SEARCH · Search NASA

Results for “Forest resilience”

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.

SourceResearch connectionFrom yearThrough year

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 91 records · Page 5

All sources NASA NTRS DOE OSTI

NASA NTRS2021

Storm Surge and Ponding Explain Mangrove Dieback in Southwest Florida Following Hurricane Irma

Mangroves buffer inland ecosystems from hurricane winds and storm surge. However, their ability to withstand harsh cyclone conditions depends on plant resilience traits and geomorphology. Using airborne lidar and satellite imagery collected before and after Hurricane Irma, we estimated that 62% of mangroves in southwest Florida suffered canopy damage, with largest impacts in tall forests (>10 m). Mangroves on well-drained sites (83%) resprouted new leaves within one year after the storm. By contrast, in poorly-drained inland sites, we detected one of the largest mangrove diebacks on record (10,760 ha), triggered by Irma. We found evidence that the combination of low elevation (median = 9.4 cm asl), storm surge water levels (>1.4 m above the ground surface), and hydrologic isolation drove coastal forest vulnerability and were independent of tree height or wind exposure. Our results indicated that storm surge and ponding caused dieback, not wind. Tidal restoration and hydrologic management in these vulnerable, low-lying coastal areas can reduce mangrove mortality and improve resilience to future cyclones.

David Lagomasino↗

DOE OSTI2023

Tree mortality during long-term droughts is lower in structurally complex forest stands

Increasing drought frequency and severity in a warming climate threaten forest ecosystems with widespread tree deaths. Canopy structure is important in regulating tree mortality during drought, but how it functions remains controversial. Here, we show that the interplay between tree size and forest structure explains drought-induced tree mortality during the 2012-2016 California drought. Through an analysis of over one million trees, we find that tree mortality rate follows a “negative-positive-negative” piecewise relationship with tree height, and maintains a consistent negative relationship with neighborhood canopy structure (a measure of tree competition). Trees overshadowed by tall neighboring trees experienced lower mortality, likely due to reduced exposure to solar radiation load and lower water demand from evapotranspiration. Our findings demonstrate the significance of neighborhood canopy structure in influencing tree mortality and suggest that re-establishing heterogeneity in canopy structure could improve drought resiliency. Our study also indicates the potential of advances in remote-sensing technologies for silvicultural design, supporting the transition to multi-benefit forest management.

59 BASIC BIOLOGICAL SCIENCES↗

NASA NTRS2002

Effects of Interannual Climate Variability on Water Availability and Productivity in Capoeira and Crops Under Traditional and Alternative Shifting Cultivation

Regenerating forests play an important role in long-term carbon sequestration and sustainable landuse as they act as potentially important carbon and nutrient sinks during the shifting agriculture fallow period. The long-term functioning of capoeira. is increasingly threatened by a shortening fallow period during shifting cultivation due to demographic pressures and associated increased vulnerability to severe climatic events. Declining productivity and functioning of fallow forests of shifting cultivation combined with progressive loss of nutrients by successive burning and cropping activities has resulted in declining agricultural productivity. In addition to the effects of intense land use practices, droughts associated with El Nino events are becoming more frequent and severe in moist tropical forests and negative effects on capoeira productivity could be considerable. In Igarape-Acu (near Belem, Para), we hypothesize that experimental alternative landuse/clearing practices (mulching and fallow vegetation improvement by planting with fast-growing leguminous tree species) may make capoeira and agriculture more resilient to the effects of agricultural pressures and drought through (1) increased biomass, soil organic matter and associated increase in soil water storage, and nutrient retention and (2) greater rooting depth of trees planted for fallow improvement. This experimental practice (moto mechanized chop-and-mulch with fallow improvement) has resulted increased soil moisture during the cropping phase, reduced loss of nutrients and organic matter, and higher rates of secondary-forest biomass accumulation. We present preliminary data on water relations during the dry season of 2001 in capoeira and crops for both traditional slash-and-burn and alternative chop-and-mulch practices. These data will be used to test IKONOS data for the detection of moisture status differences. The principal goal of the research is to determine the extent to which capoeira and agricultural fields are susceptible to extreme climate events (drought) under contrasting landuse/clearing practices.

Guild, Liane S.↗

DOE OSTI2021

State changes: insights from the U.S. Long Term Ecological Research Network

Understanding the complex and unpredictable ways ecosystems are changing and predicting the state of ecosystems and the services they will provide in the future requires coordinated, long-term research. This paper is a product of a U.S. National Science Foundation funded Long Term Ecological Research (LTER)network synthesis effort that addressed anticipated changes in future populations and communities. Each LTER site described what their site would look like in50 or 100 yr based on long-term patterns and responses to global change drivers in each ecosystem. Common themes emerged and predictions were grouped into state change, connectivity, resilience, time lags, and cascading effects. Here, we report on the “state change” theme, which includes examples from the Georgia Coastal (coastal marsh), Konza Prairie (mesic grassland), Luquillo(tropical forest), Sevilleta (arid grassland), and Virginia Coastal (coastal grassland) sites. Ecological thresholds(the point at which small changes in an environmental driver can produce an abrupt and persistent state change in an ecosystem quality, property, or phenomenon) were most commonly predicted. For example, in coastal ecosystems, sea-level rise and climate change could convert salt marsh to mangroves and coastal barrier dunes to shrub thicket. Reduced fire frequency has converted grassland to shrubland in mesic prairie, whereas overgrazing combined with drought drive shrub encroachment in arid grasslands. Lastly, tropical cloud forests are susceptible to climate-induced changes in cloud base altitude leading to shifts in species distributions. Overall, these examples reveal that state change is a likely outcome of global environmental change across adverse range of ecosystems and highlight the need for long-term studies to sort out the causes and consequences of state change. The diversity of sites within the LTER network facilitates the emergence of overarching concepts about state changes as an important driver of ecosystem structure, function, services, and futures.

54 ENVIRONMENTAL SCIENCES↗

DOE OSTI2022

Post-Disaster Microgrid Formation for Enhanced Distribution System Resilience

This paper proposes a deep reinforcement learning (DRL) based approach for post-disaster critical load restoration in active distribution systems to form microgrids through network reconfiguration to minimize critical load curtailments. Distribution networks are represented as graph networks, and optimal network configurations with microgrids are obtained by searching for the optimal spanning forest. The constraints to the research question being explored are the radial topology and power balance. Unlike existing analytical and population-based approaches, which necessitate the repetition of entire analyses and computation for each outage scenario to find the optimal spanning forest, the proposed approach, once properly trained, can quickly determine the optimal, or near-optimal, spanning forest even when outage scenarios change. When multiple lines fail in the system, the proposed approach forms microgrids with distributed energy resources in active distribution systems to reduce critical load curtailment. The proposed DRL-based model learns the action-value function using the REINFORCE algorithm, which is a model-free reinforcement learning technique based on stochastic policy gradients. A case study was conducted on a 33-node distribution test system, demonstrating the effectiveness of the proposed approach for post-disaster critical load restoration.

active distribution systems↗

DOE OSTI2022

Divergent responses of soil microorganisms to throughfall exclusion across tropical forest soils driven by soil fertility and climate history

Model projections predict tropical forests will experience longer periods of drought and more intense precipitation cycles under a changing climate. Such transitions have implications for structure-function relationships within microbial communities. We examine how throughfall exclusion might reshape prokaryotic and fungal communities across four lowland forests in Panama with a wide variation in mean annual precipitation and soil fertility. Four sites were established across a 1000 mm span in Mean Annual Precipitation (MAP: 2335–3421 mm). We expected microbial communities at sites with lower MAP to be less sensitive to throughfall exclusion than sites with higher MAP and fungal communities to be more resistant to disturbance than prokaryotes. At each location, partial throughfall exclusion structures were established over 10 × 10 m plots to reduce direct precipitation input. After short-term (~3–9 months) throughfall exclusion, prokaryotic communities showed no change in composition. However, prolonged (12–18 months) throughfall exclusion resulted in divergent prokaryotic community responses, reflecting MAP and soil fertility. We observed the emergence of a “drought microbiome” within infertile sites, whereby the community structure of the experimental throughfall exclusion plots at the lower MAP sites diverged from their respective control sites and converged towards overlapping assemblages. Furthermore, under throughfall exclusion, taxa increasing in relative abundance at the wettest site reflected that endemic to control plots at the lowest MAP site, suggesting a shift toward communities with lifehistory traits selected for under a lower MAP. By contrast, fungal community composition across sites was resilient to throughfall exclusion; however, biomass diverged in response to throughfall exclusion, increasing at two sites while decreasing in the other two. Broadly, our results suggest that microbial communities’ sensitivity to frequent drying and rewetting periods in tropical forest soils will depend on climate history and soil fertility, with infertile sites likely to respond readily to changes in precipitation.

54 ENVIRONMENTAL SCIENCES↗

DOE OSTI2023

Monitoring and Documentation of Forest Management Activities at Los Alamos National Laboratory

Forest management treatments at Los Alamos National Laboratory (LANL) are administered by the Emergency Management Division (EMD-DO) Wildland Fire Program within the Wildland Fire and Forest Management Program (WFFM Program or the Program). Open space forest inventory monitoring is conducted by Forest Health Program staff and students within the Environmental Stewardship Group (EPC-ES). The goals of the integrated Wildland Fire and Forest Management Program are to reduce impacts to Laboratory operations from climate driven events by implementing forest management and healthy forest initiatives such as forest thinning and erosion control. The LANL Wildland Fire Mitigation and Forest Health Plan (EMD PLAN-200, LA-UR-19-25122; LANL 2019) presents treatment standards for LANL property to meet the following goals: 1) Restore and maintain landscapes: LANL landscapes are resilient to disturbances; 2) Develop a fire-adapted community: LANL workforce, neighbors, and infrastructure can withstand a wildland fire without loss of life and property; 3) Ensure wildland fire mitigation implementation: All wildland fire mitigation working group organizations participate in making and implementing safe, effective, efficient risk-based wildland fire management decisions.

54 ENVIRONMENTAL SCIENCES↗

DOE OSTI2025

From pixels to patterns: Coupling Optical Coherence Tomography and machine learning for monitoring coastal wetland root systems

Coastal wetlands are crucial in shoreline stabilization, carbon sequestration, and storm protection. Yet, due to limitations in traditional destructive sampling techniques, the belowground biomass (live root mass) and necromass (dead and decaying roots) remain difficult to assess in coastal wetlands, limiting our understanding on coastal resilience, nutrient cycling, and soil structure. This study employs Optical Coherence Tomography (OCT) as a high-resolution imaging technique to analyze root biomass and necromass in the Terrebonne Basin, Louisiana. A Random Forest (RF) model was developed to classify root health states based on OCT-derived features, achieving an accuracy of 70% in distinguishing live from dead root segments. The results demonstrate that OCT, combined with ML, offers a promising novel approach to root analysis, providing fine-scale insights into root morphology and decay patterns that are not easily captured by conventional methods. This research lays the foundation for future integration of OCT with complementary imaging modalities such as X-ray Computed Tomography (XCT) and advanced ML algorithms to enhance classification accuracy and scalability. Future work aims to expand the dataset diversity across different wetland types and apply the methodology for large-scale, repeatable assessments of root biomass turnover and accumulation, with important implications for wetland monitoring, conservation, and restoration under changing environmental conditions.

AI/ML↗

NASA NTRSDate not supplied

Cloud-Based Solutions for Monitoring Coastal Ecosystems and Prioritization of Restoration Efforts Across Belize

In recent years the availability of automated change detection algorithms in Google Earth Engine has permitted cloud-based processing of large time series of satellite imagery. Models such as the Continuous Change Detection and Classification (CCDC), CCDC-Spectral Mixture Analysis (CCDC-SMA), and Landsat-based Detection of Trends in Disturbance and Recovery (LandTrendr) allow users to exploit decades of Earth Observations (EO) , leveraging the Landsat archive and data from other sensors to detect disturbance in forest ecosystems. Despite the wide adoption of these methods, robust documentation and growing community of users, little research has explored their use in mangrove environments. Mangroves are dynamic environments subject to changes due to not only the natural migration of mudflats but also coastal erosion, urban expansion, aquaculture practices, etc. This work aims to identify best practices for the application of these models to identify and monitor changes in the Belizean mangroves, which experienced an estimated 5.4% decrease in extent between 1980 and 2017 (Cherrington et al. 2020). Partnering directly with the Belizean Forest Department, our team will develop a replicable, efficient methodology to annually update the country’s mangrove extent employing EO-based change detection. This collaboration supports Belize’s marine conservation and climate resilience efforts, such as its Blue Bond agreement with the Nature Conservancy, building on national processes to monitor these critical ecosystems.

Mangroves↗

DOE OSTI2024

Securing Grid-interactive Efficient Buildings (GEB) through Cyber Defense and Resilient System (CYDRES)

The DOE CYDRES project is driven by the urgent need to address critical research gaps in the domain of cyber-physical security of smart buildings, including Grid-interactive Efficient Buildings (GEBs). CYDRES, a real-time advanced building resilient platform, aims to enhance the cyber-attack-immune capabilities of buildings through multi-layered prevention, detection, and adaptation mechanisms. CYDRES consists of five key modules: a multi-layer network analyzer, an Automatic Fault Detection, Diagnosis, and Prognosis (AFDDP) framework, an intelligent mode selector, a cyber-resilient control framework, and a situation awareness platform. The Network Analyzer employs a data-driven framework that includes a protocol state learning tool and a CRF (Conditional Random Field) command validator. In Hardware-In-the-Loop (HIL) testbeds, it achieved 100% detection accuracy with a false alarm rate of 3%, validating its efficacy in identifying selected cyber-attacks. The AFDDP framework leverages pattern matching, PCA (Principal Component Analysis)-based strategies, and a DBN (Dynamic Bayesian Network)-based fault diagnosis approach to pinpoint the causes of physical system abnormalities using Building Automation System (BAS) data. In HIL experiments, the AFDDP module attained a detection accuracy of over 95% with a false alarm rate below 7%. Additionally, the fault detector utilized machine learning (Random Forest) and deep learning (Multi-Layer Perceptron) methods with acoustic sensor data to achieve a 100% fault detection accuracy in Heating, Ventilation, and Air-Conditioning (HVAC) equipment. The Mode Selector offered real-time impact analysis, allowing immediate actions to protect BASs in the face of emerging threats. The cyber-resilient control framework included an adaptive Model Predictive Control (MPC) and a measurement compensator, reducing temperature violations by up to 94% and improving the total demand flexibility by up to 70% in HIL experiments. Such HIL experiments covered a cyber-attack case and a physical fault case, showcasing CYDRES’ efficiency in maintaining operational continuity during threats. The situation awareness platform in Grafana enhanced real-time threat detection and response visualization, augmenting the operational awareness for building operators. CYDRES demonstrated high technical effectiveness in various test scenarios, particularly in HIL environments. The project's phased development approach ensured efficient use of resources, highlighting its practical feasibility and readiness for commercialization. By enhancing the security and resilience of building operations, CYDRES represents a significant advance in mitigating risks associated with cyber-physical systems, thereby enhancing public confidence in the safety of modern building infrastructure. Future directions for the project include expanding testing protocols, refining AFDDP methodologies, exploring more comprehensive resilient control strategies, and testing in real commercial buildings.

42 ENGINEERING↗

DOE OSTI2023

Postdisaster Routing of Movable Energy Resources for Enhanced Distribution System Resilience: A Deep Reinforcement Learning-Based Approach

The deployment of movable energy resources (MERs) can be an effective strategy to restore critical loads to enhance power system resilience when no other energy sources are available after the occurrence of an extreme event. Since the optimal locations of MERs following an extreme event are dependent on system operating states (e.g., the loads at each node, on/off status of system branches, and so on), existing analytical and population-based approaches must repeat the entire analysis and calculation when the system operating states change. On the contrary, if deep reinforcement learning (DRL)-based algorithms are sufficiently trained with a wide range of scenarios, they can quickly find optimal or near-optimal locations irrespective of changes in system states. A deep Q-learning-based approach is proposed for optimal MER deployment to enhance power system resilience. MERs can be also utilized to complement other types of resources, if available. The proposed approach operates in two stages after the occurrence of extreme events. In the first stage, the distribution network is represented as a graph, and the network is then reconfigured using tie switches by using Kruskal’s spanning forest search algorithm (KSFSA). To maximize critical load recovery, the optimal or near-optimal locations of MERs are chosen in the second stage. Further, case studies on a 33-node distribution system and a modified IEEE 123-node system demonstrate the effectiveness of the proposed approach for postdisaster routing of MERs.

24 POWER TRANSMISSION AND DISTRIBUTION↗

DOE OSTI2023

Drought conditioning of rhizosphere microbiome influences maize water use traits

Background and Aims: Beneficial plant–microbe interactions can improve plant performance under drought; however, we know less about how drought-induced shifts in microbial communities affect plant traits. Methods: We cultivated Zea mays in fritted clay with soil microbiomes originating from contrasting environments (agriculture or forest) under two irrigation treatments (well-watered or water limited). Using this design, we investigated whether water conditioning was carried forward through the microbiome to affect a subsequent plant cohort that was subjected to either a well-watered or water limited treatment. Results: Regardless of the microbiome-origin, plants inoculated with a microbiome from a water limited legacy had traits that allowed them to avoid stress but conserve water. They produced longer roots to explore soil, generated greater soil dissolved organic carbon, potentially stimulating the microbiome, and slower soil water content loss during drought. A well-watered legacy resulted in plants that delayed permanent stomatal closure and higher photosynthetic nitrogen use efficiency. In plants with a forest-originated microbiome, a well-watered legacy and water treatment also resulted in higher rates of photosynthesis and stomatal conductance. Conclusion: These results demonstrate that soil microbiomes can be developed to influence plant drought performance, impacting crop resilience, using short-term microbial conditioning.

60 APPLIED LIFE SCIENCES↗

DOE OSTI2022

Climate warming causes photobiont degradation and carbon starvation in a boreal climate sentinel lichen

The long-term potential for acclimation by lichens to changing climates is poorly known, despite their prominent roles in forested ecosystems. Although often considered “extremophiles,” lichens may not readily acclimate to novel climates well beyond historical norms. In a previous study, Evernia mesomorpha transplants in a whole-ecosystem climate change experiment showed drastic mass loss after 1 yr of warming and drying; however, the causes of this mass loss were not addressed. We examined the causes of this warming-induced mass loss by measuring physiological, functional, and reproductive attributes of lichen transplants. Severe loss of mass and physiological function occurred above +2°C of experimental warming. Loss of algal symbionts (“bleaching”) and turnover in algal community compositions increased with temperature and were the clearest impacts of experimental warming. Enhanced CO 2 had no significant physiological or symbiont composition effects. The functional loss of algal photobionts led to significant loss of mass and specific thallus mass (STM), which in turn reduced water-holding capacity (WHC). Although algal genotypes remained detectable in thalli exposed to higher stress, within-thallus photobiont communities shifted in composition toward greater diversity. The strong negative impacts of warming and/or lower humidity on Evernia mesomorpha were driven by a loss of photobiont activity. Analogous to the effects of climate change on corals, the balance of symbiont carbon metabolism in lichens is central to their resilience to changing conditions.

54 ENVIRONMENTAL SCIENCES↗

DOE OSTI2023

Climate-driven tradeoffs between landscape connectivity and the maintenance of the coastal carbon sink

Abstract Ecosystem connectivity tends to increase the resilience and function of ecosystems responding to stressors. Coastal ecosystems sequester disproportionately large amounts of carbon, but rapid exchange of water, nutrients, and sediment makes them vulnerable to sea level rise and coastal erosion. Individual components of the coastal landscape (i.e., marsh, forest, bay) have contrasting responses to sea level rise, making it difficult to forecast the response of the integrated coastal carbon sink. Here we couple a spatially-explicit geomorphic model with a point-based carbon accumulation model, and show that landscape connectivity, in-situ carbon accumulation rates, and the size of the landscape-scale coastal carbon stock all peak at intermediate sea level rise rates despite divergent responses of individual components. Progressive loss of forest biomass under increasing sea level rise leads to a shift from a system dominated by forest biomass carbon towards one dominated by marsh soil carbon that is maintained by substantial recycling of organic carbon between marshes and bays. These results suggest that climate change strengthens connectivity between adjacent coastal ecosystems, but with tradeoffs that include a shift towards more labile carbon, smaller marsh and forest extents, and the accumulation of carbon in portions of the landscape more vulnerable to sea level rise and erosion.

54 ENVIRONMENTAL SCIENCES↗

DOE OSTI2020

Large Trees Dominate Carbon Storage in Forests East of the Cascade Crest in the United States Pacific Northwest

Large-diameter trees store disproportionally massive amounts of carbon and are a major driver of carbon cycle dynamics in forests worldwide. In the temperate forests of the western United States, proposed changes to Forest Plans would significantly weaken protections for a large portion of trees greater than 53 cm (21 inches) in diameter (herein referred to as “large-diameter trees”) across 11.5 million acres (~4.7 million ha) of National Forest lands. This study is among the first to report how carbon storage in large trees and forest ecosystems would be affected by a proposed policy. We examined the proportion of large-diameter trees on National Forest lands east of the Cascade Mountains crest in Oregon and Washington, their contribution to overall aboveground carbon (AGC) storage, and the potential reduction in carbon stocks resulting from widespread harvest. We analyzed forest inventory data collected on 3,335 plots and found that large trees play a major role in the accumulated carbon stock of these forests. Tree AGC (kg) increases sharply with tree diameter at breast height (DBH; cm) among five dominant tree species. Large trees accounted for 2.0 to 3.7% of all stems (DBH ≥ 1” or 2.54 cm) among five tree species; but held 33 to 46% of the total AGC stored by each species. Pooled across the five dominant species, large trees accounted for 3% of the 636,520 trees occurring on the inventory plots but stored 42% of the total AGC. A recently proposed large-scale vegetation management project that involved widespread harvest of large trees, mostly grand fir, would have removed ~44% of the AGC stored in these large-diameter trees, and released a large amount of carbon dioxide to the atmosphere. Given the urgency of keeping additional carbon out of the atmosphere and continuing carbon accumulation from the atmosphere to protect the climate system, it would be prudent to continue protecting ecosystems with large trees for their carbon stores, and also for their co-benefits of habitat for biodiversity, resilience to drought and fire, and microclimate buffering under future climate extremes.

21-inch rule↗

NASA NTRS2020

Southern Colorado Disasters: Using NASA Observations to Map Aspen Extent and Recovery Due to Wildfire

Quaking aspen (Populus tremuloides) is an important species for wildlife, watershed health, and ecosystem resilience across its range. Heavy ungulate browsing and factors influenced by a changing climate including seasonal temperature changes and moisture deficit have led to reduced post-fire aspen regeneration rates in southern Colorado. This project partnered with Trinchera Ranch and the Colorado State Forest Service to estimate aspen recovery after the Spring Creek Fire, which ignited in June of 2018. The Southern Colorado Disasters team utilized field measurements and satellite imagery from Landsat Operational Land Imager (OLI), Sentinel-2 MultiSpectral Instrument (MSI), and the Shuttle Radar Topography Mission (SRTM) to train and run several random forest models that detect pre- and post-fire aspen extent. Ocular sampling of over 500 points on high-resolution pre-fire and post-fire images identified percentage aspen cover in 30 x 30-meter grid cells. This process provided training data for regression models, which were able to detect aspen across the landscape for both time periods using multiple remote sensing vegetation health indices. In addition, landscape suitability for aspen regeneration was modeled to provide a guide for managers on where to monitor for aspen regeneration post-fire.

DEVELOP Project Summary↗

NASA NTRS2020

Southern Colorado Disasters: Using NASA Earth Observations to Map Aspen Extent and Recovery Due to Wildfire

DEVELOP Technical Paper↗

DOE OSTI2023

Machine Learning Based Resilience Testing of an Address Randomization Cyber Defense

Moving target defenses (MTDs) are widely used as an active defense strategy for thwarting cyberattacks on cyber-physical systems by increasing diversity of software and network paths. Recently, machine Learning (ML) and deep Learning (DL) models have been demonstrated to defeat some of the cyber defenses by learning attack detection patterns and defense strategies. It raises concerns about the susceptibility of MTD to ML and DL methods. Here, in this article, we analyze the effectiveness of ML and DL models when it comes to deciphering MTD methods and ultimately evade MTD-based protections in real-time systems. Specifically, we consider a MTD algorithm that periodically randomizes address assignments within the MIL-STD-1553 protocol—a military standard serial data bus. Two ML and DL-based tasks are performed on MIL-STD-1553 protocol to measure the effectiveness of the learning models in deciphering the MTD algorithm: 1) determining whether there is an address assignments change i.e., whether the given system employs a MTD protocol and if it does 2) predicting the future address assignments. The supervised learning models (random forest and k-nearest neighbors) effectively detected the address assignment changes and classified whether the given system is equipped with a specified MTD protocol. On the other hand, the unsupervised learning model (K-means) was significantly less effective. The DL model (long short-term memory) was able to predict the future addresses with varied effectiveness based on MTD algorithm's settings.

45 MILITARY TECHNOLOGY, WEAPONRY, AND NATIONAL DEF↗