SEARCH · Search NASA
Results for “spatiotemporal decision”
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.
Combining Machine Learning and Numerical Simulation for High-Resolution PM2.5 Concentration Forecast
Forecasting ambient PM2.5 concentrations with spatiotemporal coverage is key to alerting decision-makers of pollution episodes and preventing detrimental public exposure, especially in regions with limited ground air monitoring stations. The existing methods either rely on chemical transport models (CTMs) to forecast spatial distribution of PM2.5 with nontrivial uncertainty or statistical algorithms to forecast PM2.5 concentration time-series at air monitoring locations without continuous spatial coverage. In this study, we developed a PM2.5 forecast framework by combining the robust Random Forest algorithm with a publicly accessible global CTM forecast product – NASA’s Goddard Earth Observing System “Composition Forecasting” (GEOS-CF), providing spatiotemporally continuous PM2.5 concentration forecasts for the next five days at a 1-km spatial resolution. Our forecast experiment was conducted for a region in Central China including the populous and polluted Fenwei Plain. The forecast for the next two days had overall validation R2 of 0.76 and 0.64, respectively; the R2 was around 0.5 for the following three forecast days. Spatial cross-validation showed similar validation metrics. Our forecast model, with validation normalized mean bias close to zero, substantially reduced the large biases in GEOS-CF. The proposed framework requires minimal computational resources compared to running CTMs at urban scales, enabling near-real-time PM2.5 forecast in resource-restricted environments.
A spatiotemporally explicit and scalable indicator of intact lands across the conterminous United States, 1986–2023
Globally, ecologically intact areas are increasingly scarce. Agricultural expansion into previously uncultivated areas drives the loss of intact lands that might otherwise exhibit high levels of ecological integrity. Thus, the absence of cultivation can be an indicator of intact lands as measured from remote sensing data and thematic maps. Our objective for this study was to develop and compare tractable approaches based on remotely sensed satellite data to map spatial patterns of potentially intact lands across the conterminous U.S. (CONUS). Using annual cultivation probabilities derived from satellite observations, we classified and mapped potentially intact lands across CONUS from 1986 to 2023 at 30 m resolution. We created three maps, first by applying a constant cultivation probability threshold across CONUS, second by varying the threshold state-by-state to maximize state-level overall accuracies, and third by equalizing the state-level user's and producer's accuracies to minimize classification bias. Validation against 800,000+ independent ground samples resulted in CONUS-level overall accuracies ≥85% for the roughly 660 million ha of potentially intact land. Map accuracy varied with the proportion of potentially intact lands across regions, with the Pacific-Mountain and Great Plains regions exhibiting the highest accuracies, while Eastern CONUS exhibited a greater mix of potentially intact and non-intact lands and more moderate map accuracies. These novel maps and approaches can be adapted to different spatiotemporal extents to support conservation and production decisions ranging from species and ecosystems protection to reducing land conversion and climate mitigation.
Disentangling error structures of precipitation datasets using decision trees
Characterizing error structures in precipitation products not only facilitates their proper applications for scientific and practical purposes but also helps improve their retrieval algorithms and processing methods. Despite the fact that multiple precipitation products have been assessed in the literature, factors that affect their error structures remain inadequately addressed. By interpreting 60 binary decision trees, this study disentangles the error characteristics of precipitation products in terms of their spatiotemporal patterns and geographical factors. Three independent precipitation products - two satellite-based and one reanalysis datasets: the Integrated Multi-satellitE Retrievals for GPM (Global Precipitation Measurement) late run (IMERG-L), Soil Moisture to Rain-Advanced SCATterometer (SM2RAIN-ASCAT), and the Modern-Era Retrospective analysis for Research and Applications, Version 2 uncorrected precipitation output (MERRA2-UC), are evaluated across the contiguous United States from 2010 to 2019. Here, the ground-based Stage IV precipitation dataset is used as the ground truth. Results indicate that the MERRA2-UC outperforms the IMERG-L and SM2RAIN-ASCAT with higher accuracy and more stable interannual patterns for the analysis period. Decision trees cross-assess three spatiotemporal factors and find that the underestimation of MERRA2-UC occurs in the east of the Rocky Mountains, and SM2RAIN-ASCAT underestimates precipitation over high latitudes, especially in winter. Additionally, the decision tree method ascribes system errors to nine different geographical characteristics, of which the distance to the coast, soil type, and DEM are the three dominant features. On the other hand, the land cover type, topography position index, and aspect are three relatively weak factors.
Pipeline Hydrogen Decarbonization and Repurposing Analyzers (P-HyDRAs)
The Pipeline Hydrogen Decarbonization and Repurposing Analyzers (P-HyDRAs) are a set of prototype computational tools for simulating and optimizing midstream natural gas pipeline system operations subject to location and time-dependent hydrogen blending. The models can accurately resolve dynamic gas flows through large-scale pipeline networks using non-ideal gas equations of state. The codes can be used as decision support for planning and design decisions involving intra-day energy flow schedules as well as spatiotemporal economic values of natural gas, hydrogen, and net energy delivered to consumers while ensuring that pipeline hydraulic limitations, gas compressor station constraints, operational factors, and pre-existing shipping contracts are satisfied. The inputs to the codes are a model of the pipeline system as well as time-series data that specify boundary conditions on the network. For optimization, the code module requires price and quantity offers for natural gas and hydrogen and price and quantity bids for energy, which are used as time-dependent constraints in an optimal control problem. The outputs are time-series data that provide a predictive simulation of gas flows, mass fractions, and pressures, or with additional degrees of freedom give an approximately optimal solution for gas injections/withdrawals, compressor settings, and sensitivities to the objective function that provide locational values of energy.
Analyzing inference workloads for spatiotemporal modeling
Ensuring power grid resiliency, forecasting climate conditions, and optimization of transportation infrastructure are some of the many application areas where data is collected in both space and time. Spatiotemporal modeling is about modeling those patterns for forecasting future trends and carrying out critical decision-making by leveraging machine learning/deep learning. Once trained offline, field deployment of trained models for near real-time inference could be challenging because performance can vary significantly depending on the environment, available compute resources and tolerance to ambiguity in results. Users deploying spatiotemporal models for solving complex problems can benefit from analytical studies considering a plethora of system adaptations to understand the associated performance-quality trade-offs. To facilitate the co-design of next-generation hardware architectures for field deployment of trained models, it is critical to characterize the workloads of these deep learning (DL) applications during inference and assess their computational patterns at different levels of the execution stack. In this paper, we develop several variants of deep learning applications that use spatiotemporal data from dynamical systems. We study the associated computational patterns for inference workloads at different levels, considering relevant models (Long short-term Memory, Convolutional Neural Network and Spatio-Temporal Graph Convolution Network), DL frameworks (Tensorflow and PyTorch), precision (FP16, FP32, AMP, INT16 and INT8), inference runtime (ONNX and AI Template), post-training quantization (TensorRT) and platforms (Nvidia DGX A100 and Sambanova SN10 RDU). Overall, our findings indicate that although there is potential in mixed-precision models and post-training quantization for spatiotemporal modeling, extracting efficiency from contemporary GPU systems might be challenging. Instead, co-designing custom accelerators by leveraging optimized High Level Synthesis frameworks (such as SODA High-Level Synthesizer for customized FPGA/ASIC targets) can make workload-specific adjustments to enhance the efficiency.
Multimodal sensor fusion framework for residential building occupancy detection
For several years now, smart building energy systems have been a research area of intensive activity. In light of the increasing need for sustainable buildings and energy systems, this trend motivates an increasing need for a solution to reduce carbon dioxide emissions and improve energy efficiency. This work proposes a high-performing and transferable occupancy detection framework that combines sensor data from different data modalities, including time series environmental data (temperature, humidity, and illuminance), image data, and acoustic energy data using ensemble method. To draw out the best prediction performance in each modality, the proposed framework was developed, including various models that were designed to learn the occupancy patterns reflected in the physical data streams. To tackle the time series environmental data, we designed two variants of an occupancy detection spatiotemporal pattern network (Occ-STPN) that performs both feature level and decision level fusion, respectively. We also propose a new metric; the fading memory mean square error (FMMSE), that provides a fair evaluation and penalization of delayed occupancy predictions. Multiple open-sourced datasets, including the Electricity Consumption and Occupancy and the University of California, Irvine's (UCI) building occupancy detection dataset, along with our own real data collected from six different houses, were used to validate the algorithms' performance. The experimental results presented herein break down the performance for each sensing modality, and a detailed analysis of the performance is also discussed.
Meeting Global Health Needs via Infectious Disease Forecasting: Development of a Reliable Data-Driven Framework
Infectious diseases (IDs) have a significant detrimental impact on global health. Timely and accurate ID forecasting can result in more informed implementation of control measures and prevention policies. To meet the operational decision-making needs of real-world circumstances, we aimed to build a standardized, reliable, and trustworthy ID forecasting pipeline and visualization dashboard that is generalizable across a wide range of modeling techniques, IDs, and global locations. We forecasted 6 diverse, zoonotic diseases (brucellosis, campylobacteriosis, Middle East respiratory syndrome, Q fever, tick-borne encephalitis, and tularemia) across 4 continents and 8 countries. We included a wide range of statistical, machine learning, and deep learning models (n=9) and trained them on a multitude of features (average n=2326) within the One Health landscape, including demography, landscape, climate, and socioeconomic factors. The pipeline and dashboard were created in consideration of crucial operational metrics—prediction accuracy, computational efficiency, spatiotemporal generalizability, uncertainty quantification, and interpretability—which are essential to strategic data-driven decisions. While no single best model was suitable for all disease, region, and country combinations, our ensemble technique selects the best-performing model for each given scenario to achieve the closest prediction. For new or emerging diseases in a region, the ensemble model can predict how the disease may behave in the new region using a pretrained model from a similar region with a history of that disease. The data visualization dashboard provides a clean interface of important analytical metrics, such as ID temporal patterns, forecasts, prediction uncertainties, and model feature importance across all geographic locations and disease combinations. As the need for real-time, operational ID forecasting capabilities increases, this standardized and automated platform for data collection, analysis, and reporting is a major step forward in enabling evidence-based public health decisions and policies for the prevention and mitigation of future ID outbreaks.
Characterizing spatiotemporal patterns of crop phenology across North America during 2000–2016 using satellite imagery and agricultural survey data
Crop phenology represents an integrative indicator of climate change and plays a vital role in terrestrial carbon dynamics and sustainable agricultural development. However, spatiotemporal variations of crop phenology remain unclear at large scales. This knowledge gap has hindered our ability to realistically quantify the biogeochemical dynamics in agroecosystems, predict future climate, and make informed decisions for climate change mitigation and adaptation. In this study, we improved an EVI-curve-based approach and used it to detect spatiotemporal patterns in cropping intensity and five major phenological stages over North America during 2000–2016 using vegetation index in combination with agricultural survey data and other ancillary maps. Our predicted crop phenological stages showed strong linear relationships with the survey-based datasets, with R(exp 2), RMSEs, and MAEs in the ranges of 0.35 –0.99, three to ten days, and two to eight days, respectively. During the study period, the planting dates were advanced by 0.60 days/year (p < 0.01), and harvesting dates were delayed by 0.78 days/year (p < 0.01) over North America. A minimum temperature increase by 1 °C caused a 4.26-day planting advance (r = −0.50, p < 0. 01) or a 0.66-day harvest delay (r = 0.10, p < 0.01). While, a higher maximum temperature resulted in a planting advance by 4.48 days/°C (r = −0.62, p < 0.01) or a harvest advance by 2.22 days/°C (r = −0.40, p < 0.01). Our analysis illustrated evident spatiotemporal variations in crop phenology in response to climate change and management practices. The derived crop phenological datasets and cropping intensity maps can be used in regional climate assessments and in developing adaptation strategies.
Exploring the future energy-mobility nexus: The transportation energy & mobility pathway options (TEMPO) model
Not Available
The Transportation Energy and Mobility Pathway Options (TEMPO) Model: Overview and Validation of V1.0 [Slides]
This presentation documents the approaches and methods used in the Transportation Energy & Mobility Pathway Options™ (TEMPO) model to evaluate passenger and freight demand for transportation and mobility services, project vehicle ownership and technology adoption decisions, and determine transport mode choices to derive scenarios of future energy use and emissions. TEMPO is an all-inclusive transportation demand model that covers the entire United States, with an implicit spatial resolution and an hourly temporal resolution that allows for generating time-resolved energy use profiles to assess multisectoral integration aspects. Key features of the TEMPO model include the ability to perform endogenous out-of-sample forecasting to extrapolate recent emerging trends and analyze impacts of disruptive technological breakthroughs and behavioral changes. TEMPO employs an innovative representation of passenger mobility demand stemming from household-level decisions that determine vehicle adoption, ownership, and use based on sociodemographics (e.g., income, household composition), technology attributes (e.g., travel cost, time), geography (e.g., urban, suburban, rural) and population-specific multiday mobility and travel requirements. This representation enables a more forward-looking perspective on the use of new mobility options and the adoption of alternative fuel vehicles, as well as a more accurate representation of their energy usage profiles than previous modeling approaches. A comparison with the U.S. Energy Information Administration’s Annual Energy Outlook showcases the ability of TEMPO to accurately replicate widely accepted projections by representing the key elements of the entire transportation sector at the appropriate level of resolution. TEMPO is intended to generate future scenarios of technology adoption, energy use, and emissions in the transportation sector to compare alternatives, inform decision makers, and assess integration with energy infrastructure and supply systems at an appropriate spatiotemporal resolution.
Remote monitoring of agricultural systems using NDVI time series and machine learning methods: a tool for an adaptive agricultural policy
This study aims to provide accurate information about changes in agricultural systems (AS) using phenological metrics derived from the NDVI time series. Use of such information could help land managers optimize land use choices and monitor the status of agricultural lands, under a variety of environmental and socioeconomic conditions. For this purpose, the Moderate Resolution Imaging Spectroradiometer (MODIS) NDVI data were used to derive phenological metrics over the Oum Er-Rbia basin (central Morocco). Random forest (RF), support vector machine (SVM), and K-nearest neighbor (KNN) classifiers were explored and compared on their ability to classify AS classes over the study area. Four main AS classes have been considered: (1) irrigated annual crop (IAC), (2) irrigated perennial crop (IPC), (3) rainfed area (RA), and (4) fallow (FA). By comparing the accuracy of the three classifiers, the RF method showed the best performance with an overall accuracy of 0.97 and kappa coefficient of 0.96.The RF method was then chosen to examine time variations in AS over a 16-year period (2000–2016). The AS main variations were detected and evaluated for the four AS classes. These variations have been found to be linked well with other indicators of local agricultural land management, as well as the historical agricultural drought changes over the study area. Overall, the results present a tool for decision makers to improve agricultural management and provide a different perspective in understanding the spatiotemporal dynamics of agricultural systems.
The Role of Groundwater Withdrawals on River Regulation: Example From the Columbia River Basin
The Columbia River Basin (CRB) is heavily regulated by more than 250 dams on its river system while depending significantly on groundwater withdrawals in certain sub-basins. Neglecting groundwater withdrawals in hydrologic models of the basin could result in inaccurate predictions of its water budget and thus mislead water management decisions in the basin. This work aims to understand the impacts of groundwater pumping on the spatiotemporal patterns of modeling regulated streamflow in the CRB using a modified version of the Variable Infiltration Capacity (VIC) model integrated with a water management component that accounts for groundwater withdrawals, irrigation demands, and reservoir operation (VIC-GIRR). The VIC-GIRR simulations showed that considering additional groundwater withdrawals would alleviate the stress of irrigation water deficit in the Snake River Basin with an average reduction of 10 km 3 /year. Such a reduction in water deficit resulted in slight streamflow increase over the CRB with maximum increase up to 40% during dry period in certain locations. We also note that the implementation of groundwater withdrawal does not, however, improve the overall model performance in long-term averaged streamflow and storage predictions. Our results highlight the efforts needed to examine additional important processes in representing the interactions between water withdrawals and reservoir operations. Such efforts will aid in better simulation of multi-reservoir system and improve effectiveness for agricultural productivity, power generation, flood control, and navigation purposes.
Robotic Planning under Uncertainty in Spatiotemporal Environments in Expeditionary Science
In the expeditionary sciences, spatiotemporally varying environments -- hydrothermal plumes, algal blooms, lava flows, or animal migrations -- are ubiquitous. Mobile robots are uniquely well-suited to study these dynamic, mesoscale natural environments. We formalize expeditionary science as a sequential decision-making problem, modeled using the language of partially-observable Markov decision processes (POMDPs). Solving the expeditionary science POMDP under real-world constraints requires efficient probabilistic modeling and decision-making in problems with complex dynamics and observational models. Previous work in informative path planning, adaptive sampling, and experimental design have shown compelling results, largely in static environments, using data-driven models and information-based rewards. However, these methodologies do not trivially extend to expeditionary science in spatiotemporal environments: they generally do not make use of scientific knowledge such as equations of state dynamics, they focus on information gathering as opposed to scientific task execution, and they make use of decision-making approaches that scale poorly to large, continuous problems with long planning horizons and real-time operational constraints. In this work, we discuss these and other challenges related to probabilistic modeling and decision-making in expeditionary science, and present some of our preliminary work that addresses these gaps. We ground our results in a real expeditionary science deployment of an autonomous underwater vehicle (AUV) in the deep ocean for hydrothermal vent discovery and characterization. Our concluding thoughts highlight remaining work to be done, and the challenges that merit consideration by the reinforcement learning and decision-making community.
Verification of MOOSE/Bison's Heat Conduction Solver Using Combined Spatiotemporal Convergence Analysis
Bison is a computational physics code that uses the finite element method to model the thermo-mechanical response of nuclear fuel. Since Bison is used to inform high-consequence decisions, it is important that its computational results are reliable and predictive. One important step in assessing the reliability and predictive capabilities of a simulation tool is the verification process, which quantifies numerical errors in a discrete solution relative to the exact solution of the mathematical model. One step in the verification process—called code verification—ensures that the implemented numerical algorithm is a faithful representation of the underlying mathematical model, including partial differential or integral equations, initial and boundary conditions, and auxiliary relationships. In this paper, the code verification process is applied to spatiotemporal heat conduction problems in Bison. Simultaneous refinement of the discretization in space and time is employed to reveal any potential mistakes in the numerical algorithms for the interactions between the spatial and temporal components of the solution. For each verification problem, the correct spatial and temporal order of accuracy is demonstrated for both first- and second-order accurate finite elements and a variety of time-integration schemes. Furthermore, these results provide strong evidence that the Bison numerical algorithm for solving spatiotemporal problems reliably represents the underlying mathematical model in MOOSE. The selected test problems can also be used in other simulation tools that numerically solve for conduction or diffusion.
Application of Advanced Earth Observations and Model Simulations to Improve Air Quality Monitoring in the Hindu-Kush-Himalayan Region
Air pollution is a serious environmental health concern in the Hindu Kush Himalayan (HKH) region of south-central Asia, as rapid industrialization and population growth have led to increased anthropogenic emissions from transportation, residential, industrial, energy, and biomass burning sources. Natural emissions from dust and forest fires are additional sources of air pollutants that can exacerbate air quality in the region. The combination of the complex pollutant mixtures and atmospherically stable weather conditions during the winter monsoon can visibility reductions and hazardous air quality from persistent haze episodes. The Kathmandu Valley is especially vulnerable to extreme haze issues due to the surrounding mountains that restrict air movement and retains pollutants in the atmosphere. This study uses state-of-the-art satellite observations and modeling capabilities in conjunction with ground-based networks to provide a comprehensive data toolkit for advancing air quality monitoring and forecasting decisions in the HKH region. The toolkit includes new generation satellite observations from the TROPOspheric Monitoring Instrument (TROPOMI), Geostationary Environment Monitoring Spectrometer (GEMS), and Advanced Meteorological Imager, which provide high spatiotemporal information on NO2, HCHO, SO2, O3, and aerosol optical depth (AOD). Particulate matter with diameters less than 2.5 micrometers (PM2.5) are derived from the satellite-retrieved AOD using ground-based observations and forecast model data. The satellite observations are also used to initialize and constrain forecast model systems designed for the HKH region. This talk will highlight the performance of the air quality toolkit for enhancing decision-making processes during exceptional air quality events in the region. Note: Presentation includes additional attachment of full presentation with sound and animation (best when viewed as slide show) with runtime of 15 min 32 secs
Self-Aware Local Autonomous and Semi-Cooperative Control for Cross-Layered Resilience (SLAC3R)
The objective of this work is to develop and demonstrate novel, adaptive, lightweight algorithms that enable the decision-making agents in a large cyber-physical network to act both autonomously and in collaborative harmony to enforce assured resilience across spatiotemporal layers, even under unforeseen adversarial scenarios (e.g., high- impact-low-probability events). Towards this end, the proposed solution will serve as minimally invasive add-on layers that bridge the existing (faster, reactive) local myopic controls and (slower, predictive) centralized optimization. Importantly, the proposed algorithms will enable the multi-agent network to autonomously and collaboratively enforce resilient operation under no or limited communication environment typical of severe cyber- physical adversarial events. The expected outcome of this effort is a suite of prototype, open-source, software algorithms for safety-aware local autonomous and semi-cooperative control (SLAC3R), demonstrated on networked microgrids (via RD2C/Thrust-1 OPAL-RT testbed).
Advancing spatiotemporal forecasts of CO 2 plume migration using deep learning networks with transfer learning and interpretation analysis
Accurate and timely forecasts of CO 2 plume distribution throughout the injection and post-injection phases are crucial for detecting plume migration, assessing leakage risks, and supporting operational decisions in geologic carbon storage (GCS). Current convolutional neural network-based approaches primarily focus on spatial information and overlook temporal dependencies in plume distributions, thus limiting their ability to capture dynamic movement effects and provide accurate predictions of plume migration. In this work, we propose two deep learning models, Auto-Encoder (AE)-LSTM and Encoder-Decoder (ED)-ConvLSTM, each uniquely designed to capture both spatial and temporal features. We apply the proposed methods to forecast the dynamic distribution of CO 2 plumes based on 108 reservoir simulations over a 30-year injection and a 30-year post-injection period. The results indicate that the ED-ConvLSTM model outperforms the AE-LSTM model in accurately predicting the spatiotemporal dynamics of CO 2 plume migration, achieving R 2 values above 0.99. To provide a deeper understanding of these model predictions, we employ a gradient-based explanation method on the trained models. This approach provides insights into the influence of input variables on plume migration forecasts and uncovers the underlying prediction mechanisms of the proposed models. Furthermore, we introduce a transfer learning technique, enabling fast and accurate plume migration forecasting in the post-injection phase by leveraging the trained model during the injection phase. This reduces the necessity for extensive data collection or re-training. In conclusion, the methods proposed in our work enhances the performance and interpretability of CO 2 plume migration forecasts, thereby facilitating informed decision-making throughout the entire lifecycle of GCS applications.