Search NASA⌕ Search

SEARCH · Search NASA

Results for “Machine Learning Models”

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 829 records · Page 46

Multi-Mission Terrain Classifier for Safe Rover Navigation and Automated Science

We previously presented Soil Property and Object Classification (SPOC), a machine learning-based terrain classifier for Mars rovers, for automatically segmenting rover images by its surface type such as sand and bedrock. This paper presents a number of practical improvements to pave the way for potential future onboard deployment. First, we achieved 97.0% overall pixel accuracy, evaluated against the classification generated by human experts on images from Mars Science Laboratory (MSL) missions. The substantial increase in accuracy was primarily enabled by the sheer volume of data used for training; we created a new large-scale dataset of Martian terrain labels, namely AI4Mars, which contains more than 400k labels contributed by citizen scientists for 50k images taken by the Mars Exploration Rovers (MER) and Mars Science Laboratory (MSL) rover. Second, we demonstrated that SPOC can quickly adapt to a new mission landed on a previously unseen site. Specifically, we pretrained a model with MER and MSL data from the AI4Mars dataset and then adapted to the Mars 2020 Rover (M2020) by feeding a small volume of data between Sol 0 and 157; the adapted model was tested on Sol 200-203 and resulted in 84.2% overall pixel accuracy and 93.4% reliability (recall) for detecting sand, the most concerning class for rover’s traversability. Third, we found that pretraining can substantially mitigate the decline of accuracy over time. We showed that the performance of a SPOC model pretrained with the ImageNet dataset and then trained by MSL images only up to Sol 390 remains comparable to a model trained by images up to Sol 1689 on the test data after Sol 1689. Fourth, we reimplemented SPOC with a light-weight convolutional neural network (CNN), MobileNetV2, which typically runs within tens of milliseconds (ms) on mobile processors such as Qualcomm’s Snapdragon. Finally, we released the AI4Mars dataset to the public to encourage open innovation.

Ono, Masahiro↗

FloodPlanet: High-Resolution Commercial Imagery for Training and Validation of Deep Learning-Based Models of Inundation Extent

Flooding events are becoming increasingly frequent worldwide and are known to cause extensive damage. Public optical and radar satellite imagery can be used to detect large areas of inundation in rural areas, however, long revisit times and coarse spatial resolution limit applications for short-lived events and urban areas. Commercial constellations such as those operated by Planet offer increased spatial and temporal resolution and can supplement mapping efforts to provide more information to disaster response, relief, and mitigation efforts. Deep learning requires high quality labeled data for training across coincident sensors. The FloodPlanet dataset presented here contains labeled surface water for 18 events across the world based on Planetscope imagery with coincident Harmonized Landsat Sentinel-2 ( HLS) or Sentinel-1 and builds upon the previously existing Sen1Floods11, xBD, and NASA Sentinel-1 datasets. Sen1Floods11 includes 4,831 512x512 pixel overlapping tiles of coincident Sentinel-1 and Sentinel-2 data observing 11 flood events across the world from 2017-2019. The dataset contains a combination of automated and hand-labeled surface water for use in training and validation of inundation modeling efforts. The xBD dataset identifies flood-damaged buildings and indicates the scale of damage to each (none, minor, moderate, and major) from four flood events which occurred in the United States, India, Nepal, and Bangladesh from the same time period. The NASA dataset contains hand-labeled water bodies observed in Sentinel-1 imagery during five flood events within the 2017-2019 period. The effort presented here utilizes observations from these previously investigated flood events to generate labels of surface water at the 3-5m spatial resolution provided by Planetscope and facilitate the comparison between public and commercial data. A data pipeline was built which uses clustering algorithms to pick the most suitable overlapping chips between the public data and PlanetScope data for manual labeling. Labels were created manually using NASA’s ImageLabeler tool and include areas of high- and low-confidence water. The high confidence designation is reserved for areas of open, unobstructed water while low confidence is used for areas of suspected water beneath vegetation, clouds, or cloud shadows. Expected to be released in late 2022, the FloodPlanet dataset will include tiled imagery with a unique ID for each 1024x1024 pixel tile, 7 bands of HLS data, and high- and low-confidence flood labels in both shapefile and tiff formats. The authors will follow Spatial Temporal Access Catalog (STAC) guidelines to release FloodPlanet on the Radiant Earth ML hub, which hosts public datasets for machine learning.

Alexander Melancon↗

Parametric Optimization of Rigid Wheels for Planetary Surface Mobility Applications

Design-Build-Test approaches for spaceflight hardware are time and cost intensive, which can result in suboptimal mechanism designs. Optimization-based approaches that utilize high-fidelity models and physics simulation could overcome these limitations while simultaneously speeding up the mechanical design process and reducing cost. In this work, we present a toolchain that enables the multi-objective optimization of rigid rover wheels for planetary surface mobility applications. The toolchain uses Chrono’s Continuous Representation Model (CRM) functionality to simulate granular soil and performs multi-objective parametric optimization on candidate rover wheels to meet a desired performance criterion. The resulting wheel design is then evaluated experimentally using a single-wheel testbed. We end with a discussion of how the toolchain can be extended to simultaneously co-optimize other system parameters, such as system power consumption and feedback control gains.

Optimization↗

Can Machine Learning Reveal Precursors of Reversals of the Geomagnetic Axial Dipole Field?

It is well known that the axial dipole part of Earth’s magnetic field reverses polarity, so that the magnetic North Pole becomes the South Pole and vice versa. The timing of reversals is well documented for the past 160 Myr, but the conditions that lead to a reversal are still not well understood. It is not known if there are reliable ‘precursors’ of reversals (events that indicate that a reversal is upcoming) or what they might be. We investigate if machine learning (ML) techniques can reliably identify precursors of reversals based on time-series of the axial magnetic dipole field. The basic idea is to train a classifier using segments of time-series of the axial magnetic dipole. This training step requires modification of standard ML techniques to account for the fact that we are interested in rare events—a reversal is unusual, while a non-reversing field is the norm. Without our tweak, the ML classifiers lead to useless predictions. Perhaps even more importantly, the usable observational record is limited to 0–2 Ma and contains only five reversals, necessitating that we determine if the data are even sufficient to reliably train and validate an ML algorithm. To answer these questions we use several ML classifiers (linear/non-linear support vector machines and long short-term memory networks), invoke a hierarchy of numerical models (from simplified models to 3-D geodynamo simulations), and two palaeomagnetic reconstructions (PADM2M and Sint-2000). The performance of the ML classifiers varies across the models and the observational record and we provide evidence that this is not an artefact of the numerics, but rather reflects how ‘predictable’ a model or observational record is. Studying models of Earth’s magnetic field via ML classifiers thus can help with identifying shortcomings or advantages of the various models. For Earth’s magnetic field, we conclude that the ability of ML to identify precursors of reversals is limited, largely due to the small amount and low frequency resolution of data, which makes training and subsequent validation nearly impossible. Put simply: the ML techniques we tried are not currently capable of reliably identifying an axial dipole moment (ADM) precursor for geomagnetic reversals. This does not necessarily imply that such a precursor does not exist, and improvements in temporal resolution and length of ADM records may well offer better prospects in the future.

Kyle Gwirtz↗

Amino Acid Encoding for Deep Learning Applications

Background: The number of applications of deep learning algorithms in bioinformatics is increasing as they usually achieve superior performance over classical approaches, especially, when bigger training datasets are available. In deep learning applications, discrete data, e.g. words or n-grams in language, or amino acids or nucleotides in bioinformatics, are generally represented as a continuous vector through an embedding matrix. Recently, learning this embedding matrix directly from the data as part of the continuous iteration of the model to optimize the target prediction – a process called ‘end-to-end learning’ – has led to state-of-the-art results in many fields. Although usage of embeddings is well described in the bioinformatics literature, the potential of end-to-end learning for single amino acids, as compared to more classical manually-curated encoding strategies, has not been systematically addressed. To this end, we compared classical encoding matrices, namely one-hot, VHSE8 and BLOSUM62, to end-to-end learning of amino acid embeddings for two different prediction tasks using three widely used architectures, namely recurrent neural networks (RNN), convolutional neural networks (CNN), and the hybrid CNN-RNN. Results: By using different deep learning architectures, we show that end-to-end learning is on par with classical encodings for embeddings of the same dimension even when limited training data is available, and might allow for a reduction in the embedding dimension without performance loss, which is critical when deploying the models to devices with limited computational capacities. We found that the embedding dimension is a major factor in controlling the model performance. Surprisingly, we observed that deep learning models are capable of learning from random vectors of appropriate dimension. Conclusion: Our study shows that end-to-end learning is a flexible and powerful method for amino acid encoding. Further, due to the flexibility of deep learning systems, amino acid encoding schemes should be benchmarked against random vectors of the same dimension to disentangle the information content provided by the encoding scheme from the distinguishability effect provided by the scheme.

Deep-learning↗

Multisensor Machine Learning to Retrieve High Spatiotemporal Resolution Land Surface Temperature

Climate change is making heat waves more frequent, long-lasting, and severe. While multiple satellite types provide data to monitor surface temperature, geostationary (GEO) sensors provide near-continuous, continental-scale observations which can better capture the diurnal variability of land surface temperature (LST) than intermittent observations from low-earth orbit (LEO) sensors. However, standard products from GEO satellites are available at coarsened spatial and temporal resolutions compared to the native sensor resolution. Using datasets from the NASA Earth Exchange, we leveraged co-located, co-temporal observations from LEO and GEO satellites to learn a data-driven mapping using a convolutional neural network. The resulting NASA Earth eXchange Artificial Intelligence LST (NEXAI-LST) achieved a mean absolute error of 1.73 K relative to the target LEO product and improves on both spatial and temporal resolution [2 km, 10 minute] compared to the GEO full disk standard product [10 km, hourly]. In validation against measurements from a ground-based sensor network, NEXAI-LST achieves similar or better fit than both LEO and GEO standard products, while depending none of the prior knowledge of land surface and atmospheric states required by physical-statistical models. Further, application of the model to unseen LEO and GEO satellites demonstrates robust generalization of the model across spatial region, time of day, and sensor. In support of NASA’s open-source science initiative, we make our NEXAI-LST product, model, and codes available to facilitate data exploration and further studies.

Kate Marie Duffy↗

Energy-Optimized Path Planning for Uas in Varying Winds Via Reinforcement Learning

In this paper we propose a reinforcement learning (RL) algorithm for path planning of Unmanned Aviation Vehicles (UAVs) under varying wind conditions. Solutions to UAV path planning problems are becoming increasingly necessary as autonomous UAVs continue to enter commercial and government spaces. Path-planning is inherently challenging, as UAVs need to account for dynamically changing flying conditions such as weather, obstacle or no-fly zones, degraded vehicle health, and off-nominal battery power consumption. Machine learning methods such as reinforcement learning (RL) have the potential to revolutionize how vehicles navigate in such uncertain environments. In this study, we compute UAV trajectories from a pre-determined starting position to a target cell within a 7X7 grid environment by optimizing parameters for mission assurance and safety limits in addition to the energy consumption and operation time. The UAV navigates the grid by taking actions to move in any of the eight cardinal and inter-cardinal directions, under constant thrust profile. The resultant UAV state is sampled from a probability distribution which accounts for the UAV’s action, local wind velocity, and the presence of obstacles or boundaries. As the unmanned airspace gets more complex due to multiple vehicles and environmental uncertainties, trade-offs between energy consumption, operation time, risk tolerance, and mission assurance need to be made. Our Markov Decision Process (MDP) environment model can capture any combination of these in the optimization objective, making it novel compared to other work in the field.

trajectory planning↗

Enabling Space Biological Knowledge Discovery Through Image and Video Data Sharing

Increased biomedical risks associated with deep space crewed missions (cis-Lunar, Mars transit/surface) require development of health countermeasures, novel ecosystem support, risk modeling, and fundamental space biological knowledge discovery. Molecular-omics, physiological-phenotypic-behavioral, and environmental-radiation telemetry data from space biological and health studies are needed for reuse by scientists to address these tasks. The data as well as space-relevant biospecimens are being made more findable, accessible, interoperable, and reusable through NASA’s Open Science Data Repository (OSDR). This new OSDR umbrella grouping includes NASA GeneLab, the NASA Ames Life Sciences Data Archive (ALSDA), and the NASA Biological Institutional Scientific Collection. The OSDR system design appropriately handles metadata and processed-tabular results from ALSDA studies collected from space experiments. But raw and processed ALSDA bioimage and video datasets require an expansion of OSDR’s data architecture to handle ingestion, curation, and egress. The academic-industry bioimaging field saw a scientific renaissance in the past several years through leveraging open-source software, international collaborations, machine learning, and other open science/programming approaches. As crewed missions and more biological experiments are on the deep space horizon, OSDR is embracing data stewardship through listening to feedback from subject matter experts and designing an expanded architecture which is appropriate for NASA’s goals to enable analysis and reuse of bioimaging and video data for the public science community.Discovery Through Image and Video Data Sharing

space biology↗

Application of Domain Knowledge to Software Quality Assurance

This work focused on capturing, using, and evolving a qualitative decision support structure across the life cycle of a project. The particular application of this study was towards business process reengineering and the representation of the business process in a set of Business Rules (BR). In this work, we defined a decision model which captured the qualitative decision deliberation process. It represented arguments both for and against proposed alternatives to a problem. It was felt that the subjective nature of many critical business policy decisions required a qualitative modeling approach similar to that of Lee and Mylopoulos. While previous work was limited almost exclusively to the decision capture phase, which occurs early in the project life cycle, we investigated the use of such a model during the later stages as well. One of our significant developments was the use of the decision model during the operational phase of a project. By operational phase, we mean the phase in which the system or set of policies which were earlier decided are deployed and put into practice. By making the decision model available to operational decision makers, they would have access to the arguments pro and con for a variety of actions and can thus make a more informed decision which balances the often conflicting criteria by which the value of action is measured. We also developed the concept of a 'monitored decision' in which metrics of performance were identified during the decision making process and used to evaluate the quality of that decision. It is important to monitor those decision which seem at highest risk of not meeting their stated objectives. Operational decisions are also potentially high risk decisions. Finally, we investigated the use of performance metrics for monitored decisions and audit logs of operational decisions in order to feed an evolutionary phase of the the life cycle. During evolution, decisions are revisisted, assumptions verified or refuted, and possible reassessments resulting in new policy are made. In this regard we implemented a machine learning algorithm which automatically defined business rules based on expert assessment of the quality of operational decisions as recorded during deployment.

Wild, Christian W.↗

LIPA: Lunar Ice Perception Algorithm

The highest concentration of Lunar water-ice stores exists within the Permanently Shadowed Regions (PSRs) of the Lunar South Pole. As such, the ability to locate in situ water-ice stores in an accurate, systematic, and safe manner will prove vital for future Lunar activities which rely on hydrogen-based resources. Here we show how the strong absorptive properties of ice can be exploited (by coupling robotics, infrared imaging techniques, and machine learning) so that surface frost located in PSRs can be easily differentiated from the surrounding frozen regolith. Testbeds which simulate an icy lunar landscape were created and then imaged using a mid-wave infrared (MWIR) camera system mounted to a robotic arm (UR5e). Testbeds were imaged under two filter modes (1) wide band mode: whereby imagery captured filled a spectral range of 3.0 - 5.0 μm and (2) narrow band mode: whereby imagery captured were confined to a single central wavelength (CWL) of 3.15 ± 0.03 μm. A CWL of 3.15 μm was chosen due to the highly absorptive nature of ice at that specific wavelength. Images produced under both camera modes were processed in MATLAB. Narrow band images (NB) were subtracted from their wide band (WB) counterparts to produce differenced images (DI) which clearly demonstrated the spatial extent of ice (e.g., WB – NB = DI). Differenced images were used to train a Microsoft Azure model to discriminate between frozen regolith which did and did not contain ice. These works prove promising for future in situ resource utilization (ISRU) missions which employ robotics in combination with camera systems to advance science objectives (e.g., locate water-ice in frozen regolith) on the lunar surface.

Ane Slabic↗

Mapping Inundation from Hurricane Florence (2018) with L-Band Synthetic Aperture Radar, Commercial Imagery, and Ancillary Data via Machine Learning Classification

During and after flooding events, mapping the extent of floodwaters aids in the distribution of resources, recovery efforts, and damage assessment practices. Development of a land cover classification system focused on mapping inundation after major hurricane events using synthetic aperture radar (SAR) data could allow for the production of near-real-time inundation mapping, enabling government and emergency response entities to get a preliminary idea of a developing situation. Complimentary optical and SAR images from domestic and foreign entities are brought together through activations of the International Charter: Space and Major Disasters to support response efforts, from true-color, near-infrared, and thermal remote sensing data obtained by NASA, NOAA, and international satellites to the collection of high-resolution true color aerial photography by NOAA and the National Geodetic Survey. In response to Hurricane Florence of 2018, NASA JPL collected numerous swaths of quad-pol L-band SAR data with the Uninhabited Aerial Vehicle Synthetic Aperture Radar (UAVSAR) instrument observing the record-setting river stages across North and South Carolina. The resulting fully-polarized SAR images allow for mapping of inundation extent at a high spatial resolution with a unique advantage over optical imaging stemming from the sensor’s ability to penetrate cloud cover and dense vegetation. In this study, true-color NOAA aerial and commercial satellite imagery are used in conjunction with four UAVSAR data swaths centered on the Lumberton and Cape Fear River basins in southeastern North Carolina to develop a Random Forest classification model focused on mapping open water and floodwater otherwise obscured by vegetation or lingering cloud cover. Ancillary building footprint, transportation route, and population data will also be incorporated into the classification scheme to estimate the societal impacts of flooding based on the proximity of features to detected inundation. Preliminary results from the Hurricane Florence case study will be discussed in addition to the limitations of available validation data for assessment of the classifier’s accuracy.

Alexander M Melancon↗

Applications of Intelligent Tutoring Systems to Human-Robotic Exploration of Mars

Space missions with small crews extending over several years with time-delay preventing normal conversations with people on earth will raise many challenges for training. Of special interest are possible three-year missions to Mars, requiring refresher instruction and learning new skills based on unexpected problems with machines and environmental conditions. For example, the crew will be required to monitor and repair more complex life support systems for air and water recycling than we even know how to build today. Highly educated astronauts, often with several doctorate degrees, require a very different mode of interaction than we have developed for school children or even typical college students. Explanation methods may need to differ-using analogies and techniques from different domains-depending on whether the astronaut is an astrophysicist, a pilot, or a geologist.Virtual reality (e.g., for Hubble repair missions) and "integrated" simulations (involving role-playing and emphasizing failure scenarios) are the most common advanced forms of instruction used in space flight today. The emphasis is on collaborative, embodied interaction with the same workstations and tools used in practice (e.g., a cockpit simulator). Otherwise, computerized instructional technology used by NASA is not model-based or tutorial in nature. This discussion will review some of the key instructional methods used at NASA over the past two decades and consider why ITS methods have not been exploited. Some of the problems and opportunities for training for Mars missions are examined, including how using robots in exploration activities will help but raise new training problems. These ideas will be illustrated with examples from the BrahmsVE system in which a browser- based virtual reality display with avatars allows interacting with a distributed multiagent system, in which agents can be people, robots, or software programs. Using BrahmsVE may provide a way for astronauts to interact with proxies of people who serve as instructional coaches on Mars.

Clancey, William J.↗

Real World Applications of AI/ML in Optimizing Airspace Operations

As National Airspace System (NAS) is going through the Digital Transformation journey, data science and analytics methods can significantly contribute to improving the traditional physics-based decision-making tools. The adoption of AI/ML methods will not only help accelerate Federal Aviation Administration (FAA)’s vision of Info-centric NAS but also contribute to the overall objective of sustainable aviation. AI/ML can improve the ground and airspace operations by enhancing the accuracy of current decision-making tools used by the airlines and the FAA to manage traffic on the ground and in the air. Huge amount of data that gets collected during a flight. AI/ML methods can extract information from this data and provide valuable insights to make better operational decisions. NASA has partnered with the FAA and commercial airlines such as American and Southwest Airlines on this effort and has successfully demonstrated the benefits of using ML in real world environment by reducing delays and optimizing ground operations at the US airports. In 2022 itself, NASA demonstrated real-world benefits (over 24K lbs. of fuel savings, over 76.6K lbs. CO2 emission savings, and several hours of delay savings) by deploying ML based prediction models to optimize ground operations at Dallas/Fort Worth International and Dallas Love Field Airports in Texas. These tools are being deployed on the cloud for broader deployment, adaptability, and scalability. NASA is developed a reference implementation of the cloud-based platform to significantly lower the bar to development and distribution of these digital services for aviation. In this talk, I will share information about the Digital Information Platform project, the novel AI/ML based approaches used for optimizing ground operations and the opportunities to partner with NASA on these demonstrations.

air traffic management↗

From biological neural networks to thinking machines: Transitioning biological organizational principles to computer technology

The three-dimensional organization of the vestibular macula is under study by computer assisted reconstruction and simulation methods as a model for more complex neural systems. One goal of this research is to transition knowledge of biological neural network architecture and functioning to computer technology, to contribute to the development of thinking computers. Maculas are organized as weighted neural networks for parallel distributed processing of information. The network is characterized by non-linearity of its terminal/receptive fields. Wiring appears to develop through constrained randomness. A further property is the presence of two main circuits, highly channeled and distributed modifying, that are connected through feedforward-feedback collaterals and biasing subcircuit. Computer simulations demonstrate that differences in geometry of the feedback (afferent) collaterals affects the timing and the magnitude of voltage changes delivered to the spike initiation zone. Feedforward (efferent) collaterals act as voltage followers and likely inhibit neurons of the distributed modifying circuit. These results illustrate the importance of feedforward-feedback loops, of timing, and of inhibition in refining neural network output. They also suggest that it is the distributed modifying network that is most involved in adaptation, memory, and learning. Tests of macular adaptation, through hyper- and microgravitational studies, support this hypothesis since synapses in the distributed modifying circuit, but not the channeled circuit, are altered. Transitioning knowledge of biological systems to computer technology, however, remains problematical.

Ross, Muriel D.↗

Towards Understanding Data Requirements for Developing Automatic Speech Recognition Systems for Air Traffic Control

In recent years, the application of automatic speech recognition has gained popularity across diverse industries, including aviation. Given the many applications focusing on transcribing air traffic control and management communication, this paper explores the training of OpenAI's Whisper model across multiple existing public and private air traffic control voice datasets in an effort to improve robustness. Combining roughly 60+ hours of various air traffic datasets, our goal is to train a unified Whisper model and expect an average word error rate reduction across testing datasets. Furthermore, this work aims to understand the data quantity requirements for achieving state-of-the art results by comprehensively training Whisper on varying dataset sizes. This work has the potential to improve automatic speech recognition performance across the domain, improve understanding of the quantity of data required by an aviation speech recognition system, and lastly provide metrics to compare and improve upon in future research.

ATC↗

Mechanical Prototyping and Manufacturing Internship

The internship was located at the Johnson Space Center (JSC) Innovation Design Center (IDC), which is a facility where the JSC workforce can meet and conduct hands-on innovative design, fabrication, evaluation, and testing of ideas and concepts relevant to NASA's mission. The tasks of the internship included mechanical prototyping design and manufacturing projects in service of research and development as well as assisting the users of the IDC in completing their manufacturing projects. The first project was to manufacture hatch mechanisms for a team in the Systems Engineering and Project Advancement Program (SETMAP) hexacopter competition. These mechanisms were intended to improve the performance of the servomotors and offer an access point that would also seal to prevent cross-contamination. I also assisted other teams as they were constructing and modifying their hexacopters. The success of this competition demonstrated a proof of concept for aerial reconnaissance and sample return to be potentially used in future NASA missions. I also worked with Dr. Kumar Krishen to prototype an improved thermos and a novel, portable solar array. Computer-aided design (CAD) software was used to model the parts for both of these projects. Then, 3D printing as well as conventional techniques were used to produce the parts. These prototypes were then subjected to trials to determine the success of the designs. The solar array is intended to work in a cluster that is easy to set up and take down and doesn't require powered servomechanisms. It could be used terrestrially in areas not serviced by power grids. Both projects improve planetary exploration capabilities to future astronauts. Other projects included manufacturing custom rail brackets for EG-2, assisting engineers working on underwater instrument and tool cases for the NEEMO project, and helping to create mock-up parts for Space Center Houston. The use of the IDC enabled efficient completion of these projects at significantly reduced cost. I acquired and improved manufacturing and prototyping skills during my tour including learning about a CAD (Computer-Aided Design) program called Creo (Creo Parametric; design software), gaining valuable conventional machining experience with lathes, CNC (Computer Numerical Control) milling machines and various other tools, and improving my engineering project communication and collaboration skills. The internship also allowed me to better understand operations at NASA. I plan to work in the aerospace industry or do academic research benefitting space science and exploration, and this internship experience will enable me to have insight into manufacturing processes for research and development.

Grenfell, Peter↗

Monitoring Airspace Complexity and Determining Contributing Factors

The national airspace has evolved over many years to accommodate increased traffic demand [1] while simultaneously maintaining one of the safest forms of transportation [2], [3]. One of the reasons for this success is the ability of the system and the operators to adapt and accommodate to situations that routinely disrupt optimal operations. These situations may include: adverse weather, delays, early arrivals, equipment outages, and other factors that are outside the operators ability to control. These factors can lead to states where automation is unable to properly handle these issues and therefore air traffic controllers and pilots have to intervene, ultimately increasing communication between operators resulting in higher workload. As controller workload increases to handle sub-optimal operating conditions this can be viewed as an increase in complexity. The reasoning for this is because humans are now required to make tactical decisions in response to external factors, resulting in a departure from the strategic plan where operations would be more efficiently managed. Human operators control airspace complexity under rigid regulations that are constantly changing. The airspace is divided into sectors and the number of aircraft assigned to each controller is limited for safe handling. There has been past work that devised airspace complexity metrics in commercial aviation and related these metrics to controller workload (e.g., [4],[5]). The upper bounds on the system load are pre-determined. Such bounds on complexity make for a safe system, but the system cannot scale and adapt to autonomous, dense, and heterogeneous traffic, including the many types of Unmanned Aerial Vehicles (UAVs) envisioned to be added to the operations. We hypothesize that, as traffic density and heterogeneity grow, and other key metrics change, there will be phase transitions at which the way traffic should be managed changes significantly [6]. We offer a method for in-time detection of contributing factors that lead to phase transitions, characterized by increased complexity. To the best of our knowledge, there is no tool similar to our proposed effort that identifies such contributing factors or precursor patterns. To define the scope we are proposing to measure complexity from the viewpoint of the Terminal Radar Approach Control Facilities (TRACON) controller’s perspective. In particular we are analyzing arrivals into KSFO. With safety as the top concern for airspace operators, it is important to recognize that as density and heterogeneity grow, the focus of the system will change. Times of the day when the airspace has low density and heterogeneity, the flights will follow more efficient paths where the aircraft move on established routes that are more or less directly to the destination. However, when density and heterogeneity increases, the system will begin changing focus to avoiding conflicts and collisions and route the flights in a more flexible way. Higher flexibility requires more communication and coordination between controllers and pilots which the current automation is unable to handle. This paper proposes a novel approach that monitors airspace complexity at multiple scales, uses a Machine Learning-based tool that predicts when operations will transition to a regime of greater complexity, and identifies actions that can reduce the complexity while still maintaining efficient and safe operations. We demonstrate our proposed approach using data from multiple complementary sources. This includes, but is not limited to: historical aircraft surveillance data from NASA’s Sherlock Data Warehouse [7], METAR weather data, and airport configuration data from Aviation System Performance Metrics (ASPM). The surveillance data flight paths are sampled at a variable sample rate — increasing as the aircraft approaches the airport. This is due to how Sherlock manages flight track stitching between different radar facilities which have different sampling rates. The weather and performance data are logged at defined intervals throughout the day at a courser refresh rate. In addition to the logged data and metrics, we leverage pre-defined Standard Terminal Arrival Routes (STARs) procedures to characterize the path of each flight. Each flight files for one of these routes in the flight plan well before entering the terminal airspace, and approximately follows the route until it leaves the STAR, typically on the final fix of a runway transition. However, most flights do not always fly the full STAR procedure to completion [8], but the majority do adhere to the fixes within the common route of the procedure. Our approach leverages fixes in the common route of each of the STARs to build a reference path to the airport. This allows us to characterize the flight paths in what we are defining as the “maneuvering area” (the airspace between the STAR and before the flight is lined up on the runway’s final approach) to determine how off nominal the flights are to calculate its complexity score. Determining airspace complexity is a concept that does not have a concrete answer. In designing this metric, we consider what increases the workload for the air traffic controllers. Consequently more specialized vectoring maneuvers results in higher workload. Accordingly, we start with a theory: each flight has a direct path it takes from the STAR’s common route to the final approach’s outer marker fix for the flight’s landing runway. It is important to note that the direct path is only used as a reference. If the majority of the flights have a large consistent offset as compared to other routes it does not necessarily mean that those flights have higher complexity. We are merely building a distribution based on this direct path for that particular STAR and runway pair to determine the normal mode of operations for that route. Flights that are in the upper tail of these distributions will result in higher complexity scores and flights that fly in the median will represent the normal mode of operations and therefore will have lower complexity scores. Since flights following each STAR route take different paths to the airport, we have a different distribution for each STAR route and therefore can model these distributions to compute a complexity score from their respective normalized distributions. To evaluate the effectiveness of our proposed airspace complexity metric we will compare against an established approach based on trajectory clustering [9]. This unsupervised learning technique consists of the following steps: (1) identify the general maneuvering areas (waypoints) by performing $\kappa$-means or DBSCAN clustering on locations where aircraft frequently turn based on the surveillance radar track data, (2) map flight trajectories onto sequences of waypoints, and (3) cluster the sequences based on their common subsequences. From a high-level perspective, this baseline model learns nominal operations in the airspace through the sequence of waypoints that are representative of where aircraft change direction and defines deviations from the nominal operations as “complex.” Therefore, more deviations from the nominal operations correspond to higher complexity values. For our validation, we re-implemented this technique and tune model hyper-parameters to correctly detect waypoints for the arrival traffic into the San Francisco bay area. We will compute the complexity measure over a one-year period using our proposed technique as well as the baseline. Our validation will be based on each technique’s ability to detect a set of undesirable outcomes (e.g., go-arounds, holding patterns, average time in the airspace, etc.). Since our current complexity metric is derived from the offset from the direct reference path, it’s important to understand what causes these offsets. In many of the flights with high offset distance, flights performing holding patterns and S turns can be observed. These maneuvering tactics are utilized to add distance between the aircraft and the destination runway to prevent multiple flights from having conflicting arrival times. In order to predict a rise in complexity (or the precursor to complexity), it’s necessary to be able to identify these potential conflicts (which in turn, result in higher offsets). To do this, we define a “representative flight” for each STAR route and runway pair. This flight is approximately the path the flight would take if there was a clear path with no other flights in the airspace — including the time remaining to the airport. We first identify the flights for a given STAR runway pair using the offset to the reference path distributions that fall between the 44-55 percentiles. This yields the flights that conform to the most normal mode of operation. Each of these flights is partitioned based on the percent complete from the entry point into the maneuvering areas from 0\% – 100\% complete. Then for each percent “bin”, we take the median value of the flight’s latitude/longitude coordinates, airspeed, and (non causal) time remaining to the airport to construct a lookup table for each percent complete bin on a given route. As a flight enters the maneuvering area, we can find the estimated arrival time of a flight to the airport by finding the closest point to the representative path’s percent complete bin (relative to the flight’s current position at any snapshot in the airspace) and therefore retrieve the corresponding remaining time left on the “representative path”. We assume that the flight will follow the representative path to completion when deriving these estimates. We can then compare these estimated arrival times against other flights for the same snapshot in time to identify potential conflicts. If more flights are estimated to arrive within a tolerance window than there are runways available, then we have a potential conflict. We can use this derived measure along with other factors expected to add disruption to the operation such as weather and runway configuration changes as an input to machine learning tools to detect precursors that increases in our complexity measure. This novel method will assist in uncovering insights into the contributing factors that lead to increased complexity that may allow for in-time responses to avoid reaching a high complexity state in the airspace.

complexity↗

Large-Scale Groundwater Monitoring in Brazil Assisted With Satellite-Based Artificial Intelligence Techniques

Here, we develop and test an artificial intelligence (AI)-based approach to monitor major Brazilian aquifers. The approach combines Gravity Recovery and Climate Experiment (GRACE) data and ground-based hydrogeological measurements from Brazil’s Integrated Groundwater Monitoring Network at hundreds of wells distributed in twelve aquifers across the country. We tested model ensembles based on three AI approaches: Extreme Gradient Boost, Light Gradient Boosting Model and CatBoost, followed by a Linear Regression (LR) step. The approach is further boosted with wavelet and seasonal decomposition processes applied to GRACE data. To determine the AI-based model’s sensitivity to data availability, we propose four experiments combining hydrogeological measurements from different aquifers. Groundwater storage estimates from the Global Land Data Assimilation System (GLDAS) are used as benchmark. A sensitivity analysis shows that the LR-based model ensemble is the best suited and to reproduce groundwater storage change in all studied Brazilian aquifers. Results show that the proposed approach outperforms GLDAS in all experiments, with an RMSE value of 2.68cm for the experiment that covers all monitored wells in Brazil. GLDAS resulted in RMSE=6.76cm. Using our AI model outputs, we quantified the groundwater storage change of two major aquifers, Urucuia and Bauru-Caiuá, over the past two decades: -31km 3 and -6km 3 , respectively. Water loss is driven by a prolonged drought across most of the country and intensification of groundwater pumping for irrigation. This study demonstrates that combining satellite data and AI can be a cost-effective alternative to monitor poorly equipped aquifers at the continental scale, with possible global replicability.

GRACE↗