An official website of the United States government
We present a knowledge‐guided machine learning framework for operational hydrologic forecasting at the catchment scale. Our approach, a Factorized Hierarchical Neural Network (FHNN), has two main components: inverse and forward models. The inverse model uses observed precipitation, temperature, and streamflow data to generate a representation of the current underlying catchment state. The forward model predicts streamflow using the learned catchment state. The FHNN architecture is designed to model multi‐scale processes and capture their interactions, a critical ability for flood modeling. FHNN also improves forecasts based on real‐time data through an inference‐based data integration approach using inverse modeling. FHNN's data integration approach improves forecasts in response to observed data more efficiently than data assimilation methods that require computationally intensive optimization. We compare the FHNN to a leading deep learning alternative (autoregressive LSTM) on the large‐sample CAMELS‐US data set, and operational flood forecast data from the US National Weather Service (NWS). Official NWS flood forecasts are generated by expert human forecasters using a physics‐based model, in a human‐in‐the‐loop process. Thus, we assess the flood forecast ability of FHNN by directly comparing its performance against these NWS expert‐derived forecasts. The human forecaster creates a more accurate forecast within the first 12–18 hr of a forecast's issuance, but FHNN has significantly better predictions thereafter. This research lays the groundwork for leveraging the predictive performance of AI‐based models with the expertise in forecasting agencies to produce better river forecasts.
more »
« less
This content will become publicly available on August 21, 2027
WP-MIP: An Artificial Intelligence, Hybrid, and Physically Based Model Intercomparison Project for Weather Prediction
Abstract Rapid progress in the field of machine-learning for weather prediction has led to the emergence of algorithms whose forecasting skill can exceed that of traditional physically based models. This development represents an opportunity to improve the quality of forecasting services provided by operational centers, particularly given the speed at which machine-learning based models generate predictions. Despite the clear promise of these systems, questions remain about the ability of the current generation of machine-learning models to generate physically consistent predictions of the full suite of required forecast fields under all conditions. Answering these questions will require careful comparisons between the well-understood physically based models, current state-of-the-art machine-learning models, and the hybrid models that combine elements of these two archetypes. The Weather Prediction Model Intercomparison Project (WP-MIP) is a World Meteorological Organization-supported initiative whose initial goal is to create a centralized database of physically based, machine-learning, and hybrid model forecasts to enable a distributed assessment and evaluation effort. The first instance of WP-MIP focuses on global deterministic predictions using both center-specific and common initializations to facilitate sensitivity studies. Forecasts contributed by institutions across six continents will be used to develop AI-ready verification techniques that highlight the strengths and weaknesses of each class of prediction system, with the goal of establishing best-practice guidance to model developers and national weather centers. The broad engagement of the operational and forecast-evaluation communities in WP-MIP will ensure that the project’s results are highly relevant to the development and deployment of next-generation weather prediction systems.
more »
« less
- Award ID(s):
- 2530555
- PAR ID:
- 10710098
- Author(s) / Creator(s):
- ; ; ; ; ; ; ; ; ; ; ; ; ; ; ; ; ; ; ; more »
- Publisher / Repository:
- American Meteorological Society
- Date Published:
- Journal Name:
- Bulletin of the American Meteorological Society
- ISSN:
- 0003-0007
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
CoDiCast: Conditional Diffusion Model for Global Weather Forecasting with Uncertainty QuantificationAccurate weather forecasting is critical for science and society. However, existing methods have not achieved the combination of high accuracy, low uncertainty, and high computational efficiency simultaneously. On one hand, traditional numerical weather prediction (NWP) models are computationally intensive because of their complexity. On the other hand, most machine learning-based weather prediction (MLWP) approaches offer efficiency and accuracy but remain deterministic, lacking the ability to capture forecast uncertainty. To tackle these challenges, we propose a conditional diffusion model, CoDiCast, to generate global weather prediction, integrating accuracy and uncertainty quantification at a modest computational cost. The key idea behind the prediction task is to generate realistic weather scenarios at a future time point, conditioned on observations from the recent past. Due to the probabilistic nature of diffusion models, they can be properly applied to capture the uncertainty of weather predictions. Therefore, we accomplish uncertainty quantifications by repeatedly sampling from stochastic Gaussian noise for each initial weather state and running the denoising process multiple times. Experimental results demonstrate that CoDiCast outperforms several existing MLWP methods in accuracy, and is faster than NWP models in inference speed. Our model can generate 6-day global weather forecasts, at 6-hour steps and 5.625-degree latitude-longitude resolutions, for over 5 variables, in about 12 minutes on a commodity A100 GPU machine with 80GB memory. The source code is available at https://github.com/JimengShi/CoDiCast.more » « less
-
Reliable power systems are essential to modern life, as severe storms continue to disrupt grid stability and cause widespread outages. Predicting storm outages enables utilities and emergency managers to pre-stage resources and improve resilience. However, the several days of forecast lead time typically needed for preparedness significantly affect the accuracy of outage predictions. This study investigates the impact of forecast lead time on the error propagation of a Gradient Boosting Machine (GBM)-based outage prediction model (OPM) driven by Weather Research and Forecasting (WRF) model forecasts and analysis predictions. We evaluate three error-analysis scenarios: FFAP (forecast vs. analysis-based outage predictions), FFAO (forecast vs. actual outages), and LFAO (leave-one-storm-out forecast vs. actual outages). Model performance is compared using Mean Absolute Percentage Error (MAPE) and Centered Root-Mean-Square Error (CRMSE) across short (12 h–1 d), medium (2–3 d), and long (4–5 d) forecast lead-time categories, with the long category representing the upper end of the medium-range forecast window relevant to operational preparedness. The results show that forecast lead time substantially affects outage prediction accuracy, but the magnitude depends on the evaluation setup. In the controlled FFAP scenario, CRMSE increased by approximately 110% as lead time increased, from 259 to 543 outages, isolating the effect of weather forecast degradation. In the more operational LFAO scenario, CRMSE was already high at short lead times, increasing from 847 to 920 outages, indicating that model generalization error dominates once storms are unseen. Across scenarios, LFAO errors were 51% higher than FFAO errors at short lead times, highlighting the importance of testing outage models under unseen-event conditions. These results quantify how forecast degradation and model generalization jointly shape the reliability of outage prediction and provide practical guidance for lead-time-aware storm preparedness.more » « less
-
Abstract Over the last several years, artificial intelligence–based numerical weather prediction (AI-NWP) has emerged to become a promising tool in weather forecasting. Many models, like the ECMWF AI Forecasting System (AIFS) or Google DeepMind’s GraphCast, have been shown to outperform traditional NWP for particular metrics and variables. However, questions remain over their reliability in day-to-day use and when applied to extreme weather events. Further analysis is critical to properly compare these systems with traditional methods. This study will analyze the performance of three leading AI-NWP systems for high-impact winter weather along the U.S. East Coast with a goal of identifying systematic errors or improvements in predictions. Several key variables, including the quantitative precipitation forecast, are examined from both deterministic and ensemble-based perspectives. Evaluation of a collection of storms against reanalysis and other observations affirms the ability for AI-NWP to outperform traditional methods by up to 20%–30% for standard metrics like root-mean-square error (RMSE) over a regional domain. Additionally, AI-NWP is shown to be capable of recognizing key high-amplitude winter storm features, like conveyor belts, even at long forecast lead times (7–10 days). Analysis of an ensemble sensitivity test applied to GraphCast track errors displays physically realistic upper-level drivers when compared against a physics-based ensemble. By examining the performance of traditional NWP and AI-NWP at predicting winter storm features as a function of lead time, the practical predictability of snowstorms is reevaluated. As a result, this work can allow for meteorologists to have higher confidence when utilizing AI-NWP in an operational setting. Significance StatementArtificial intelligence methods for weather prediction are rapidly expanding in popularity among weather forecasters, research meteorologists, and the general meteorological community. Given their rise in use, it is paramount that a robust understanding of the accuracy of these systems is developed in various cases. Many studies from model developers have shown positive performance for these systems on global scales compared to traditional baselines. However, these results often leave out many areas of interest in weather prediction, including for anomalous weather events and when considering smaller spatial scales. This study will attempt to provide clearer insight into some of these questions with respect to one type of high-impact weather event: winter storms in the eastern United States.more » « less
-
The ever-increasing demand for energy is resulting in considerable carbon emissions from the electricity grid. In recent years, there has been growing attention on demand-side optimizations to reduce carbon emissions from electricity usage. A vital component of these optimizations is short-term forecasting of the carbon intensity of the grid-supplied electricity. Many recent forecasting techniques focus on day-ahead forecasts, but obtaining such forecasts for longer periods, such as multiple days, while useful, has not gotten much attention. In this paper, we present CarbonCast, a machine-learning-based hierarchical approach that provides multi-day forecasts of the grid's carbon intensity. CarbonCast uses neural networks to first generate production forecasts for all the electricity-generating sources. It then uses a hybrid CNN-LSTM approach to combine these first-tier forecasts with historical carbon intensity data and weather forecasts to generate a carbon intensity forecast for up to four days. Our results show that such a hierarchical design improves the robustness of the predictions against the uncertainty associated with a longer multi-day forecasting period. We analyze which factors most influence the carbon intensity forecasts of any region with a specific mixture of electricity-generating sources and also show that accurate source production forecasts are vital in obtaining precise carbon intensity forecasts. CarbonCast's 4-day forecasts have a MAPE of 3.42--19.95% across 13 geographically distributed regions while outperforming state-of-the-art methods. Importantly, CarbonCast is the first open-sourced tool for multi-day carbon intensity forecasts where the code and data are freely available to the research community.more » « less
