Engineering topics

Feinstein, Jeremy

Publications and source records attributed to Feinstein, Jeremy.

7 records

DOE OSTI2024

The Relationship of Hydrology in the Green River to Colorado Pikeminnow Populations

The Federally listed Colorado Pikeminnow (CP) (Ptychocheilus Lucius) has been declining in the Green River Basin over the last 20 years. Muth et al. (2000) recommended flows and temperatures to benefit endangered fish species downstream of Flaming Gorge Dam on the Green River. The recommendations identified a range of flows during the base flow period (flows that occur after the annual snowmelt runoff period, usually from early summer to the following spring) that were intended to benefit CP. The recommendations indicated that the mean flow for the summer–winter period should be established each year on the basis of anticipated hydrologic conditions, but adjustments could be made if hydrologic conditions change. Flow should gradually decline from peak flow to base flow, with the base flow reached by early to middle summer (depending on hydrologic conditions) and maintained through February. The rate of decline should depend on rates of decline in Yampa River flows and the recommended rates of decline for dam releases. No specific recommendations were made for base flow variation in Reach 1, but variation around the annual mean base flow should be restricted to achieve recommended levels of variation in Reach 2 (middle Green River) (Table 5.5 in Muth et al. 2000). Implementation of the flow and temperature recommendations served as the proposed action for an EIS on Flaming Gorge Dam operations. A Biological Assessment of the impacts on endangered species of implementing the recommendations was prepared and a Biological Opinion that called for development of a study plan to examine the effects of implementation. Projects to address this evaluation were identified in the Green River Study Plan and have been conducted since then. The purpose of the Study Plan was to identify and recommend to the Recovery Program those monitoring or research projects necessary for implementation and evaluation of the flow and temperature recommendations. Those projects included studies to evaluate the anticipated effects of implementing the recommendations (including potential adverse effects identified in the 2006 Biological Opinion) and studies to examine recognized uncertainties of the recommendations. A new recovery program summer base flow study plan was approved in September of 2020 to evaluate stable and elevated summer base flows below Flaming Gorge Dam intended to benefit CP spawning and rearing success. Anecdotal observations suggest CP production may have been higher in years prior to flow restrictions for endangered fish. Based on long-term CP monitoring data in the Green River, Bestgen and Hill (2016) concluded that CP would benefit from higher summer baseflows (1,700-3,000 ft 3 /sec) with flows above or below associated with lower abundance of age-0 CP. Therefore, flexibility in the ROD is currently being utilized to establish higher stable summer base flows in an attempt create more advantageous conditions for spawning and rearing CP. These fish recovery flows are restrictive to WAPA in the summer months, therefore it is necessary to conduct an analysis of historic river data relationships to CP abundance to better understand if the recommended fish flows (elevated and stable base flows) are necessary for fish recovery.

54 ENVIRONMENTAL SCIENCES↗

DOE OSTI2024

Bird Species Use of Bioenergy Croplands in Illinois, USA—Can Advanced Switchgrass Cultivars Provide Suitable Habitats for Breeding Grassland Birds?

Grassland birds have sustained significant population declines in the United States through habitat loss, and replacing lost grasslands with bioenergy production areas could benefit these species and the ecological services they provide. Point count surveys and autonomous acoustic monitoring were used at two field sites in Illinois, USA, to determine if an advanced switchgrass cultivar that is being used for bioenergy feedstock production could provide suitable habitats for grassland and other bird species. At the Brighton site, the bird use of switchgrass plots was compared to that of corn plots during the breeding seasons of 2020–2022. At the Urbana site, the bird use of restored prairie, switchgrass, and Miscanthus × giganteus was studied in the 2022 breeding season. At Brighton, Common Yellowthroat, Dickcissel, Grasshopper Sparrow, and Sedge Wren occurred on switchgrass plots more often than on corn; Common Yellowthroat and Dickcissel increased on experimental plots as the perennial switchgrass increased in height and density over the study period; and the other two species declined over the same period. At Urbana, Dickcissel was most frequent in prairie and switchgrass; Common Yellowthroat was most frequent in miscanthus and switchgrass. These findings suggest that advanced switchgrass cultivars could provide suitable habitats for grassland birds, replace lost habitats, and contribute to the recovery of these vulnerable species.

59 BASIC BIOLOGICAL SCIENCES↗

DOE OSTI2024

Applying machine learning and quantum chemistry to predict the glass transition temperatures of polymers

Glass transition temperature (T g ) is important for understanding the physical and mechanical properties of a polymer material because it relates to the thermal energy required to transition between a hard glassy state and a soft rubbery one. Over the years, various models have been developed for predicting this thermal property from molecular structure to aid in designing novel polymers in selected classes. This work builds on those efforts by utilizing both machine learning (ML) and quantum chemistry (QC) techniques to develop models that can predict T g values from the molecular structure under different data availability scenarios and for a wide variety of polymer types. For the ML model, a graph convolutional network (GCN) was used to map topological polymer features; this model was trained against a dataset of more than 7500 T g values and resulted in a root mean square error (RMSE) of 38.1 °C. The QC-based regression model was trained on 83 T g values and produced an RMSE of 34.5 °C. In conclusion, this work demonstrated that while both model techniques produce accurate predictions and are suitable for different data availability scenarios, the QC-based regression model offered a more interpretable model framework with significantly less training data.

36 MATERIALS SCIENCE↗

DOE OSTI2023

Using Data-Driven Prediction of Downstream 1D River Flow to Overcome the Challenges of Hydrologic River Modeling

Methods for downstream river flow prediction can be categorized into physics-based and empirical approaches. Although based on well-studied physical relationships, physics-based models rely on numerous hydrologic variables characteristic of the specific river system that can be costly to acquire. Moreover, simulation is often computationally intensive. Conversely, empirical models require less information about the system being modeled and can capture a system’s interactions based on a smaller set of observed data. This article introduces two empirical methods to predict downstream hydraulic variables based on observed stream data: a linear programming (LP) model, and a convolutional neural network (CNN). We apply both empirical models within the Colorado River system to a site located on the Green River, downstream of the Yampa River confluence and Flaming Gorge Dam, and compare it to the physics-based model Streamflow Synthesis and Reservoir Regulation (SSARR) currently used by federal agencies. Results show that both proposed models significantly outperform the SSARR model. Moreover, the CNN model outperforms the LP model for hourly predictions whereas both perform similarly for daily predictions. Although less accurate than the CNN model at finer temporal resolution, the LP model is ideal for linear water scheduling tools.

13 HYDRO ENERGY↗

DOE OSTI2023

Predicting Biomass Yields of Advanced Switchgrass Cultivars for Bioenergy and Ecosystem Services Using Machine Learning

The production of advanced perennial bioenergy crops within marginal areas of the agricultural landscape is gaining interest due to its potential to sustainably produce feedstocks for biofuels and bioproducts while also improving the sustainability and resilience of commodity crop production. However, predicting the biomass yields of this production system is challenging because marginal areas are often relatively small and spread around agricultural fields and are typically associated with various abiotic conditions that limit crop production. Machine learning (ML) offers a viable solution as a biomass yield prediction tool because it is suited to predicting relationships with complex functional associations. The objectives of this study were to (1) evaluate the accuracy of commonly applied ML algorithms in agricultural applications for predicting the biomass yields of advanced switchgrass cultivars for bioenergy and ecosystem services and (2) determine the most important biomass yield predictors. Datasets on biomass yield, weather, land marginality, soil properties, and agronomic management were generated from three field study sites in two U.S. Midwest states (Illinois and Iowa) over three growing seasons. The ML algorithms evaluated in the study included random forests (RFs), gradient boosting machines (GBMs), artificial neural networks (ANNs), K-neighbors regressor (KNR), AdaBoost regressor (ABR), and partial least squares regression (PLSR). Coefficient of determination (R 2 ) and mean absolute error (MAE) were used to evaluate the predictive accuracy of the tested algorithms. Results showed that the ensemble methods, RF (R 2 = 0.86, MAE = 0.62 Mg/ha), GBM (R 2 = 0.88, MAE = 0.57 Mg/ha), and GBM (R 2 = 0.78, MAE = 0.66 Mg/ha), were the most accurate in predicting biomass yields of the Independence, Liberty, and Shawnee switchgrass cultivars, respectively. This is in agreement with similar studies that apply ML to multi-feature problems where traditional statistical methods are less applicable and datasets used were considered to be relatively small for ANNs. Consistent with previous studies on switchgrass, the most important predictors of biomass yield included average annual temperature, average growing season temperature, sum of the growing season precipitation, field slope, and elevation. This study helps pave the way for applying ML as a management tool for alternative bioenergy landscapes where understanding agronomic and environmental performance of a multifunctional cropping system seasonally and interannually at the sub-field scale is critical.

09 BIOMASS FUELS↗

DOE OSTI2023

Projected changes in extreme streamflow and inland flooding in the mid-21st century over Northeastern United States using ensemble WRF-Hydro simulations

Study region: Northeastern United States (NEUS). Study focus: We investigate the potential impacts of climate change on precipitation, streamflow, and inland flooding in the NEUS during the mid-21st century. Dynamically downscaled climate projections from three global climate models for historical (1995-2004) and future (2045-2054) periods under business-as-usual scenarios were used to force the hydrologic model WRF-Hydro at 200-meter resolution and create ensemble hydrologic simulations. Additionally, an extreme value model was developed to project the risks associated with low-frequency hydrologic events. New hydrological insights for the region: Results from four major watersheds indicate a significantly wetter regime in winter months and potential drier conditions during late spring to early summer. Discharges in fall are projected to decrease in the northern watersheds and increase toward the south. Extreme flow and water depths resulting from extreme inland flooding are projected to increase by 5-20% and > 100%, respectively. The extent of the total flooded area is likely to be 20% greater by the mid-century. These increased risks can be attributed to (i) an approximate 25% increase in decadal mean and > 40% increase in decadal extreme precipitation intensity, (ii) up to 30% lower snow availability and 5-25% higher evapotranspiration throughout the year, and (iii) a projected 5% increase in soil moisture in all seasons except summer. Furthermore, rapid snow melting in winter will likely cause an earlier peak flow in the rivers.

54 ENVIRONMENTAL SCIENCES↗

DOE OSTI2022

2022 AI Testbed Expeditions Report

By exploiting the coherent properties of a light source, coherent diffraction imaging (CDI) is able to obtain the sample image at a nanoscale resolution using the measured diffraction pattern. Bragg Coherent Diffraction Imaging (BCDI) has become valuable for recovering the displacement and strain field of crystals, providing a valuable tool in material science and solid-state physics. X-ray ptychography is another emerging CDI technique that can produce a high-resolution image of the extended sample and has become popular in many research areas (e.g., materials science, biology, electronics, and optics characterization). CDI including BCDI and ptychography has become an established technique in Synchrotron Facilities including the Advanced Photon Source (APS) and will greatly benefit from the 100x coherent flux increase of the upcoming APS Upgrade (APSU). The current image formation process in CDI employs iterative phase retrieval algorithms, which is a time-consuming and computationally expensive process. Especially after APSU, the traditional iterative methods will not be able to match the experimental data acquisition speed. We employ deep learning (DL) approach to replace the iterative approaches, therefore allowing hundreds of times faster recovery of the object. We developed AutoPhaseNN, a DL-based approach which learns to solve the inverse problem without labeled data. Taking 3D BCDI as a representative technique, AutoPhaseNN has been demonstrated to be one hundred times faster than traditional iterative phase retrieval methods while providing comparable image quality. The current network is trained with 64 x 64 x 64 data size, to achieve higher resolution imaging, we will need to scale the network to input and train/infer 3D arrays of size 256 x 256 x 256 (today) and of size 2560x2560x2560 (APSU). However, the scalability of the network is restricted due to the memory-intensive training process. To perform the training for a 256 x 256 x 256 data size, the required memory exceeds the capacity of the current machine. In this project, we explore using Sambanova system to train the network for the direct data inversion for CDI.

36 MATERIALS SCIENCE↗