Search NASA⌕ Search

SEARCH · Search NASA

Results for “spectrum training”

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 145 records · Page 8
All sourcesNASA NTRSDOE OSTI
DOE OSTI2024

Spread spectrum time domain reflectometry (SSTDR) and frequency domain reflectometry (FDR) cable inspection using machine learning

Cables are initially qualified for nuclear power plant use for 40 years. As plants extend their operating license to 60 and 80 years, justification for continued cable use must shift to a condition-based approach since it is cost prohibitive to completely replace cables that are likely still capable of performing their design function. The Pacific Northwest National Laboratory (PNNL) Accelerated and Real Time Experimental Nodal Analysis (ARENA) cable motor test bed was used to test the response of a commercial spread spectrum time domain reflectometry (SSTDR) system, a laboratory instrument software-controlled SSTDR, and a vector network analyzer-based frequency domain reflectometry (FDR) system to various cable anomalies. The three instrument systems were able to interrogate cables over a range of frequency bandwidths that can be helpful for human data analysis. Data were subjected to supervised and unsupervised machine learning (ML) analyses to distinguish normal undamaged cable responses from anomalous cable responses. Both supervised and unsupervised ML approaches produced encouraging results with an undamaged/anomalous prediction accuracy from 0.69% to 0.87%. Recommendations for further development and field implementation include increased and more balanced sample sets particularly including more training data.

SSTDR, FDR, Reflectometry, Machine Learning, ARENA↗
DOE OSTI2022

Super-resolution image display using diffractive decoders

High-resolution image projection over a large field of view (FOV) is hindered by the restricted space-bandwidth product (SBP) of wavefront modulators. We report a deep learning–enabled diffractive display based on a jointly trained pair of an electronic encoder and a diffractive decoder to synthesize/project super-resolved images using low-resolution wavefront modulators. The digital encoder rapidly preprocesses the high-resolution images so that their spatial information is encoded into low-resolution patterns, projected via a low SBP wavefront modulator. The diffractive decoder processes these low-resolution patterns using transmissive layers structured using deep learning to all-optically synthesize/project super-resolved images at its output FOV. This diffractive image display can achieve a super-resolution factor of ~4, increasing the SBP by ~16-fold. We experimentally validate its success using 3D-printed diffractive decoders that operate at the terahertz spectrum. This diffractive image decoder can be scaled to operate at visible wavelengths and used to design large SBP displays that are compact, low power, and computationally efficient.

36 MATERIALS SCIENCE↗
DOE OSTI2025

Contrasting Time-Frequency Representations for Unknown Waveform Detection

In real-world applications like spectrum management and interference detection, dealing with unseen electromagnetic waveforms is critical. Although some methods attempt to simulate open set data using generator models, they face challenges in generating synthetic samples for open set while simultaneously selecting an optimal discriminator for accurate classification. This results in difficulties capturing distinctive features across classes, especially in dynamic scenarios where new classes emerge. To detect unseen waveforms, we propose combining time and frequency domain features with cosine similarity loss to enhance feature distinctiveness and enabling more accurate predictions. This approach efficiently captures more comprehensive information than single-domain representations or approaches without cosine loss. Additionally, our model avoids generic feature vectors by extracting class-specific features during training, resulting in improved class representation. The experiment results show that this combined feature approach with cosine loss outperforms single-domain models and improves accuracy by 10\% over models without cosine loss.

99 - GENERAL AND MISCELLANEOUS↗
DOE OSTI2025

Contrasting Time-Frequency Representations for Unknown Waveform Detection

Identifying unseen electromagnetic waveforms is critical for many applications, like interference management, electronic warfare and spectrum management. Traditionally this is done using statistical methods for anomaly detection, which has evolved to deep learning models for identifying the unseen data, formally termed as open set recognition. Some prior methods use a generative model to emulate open set data, which face challenges in generating synthetic samples for open set while simultaneously selecting an optimal discriminator for accurate classification. To alleviate this issue, we propose a discriminative model that effectively combines time and frequency domain features of communication signals for accurate predictions. We further introduce a cosine similarity loss that makes the domain specific features unique to enhance the prediction rate. Additionally, our model avoids generic feature vectors by extracting class-specific features during training, resulting in improved class representation. The experiment results show that this combined feature approach with cosine loss outperforms single-domain models and improves accuracy by 10% over models without cosine loss.

99 - GENERAL AND MISCELLANEOUS↗
DOE OSTI2023

A Transductive Graph Neural Network learning for Grid Resilience Analysis

Power grids are critical infrastructures that require robust resilience analysis to ensure reliable and uninterrupted electricity supply. Traditional simulation-based methods for grid resilience analysis suffer from computational complexity and limited ability to capture the full spectrum of potential disruptions. This paper presents a novel approach to enhance grid resilience by leveraging transductive graph neural network (GNN) learning to identify critical nodes and links. By leveraging the graph structure and system features, GNNs effectively learn resilience metrics and accurately identify critical nodes based on actual grid operational behavior. The efficacy of the proposed approach is demonstrated through case studies on node criticality scoring and critical node/line identification in cascading outage scenarios. The results highlight the advantages of learning-based methods over traditional simulation-based approaches and their potential to revolutionize grid resilience analysis. The contributions of this paper include a graph-based scalable approach for fast cascading analysis, an inductive formulation for training GNN models, and a transfer learning-based approach to scale the model to largescale power systems.

grid resilience, graph neural networks, transducti↗
DOE OSTI2025

A cross-dimensional analysis of data-driven short-term load forecasting methods with large-scale smart meter data

Electricity load forecasting is essential to utility operation and power grid stability. A wide spectrum of data-driven methods, ranging from linear regression models to more recent deep learning models have been adopted to forecast electric load over the years. However, there still lacks a holistic evaluation of the applicability of conventional statistical and machine learning based algorithms with respect to different temporal and spatial scopes, computational requirements, and sensitivity of model-tuning. Enabled by a large-scale electricity load profile dataset of over 40,000 residential customers in a utility region, we conducted a cross-dimensional analysis of data-driven load forecasting methods. Three regression-based and seven deep learning algorithms with different model configurations were evaluated in terms of their overall and peak load prediction accuracy, and training burdens, across spatial aggregation levels ranging from the transformer, feeder, substation, to neighborhood. We found, first, the load forecasting accuracy is constrained by a predictability boundary, influenced by the forecasting horizon and spatial aggregation level. Specifically, RandomForest, XGBoost, TFT, TSMixer, and TiDE models achieved less than 10 % prediction error for up to 96-h ahead forecasting for district, substation, and feeder levels, while other models struggle at long-horizon predictions; Second, for winter and summer peak load dates, most models were able to predict the peak demand timing within ± 1 h, but the prediction percentage error varied by models, with TFT and TiDE models being the top performers; Third, models with similar prediction accuracy can differ in training burden by an order of magnitude. Therefore, choosing model configurations that balance prediction performance and computational resource is an important practical consideration for large-scale deployment of the machine learning based load forecasting. The outcome of this study can guide researchers and practitioners to choose the proper load forecasting algorithms based on their problem scope, required accuracy, and available resources. The predictability boundary can serve as a benchmark for electricity load forecasting problems with new algorithms and datasets.

Li, Han↗
DOE OSTI2026

Random forest models accurately classify synthetic opioids using high-dimensionality mass spectrometry datasets

Detection of novel threat agents presents several challenges, a principle one being the development of untargeted methods to screen an increasing number of threat chemicals whose exact structures are unknown. With the use of Machine Learning (ML) tools, we can guide the development of analytical methods for broad-spectrum detection of unbounded threat chemical families in complex mixtures. Toward this goal, we used nominal mass and high-resolution mass spectrometry data for hundreds of synthetic opioids and non-opioid compounds. We tested two ML techniques, logistic regression and random forest, to develop models towards a practical, implementable method for opioid detection. We found that of these tested ML methods, random forest models resulted in the highest validation accuracy (95+%) for both nominal mass and high-resolution classification of opioids versus non-opioids, with low false positive and false negative rates. The RF models were then used to successfully predict the classification of 10 compounds—five opioids and five non-opioids not part of the training and validation analysis. This application of ML is a critical step towards the development of field-deployable nominal mass spectrometers with ML-driven analyses for classification of emergent threats.

Chemistry↗
DOE OSTI2025

Random forest models accurately classify synthetic opioids using high-dimensionality mass spectrometry datasets

Detection of novel threat agents presents several challenges, a principle one being the development of untargeted methods to screen an increasing number of threat chemicals whose exact structures are unknown. With the use of Machine Learning (ML) tools, we can guide the development of analytical methods for broad-spectrum detection of unbounded threat chemical families in complex mixtures. Toward this goal, we used nominal mass and high-resolution mass spectrometry data for hundreds of synthetic opioids and non-opioid compounds. We tested two ML techniques, logistic regression and random forest, to develop models towards a practical, implementable method for opioid detection. We found that of these tested ML methods, random forest models resulted in the highest validation accuracy (95+%) for both nominal mass and high-resolution classification of opioids versus non-opioids, with low false positive and false negative rates. The RF models were then used to successfully predict the classification of 10 compounds—five opioids and five non-opioids not part of the training and validation analysis. This application of ML is a critical step towards the development of field-deployable nominal mass spectrometers with ML-driven analyses for classification of emergent threats.

Arasteh, Kourosh [Lawrence Livermore National Labo↗
DOE OSTI2024

Augmented Human Analysis (AHA)

Radio frequency (RF) signal monitoring generally emphasizes intentionally generated signals, such as WiFi, Bluetooth, or cellular transmissions. However, electronic devices also produce unintended radiated emissions (UREs), which could also be useful in RF spectrum analysis. In either case, deriving intelligence from RF signals is typically a human-intensive process requiring significant domain knowledge. In the Augmented Human Analysis (AHA) project, we investigate the utility of dimensionally aligned signal projection (DASP) and machine learning (ML) algorithms for accelerating RF analysis workflows. We find that while DASP algorithms can indeed highlight signal characteristics relevant for classification tasks, the choice of algorithmic hyperparameters greatly affects performance. To address this challenge, we evaluate the quality of DASP outputs using the silhouette score, which measures how well data points cluster; high silhouette scores indicate good clustering, and thus good hyperparameter values. This approach is critical for machine learning pipelines as the DASP parameters cannot be directly optimized during model training. By identifying good DASP parameters, and thus good DASP outputs, as a preprocessing step, we can decrease the amount of effort required for downstream ML model training. We demonstrate our workflow using a dataset of UREs from common household devices, showing that even without the aid of ML, proper selection of DASP parameters enables clustering by device type.

42 ENGINEERING↗
DOE OSTI2023

Application of unsupervised deep learning to image segmentation and in-situ contact angle measurements in a CO 2 -water-rock system

Rock surface wettability is a critical property that regulates multiphase flows in porous media, which can be quantified using the surface contact angle (CA). X-ray micro-computed tomography (μCT) provides an effective approach to in-situ measurements of surface CAs. However, the CA measurement accuracy depends significantly on the quality of CT image segmentation, which is the clustering of CT pixels into separate phases. Inspired by this, we developed a deep learning (DL)-based CA measurement workflow. Motivated by the recent tremendous progress in unsupervised learning techniques and aiming to avoid expensive manual data annotations, an unsupervised DL pipeline for CT image segmentation was proposed and implemented, which includes unsupervised model training and post-processing. The unsupervised model training was driven by a novel loss function constrained with feature similarity and spatial continuity and implemented by iterative forward and backward paths; the former clustered the pixel-wise feature vectors extracted by convolution neural networks, whereas the latter updated the parameters using gradient descent. An over-segmentation strategy was adopted for model training. The post-processing steps based on agglomerative hierarchical clustering (AHC) were implemented to further merge the over-segmented model output to the desired cluster number, which is intended to improve the efficiency of image segmentation. The developed unsupervised DL pipeline was compared with other commonly-used image segmentation methods using pixel-wise and physics-based evaluation metrics on a synthetic raw-image dataset, which had a known ground truth. The unsupervised DL pipeline showed the best performance. Next, the segmented images were input to an automatic CA measurement tool, and the results were validated by comparisons with manual measurements. The CA values from the manual and automatic measurements showed similar distributions and statistical properties. The automatic measurement demonstrated a wider spectrum because of the much larger number of measurement data points. The primary novelty of the unsupervised DL pipeline developed in this study lies in the novel loss function and the over-segmentation strategy associated with AHC post-processing. Finally, the workflow has been proven an efficient tool for pore-scale wettability characterization, which has a wide range of applications in fundamental studies of multiphase flows in natural porous media, which have critical implications to geological carbon sequestration, hydrocarbon energy recovery, and contaminant transport in groundwater.

42 ENGINEERING↗
DOE OSTI2022

1.4.2.403 - Water Power STEM Workforce Development (Hydro)

As interest in renewable energy grows, water power technologies will continue to play a robust and growing role. However, the industry needs new talent to spur innovation and to support industry needs. With one-quarter of the domestic hydropower workforce retiring in the coming decade, the need to fill the workforce pipeline has never been more critical. The lack of new hydropower development has limited the number of educational programs focused on this sector at all levels of education. NREL has a long track record of working to address educational needs across the renewable energy spectrum. Leveraging this track record, this project brought the Hydropower STEM Portal to water power stakeholders fueled by information from a multitude of sectors, our partnership with the Hydropower Foundation, NEED, and others. The team has also sought to integrate activities with the Bonneville Environmental Foundation, to increase dissemination opportunities and interfaces. The purpose of the portal is to be a one-stop shop to information geared at inspiring the next-generation water power professional. NREL also leverages experience in engaging with stakeholders to understand barriers to technology adoption to identify issues and drivers, provide feedback to the R&D community, work to clarify misperceptions, and inform decisions to facilitate market adoption. The outcome of this work is a more successful and diverse water power industry based on a motivated and better-trained workforce.

ENERGY PLANNING, POLICY, AND ECONOMY,HYDRO ENERGY↗
DOE OSTI2024

Topological and Dynamical Representations for Radio Frequency Signal Classification

Radio Frequency (RF) signals are found throughout our world, carrying over-the-air information for both digital and analog uses with applications ranging from WiFi to the radio. One area of focus in RF signal analysis is determining the modulation schemes employed in these signals which is crucial in many RF signal processing domains from secure communication to spectrum monitoring. This work investigates the accuracy and noise robustness of novel Topological Data Analysis (TDA) and dynamic representation based approaches paired with a small convolution neural network for RF signal modulation classification with a comparison to state-of-the-art deep neural network approaches. We show that using TDA tools, like Vietoris-Rips and lower star filtrations, and the Takens' embedding in conjunction with a standard shallow neural network we can capture the intrinsic dynamical, geometric, and topological features of the underlying signal's manifold, offering informative representations of the RF signals. Our approach is effective in handling the modulation classification task and is notably noise robust, outperforming the commonly used deep neural network approaches in mode classification. Moreover, our fusion of dynamical and topological information is able to attain similar performance to deep neural network architectures with significantly smaller training datasets.

Myers, Audun D.↗
DOE OSTI2024

Machine Learning a Simple Interpretable Short-Range Potential for Silica

A wide array of models, spanning from computationally expensive ab initio methods to a spectrum of force-field approaches, have been developed and employed to probe silica polymorphs and understand growth processes and atomic-level dynamical transitions in silica. However, the quest for a model capable of making accurate predictions with high computational efficiency for various silica polymorphs is still ongoing. Recent developments in short-range machine-learned models, such as GAP and NNPScan, have shown promise in providing reasonable descriptions of silica, but their computational cost remains high compared to force fields such as BKS which are based on simple interpretable functional forms. Here, in this study, we build on the recent success of our reinforcement learning (RL) workflow to derive a new set of optimal parameters for a promising short-range BKS-based model proposed by Soules. We use RL to navigate the eight-dimensional parameter space of the Soules potential using an experimental training data set that includes both local and global structural features from approximately 21 experimentally realized silica polymorphs, including high density phases and porous zeolites. We compare the performance of our machine-learned ML-Soules model with other high quality models including our recent machine-learned parametrization of BKS (ML-BKS), a machine-learned potential (GAP), as well as predictions of ab initio calculations with the highly fidelity SCAN functional. The ML-Soules accurately captures the relative energetic ordering of various polymorphs as well as their structural features at a significantly reduced computational expense. The ML-Soules model also reasonably captures the structure, density, and elastic constants of quartz, as well as metastable silica polymorphs. We further discuss the limitations of the Soules functional form and propose potential enhancements, including the incorporation of additional three-body terms and/or the utilization of different short-ranged functional forms to achieve greater accuracy for both global and local features in the modeling of silica while retaining low computational cost.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2022

Health Physics Research Reactor Criticality Accident Alarm System Benchmark Overview [Slides]

This presentation discusses the Health Physics Research Reactor (HPRR) or Fast Burst Reactor (FBR) and how available data from Health Physics Research Reactor (HPRR) operation to can be used to create a benchmark report for inclusion in the ICSBEP, as a Criticality Accident Alarm System (CAAS) shielding benchmark. The evaluation of experimental data is also presented, specifically four experimental candidates are considered of potential value for the benchmark: 1. Neutron source estimation from a HPRR pulse (energy spectrum, fission yield), 2. Threshold Detector Unit (TDU) measurements at different distances from a HPRR pulse, shielded and unshielded, 3. Sulfur pellet activation at different distances from a HPRR pulse, shielded and unshielded, and 4. Total neutron fluence from a HPRR pulse measured by Bonner Sphere Spectrometry, shielded and unshielded. Additionally, a benchmark model overview is discussed as are sample calculation results.

61 RADIATION PROTECTION AND DOSIMETRY↗
DOE OSTI2022

AMTS update for STTR

Advanced nuclear reactor systems currently in development include designs that utilize higher energy neutron spectrums, higher temperatures, and corrosive environments that are quite different from the current fleet of nuclear power plants in use today. As a result, new structural materials must be developed and qualified for use to support these advanced systems. For example, research is currently being conducted on a new class of materials known as multi-principle-element-alloys. These alloys show some promise to be able to meet the structural needs of these challenging reactor systems. However, due to the vast available compositional space, and the limited amount of research conducted thus far, Idaho National Laboratory (INL)sought a way to advanced mechanical testing capability for highly irradiated structural materials to increase both throughput and higher fidelity data analysis through incorporation of digital image correlation. The Automated Mechanical Testing System accomplishes these tasks by automating the testing and incorporating digital image correlation to provide higher fidelity data. INL has now received this system and is currently performing functional testing and training. INL is also performing some modifications to the system to allow for installation into a remote shielded enclosure where testing of irradiated structural materials can be performed. After testing, training, and modifications of the system are complete, INL will install the system into a shielded enclosure and begin using the system to test irradiated structural materials.

36 MATERIALS SCIENCE↗
DOE OSTI2021

Processed Lab Data for Neural Network-Based Shear Stress Level Prediction

Machine learning can be used to predict fault properties such as shear stress, friction, and time to failure using continuous records of fault zone acoustic emissions. The files are extracted features and labels from lab data (experiment p4679). The features are extracted with a non-overlapping window from the original acoustic data. The first column is the time of the window. The second and third columns are the mean and the variance of the acoustic data in this window, respectively. The 4th-11th column is the the power spectrum density ranging from low to high frequency. And the last column is the corresponding label (shear stress level). The name of the file means which driving velocity the sequence is generated from. Data were generated from laboratory friction experiments conducted with a biaxial shear apparatus. Experiments were conducted in the double direct shear configuration in which two fault zones are sheared between three rigid forcing blocks. Our samples consisted of two 5-mm-thick layers of simulated fault gouge with a nominal contact area of 10 by 10 cm^2. Gouge material consisted of soda-lime glass beads with initial particle size between 105 and 149 micrometers. Prior to shearing, we impose a constant fault normal stress of 2 MPa using a servo-controlled load-feedback mechanism and allow the sample to compact. Once the sample has reached a constant layer thickness, the central block is driven down at constant rate of 10 micrometers per second. In tandem, we collect an AE signal continuously at 4 MHz from a piezoceramic sensor embedded in a steel forcing block about 22 mm from the gouge layer The data from this experiment can be used with the deep learning algorithm to train it for future fault property prediction.

15 GEOTHERMAL ENERGY↗
DOE OSTI2024

Probabilistic Seismic Hazard Assessment for Azerbaijan

Probabilistic Seismic Hazard Assessments (PSHA) underpin the determination of seismic loads in most contemporary seismic provisions of building codes around the world. Modern building codes are migrating towards using the entire uniform hazard spectrum at a range of vibration periods (typically up to 4 s or 10 s) rather than a single peak value such as peak ground acceleration (PGA), thus requiring a larger range of PSHA outputs. The hazard maps in the current version of the building code of Azerbaijan (2011) are in terms of intensity and peak ground acceleration. Recognizing the need for an up-to-date seismic hazard assessment in the country, Seismic Cooperation Program (SCP) under the Lawrence Livermore National Laboratory (LLNL) undertook, in coordination with the Republican Seismic Survey Center of the Azerbaijan National Academy of Sciences and the Azerbaijan Scientific Research Institute of Construction and Architecture, a PSHA study that reflects new seismic data recorded locally and recent research conducted nationally and regionally since the last update to the building code. The PSHA framework for this project was designed to help develop a new earthquake catalogue, to incorporate a novel characterization of ground motions that specifically reflects the attenuation characteristics in the eastern Caucasus, and to generate hazard information in a form that is useful for an update of the current building code or the development of a new building code for Azerbaijan. The project also aimed to provide training and support for the local seismologists and engineers related to the seismic hazard models, probabilistic seismic hazard results and their use towards changes in the building code.

58 GEOSCIENCES↗
DOE OSTI2020

Sulfur Pellets Responses to a Bare and Steel Reflected Pulse of the Oak Ridge National Laboratory Health Physics Research Reactor

The experiments analyzed in this report were conducted at the Health Physics Research Reactor (HPRR), also known as the $\textit{Fast Burst Reactor}$. The reactor was designed and built at Oak Ridge National Laboratory (ORNL) in 1961. The HPRR was an unmoderated, unshielded fast reactor that used highly enriched uranium and molybdenum alloy as fuel. The reactor was initially sent to the Nevada Test Site in 1962, where it was used to evaluate radiation doses received as a result of the Hiroshima and Nagasaki bombings during World War II. A few years later, the reactor was sent back to ORNL to be part of the Dosimetry Application Research (DOSAR) facility shown in Figure 1, which included a reactor building shown on the left (west) of the picture and a control and laboratory building in the upper right corner (northeast). The critical assembly was used for numerous technical studies, including systems calibration, dosimetry, radiobiology of plants and animals, testing of radiation alarms, as well as teaching and training in radiation dosimetry and nuclear engineering. Between 1963 and 1987, the HPRR was operated for thousands of hours, achieving criticality close to 10,000 times and motivating many publications. The HPRR was decommissioned in 1987. The goal of this effort was to use historical data from operation of the HPRR to create a criticality accident alarm system (CAAS) benchmark to be included in the $\textit{International Handbook of Evaluated Criticality Safety Benchmark Experiments}$ (ICSBEP Handbook). A thorough inspection was performed of all available documentation and information available. The most promising experiments that were selected for evaluation were those described in the 1987 ORNL report entitled $\textit{Health Physics Research Reactor Reference Dosimetry}$, ORNL-6240. The report includes reference dosimetry results of the shielded and unshielded configurations of the HPRR after burst operations. Because of changes to the reactor positioning and storage systems that were made in 1985, the previous dosimetry reports became obsolete, and the newly designed experiments were needed to create the HPRR’s adjusted dosimetry data. The various results reported in ORNL-6240 include reference doses and dose equivalents from different conventions at different distances and elevations as determined using the detected neutron fluence and conversion factors. The HPRR neutron fluence was obtained through different methods, including sulfur pellet analysis and threshold detector unit data. Information about the HPRR spectrum was also obtained through Bonner sphere measurements. This benchmark is focused on a part of the measured sulfur fluences reported in Appendix H of ORNL-6240. Standard commercial sulfur pellets were placed at different distances from the HPRR centerline during burst operation and were activated due to the 32 S(n,p) 32 P reaction. The resulting 32 P activity was then measured and the information about the corresponding sulfur fluence and/or neutron dose could be extracted. Many of those measurements have 7 been performed with the HPRR in its bare configuration or with different shields (combinations of Lucite, concrete, steel). All the necessary, precise information about material and/or dimensions of the different shields was not found, so it was decided to focus only on the unshielded and steel-shielded configurations to minimize the benchmark uncertainty. A total of 31 cases (24 unshielded and 7 shielded cases at different positions) of sulfur fluence were selected before evaluation to develop the benchmark.

21 SPECIFIC NUCLEAR REACTORS AND ASSOCIATED PLANTS↗