SEARCH · Engineering Papers

Results for “predicted”

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.

SourceResearch connectionFrom yearThrough year

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

At least 775 records · Page 43

All sources NASA NTRS DOE OSTI

DOE OSTI2015

MO-G-304-02: Knowledge Based DVH Prediction Using a Geometric Dose Transform

Purpose: To demonstrate a novel method for predicting patient dose-volume histograms (DVHs) using a prior database of optimized radiotherapy treatment plans. Such predicted DVHs could be useful for automating treatment planning. Methods: Our initial demonstration utilized a database of 100 prostate intensity-modulated radiotherapy (IMRT) data-sets. Each data-set contained a CT image with contours of the planning target volume (PTV), rectum, and bladder, the parameters of a clinically approved IMRT plan, and a corresponding simulated dose distribution. We applied a novel geometric transformation to remove the influence of the PTV size, shape, and location on the dose distribution. We termed the transformed distribution the geometrically normalized dose distribution (GNDD). This normalization transform was applied to 80 data-sets randomly selected from the database, and a population GNDD was computed as the average. Next, the population GNDD was mapped onto each of the remaining 20 patient datasets using the reverse of the geometric normalization transform, and predicted DVHs were calculated from the reverse transformed dose distributions (GNDD-DVHs). In addition, a state of the art machine learning based method from the literature was tested for comparison. Results: DVH prediction accuracy was quantified by calculating the relative root mean squared error (rRMSE) on predicted DVHs for the 20 test patients using their known DVHs. For bladder, rectum, and PTV average rRMSEs for the GNDD method were 9.7 ± 4.2%, 13.9 ± 6.0%, and 2.3 ± 0.5% respectively. Prediction results using GNDD were roughly equivalent to that from the machine learning method. Conclusion: We developed a new method for predicting DVH curves from a database of prior patient plans. We demonstrated that our simple approach achieves accuracy comparable to a method using a complicated machine learning based approach.

60 APPLIED LIFE SCIENCES↗

DOE OSTI2015

TU-G-BRA-03: Predicting Radiation Therapy Induced Ventilation Changes Using 4DCT Jacobian Calculations

Purpose: Longitudinal changes in lung ventilation following radiation therapy can be mapped using four-dimensional computed tomography(4DCT) and image registration. This study aimed to predict ventilation changes caused by radiation therapy(RT) as a function of pre-RT ventilation and delivered dose. Methods: 4DCT images were acquired before and 3 months after radiation therapy for 13 subjects. Jacobian ventilation maps were calculated from the 4DCT images, warped to a common coordinate system, and a Jacobian ratio map was computed voxel-by-voxel as the ratio of post-RT to pre-RT Jacobian calculations. A leave-one-out method was used to build a response model for each subject: post-RT to pre-RT Jacobian ratio data and dose distributions of 12 subjects were applied to the subject’s pre-RT Jacobian map to predict the post-RT Jacobian. The predicted Jacobian map was compared to the actual post-RT Jacobian map to evaluate efficacy. Within this cohort, 8 subjects had repeat pre-RT scans that were compared as a reference for no ventilation change. Maps were compared using gamma pass rate criteria of 2mm distance-to-agreement and 6% ventilation difference. Gamma pass rates were compared using paired t-tests to determine significant differences. Further analysis masked non-radiation induced changes by excluding voxels below specified dose thresholds. Results: Visual inspection demonstrates the predicted post-RT ventilation map is similar to the actual map in magnitude and distribution. Quantitatively, the percentage of voxels in agreement when excluding voxels receiving below specified doses are: 74%/20Gy, 73%/10Gy, 73%/5Gy, and 71%/0Gy. By comparison, repeat scans produced 73% of voxels within the 6%/2mm criteria. The agreement of the actual post-RT maps with the predicted maps was significantly better than agreement with pre-RT maps (p<0.02). Conclusion: This work validates that significant changes to ventilation post-RT can be predicted. The differences between the predicted and actual outcome are similar to differences between repeat scans with equivalent ventilation. This work was supported by NIH grant CA166703 and a Pilot Grant from University of Iowa Carver College of Medicine.

60 APPLIED LIFE SCIENCES↗

DOE OSTI2015

Prediction of standard-dose brain PET image by using MRI and low-dose brain [{sup 18}F]FDG PET images

Purpose: Positron emission tomography (PET) is a nuclear medical imaging technology that produces 3D images reflecting tissue metabolic activity in human body. PET has been widely used in various clinical applications, such as in diagnosis of brain disorders. High-quality PET images play an essential role in diagnosing brain diseases/disorders. In practice, in order to obtain high-quality PET images, a standard-dose radionuclide (tracer) needs to be used and injected into a living body. As a result, it will inevitably increase the patient’s exposure to radiation. One solution to solve this problem is predicting standard-dose PET images using low-dose PET images. As yet, no previous studies with this approach have been reported. Accordingly, in this paper, the authors propose a regression forest based framework for predicting a standard-dose brain [{sup 18}F]FDG PET image by using a low-dose brain [{sup 18}F]FDG PET image and its corresponding magnetic resonance imaging (MRI) image. Methods: The authors employ a regression forest for predicting the standard-dose brain [{sup 18}F]FDG PET image by low-dose brain [{sup 18}F]FDG PET and MRI images. Specifically, the proposed method consists of two main steps. First, based on the segmented brain tissues (i.e., cerebrospinal fluid, gray matter, and white matter) in the MRI image, the authors extract features for each patch in the brain image from both low-dose PET and MRI images to build tissue-specific models that can be used to initially predict standard-dose brain [{sup 18}F]FDG PET images. Second, an iterative refinement strategy, via estimating the predicted image difference, is used to further improve the prediction accuracy. Results: The authors evaluated their algorithm on a brain dataset, consisting of 11 subjects with MRI, low-dose PET, and standard-dose PET images, using leave-one-out cross-validations. The proposed algorithm gives promising results with well-estimated standard-dose brain [{sup 18}F]FDG PET image and substantially enhanced image quality of low-dose brain [{sup 18}F]FDG PET image. Conclusions: In this paper, the authors propose a framework to generate standard-dose brain [{sup 18}F]FDG PET image using low-dose brain [{sup 18}F]FDG PET and MRI images. Both the visual and quantitative results indicate that the standard-dose brain [{sup 18}F]FDG PET can be well-predicted using MRI and low-dose brain [{sup 18}F]FDG PET.

60 APPLIED LIFE SCIENCES↗

DOE OSTI2016

SU-F-P-20: Predicting Waiting Times in Radiation Oncology Using Machine Learning

Purpose: Waiting times remain one of the most vexing patient satisfaction challenges facing healthcare. Waiting time uncertainty can cause patients, who are already sick or in pain, to worry about when they will receive the care they need. These waiting periods are often difficult for staff to predict and only rough estimates are typically provided based on personal experience. This level of uncertainty leaves most patients unable to plan their calendar, making the waiting experience uncomfortable, even painful. In the present era of electronic health records (EHRs), waiting times need not be so uncertain. Extensive EHRs provide unprecedented amounts of data that can statistically cluster towards representative values when appropriate patient cohorts are selected. Predictive modelling, such as machine learning, is a powerful approach that benefits from large, potentially complex, datasets. The essence of machine learning is to predict future outcomes by learning from previous experience. The application of a machine learning algorithm to waiting time data has the potential to produce personalized waiting time predictions such that the uncertainty may be removed from the patient’s waiting experience. Methods: In radiation oncology, patients typically experience several types of waiting (eg waiting at home for treatment planning, waiting in the waiting room for oncologist appointments and daily waiting in the waiting room for radiotherapy treatments). A daily treatment wait time model is discussed in this report. To develop a prediction model using our large dataset (with more than 100k sample points) a variety of machine learning algorithms from the Python package sklearn were tested. Results: We found that the Random Forest Regressor model provides the best predictions for daily radiotherapy treatment waiting times. Using this model, we achieved a median residual (actual value minus predicted value) of 0.25 minutes and a standard deviation residual of 6.5 minutes. This means that the majority of our estimates are within 6.5 minutes of the actual wait time. Conclusion: The goal of this project was to define an appropriate machine learning algorithm to estimate waiting times based on the collective knowledge and experience learned from previous patients. Our results offer an opportunity to improve the information that is provided to patients and family members regarding the amount of time they can expect to wait for radiotherapy treatment at our centre. AJ acknowledges support by the CREATE Medical Physics Research Training Network grant of the Natural Sciences and Engineering Research Council (Grant number: 432290) and from the 2014 Q+ Initiative of the McGill University Health Centre.

60 APPLIED LIFE SCIENCES↗

DOE OSTI2021

The Prediction Model of Risk Factors for COVID-19 Developing into Severe Illness Based on 1046 Patients with COVID-19

This study analyzed the risk factors for patients with COVID-19 developing severe illnesses and explored the value of applying the logistic model combined with ROC curve analysis to predict the risk of severe illnesses at COVID-19 patients’ admissions. The clinical data of 1046 COVID-19 patients admitted to a designated hospital in a certain city from July to September 2020 were retrospectively analyzed, the clinical characteristics of the patients were collected, and a multivariate unconditional logistic regression analysis was used to determine the risk factors for severe illnesses in COVID-19 patients during hospitalization. Based on the analysis results, a prediction model for severe conditions and the ROC curve were constructed, and the predictive value of the model was assessed. Logistic regression analysis showed that age (OR = 3.257, 95% CI 10.466–18.584), complications with chronic obstructive pulmonary disease (OR = 7.337, 95% CI 0.227–87.021), cough (OR = 5517, 95% CI 0.258–65.024), and venous thrombosis (OR = 7322, 95% CI 0.278–95.020) were risk factors for COVID-19 patients developing severe conditions during hospitalization. When complications were not taken into consideration, COVID-19 patients’ ages, number of diseases, and underlying diseases were risk factors influencing the development of severe illnesses. The ROC curve analysis results showed that the AUC that predicted the severity of COVID-19 patients at admission was 0.943, the optimal threshold was −3.24, and the specificity was 0.824, while the sensitivity was 0.827. The changes in the condition of severe COVID-19 patients are related to many factors such as age, clinical symptoms, and underlying diseases. This study has a certain value in predicting COVID-19 patients that develop from mild to severe conditions, and this prediction model is a useful tool in the quick prediction of the changes in patients’ conditions and providing early intervention for those with risk factors.

Lian, Zhichuang↗

DOE OSTI2016

Quasi-linear gyrokinetic predictions of the Coriolis momentum pinch in NSTX

This paper presents quasi-linear gyrokinetic predictions of the Coriolis momentum pinch for low aspect-ratio NSTX H-modes where previous experimental measurements were focused. Local, linear calculations predict that in the region of interest (just outside the mid-radius) of these relatively high-beta plasmas, profiles are most unstable to microtearing modes that are only effective in transporting electron energy. However, sub-dominant electromagnetic and electrostatic ballooning modes are also unstable, which are effective at transporting energy, particles and momentum. The quasi-linear prediction of transport from these weaker ballooning modes, assuming they contribute transport in addition to that from microtearing modes in a nonlinear turbulent state, leads to a very small or outward convection of momentum, inconsistent with the experimentally measured inward pinch, and opposite to predictions in conventional aspect ratio tokamaks. Additional predictions of a low beta L-mode plasma, unstable to more traditional electrostatic ion temperature gradient-trapped electron mode instability, show that the Coriolis pinch is inward but remains relatively weak and insensitive to many parameter variations. The weak or outward pinch predicted in NSTX plasmas appears to be at least partially correlated to changes in the parallel mode structure that occur at finite beta and low aspect ratio, as discussed in previous theories. The only conditions identified where a stronger inward pinch is predicted occur either in the purely electrostatic limit or if the aspect ratio is increased. As the Coriolis pinch cannot explain the measured momentum pinch, additional theoretical momentum transport mechanisms are discussed that may be potentially important.

Tokamak Turbulence Transport Momentum pinch↗

DOE OSTI2013

Evaluation of WRF-Predicted Near-Hub-Height Winds and Ramp Events over a Pacific Northwest Site with Complex Terrain

The WRF model version 3.3 is used to simulate near hub-height winds and power ramps utilizing three commonly used planetary boundary-layer (PBL) schemes: Mellor-Yamada-Janjic (MYJ), University of Washington (UW), and Yonsei University (YSU). The predicted winds have small mean biases compared with observations. Power ramps and step changes (changes within an hour) consistently show that the UW scheme performed better in predicting up ramps under stable conditions with higher prediction accuracy and capture rates. Both YSU and UW scheme show good performance predicting up- and down- ramps under unstable conditions with YSU being slightly better for ramp durations longer than an hour. MYJ is the most successful simulating down-ramps under stable conditions. The high wind speed and large shear associated with low-level jets are frequently associated with power ramps, and the biases in predicted low-level jet explain some of the shown differences in ramp predictions among different PBL schemes. Low-level jets were observed as low as ~200 m in altitude over the Columbia Basin Wind Energy Study (CBWES) site, located in an area of complex terrain. The shear, low-level peak wind speeds, as well as the height of maximum wind speed are not well predicted. Model simulations with 3 PBL schemes show the largest variability among them under stable conditions.

Yang, Qing↗

DOE OSTI2025

An Alternative Ensemble Streamflow Prediction Approach Using Improved Subseasonal Precipitation Forecasts from the North America Multi-Model Ensemble Phase II

In this article, streamflow forecasting at a subseasonal time scale (10–30 days into the future) is important for various human activities. The ensemble streamflow prediction (ESP) is a widely applied technique for subseasonal streamflow forecasting. However, ESP’s reliance on the randomly resampled historical precipitation limits its predictive capability. Available dynamical subseasonal precipitation forecasts provide an alternative to the randomly resampled precipitation in ESP. Prior studies found the predictive performance of raw subseasonal precipitation forecast is limited in many regions such as the central south of the United States, which raises questions about its effectiveness in assisting streamflow forecasting. To further assess the hydrologic applicability of dynamical subseasonal precipitation forecasts, we test the subseasonal precipitation forecast from North America Multi-Model Ensemble Phase II (NMME-2) at four watersheds in the central south region of the United States. The subseasonal precipitation forecasts are postprocessed with bias correction and spatial disaggregation (BCSD) to correct bias and improve spatial resolution before replacing the randomly resampled precipitation in ESP for streamflow predictions. The performance of the resulting streamflow predictions is benchmarked with ESP. Evaluation is conducted using Kling–Gupta Efficiency (KGE), continuous ranked probability score (CRPS), probability of detection (POD), false alarm ratios (FARs), as well as reliability diagrams. Our results suggest that BCSD-corrected subseasonal precipitation forecasts lead to overall improved streamflow predictions due to added skills in winter and spring. Our results also suggest that BCSD-corrected subseasonal precipitation forecasts lead to improved predictions on the occurrence of high-percentile streamflow values above 75%. Overall, BCSD-corrected subseasonal precipitation has shown promising performance, highlighting its potential broader applications for river and flood forecasting.

54 ENVIRONMENTAL SCIENCES↗

DOE OSTI2024

Evaluation of the EarthSHAB Stratospheric Solar Hot Air Balloon Flight Prediction Model Using Balloon Trajectory Data

Abstract The heliotrope is a solar balloon design which is constructed out of painter’s plastic, and the exterior is coated in charcoal powder. Darkening the plastic gives the balloon a high solar absorptance, which allows it to ascend into the lower stratosphere and float for hours at a time. The balloons have previously been used to lift scientific instruments into the stratosphere to study chemical explosions, earthquakes, and stratospheric aerosols. They have also been proposed as a platform for planetary exploration. Flight predictions are crucial to preflight planning to reduce safety risks and meet flight objectives. However, there exists a wide range of possible flight paths due to varying environmental conditions and solar balloon configurations. EarthSHAB is one such software that was designed to support flight planning using the weather forecasts and balloon properties to predict the flight path of a solar balloon. We compare EarthSHAB-simulated flight paths to a set of observed flight paths for the 3.5-m diameter heliotrope design called the “Cloudskimmer.” Using the criteria that the modeled paths must fall within 5% of the observations to be considered successful, we found that EarthSHAB successfully predicted the Cloudskimmer ascent rate and average float altitude 10% and 90% of the time, respectively. We also found that the average difference in the observed and predicted landing locations was 97 km and landing times were 54 ± 38 min. Significant deviations between the observed and predicted ascent rates and excursions at float were found to be associated with heavy payloads and convective cloud development, respectively. Significance Statement Solar balloons are used to lift scientific instruments into the lower stratosphere for hours at a time to study chemical explosions, earthquakes, stratospheric aerosols, and more. The flight paths of solar balloons can be difficult to predict due to variability in their design and surrounding environment. We evaluate the accuracy of EarthSHAB, a software that predicts the altitude profile and horizontal trajectory of a solar balloon using inputs such as the weather, balloon size, and balloon mass. Our results suggest that for the balloon design used in this study, EarthSHAB is best suited for modeling the behavior of balloons with lightweight payloads that do not fly within or directly above clouds.

Lien, Jessica M. [Sandia National Laboratories, Al↗

DOE OSTI2020

Subseasonal prediction with and without a well-represented stratosphere in CESM1

There is a growing demand for understanding sources of predictability on subseasonal to seasonal (S2S) time scales. Predictability at subseasonal time scales is believed to come from processes varying slower than the atmosphere such as soil moisture, snowpack, sea ice, and ocean heat content. The stratosphere as well as tropospheric modes of variability can also provide predictability at subseasonal time scales. Furthermore, the contributions of the above sources to S2S predictability are not well quantified. Here we evaluate the subseasonal prediction skill of the Community Earth System Model, version 1 (CESM1), in the default version of the model as well as a version with the improved representation of stratospheric variability to assess the role of an improved stratosphere on prediction skill. We demonstrate that the subseasonal skill of CESM1 for surface temperature and precipitation is comparable to that of operational models. We find that a better-resolved stratosphere improves stratospheric but not surface prediction skill for weeks 3–4.

54 ENVIRONMENTAL SCIENCES↗

DOE OSTI2024

Evaluating Ensemble Predictions of South Asian Monsoon Low Pressure System Genesis

Abstract Synoptic-scale vortices known as monsoon low pressure systems (LPSs) frequently produce intense precipitation and hydrological disasters in South Asia, so accurately forecasting LPS genesis is crucial for improving disaster preparedness and response. However, the accuracy of LPS genesis forecasts by numerical weather prediction models has remained unknown. Here, we evaluate the performance of two global ensemble models—the U.S. Global Ensemble Forecast System (GEFS) and the Ensemble Prediction System of the European Centre for Medium-Range Weather Forecasts (ECMWF)—in predicting LPS genesis during the years 2021–22. The GEFS successfully predicted about half the observed LPS genesis events 1–2 days in advance; the ECMWF model captured an additional 10% of observed genesis events. Both models had a false alarm ratio (FAR) of around 50% for 1–2-day lead times. In both ensembles, the control run typically exhibited a higher probability of detection (POD) of observed events and a lower FAR compared to the perturbed ensemble members. However, a consensus forecast, in which genesis is predicted when at least 20% of ensemble members forecast LPS formation, had POD values surpassing those of the control run for all lead times. Moreover, probabilistic predictions of genesis over the Bay of Bengal, where most LPSs form, were skillful, with the fraction of ensemble members predicting LPS formation over a 5-day lead time approximating the observed frequency of genesis, without any adjustment or bias correction.

Suhas, D. L.↗

DOE OSTI2018

Network Scale Travel Time Prediction using Deep Learning

In recent years, deep learning models have been receiving increased attention within the artificial intelligence (AI) community because of their high prediction accuracy. In this paper, two deep learning models, long short-term memory (LSTM) and convolutional neural network (CNN), are proposed to predict travel time in a road network. One major advantage of using deep learning for travel time prediction is that it can make accurate predictions for all the segments in the transportation network with a single model structure, instead of building customized models for each segment separately. The proposed models were evaluated on a transportation network in the City of Saint Louis, Missouri. The prediction results show that deep learning can provide accurate prediction for both congested and uncongested traffic conditions, and can successfully capture the traffic dynamics of unexpected incidents or special events. The study findings show that deep learning offers a promising approach to real-time prediction of travel times on a network scale.

33 ADVANCED PROPULSION SYSTEMS↗

DOE OSTI2023

Review of machine learning and deep learning models for toxicity prediction

The ever-increasing number of chemicals has raised public concerns due to their adverse effects on human health and the environment. To protect public health and the environment, it is critical to assess the toxicity of these chemicals. Traditional in vitro and in vivo toxicity assays are complicated, costly, and time-consuming and may face ethical issues. These constraints raise the need for alternative methods for assessing the toxicity of chemicals. Recently, due to the advancement of machine learning algorithms and the increase in computational power, many toxicity prediction models have been developed using various machine learning and deep learning algorithms such as support vector machine, random forest, k-nearest neighbors, ensemble learning, and deep neural network. This review summarizes the machine learning- and deep learning-based toxicity prediction models developed in recent years. Support vector machine and random forest are the most popular machine learning algorithms, and hepatotoxicity, cardiotoxicity, and carcinogenicity are the frequently modeled toxicity endpoints in predictive toxicology. It is known that datasets impact model performance. The quality of datasets used in the development of toxicity prediction models using machine learning and deep learning is vital to the performance of the developed models. The different toxicity assignments for the same chemicals among different datasets of the same type of toxicity have been observed, indicating benchmarking datasets is needed for developing reliable toxicity prediction models using machine learning and deep learning algorithms. This review provides insights into current machine learning models in predictive toxicology, which are expected to promote the development and application of toxicity prediction models in the future.

Research & Experimental Medicine↗

DOE OSTI2020

Predicting potential adverse events using safety data from marketed drugs

Abstract Background While clinical trials are considered the gold standard for detecting adverse events, often these trials are not sufficiently powered to detect difficult to observe adverse events. We developed a preliminary approach to predict 135 adverse events using post-market safety data from marketed drugs. Adverse event information available from FDA product labels and scientific literature for drugs that have the same activity at one or more of the same targets, structural and target similarities, and the duration of post market experience were used as features for a classifier algorithm. The proposed method was studied using 54 drugs and a probabilistic approach of performance evaluation using bootstrapping with 10,000 iterations. Results Out of 135 adverse events, 53 had high probability of having high positive predictive value. Cross validation showed that 32% of the model-predicted safety label changes occurred within four to nine years of approval (median: six years). Conclusions This approach predicts 53 serious adverse events with high positive predictive values where well-characterized target-event relationships exist. Adverse events with well-defined target-event associations were better predicted compared to adverse events that may be idiosyncratic or related to secondary target effects that were poorly captured. Further enhancement of this model with additional features, such as target prediction and drug binding data, may increase accuracy.

Daluwatte, Chathuri↗

DOE OSTI2022

Multi-head attention-based U-Nets for predicting protein domain boundaries using 1D sequence features and 2D distance maps

Abstract The information about the domain architecture of proteins is useful for studying protein structure and function. However, accurate prediction of protein domain boundaries (i.e., sequence regions separating two domains) from sequence remains a significant challenge. In this work, we develop a deep learning method based on multi-head U-Nets (called DistDom) to predict protein domain boundaries utilizing 1D sequence features and predicted 2D inter-residue distance map as input. The 1D features contain the evolutionary and physicochemical information of protein sequences, whereas the 2D distance map includes the structural information of proteins that was rarely used in domain boundary prediction before. The 1D and 2D features are processed by the 1D and 2D U-Nets respectively to generate hidden features. The hidden features are then used by the multi-head attention to predict the probability of each residue of a protein being in a domain boundary, leveraging both local and global information in the features. The residue-level domain boundary predictions can be used to classify proteins as single-domain or multi-domain proteins. It classifies the CASP14 single-domain and multi-domain targets at the accuracy of 75.9%, 13.28% more accurate than the state-of-the-art method. Tested on the CASP14 multi-domain protein targets with expert annotated domain boundaries, the average per-target F1 measure score of the domain boundary prediction by DistDom is 0.263, 29.56% higher than the state-of-the-art method.

59 BASIC BIOLOGICAL SCIENCES↗

DOE OSTI2024

Human limits in machine learning: prediction of potato yield and disease using soil microbiome data

Abstract Background The preservation of soil health is a critical challenge in the 21st century due to its significant impact on agriculture, human health, and biodiversity. We provide one of the first comprehensive investigations into the predictive potential of machine learning models for understanding the connections between soil and biological phenotypes. We investigate an integrative framework performing accurate machine learning-based prediction of plant performance from biological, chemical, and physical properties of the soil via two models: random forest and Bayesian neural network. Results Prediction improves when we add environmental features, such as soil properties and microbial density, along with microbiome data. Different preprocessing strategies show that human decisions significantly impact predictive performance. We show that the naive total sum scaling normalization that is commonly used in microbiome research is one of the optimal strategies to maximize predictive power. Also, we find that accurately defined labels are more important than normalization, taxonomic level, or model characteristics. ML performance is limited when humans can’t classify samples accurately. Lastly, we provide domain scientists via a full model selection decision tree to identify the human choices that optimize model prediction power. Conclusions Our study highlights the importance of incorporating diverse environmental features and careful data preprocessing in enhancing the predictive power of machine learning models for soil and biological phenotype connections. This approach can significantly contribute to advancing agricultural practices and soil health management.

Aghdam, Rosa↗

DOE OSTI2023

Design and implementation of I/O performance prediction scheme on HPC systems through large-scale log analysis

Abstract Large-scale high performance computing (HPC) systems typically consist of many thousands of CPUs and storage units used by hundreds to thousands of users simultaneously. Applications from large numbers of users have diverse characteristics, such as varying computation, communication, memory, and I/O intensity. A good understanding of the performance characteristics of each user application is important for job scheduling and resource provisioning. Among these performance characteristics, I/O performance is becoming increasingly important as data sizes rapidly increase and large-scale applications, such as simulation and model training, are widely adopted. However, predicting I/O performance is difficult because I/O systems are shared among all users and involve many layers of software and hardware stack, including the application, network interconnect, operating system, file system, and storage devices. Furthermore, updates to these layers and changes in system management policy can significantly alter the I/O behavior of applications and the entire system. To improve the prediction of the I/O performance on HPC systems, we propose integrating information from several different system logs and developing a regression-based approach to predict the I/O performance. Our proposed scheme can dynamically select the most relevant features from the log entries using various feature selection algorithms and scoring functions, and can automatically select the regression algorithm with the best accuracy for the prediction task. The evaluation results show that our proposed scheme can predict the write performance with up to 90% prediction accuracy and the read performance with up to 99% prediction accuracy using the real logs from the Cori supercomputer system at NERSC.

97 MATHEMATICS AND COMPUTING↗

DOE OSTI2017

Limb-Enhancer Genie: An accessible resource of accurate enhancer predictions in the developing limb

Epigenomic mapping of enhancer-associated chromatin modifications facilitates the genome-wide discovery of tissue-specific enhancers in vivo. However, reliance on single chromatin marks leads to high rates of false-positive predictions. More sophisticated, integrative methods have been described, but commonly suffer from limited accessibility to the resulting predictions and reduced biological interpretability. Here we present the Limb-Enhancer Genie (LEG), a collection of highly accurate, genome-wide predictions of enhancers in the developing limb, available through a user-friendly online interface. We predict limb enhancers using a combination of > 50 published limb-specific datasets and clusters of evolutionarily conserved transcription factor binding sites, taking advantage of the patterns observed at previously in vivo validated elements. By combining different statistical models, our approach outperforms current state-of-the-art methods and provides interpretable measures of feature importance. Our results indicate that including a previously unappreciated score that quantifies tissue-specific nuclease accessibility significantly improves prediction performance. We demonstrate the utility of our approach through in vivo validation of newly predicted elements. Moreover, we describe general features that can guide the type of datasets to include when predicting tissue-specific enhancers genome-wide, while providing an accessible resource to the general biological community and facilitating the functional interpretation of genetic studies of limb malformations.

59 BASIC BIOLOGICAL SCIENCES↗