Search NASA⌕ Search

SEARCH · Search NASA

Results for “Distributed training”

Search indexed NASA NTRS and DOE OSTI research on propulsion, heat transfer, battery materials and energy systems. Follow report and document links to the original sources.

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 1,279 records · Page 71

The PAU Survey: narrow-band photometric redshifts using Gaussian processes

Here, we study the performance of the hybrid template machine learning photometric redshift (photo- z ) algorithm delight , which uses Gaussian processes, on a subset of the early data release of the Physics of the Accelerating Universe Survey (PAUS). We calibrate the fluxes of the 40 PAUS narrow bands with six broad-band fluxes ( uBVriz ) in the Cosmic Evolution Survey (COSMOS) field using three different methods, including a new method that utilizes the correlation between the apparent size and overall flux of the galaxy. We use a rich set of empirically derived galaxy spectral templates as guides to train the Gaussian process, and we show that our results are competitive with other standard photometric redshift algorithms. delight achieves a photo- z 68th percentile error of σ 68 = 0.0081(1 + z ) without any quality cut for galaxies with i auto < 22.5 as compared to 0.0089(1 + z ) and 0.0202(1 + z ) for the bpz and annz 2 codes, respectively. delight is also shown to produce more accurate probability distribution functions for individual redshift estimates than bpz and annz 2. Common photo- z outliers of delight and bcnz 2 (previously applied to PAUS) are found to be primarily caused by outliers in the narrow-band fluxes, with a small number of cases potentially indicating spectroscopic redshift failures in the reference sample. In the process, we introduce performance metrics derived from the results of bcnz 2 and delight , allowing us to achieve a photo- z quality of σ 68 < 0.0035(1 + z ) at a magnitude of i auto < 22.5 while keeping 50 per cent objects of the galaxy sample.

79 ASTRONOMY AND ASTROPHYSICS↗

Time-Based CAN IDS Paper Results Code

Modern vehicles are complex cyber-physical systems made of hundreds of electronic control units (ECUs) that communicate over controller area networks (CANs). This inherited complexity has expanded the CAN attack surface which is vulnerable to message injection attacks. These injections change the overall timing characteristics of messages on the bus, and thus, to detect these malicious messages, time-based intrusion detection systems (IDSs) have been proposed. However, time-based IDSs are usually trained and tested on low-fidelity datasets with unrealistic, labeled attacks. This makes difficult the task of evaluating, comparing, and validating IDSs. Here we detail and benchmark four time-based IDSs against the newly published ROAD dataset, the first open CAN IDS dataset with real (non-simulated) stealthy attacks with physically verified effects. We found that methods that perform hypothesis testing by explicitly estimating message timing distributions have lower performance than methods that seek anomalies in a distribution related statistic. In particular, these “distribution-agnostic” based methods outperform “distribution-based” methods by at least 55% in area under the precision-recall curve (AUC-PR). Our results expand the body of knowledge of CAN time-based IDSs by providing details of these methods and reporting their results when tested on datasets with real advanced attacks. Finally, we develop an after-market plug-in detector using lightweight hardware, which can be used to deploy the best performing IDS method on nearly any vehicle.

Moriano, Pablo [Oak Ridge National Lab. (ORNL), Oa↗

Models, data, and scripts associated with “Prediction of Distributed River Sediment Respiration Rates using Community-Generated Data and Machine Learning”

This data package is associated with the publication “Prediction of Distributed River Sediment Respiration Rates using Community-Generated Data and Machine Learning’’ submitted to the Journal of Geophysical Research: Machine Learning and Computation (Scheibe et al. 2024). River sediment respiration observations are expensive and labor intensive to obtain and there is no physical model for predicting this quantity. The Worldwide Hydrobiogeochemisty Observation Network for Dynamic River Systems (WHONDRS) observational data set (Goldman et al.; 2020) is used to train machine learning (ML) models to predict respiration rates at unsampled sites. This repository archives training data, ML models, predictions, and model evaluation results for the purposes of reproducibility of the results in the associated manuscript and community reuse of the ML models trained in this project. One of the key challenges in this work was to find an optimum configuration for machine learning models to work with this feature-rich (i.e. 100+ possible input variables) data set. Here, we used a two-tiered approach to managing the analysis of this complex data set: 1) a stacked ensemble of ML models that can automatically optimize hyperparameters to accelerate the process of model selection and tuning and 2) feature permutation importance to iteratively select the most important features (i.e. inputs) to the ML models. The major elements of this ML workflow are modular, portable, open, and cloud-based, thus making this implementation a potential template for other applications. This data package is associated with the GitHub repository found at Please see the file level metadata (flmd; “sl-archive-whondrs_flmd.csv”) for a list of all files contained in this data package and descriptions for each. Please see the data dictionary (dd; “sl-archive-whondrs_dd.csv”) for a list of all column headers contained within comma separated value (csv) files in this data package and descriptions for each. The GitHub repository is organized into five top-level directories: (1) “input_data” holds the training data for the ML models; (2) “ml_models” holds machine learning models trained on the data in “input_data”; (3) “scripts” contains data preprocessing and postprocessing scripts and intermediate results specific to this data set that bookend the ML workflow; (4) “examples” contains the visualization of the results in this repository including plotting scripts for the manuscript (e.g., model evaluation, FPI results) and scripts for running predictions with the ML models (i.e., reusing the trained ML models); (5) “output_data” holds the overall results of the ML model on that branch. Each trained ML model resides on its own branch in the repository; this means that inputs and outputs can be different branch-to-branch. Furthermore, depending on the number of features used to train the ML models, the preprocessing and postprocessing scripts, and their intermediate results, can also be different branch-to-branch. The “main-*” branches are meant to be starting points (i.e. trunks) for each model branch (i.e. sprouts). Please see the Branch Navigation section in the top-level README.md in the GitHub repository for more details. There is also one hidden directory “.github/workflows”. This hidden directory contains information for how to run the ML workflow as an end-to-end automated GitHub Action but it is not needed for reusing the ML models archived here. Please the top-level README.md in the GitHub repository for more details on the automation.

13C↗

AI-Based Faster-Than-Real-Time Stability Assessment of Large Power Systems with Applications on WECC System

Achieving clean energy goals will require significant advances in regard to addressing the computational needs for next-generation renewable-dominated power grids. One critical obstacle that lies in the way of transitioning today’s power grid to a renewable-dominated power grid is the lack of a faster-than-real-time stability assessment technology for operating a fast-changing power grid. This paper proposes an artificial intelligence (AI) -based method that predicts the system’s stability margin information (e.g., the frequency nadir in the frequency stability assessment and the critical clearing time (CCT) value in the transient stability assessment) directly from the system operating conditions without performing the conventional time-consuming time-domain simulations over detailed dynamic models. Since the AI method shifts the majority of the computational burden to offline training, the online evaluation is extremely fast. This paper has tested the AI-based stability assessment method using multiple dispatch cases that are converted and tuned from actual dispatch cases of the Western Electricity Coordinating Council (WECC) system model with more than 20,000 buses. The results show that the AI-based method could accurately predict the stability margin of such a large power system in less than 0.2 milliseconds using the offline-trained AI agent. Therefore, the proposed method has great potential to achieve faster-than-real-time stability assessment for practical large power systems while preserving sufficient accuracy.

24 POWER TRANSMISSION AND DISTRIBUTION↗

Preparing Los Alamos National Laboratory's Waste Management Program for the Future - 12175

The waste management program at Los Alamos National Laboratory (LANL) is undergoing significant transition to establish a lean highly functioning waste management program that will succeed the large environmental cleanup waste management program. In the coming years, the environmental cleanup activities will be mostly completed and the effort will change to long-term stewardship. What will remain in waste management is a smaller program focused on direct off-site shipping to cost-effectively enable the enduring mission of the laboratory in support of the national nuclear weapons program and fundamental science and research. It is essential that LANL implement a highly functioning efficient waste management program in support of the core missions of the national weapons program and fundamental science and research - and LANL is well on the way to that goal. As LANL continues the transition process, the following concepts have been validated: - Business drivers including the loss of onsite disposal access and completion of major environmental cleanup activities will drive large changes in waste management strategies and program. - A well conceived organizational structure; formal management systems; a customer service attitude; and enthusiastic managers are core to a successful waste management program. - During times of organizational transition, a project management approach to managing change in a complex work place with numerous complex deliverables is successful strategy. - Early and effective engagement with waste generators, especially Project Managers, is critical to successful waste planning. - A well-trained flexible waste management work force is vital. Training plans should include continuous training as a strategy. - A shared fate approach to managing institutional waste decisions, such as the LANL Waste Management Recharge Board is effective. - An efficient WM program benefits greatly from modern technology and innovation in managing waste data and reports. - Use of six-sigma tools can help improve the quality and efficiency of waste management processes. - A fair, easy to understand, transparent, and well-overseen process for distributing the cost of waste disposal and waste program oversight is essential. (authors)

12 MANAGEMENT OF RADIOACTIVE AND NON-RADIOACTIVE W↗

Computational Framework for Machine-Learning-Enabled 13 C Fluxomics

13 C metabolic flux analysis (MFA) has emerged as a powerful tool for synthetic biology. This optimization-based approach suffers long computation time and unstable solutions depending on the initial guess. Here, we develop a machine-learning-based framework for 13 C fluxomics. Specifically, training and test data sets are generated by metabolic network decomposition and flux sampling, in which flux ratios at metabolic nodes and simulated labeling patterns of metabolites are used as training targets and features, respectively. To improve prediction accuracy and simplify the model, automated processes are developed for flux ratio selection based on solvability and feature screening based on importance. We found that predictive performance can be significantly improved using both amino acids and central carbon metabolites in comparison with amino acids alone. Together with measured external fluxes, the predicted flux ratios determine the mass balance system, yielding global flux distributions. This approach is validated by flux estimation using both simulated and experimental data in comparison with canonical 13 C MFA. The approach represents a reliable fluxomics method readily applicable to high-throughput metabolic phenotyping, which highlights the advances of intelligent learning algorithms in synthetic biology, specifically in the Test and Learn stage of the Design-Build-Test-Learn cycle.

13C metabolic flux analysis↗

Use of vision and sound to classify feller-buncher operational state

Productivity measures in logging involve simultaneous recognition and classification of event occurrence and timing, and the volume of stems being handled. In full-tree felling systems these measurements are difficult to implement in an autonomous manner because of the unfavorable working environment and the abundance of confounding extraneous events. This paper proposed a vision method that used a lowcost camera to recognize feller-buncher operational events including tree cutting and piling. It used a fine K-nearest neighbors (fKNN) algorithm as the final classifier based on both audio and video features derived from short video segments as inputs. The classifier’s calibration accuracy exceeds 94%. The trained model was tested on videos recorded under various conditions. The overall accurate rates for short segments were greater than 89%. Comparisons were made between the human- and algorithm derived event detection rates, events’ durations, and inter-event timing using continuously recorded videos taken during feller operation. Video results between the fKNN model and manual observation were similar. Statistical comparison using the Kolmogorov–Smirnov test to evaluate measured parameters’ distributions (manual versus automated event duration and inter-event timing) did not show significant differences with the lowest P-value among all Kolmogorov–Smirnov tests equal to 0.12. Here the result indicated the feasibility and potential of using the method for the automatic time study of drive-to-tree feller bunchers.

97 MATHEMATICS AND COMPUTING↗

Improvement of stability of Nb 3 Sn superconductors by introducing high specific heat substances

High-J c Nb 3 Sn conductors have low stability against perturbations, which accounts for the slow training rates of high-field Nb 3 Sn magnets. While it is known that adding substances with high specific heat (C) into Nb 3 Sn wires can increase their overall specific heat and thus improve their stability, there has not been a practical method that is compatible with the fabrication of long-length conductors. In this work, we put forward a scheme to introduce such substances to distributed-barrier Nb 3 Sn wires, which adds minimum difficulty to the wire manufacturing process. Multifilamentary wires using a mixture of Cu and high-C Gd 2 O 3 powders have been successfully fabricated along this line. Measurements showed that addition of Gd 2 O 3 had no negative effects on residual resitivity ratio or non-Cu J c , and that flux jumps were remarkably reduced, and minimum quench energy values at 4.2 K, 14 T were increased by a factor of three, indicating that stability was significantly improved. We also discussed the influences of the positioning of high-C substances and their thermal diffusivity on their effectiveness in reducing the superconductor temperature rise against perturbations. Based on these results, we proposed an optimized conductor architecture to maximize the effectiveness of this approach.

43 PARTICLE ACCELERATORS↗

Improved detection of low-frequency within-host variants from deep sequencing: A case study with human papillomavirus

Abstract High-coverage sequencing allows the study of variants occurring at low frequencies within samples, but is susceptible to false-positives caused by sequencing error. Ion Torrent has a very low single nucleotide variant (SNV) error rate and has been employed for the majority of human papillomavirus (HPV) whole genome sequences. However, benchmarking of intrahost SNVs (iSNVs) has been challenging, partly due to limitations imposed by the HPV life cycle. We address this problem by deep sequencing three replicates for each of 31 samples of HPV type 18 (HPV18). Errors, defined as iSNVs observed in only one of three replicates, are dominated by C→T (G→A) changes, independently of trinucleotide context. True iSNVs, defined as those observed in all three replicates, instead show a more diverse SNV type distribution, with particularly elevated C→T rates in CCG context (CCG→CTG; CGG→CAG) and C→A rates in ACG context (ACG→AAG; CGT→CTT). Characterization of true iSNVs allowed us to develop two methods for detecting true variants: (1) VCFgenie, a dynamic binomial filtering tool which uses each variant’s allele count and coverage instead of fixed frequency cut-offs; and (2) a machine learning binary classifier which trains eXtreme Gradient Boosting models on variant features such as quality and trinucleotide context. Each approach outperforms fixed-cut-off filtering of iSNVs, and performance is enhanced when both are used together. Our results provide improved methods for identifying true iSNVs in within-host applications across sequencing platforms, specifically using HPV18 as a case study.

Virology↗

GCoD: Graph Convolutional Network Acceleration via Dedicated Algorithm and Accelerator Co-Design

Graph Convolutional Networks (GCNs) have emerged as the state-of-the-art graph learning model. However, it remains notoriously challenging to inference GCNs over large graph datasets, limiting their application to large real-world graphs and hindering the exploration of deeper and more sophisticated GCN graphs. This is because real-world graphs can be extremely large and sparse. Furthermore, the node degree of GCNs tends to follow the power-law distribution and therefore have highly irregular adjacency matrices, resulting in prohibitive inefficiencies in both data processing and movement and thus substantially limiting the achievable GCN acceleration efficiency. To this end, this paper proposes the first GCN algorithm and accelerator Co-Design framework dubbed GCoD which can largely alleviate the aforementioned GCN irregularity and boost GCNs' inference efficiency. Specifically, on the algorithm level, GCoD integrates a divide and conquer GCN training strategy that polarizes the graphs to be either denser or sparser in local neighborhoods without compromising the model accuracy, resulting in graph adjacency matrices that (mostly) have merely two levels of workload and enjoys largely enhanced regularity and thus ease of acceleration. On the hardware level, we further develop a dedicated two-pronged accelerator with a separated engine to process each of the aforementioned workloads, further boosting the overall utilization and acceleration efficiency. Extensive experiments and ablation studies validate that our GCoD consistently outperforms state-of-the-art designs in terms of accelerator efficiency while maintaining or even improving the task accuracy. Additionally, we visualize GCoD trained graph adjacency matrices to better understand its advantages. All codes and pre-trained models will be released upon acceptance.

You, Haoran↗

Transition to Online Cable Insulation Condition Monitoring

Nuclear power plant cables were originally qualified for 40 year life and generally have not required specific test verification to assure service availability through the initial plant qualification period. However, license renewals to 60 and 80 years of operation require a cable aging management program that depends on some form of test and verification to assure fitness for service. Environmental stress (temperature, radiation, chemicals, water, and mechanical) varies dramatically within a nuclear power plant and, in some cases, cables have degraded and required repair or replacement before their qualified end-of-life period. In other cases, cable conditions have been mild and dependable cable performance confirmed to extend well beyond the initial qualified life. Most offline performance-based testing requires cables to be de-coupled and de-energized for specially trained technicians to perform testing. These offline tests constitute an expensive operational burden that limits the economic viability of nuclear power plants. Although initial investment may be higher, new online test practices are emerging as options or complements to offline testing that avoid or minimize the regularly scheduled offline test burden. These online methods include electrical and fiber-optic partial discharge measurement, spread spectrum time or frequency domain reflectometry, distributed temperature profile measurements, and local interdigital capacitance measurement of insulation characteristics. Introduction of these methods must be supported by research to confirm efficacy plus either publicly financed or market driven investment to support the start-up expense of cost-effective instrumentation to monitor cable condition and assure reliable operation. This work summarizes various online cable assessment technologies plus introduces a new cable motor test bed to assess some of these technologies in a controlled test environment.

Glass, Samuel W.↗

Continual Learning for Particle Accelerators

Particle accelerators operate under dynamically changing conditions, which often lead to data distribution drifts. These drifts pose significant challenges for Machine Learning (ML) models, which typically fail to maintain performance when faced with such non-stationary data. In particle accelerators, the primary sources of these data drifts include changes in accelerator settings and non-measured parameters such as machine degradation and environmental factors. Previous research has proposed conditional models to handle multiple beam configurations effectively; however, it is challenging to train the ML models on all possible configuration settings. Additionally, conditional models alone can not address performance degradation caused by drifts due to non-measured factors. These limitations contribute to a significant gap between ML development and its deployment in real-world operational settings. To bridge this gap, in this paper, we identify some of the key areas within particle accelerators where continual learning can help mitigate drift-induced performance degradation. In addition, we present a practical use case where a conditional Auto-Encoder model coupled with memory-based continual learning has been employed to demonstrate stable performance even when underlying data drifts.

Schram, Malachi [Thomas Jefferson National Acceler↗

A Nonparametric Method for the Inference of Halo Occupation Distributions

The galaxy–halo connection traces processes by which galaxies form and evolve. The halo occupation distribution (HOD) describes the relationship between galaxies and their host dark matter haloes. Measurements of the galaxy two-point correlation function (2PCF) allow us to extract information about the HODs of observed galaxy samples. Several parametric HOD models have been proposed in the literature, but the choice of parameterization restricts the space of possible HODs. To resolve this issue, we introduce a nonparametric HOD fitting method in which we train an emulator to learn the mappings among the galaxy 2PCF, physical properties used to select galaxy samples, and the HOD, all obtained from simulated past light cones constructed with the Santa Cruz semianalytic model. Implementing this emulator within a likelihood analysis framework, we derive constraints on the HOD of a galaxy sample when provided with a measurement of its 2PCF. Using the emulator to accelerate likelihood evaluations, we test the nonparametric HOD approach on a set of 2PCFs for mock galaxy samples drawn from the TNG100-1 simulation and selected above threshold values of stellar mass and star formation rate. Our framework is able to recover TNG100-1 HODs within 0.2 dex. We use the TNG100-1 mocks to tune the reported uncertainties to estimate those expected in the analysis of observations. Comparing to parametric HOD modelling routines applied to the same mock galaxy samples, our approach consistently infers the HOD with comparable or greater precision and accuracy.

Kennedy, Jacob [Rutgers Univ., Piscataway, NJ (Uni↗

Continual Learning for Particle Accelerators

Particle accelerators operate under dynamically changing conditions, which often lead to data distribution drifts. These drifts pose significant challenges for Machine Learning (ML) models, which typically fail to maintain performance when faced with such non-stationary data. In particle accelerators, the primary sources of these data drifts include changes in accelerator settings and non-measured parameters such as machine degradation and environmental factors. Previous research has proposed conditional models to handle multiple beam configurations effectively; however, it is challenging to train the ML models on all possible configuration settings. Additionally, conditional models alone can not address performance degradation caused by drifts due to non-measured factors. These limitations contribute to a significant gap between ML development and its deployment in real-world operational settings. To bridge this gap, in this paper, we identify some of the key areas within particle accelerators where continual learning can help mitigate drift-induced performance degradation. In addition, we present a practical use case where a conditional Auto-Encoder model coupled with memory-based continual learning has been employed to demonstrate stable performance even when underlying data drifts

Rajput, Kishansingh [Thomas Jefferson National Acc↗

Heuristic Dynamic Programming for Adaptive Virtual Synchronous Generators

In this paper a neural network heuristic dynamic programing (HDP) is used for optimal control of the virtual inertia-based control of grid connected three-phase inverters. It is shown that the conventional virtual inertia controllers are not suited for non-inductive grids. A neural network-based controller is proposed to adapt to any impedance angle. Applying an adaptive dynamic programming controller instead of a supervised controlled method enables the system to adjust itself to different conditions. The proposed HDP consists of two subnetworks: critic network and action network. These networks can be trained during the same training cycle to decrease the training time. The simulation results confirm that the proposed neural network HDP controller performs better than the traditional direct-fed voltage and/or reactive power controllers in virtual inertia control schemes.

24 POWER TRANSMISSION AND DISTRIBUTION↗

Proposed Critical Thinking Metrics for Power Grid Trainees

The TRS Intro to Critical Thinking for Operational Decision-Making course for power grid operators seeks to help trainees improve their use of critical thinking skills in operation environments. To determine the effectiveness of this training, we have identified 3 categories of evaluation measures: critical thinking metrics, situation awareness (SA) evaluations, and behavioral observations. Critical thinking metrics seek to directly measure trainee’s ability to use critical thinking skills through their verbalized responses to different questions or scenarios. SA will be evaluated during various points throughout simulated exercises completed during the training. SA evaluations aim to determine the level of a trainee’s ability to perceive, comprehend and anticipate events in the operational environment. This construct will be assessed through verbalized responses to questions informed by the Situation Awareness Global Assessment Technique (SAGAT). Behavioral observations capture how trainees use the system, including which simulator displays or windows they use or actions they perform and in what order. These observations help us understand how the critical thinking training may inform operator action. We hypothesize that while these measures are correlated with each other, they provide different perspectives on each trainee’s ability to gain SA and use critical thinking skills in operation environments. By comparing these measures in a pre-assessment and a post-assessment, we can determine how much improvement a trainee gains through the training. These measures may also be used during the training as appropriate. This document specifies these 3 categories of measures, which components of these measures currently seem to be the best candidates to use in the training course, and which parts of the training course is related to each component.

24 POWER TRANSMISSION AND DISTRIBUTION↗

PreMevE‐MEO: Predicting Ultra‐Relativistic Electrons Using Observations From GPS Satellites

Abstract Ultra‐relativistic electrons with energies greater than or equal to two megaelectron‐volt (MeV) pose a major radiation threat to spaceborne electronics, and thus specifying those highly energetic electrons has a significant meaning to space weather communities. Here we report the latest progress in developing our predictive model for MeV electrons in the outer radiation belt. The new version, primarily driven by electron measurements made along medium‐Earth‐orbits (MEO), is called PREdictive MEV Electron (PreMevE)‐MEO model that nowcasts ultra‐relativistic electron flux distributions across the whole outer belt. Model inputs include >2 MeV electron fluxes observed in MEOs by a fleet of GPS satellites as well as electrons measured by one Los Alamos satellite in the geosynchronous orbit. We developed an innovative Sparse Multi‐Inputs Latent Ensemble NETwork (SmileNet) which combines convolutional neural networks with transformers, and we used long‐term in situ electron data from NASA's Van Allen Probes mission to train, validate, optimize, and test the model. It is shown that PreMevE‐MEO can provide hourly nowcasts with high model performance efficiency and high correlation with observations. This prototype PreMevE‐MEO model demonstrates the feasibility of making high‐fidelity predictions driven by observations from longstanding space infrastructure in MEO, thus has great potential of growing into an invaluable space weather operational warning tool.

79 ASTRONOMY AND ASTROPHYSICS↗

Improving Monsoon Precipitation Prediction Using Combined Convolutional and Long Short Term Memory Neural Network

Precipitation downscaling is widely employed for enhancing the resolution and accuracy of precipitation products from general circulation models (GCMs). In this study, we propose a novel statistical downscaling method to foster GCMs’ precipitation prediction resolution and accuracy for the monsoon region. We develop a deep neural network composed of a convolution and Long Short Term Memory (LSTM) recurrent module to estimate precipitation based on well-resolved atmospheric dynamical fields. The proposed model is compared against the GCM precipitation product and classical downscaling methods in the Xiangjiang River Basin in South China. Results show considerable improvement compared to the European Centre for Medium-Range Weather Forecasts (ECMWF)-Interim reanalysis precipitation. Also, the model outperforms benchmark downscaling approaches, including (1) quantile mapping, (2) the support vector machine, and (3) the convolutional neural network. To test the robustness of the model and its applicability in practical forecasting, we apply the trained network for precipitation prediction forced by retrospective forecasts from the ECMWF model. Compared to the ECMWF precipitation forecast, our model makes better use of the resolved dynamical field for more accurate precipitation prediction at lead times from 1 day up to 2 weeks. This superiority decreases with the forecast lead time, as the GCM’s skill in predicting atmospheric dynamics is diminished by the chaotic effect. Finally, we build a distributed hydrological model and force it with different sources of precipitation inputs. Hydrological simulation forced with the neural network precipitation estimation shows significant advantage over simulation forced with the original ERA-Interim precipitation (with NSE value increases from 0.06 to 0.64), and the performance is only slightly worse than the observed precipitation forced simulation (NSE = 0.82). This further proves the value of the proposed downscaling method, and suggests its potential for hydrological forecasts.

54 ENVIRONMENTAL SCIENCES↗