, a theory-based Ecosystem Demography (ED) model has been continuously developed over the past two decades and serves as a key component in major initiatives, including the Global Carbon Budget, NASA Carbon Monitoring System, and US Greenhouse Gas Center. Despite its growing importance in combating climate change and shaping carbon policies, ED's expensive computation significantly limits its ability to estimate carbon dynamics at the global scale with high spatial resolution.Recently, machine learning (ML) models have shown promising potential in approximating theory-based models with interesting success in various domains including weather forecasting, thanks to the open-source benchmark datasets made available.However, there are currently no publicly available ML-ready datasets for global carbon dynamics forecasting in forest ecosystems. The limited data availability hinders the development of corresponding ML emulators. Furthermore, the inputs needed for running ED are highly complex with over a hundred variables from various remote sensing products. To bridge the gap, we develop a new ML-ready benchmark dataset, \textit{CarbonGlobe}, for carbon dynamics forecasting, featuring that: (1) the data has a global-scale coverage at 0.5 resolution; (2) the temporal range spans 40 years; (3)more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript
- Journal Article:
- https://doi.org/10.1038/s41467-023-43860-5
