Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “temporal learning”

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 847 records · Page 47

MO-D-213-06: Quantitative Image Quality Metrics Are for Physicists, Not Radiologists: How to Communicate to Your Radiologists Using Their Language

Purpose: A framework for explaining differences in image quality to non-technical audiences in medial imaging is needed. Currently, this task is something that is learned “on the job.” The lack of a formal methodology for communicating optimal acquisition parameters into the clinic effectively mitigates many technological advances. As a community, medical physicists need to be held responsible for not only advancing image science, but also for ensuring its proper use in the clinic. This work outlines a framework that bridges the gap between the results from quantitative image quality metrics like detectability, MTF, and NPS and their effect on specific anatomical structures present in diagnostic imaging tasks. Methods: Specific structures of clinical importance were identified for a body, an extremity, a chest, and a temporal bone protocol. Using these structures, quantitative metrics were used to identify the parameter space that should yield optimal image quality constrained within the confines of clinical logistics and dose considerations. The reading room workflow for presenting the proposed changes for imaging each of these structures is presented. The workflow consists of displaying images for physician review consisting of different combinations of acquisition parameters guided by quantitative metrics. Examples of using detectability index, MTF, NPS, noise and noise non-uniformity are provided. During review, the physician was forced to judge the image quality solely on those features they need for diagnosis, not on the overall “look” of the image. Results: We found that in many cases, use of this framework settled mis-agreements between physicians. Once forced to judge images on the ability to detect specific structures inter reader agreement was obtained. Conclusion: This framework will provide consulting, research/industrial, or in-house physicists with clinically relevant imaging tasks to guide reading room image review. This framework avoids use of the overall “look” or “feel” to dictate acquisition parameter selection. Equipment grants GE Healthcare.

60 APPLIED LIFE SCIENCES↗

KGML-ag: a modeling framework of knowledge-guided machine learning to simulate agroecosystems: a case study of estimating N<sub>2</sub>O emission using data from mesocosm experiments

Abstract. Agricultural nitrous oxide (N2O) emission accounts for a non-trivial fraction of global greenhouse gas (GHG) budget. To date, estimating N2O fluxes from cropland remains a challenging task because the related microbial processes (e.g., nitrification and denitrification) are controlled by complex interactions among climate, soil, plant and human activities. Existing approaches such as process-based (PB) models have well-known limitations due to insufficient representations of the processes or uncertainties of model parameters, and due to leverage recent advances in machine learning (ML) a new method is needed to unlock the “black box” to overcome its limitations such as low interpretability, out-of-sample failure and massive data demand. In this study, we developed a first-of-its-kind knowledge-guided machine learning model for agroecosystems (KGML-ag) by incorporating biogeophysical and chemical domain knowledge from an advanced PB model, ecosys, and tested it by comparing simulating daily N2O fluxes with real observed data from mesocosm experiments. The gated recurrent unit (GRU) was used as the basis to build the model structure. To optimize the model performance, we have investigated a range of ideas, including (1) using initial values of intermediate variables (IMVs) instead of time series as model input to reduce data demand; (2) building hierarchical structures to explicitly estimate IMVs for further N2O prediction; (3) using multi-task learning to balance the simultaneous training on multiple variables; and (4) pre-training with millions of synthetic data generated from ecosys and fine-tuning with mesocosm observations. Six other pure ML models were developed using the same mesocosm data to serve as the benchmark for the KGML-ag model. Results show that KGML-ag did an excellent job in reproducing the mesocosm N2O fluxes (overall r2=0.81, and RMSE=3.6 mgNm-2d-1 from cross validation). Importantly, KGML-ag always outperforms the PB model and ML models in predicting N2O fluxes, especially for complex temporal dynamics and emission peaks. Besides, KGML-ag goes beyond the pure ML models by providing more interpretable predictions as well as pinpointing desired new knowledge and data to further empower the current KGML-ag. We believe the KGML-ag development in this study will stimulate a new body of research on interpretable ML for biogeochemistry and other related geoscience processes.

54 ENVIRONMENTAL SCIENCES↗

Using automated machine learning for the upscaling of gross primary productivity

Estimating gross primary productivity (GPP) over space and time is fundamental for understanding the response of the terrestrial biosphere to climate change. Eddy covariance flux towers provide in situ estimates of GPP at the ecosystem scale, but their sparse geographical distribution limits larger-scale inference. Machine learning (ML) techniques have been used to address this problem by extrapolating local GPP measurements over space using satellite remote sensing data. However, the accuracy of the regression model can be affected by uncertainties introduced by model selection, parameterization, and choice of explanatory features, among others. Recent advances in automated ML (AutoML) provide a novel automated way to select and synthesize different ML models. In this work, we explore the potential of AutoML by training three major AutoML frameworks on eddy covariance measurements of GPP at 243 globally distributed sites. We compared their ability to predict GPP and its spatial and temporal variability based on different sets of remote sensing explanatory variables. Explanatory variables from only Moderate Resolution Imaging Spectroradiometer (MODIS) surface reflectance data and photosynthetically active radiation explained over 70 % of the monthly variability in GPP, while satellite-derived proxies for canopy structure, photosynthetic activity, environmental stressors, and meteorological variables from reanalysis (ERA5-Land) further improved the frameworks' predictive ability. We found that the AutoML framework Auto-sklearn consistently outperformed other AutoML frameworks as well as a classical random forest regressor in predicting GPP but with small performance differences, reaching an r 2 of up to 0.75. We deployed the best-performing framework to generate global wall-to-wall maps highlighting GPP patterns in good agreement with satellite-derived reference data. This research benchmarks the application of AutoML in GPP estimation and assesses its potential and limitations in quantifying global photosynthetic activity.

54 ENVIRONMENTAL SCIENCES↗

Development of a Consistent GEOsat Cloud Property Dataset for the CERES Climate Data Record

Cloud properties are critical for understanding the Earth’s radiation budget and cloud feedbacks. At NASA Langley Research Center, the Satellite ClOud and Radiative Property retrieval System (SatCORPS) provides real-time and historical analyses of clouds derived from Geostationary satellite (GEOsat) data for weather and climate applications. For the Clouds and the Earth’s Radiant Energy System (CERES) program, the global constellation of GEOsats has been analyzed since 2000 to help characterize and account for the diurnal cycle of clouds and their radiative impacts in the CERES climate data record. Obtaining consistent cloud properties over the GEOsat data record during the CERES era is a major objective but a significant challenge considering the diversity of imaging capabilities deployed during that time. The GEOsat data analysis approach for the current CERES Edition-4 (Ed4) data products was focused on accuracy and consistency with MODIS by employing as much spectral information as possible from each satellite. However, the inconsistent use of spectral information across GEOsats led to marked discontinuities in the spatial and temporal record of cloud properties that had to be accounted for post facto in downstream CERES processing. This paper reports progress in developing a new GEOsat analysis system for the next CERES edition (Ed5) that has potential to improve cross-platform consistency and continuity. In this approach, the spectral channel complement is limited to just 3-channels during daytime, ~0.65 µm (VIS), ~3.9 µm (NIR), and ~10.8 µm (IR), common to nearly all of the satellites in the record. At night, a 2-channel approach is taken with the NIR and IR, and ~6.7 µm bands that includes a machine learning approach for optically thick cloud properties. A tradeoff is the potential for reduced accuracy particularly using data from the more advanced satellites that have more spectral channels (e.g. SEVIRI, AHI and ABI) that are known to help improve thin cirrus detection, cloud-aerosol discrimination and estimates in other difficult conditions that challenge cloud remote sensing. The new continuity approach is applied to one month of global GEOSat data for each year of the CERES record since 2000 and compared with the Ed4 GEO and MODIS cloud property time series in order to evaluate the level of improved consistency in the GEOsat record and to assess the accuracy impacts. Cloud fraction will also be assessed with CALIPSO data. Outstanding issues and challenges will be discussed. The results are expected to guide future work needed to develop a more robust GEOsat cloud data record for CERES.

CERES CDR↗

Forecasting Multi-Step-Ahead Street-Scale Nuisance Flooding using a seq2seq LSTM Surrogate Model for Real-Time Application in a Coastal-Urban City

In coastal-urban cities facing an elevated risk of nuisance flooding (by rain and tide) due to increased heavy rainfall, sea level rise, urbanization, and aging drainage systems, real-time flood forecasting at the street-scale can provide useful information to transportation decision-makers. Physics-Based Models (PBMs) that offer high accuracy come with high computational runtimes and costs that limit their application for real-time flood forecasting. To address this challenge, Machine Learning (ML) surrogate models trained from PBMs have been proposed to provide street-scale flood forecasts. Previous related studies have focused on using Long Short-Term Memory (LSTM) architectures to model hourly flood depth on streets. While LSTM models can capture input sequences effectively, they fall short in accurately preserving output sequences, limiting their suitability for multi-step-ahead forecasts. The seq2seq LSTM architecture offers a key advantage here by capturing the full sequence of input–output, making it potentially more suitable for multi-step-ahead flood forecasts compared to traditional LSTM models. However, seq2seq LSTM has not been tested for street-scale flood forecasting, particularly for rapidly fluctuating nuisance flooding events which require special attention to its temporal sequences. Hence, in this study, we applied the seq2seq LSTM model to explore multi-step-ahead street-scale nuisance flooding and compared its results to the traditional LSTM model as a benchmark model. LSTM and seq2seq LSTM surrogate models were applied to 22 flood-prone streets in Norfolk, Virginia, as a case study with a 4-hr (short-term) and 8-hr (long-term) lead time. The models were trained with environmental (rainfall and tide) and topographic (elevation, Topographic Wetness Index, and Depth-To-Water) features along with PBM-derived water depths for different storm events. The results demonstrated satisfactory performance of both LSTM and seq2seq LSTM surrogate models throughout the forecast period compared to the PBM. However, the seq2seq LSTM showed lower Mean Absolute Error (MAE)/ Root Mean Square Error (RMSE) and higher Nash–Sutcliffe Efficiency (NSE)/ correlation than the LSTM across most lead times, particularly for long-term forecasting due to its supremacy in handling both input–output sequences together, which is missing in the traditional LSTM. For example, in the long-term, the average RMSE ranges were 0.0268–0.0373 m for LSTM and 0.0226–0.0319 m for seq2seq LSTM, while in the short-term, they were 0.0263–0.0293 m and 0.0261–0.0283 m, respectively. Additionally, while both models exhibited similar performance in distinguishing flooded and non-flooded streets for flood depth ≥ 0.1 m, the seq2seq LSTM model demonstrated superior performance for higher flood depths (such as ≥ 0.2 m and ≥ 0.3 m). Once trained, inference took only 0.09 to 0.11 s (short-term) and 0.30 to 0.35 s (long-term) per storm event for the 22 streets, making the application highly suitable for real-time decision-making during nuisance flood events.

54 ENVIRONMENTAL SCIENCES↗

Deep Learning Scene Classification Experiments in Automatic Detection of Slums on Planetscope Imagery

Population growth is increasingly happening in slum settlements of the large urban centers in the Global South. The term "slum" encompasses a wide range of communities, located mostly in underserved areas, and often exhibiting distinct structural and functional informalities with a relatively high concentration of marginalized populations. To address the issues confronting slums for effective planning and development, including the realistic estimation of the resident population, identifying them accurately is fundamental. Given the disagreements over a universal definition, diverse characteristic features, and socio-political limitations, global detection of slums is a veritable challenge. In this paper, we present experiments in slum detection using a scene classification algorithm and 3-meter spatial resolution satellite imagery. We train and evaluate the model for slum detection in Mumbai, India for the year 2023 and test the temporal generalization of the trained model on Mumbai in 2020 and 2018. In addition, we explore the pathways toward geographic generalization to Kolkata and Delhi (India). We discuss several limitations in the workflow and model, situate our findings in the existing literature, and suggest improvements and alternatives. With this, we establish baseline methods and experiments as a first step towards developing an image-based global slum detection framework and algorithm. This work adds to the community discussion on methods, data challenges, and open questions related to the detection of slums globally. With this research, we hope to improve our understanding of human settlements, especially in critical areas, improve population estimates, and help measure progress towards the sustainable development goals.

Arndt, Jacob↗

Prediction of Individual Social-Demographic Role Based on Travel Behavior Variability Using Long-Term GPS Data

With the development of and advances in smartphones and global positioning system (GPS) devices, travelers’ long-term travel behaviors are not impossible to obtain. This study investigates the pattern of individual travel behavior and its correlation with social-demographic features. For different social-demographic groups (e.g., full-time employees and students), the individual travel behavior may have specific temporal-spatial-mobile constraints. The study first extracts the home-based tours, including Home-to-Home and Home-to-Non-Home, from long-term raw GPS data. The travel behavior pattern is then delineated by home-based tour features, such as departure time, destination location entropy, travel time, and driving time ratio. The travel behavior variability describes the variances of travelers’ activity behavior features for an extended period. After that, the variability pattern of an individual’s travel behavior is used for estimating the individual’s social-demographic information, such as social-demographic role, by a supervised learning approach, support vector machine. In this study, a long-term (18-month) recorded GPS data set from Puget Sound Regional Council is used. The experiment’s result is very promising. The sensitivity analysis shows that as the number of tours thresholds increases, the variability of most travel behavior features converges, while the prediction performance may not change for the fixed test data.

29 ENERGY PLANNING, POLICY, AND ECONOMY↗

Dilute Combustion Control Using Spiking Neural Networks

Dilute combustion with exhaust gas recirculation (EGR) in spark-ignition engines presents a cost-effective method for achieving higher levels of engine efficiency. At high levels of EGR, however, cycle-to-cycle variability (CCV) of the combustion process is exacerbated by sporadic occurrences of misfires and partial burns. Previous studies have shown that temporal deterministic patterns emerge at such conditions and certain combustion cycles have a significant influence over future events. Due to the complexity of the combustion process and the nature of CCV, harnessing all the deterministic information for control purposes has remained challenging even with physics based 0-D, 1-D, and high-fidelity computational fluid dynamics (CFD) models. In this study, we present a data-driven approach to optimize the combustion process by controlling CCV adjusting the cycle-to-cycle fuel injection quantity. Readily available data from in-cylinder pressure was used to train a spiking neural network (SNN) which learns the optimal way to manage fuel injection in order to reduce CCV while maintaining acceptable levels of fuel consumption. SNNs are particularly well suited for powertrain control applications due to their ability to be deployed on FPGA-based neuromorphic hardware which are small, inexpensive, and have a low power demand. The high-performance computing (HPC) resources of Oak Ridge National Laboratory were used to run an evolutionary-based training approach for choosing the best SNN configuration that minimizes the size of the network while achieving the desired goal. The neuromorphic hardware with the optimized SNN deployed was connected to the rapid prototyping engine control system for real-time control implementation and tested on a single cylinder version of a GM LNF 4-cylinder engine. The results show a significant reduction of CCV with a small percentage of additional fuel used to stabilize the charge.

33 ADVANCED PROPULSION SYSTEMS↗

Deep-Learning based Reconstruction of the Shower Maximum $X_{\mathrm{max}}$ using the Water-Cherenkov Detectors of the Pierre Auger Observatory

The atmospheric depth of the air shower maximum X max is an observable commonly used for the determination of the nuclear mass composition of ultra-high energy cosmic rays. Direct measurements of X max are performed using observations of the longitudinal shower development with fluorescence telescopes. At the same time, several methods have been proposed for an indirect estimation of X max from the characteristics of the shower particles registered with surface detector arrays. In this paper, we present a deep neural network (DNN) for the estimation of X max . The reconstruction relies on the signals induced by shower particles in the ground based water-Cherenkov detectors of the Pierre Auger Observatory. The network architecture features recurrent long short-term memory layers to process the temporal structure of signals and hexagonal convolutions to exploit the symmetry of the surface detector array. We evaluate the performance of the network using air showers simulated with three different hadronic interaction models. Thereafter, we account for long-term detector effects and calibrate the reconstructed X max using fluorescence measurements. Finally, we show that the event-by-event resolution in the reconstruction of the shower maximum improves with increasing shower energy and reaches less than 25 g/cm 2 at energies above 2 × 10 19 eV.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗

Efficient and generalizable nested Fourier-DeepONet for three-dimensional geological carbon sequestration

Geological carbon sequestration (GCS) involves injecting CO2 into subsurface geological formationsfor permanent storage. Numerical simulations could guide decisions in GCS projects by predictingCO 2 migration pathways and the pressure distribution in storage formation. However, these simula-tions are often computationally expensive due to highly coupled physics and large spatial-temporalsimulation domains. Surrogate modelling with data-driven machine learning has become a promis-ing alternative to accelerate physics-based simulations. Among these, the Fourier neural operator(FNO) has been applied to three-dimensional synthetic subsurface models. Despite its good accuracyin simulating CO 2 plume migration, it requires large computational resources in training and alsolacks generalizability. Here, to further improve performance, we have developed a nested Fourier-DeepONet by combining the expressiveness of the FNO with the modularity of a deep operatornetwork (DeepONet). This new framework is twice as efficient as a nested FNO for training and has atleast 80% lower GPU memory requirement due to its flexibility to treat temporal coordinates sepa-rately. These performance improvements are achieved without compromising prediction accuracy.In addition, the generalization and extrapolation ability of nested Fourier-DeepONet beyond thetraining range has been thoroughly evaluated. Nested Fourier-DeepONet outperformed the nestedFNO for extrapolation in time with more than 50% reduced error. It also exhibited good extrapolationaccuracy beyond the training range in terms of reservoir properties, number of wells, and injectionrate.

Lee, Jonathan E. [Department of Chemical and Envir↗

The ABCs of On-Demand Transit (ODT)

On-demand mobility - also referred to as on-demand transit (ODT) - is a form of public mobility that is flexible with respect to where and when service is provided, and ODT deployments have increased significantly in recent years. Transit agencies are becoming increasingly interested in ODT, and due to differing definitions and various service design and business model options, it can be difficult to learn about the emerging industry. This work provides an overview of the definitions of ODT, recent trends internationally and in the U.S., ODT's benefits and challenges (particularly compared to fixed-route transit), three primary service design options, system costs and funding considerations, and a metrics framework for evaluating ODT systems to ensure continued successful performance. Identified benefits include increased service areas, short ride and wait times, increased user flexibility, potential to reduce energy consumption and emissions through shared trips and smaller, right-sized vehicles, increased safety and comfort through door-to-door service, and rich data streams including granular spatio-temporal data that can be analyzed to continuously improve the service. Challenges include scaling ODT service up as small increases in ridership require additional supply to keep service quality high, serving peak times including keeping low wait times, the lack of fixed schedule being challenging for commuters, integrating ODT services with nearby transit systems, and equity for riders without smartphones who cannot track the vehicle in a mobile app. Finally, an overview of seven ODT case studies (in Texas, Missouri, New York, and Ontario, Canada) performed by NREL and related analysis of travel time, energy and emissions, costs, and equity are presented. Initial key findings include: ODT can be cost- and energy-effective compared to fixed-route transit, ODT serves more people than other transit options, and ODT system deployments can be followed by rapid growth.

24 POWER TRANSMISSION AND DISTRIBUTION↗

Comparison of Multivariate Time Series Prediction Techniques for Emulating Noah-LSM Soil Moisture Outputs

Land surface models are crucial tools for many earth science applications including numerical weather prediction, water resource and crop monitoring, and climatological analysis. Given a set of atmospheric forcings, seasonal data, and static parameters, models like Noah-LSM solve for land surface quantities including skin temperature, sensible heat flux, and soil moisture. While these calculations are theoretically robust, they are often computationally expensive. Since artificial neural networks (ANNs) are universal function approximators, they can learn to emulate the output of a deterministic numerical model given a time series of input forcings, with the learned ANN having substantially shorter execution time. The ANN could efficiently parameterize other models, generate ensembles, and provide first-guess inputs for retrievals. As such, with the goal of developing a model that efficiently mimics the output of Noah-LSM given NLDAS2 forcings on a region covering much of the central US, we examine and compare several neural network architectures for the multi-horizon multivariate time series forecasting problem. Recent literature includes a diverse set of approaches including autoregressive architectures like LSTM and GRU, parametric and non-parametric statistical predictors (ForecastNet and MQRNN), self-attention (LSTM-attention-LSTM), and temporal convovlution (DeepTCN). We implement several of these models for the Noah-LSM prediction task, highlighting the features and challenges for each and providing practical insight on the training process.

Mitchell Dodson↗

Exploring the Capabilities of a Machine Learning Algorithm to Detect Space Weather-Significant Emerging Active Regions

Active regions are a source of various phenomena responsible for Space Weather disturbances; therefore, developing a technology for early warning about upcoming magnetic activity is crucial to mitigate its impact. However, observational limitations and the high nonlinearity of processes associated with the accumulation of magnetic flux and its interaction with the surrounding plasma during the emergence through the convection zone make early activity detection a challenging problem. To address these challenges, we developed a physics-driven machine learning model that allows us to detect active regions (ARs) before they become visible on the solar surface by analyzing the power spectra of acoustic oscillations observed by the SDO/HMI instrument. This study is based on a time series of Doppler shift maps of 31x31-degree areas tracked with the Carrington rotation rate for four days before and after the emergence. The Doppler shift time series are processed into the oscillation power maps for four frequency ranges and accompanied by line-of-sight magnetograms and the continuum intensity maps from SDO/HMI. The resulting data are converted into a 1D time series representing the mean temporal variations of these quantities. The redacted time series are used as input to predict AR emergence using the Long Short Term Memory (LSTM) method. The training of the LSTM model is based on 40 ARs, which includes an independent analysis for each sub region that exhibits AR emergence or remains quiet. The emergence of magnetic flux (defined as a decrease of the continuum intensity) was detected with the developed LSTM algorithm from 5 to 48 hours before the reported time by NOAA. The developed model is capable of pointing to the time and location of active region formation. In this presentation, we discuss reasons that impact how early in advance the model can identify the upcoming activity and the possibility of improving the current predictive skills and steps to transition to the operational forecast.

Heliophysics↗

Predicting future well performance for environmental remediation design using deep learning

Here in this study, we developed a deep learning (DL) framework with a multi-channel three-dimensional convolutional neural network (MC3D-CNN) to predict well performance and thereby assist future environmental remediation design. Such prediction of extraction well performance at designated locations is critical for configuring pump-and-treat (P&T) well network design and operation, setting reasonable target closure dates for overall remedying, and estimating remedy costs. The framework is developed with operational and monitoring data routinely collected during P&T remedy operations, including well extraction and injection rates as well as in situ contaminant concentrations. Traditionally, the collected data were rarely used for purposes other than assessing past well performance and the accuracy of the conceptual site model. However, recent advances in data-driven computational approaches enable better use of the large datasets to inform future well performance, enhance site characterization, and improve remediation planning. In this study, we established a DL framework to integrate transient three-dimensional contaminant plumes and multiple aquifer properties (e.g., hydraulic conductivity and hydrostratigraphic maps) to identify characteristic patterns controlling and representing extraction well mass recovery, aiming at providing future mass recovery estimates for existing wells and candidate wells at any proposed locations. We evaluated our framework by using a realistic synthetic dataset generated from a well-calibrated flow and transport model used in the 200 West Area of the U.S. Department of Energy’s Hanford Site in southeastern Washington state. The multi-channel feature in our framework allows integration of various types and temporal densities of training datasets for DL model development. Overall, we found that the trained DL model achieved an accuracy of over 90% in ranking extraction well performance in validation datasets, and over 80% in predicting high-performance-ranking well locations. This data-informed approach provides a flexible tool to support adaptive site management, streamline decision-making, and potentially reduce remediation time and costs. Our DL framework can be used as a filtering tool to improve the current P&T network optimization design by reducing the number of candidate well locations.

54 ENVIRONMENTAL SCIENCES↗

Seeing the Disturbed Forest for the Trees: Remote Sensing Is Underutilized to Quantify Critical Zone Response to Unprecedented Disturbance

Understanding the severity and extent of near surface critical zone (CZ) disturbances and their ecosystem response is a pressing concern in the face of increasing human and natural disturbances. Predicting disturbance severity and recovery in a changing climate requires comprehensive understanding of ecosystem feedbacks among vegetation and the surrounding environment, including climate, hydrology, geomorphology, and biogeochemistry. Field surveys and satellite remote sensing have limited ability to effectively capture the spatial and temporal variability of disturbance and CZ properties. Technological advances in remote sensing using new sensors and new platforms have improved observations of changes in vegetation canopy structure and productivity; however, integrating measures of forest disturbance from various sensing platforms is complex. By connecting the potential for remote sensing technologies to observe different CZ disturbance vectors, we show that lower severity disturbance and slower vegetation recovery are more difficult to quantify. Case studies in montane forests from the western United States highlight new opportunities, including evaluating post-disturbance forest recovery at multiple scales, shedding light on understory vegetation regrowth, detecting specific physiological responses, and refining ecohydrological modeling. Learning from regional CZ disturbance case studies, we propose future directions to synthesize fragmented findings with (a) new data analysis using new or existing sensors, (b) data fusion across multiple sensors and platforms, (c) increasing the value of ground-based observations, (d) disturbance modeling, and (e) synthesis to improve understanding of disturbance.

54 ENVIRONMENTAL SCIENCES↗

Multidimensional perspectives of geo-epidemiology: from interdisciplinary learning and research to cost–benefit oriented decision-making

Research typically promotes two types of outcomes (inventions and discoveries), which induce a virtuous cycle: something suspected or desired (not previously demonstrated) may become known or feasible once a new tool or procedure is invented and, later, the use of this invention may discover new knowledge. Research also promotes the opposite sequence—from new knowledge to new inventions. This bidirectional process is observed in geo-referenced epidemiology—a field that relates to but may also differ from spatial epidemiology. Geo-epidemiology encompasses several theories and technologies that promote inter/transdisciplinary knowledge integration, education, and research in population health. Based on visual examples derived from geo-referenced studies on epidemics and epizootics, this report demonstrates that this field may extract more (geographically related) information than simple spatial analyses, which then supports more effective and/or less costly interventions. Actual (not simulated) bio-geo-temporal interactions (never captured before the emergence of technologies that analyze geo-referenced data, such as geographical information systems) can now address research questions that relate to several fields, such as Network Theory. Thus, a new opportunity arises before us, which exceeds research: it also demands knowledge integration across disciplines as well as novel educational programs which, to be biomedically and socially justified, should demonstrate cost-effectiveness. Grounded on many bio-temporal-georeferenced examples, this report reviews the literature that supports this hypothesis: novel educational programs that focus on geo-referenced epidemic data may help generate cost-effective policies that prevent or control disease dissemination.

59 BASIC BIOLOGICAL SCIENCES↗

Application of the AI2 Climate Emulator to E3SMv2's Global Atmosphere Model, With a Focus on Precipitation Fidelity

Abstract Can the current successes of global machine learning‐based weather simulators be generalized beyond 2‐week forecasts to stable and accurate multiyear runs? The recently developed AI2 Climate Emulator (ACE) suggests this is feasible, based upon 10‐year simulations with a network trained on output from a physics‐based global atmosphere model using a grid spacing of approximately 110 km and forced by a repeating annual cycle of sea‐surface temperature. Here we show that ACE, without modification, can be trained to emulate another major atmospheric model, EAMv2, run at a comparable grid spacing for at least 10 years with similarly small climate biases—a prerequisite to wider applicability. With an analysis that combines multiple temporal, spatial, and frequency domain perspectives, we show that ACE faithfully represents the spatiotemporal structure of EAMv2 precipitation and related variables. Finally, we show that a pretrained ACE network is able to adapt to a new global climate model simulation data set with 10 fewer training steps than when starting from random initialization, all while still maintaining low levels of climate bias. Further analysis of these fine‐tuning experiments reveal ACE's intriguing ability to interpolate between distinct global climate models.

Duncan, James P. C.↗

Interactive Machine Learning at Scale with CHISSL

We demonstrate CHISSL, a scalable client-server system for real-time interactive machine learning. Our system is capa- ble of incorporating user feedback incrementally and imme- diately without a structured or pre-defined prediction task. Computation is partitioned between a lightweight web-client and a heavyweight server. The server relies on representation learning and agglomerative clustering to learn a dendrogram, a hierarchical approximation of a representation space. The client uses only this dendrogram to incorporate user feedback into the model via transduction. Distances and predictions for each unlabeled instance are updated incrementally and deter- ministically, with O(n) space and time complexity. Our al- gorithm is implemented in a functional prototype, designed to be easy to use by non-experts. The prototype organizes the large amounts of data into recommendations. This allows the user to interact with actual instances by dragging and drop- ping to provide feedback in an intuitive manner. We applied CHISSL to several domains including cyber, social media, and geo-temporal analysis.

Arendt, Dustin L.↗