59 hasil
Menampilkan 1–20 · 0,17 detik · RSS
Machine Learning. Earth
ISSN 3049-4753 · IOP Publishing · 59 artikel di indeks
-
Artikel Jurnal
Enabling real-time training of a wildfire-to-smoke map with multilinear operators
Wildfires are a major producer of fine particulate matter, impacting human health and the electrical grid. Accurately forecasting smoke impacts over long time scales incorporates fuel treatment strategies, natural fuel succession, and stochastic events like lightning strikes. However, predicting…
-
Artikel Jurnal
From stable online coupling to decade-long climate simulations: a machine learning parameterization for cloud microphysics in ICON
The representation of cloud microphysics and its nonlinear character and scale-dependence is a remaining source of uncertainty in Earth system models (ESMs). Here, we develop and couple online a machine learning (ML)-based cloud microphysics parameterization with the Icosahedral non-hydrostatic…
-
Artikel Jurnal
Data-driven subgrid-scale turbulence parameterization: methods for improving model efficiency
Data-driven parameterization schemes have gained much attention in atmospheric science in recent years. We designed an idealized testing case with the barotropic vorticity equation model, which employed a subgrid-scale turbulence parameterization based on a deep learning (DL) model. Its effective…
-
Artikel Jurnal
How accurate are salinity measurements around Antarctica? A machine learning based approach
The Antarctic margin is a critically under-observed region despite its importance to the global climate. Here, in-situ ocean observations are difficult to obtain and clustered in easier-to-access regions. In addition, autonomous salinity measurements have to be corrected for drift or bias after…
-
Artikel Jurnal
Machine learning of vertical fluxes by unresolved midlatitude mesoscale processes
Machine learning (ML) can represent processes unresolved in coarse-resolution Earth system models (ESMs) by learning from high-resolution climate data. Such ML parameterization approaches have been primarily tested in idealized setups (e.g. aquaplanets), where they have focused on deep convection…
-
Artikel Jurnal
Can deep learning outperform mechanistic modeling of peatland water table dynamics?
Peatlands are hotspots in the global carbon budget, with the water level (WL) as a key driver of the carbon sink-source dynamics. While process-based models have been developed to simulate peatland WL, data-driven approaches remain underexplored. This study investigates a long short-term memory…
-
Artikel Jurnal
An interpretable latent space reveals changing dynamics of European heatwaves
Due to climate change, heatwaves are becoming more frequent and intense, with western Europe experiencing the strongest trends in the Northern Hemisphere mid-latitudes. Part of the temperature trends are caused by circulation changes, which are not accurately captured in climate models. Here we…
-
Artikel Jurnal
TeleViT1.0: teleconnection-informed vision transformers for subseasonal to seasonal wildfire pattern forecasts
Forecasting wildfires weeks to months in advance is difficult, yet crucial for planning fuel treatments and allocating resources. While short-term predictions typically rely on local weather conditions, long-term forecasting requires accounting for the Earth’s interconnectedness, including global…
-
Artikel Jurnal
A deep learning bias-correction layer for land surface models: application to soil moisture during drought and hurricane events
Accurate soil moisture prediction during extreme events remains a challenge for Earth system modeling, with significant implications for drought monitoring, flood forecasting, and climate adaptation strategies. Although land surface models (LSMs) provide physics-based predictions, their…
-
Artikel Jurnal
HydroTFT: a cross-basin attention model for multi-horizon rainfall–runoff prediction
Streamflow prediction is essential for water resources management, flood forecasting, and climate resilience. Long short-term memory (LSTM) networks have advanced large-sample hydrology through cross-basin learning, but their recurrent architectures have limited ability to capture long-range…
-
Artikel Jurnal
Estimation of carbon fluxes in urban vegetation using machine learning emulators of the land surface model JSBACH
Effective land management and climate adaptation call for tools that are reliable and easy to use. In this paper, we present the development and evaluation of machine learning emulators trained to reproduce ecosystem model outputs of urban vegetation carbon fluxes: photosynthesis (GPP) and net…
-
Artikel Jurnal
Success and limits of reconstructing phytoplankton pigment temporal variations from simultaneous surface ocean physics with a Unet model
Phytoplankton form the base of marine food webs and play a central role in the ocean carbon cycle. Satellite observations of ocean color provide global information on phytoplankton pigments: Chlorophyll-a proxy for the total phytoplankton biomass and other accessory pigments which provide…
-
Artikel Jurnal
CoDiT: conditional diffusion models for multi-day ocean drifter trajectory prediction
Accurate multi-day forecasting of floating-object trajectories on the ocean surface is critical for applications ranging from search-and-rescue to environmental tracking. This task remains however challenging due to the complex interplay of influencing factors such as ocean currents and winds. In…
-
Artikel Jurnal
Interpretable neural networks to predict momentum fluxes of orographic gravity waves
State-of-the-art Earth system models (ESMs) cannot explicitly resolve many small-scale atmospheric processes such as atmospheric gravity waves, and thus must represent, or parameterise, their effects on the resolved state. Machine learning (ML) has the potential to improve these parameterisations…
-
Artikel Jurnal
Towards generalized hydrological forecasting using transformer models for 120 h streamflow prediction
This study explores the efficacy of a transformer model for hourly streamflow prediction, generating forecasts up to 120 h ahead across 125 diverse locations in Iowa, US. Utilizing data from the preceding 72 h, including precipitation, evapotranspiration, and discharge values, we developed a…
-
Artikel Jurnal
An update of the LDEO fCO2-residual data product: algorithmic choices improve ocean carbon sink estimates
We evaluate the impact of various algorithmic design choices on reconstruction skill and estimated air–sea CO _2 flux using the Lamont–Doherty Earth Observatory fCO _2 -Residual machine learning data product. We reconstruct fCO _2 globally over the period 1982–2023 by optimizing the hyperparameter…
-
Artikel Jurnal
Seasonal forecast of sea surface temperatures via Neural ODEs
Global meteorological agencies provide seasonal forecasts based on indicators such as El Niño–Southern Oscillation and Indian Ocean variability. The NOAA operates forecasts up to 9 months, while the ECMWF offers extended predictions up to 13 months. However, these physics-based forecasting systems…
-
Artikel Jurnal
A variational approach at uncertainty estimation in data-driven rainfall-runoff modeling
Reliable uncertainty estimation is essential for decision making, evaluating model performance, and defining the limits of what can be inferred from data. While uncertainty estimation typically requires specifying prior assumptions about a distributional form, we introduce an approach to learn the…
-
Artikel Jurnal
Data curation strategies for geospatial machine learning: a case study in peatland classification
The quality of training datasets can have a large impact on machine learning models, yet this aspect of the pipeline frequently receives less scrutiny than it should. In the context of geospatial mapping from point-scale field data, quality control strategies to remove erroneous or misleading data…
-
Artikel Jurnal
Uncertainty-aware deep learning for wildfire danger forecasting
Wildfires are among the most severe natural hazards, posing a significant threat to both humans and natural ecosystems. The growing risk of wildfires increases the demand for forecasting models that are not only accurate but also reliable. deep learning (DL) has shown promise in predicting wildfire…