Search NASA⌕ Search

SEARCH · Search NASA

Results for “Forest Modeling”

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 1,315 records · Page 73

Belowground Response to Drought in a Tropical Forest Soil. II. Change in Microbial Function Impacts Carbon Composition

Climate model projections for tropical regions show clear perturbation of precipitation patterns leading to increased frequency and severity of drought in some regions. Previous work has shown declining soil moisture to be a strong driver of changes in microbial trait distribution, however, the feedback of any shift in functional potential on ecosystem properties related to carbon cycling are poorly understood. Here we show that drought-induced changes in microbial functional diversity and activity shape, and are in turn shaped by, the composition of dissolved and soil-associated carbon. We also demonstrate that a shift in microbial functional traits that favor the production of hygroscopic compounds alter the efflux of carbon dioxide following soil rewetting. Under drought the composition of the dissolved organic carbon pool changed in a manner consistent with a microbial metabolic response. We hypothesize that this microbial ecophysiological response to changing soil moisture elevates the intracellular carbon demand stimulating extracellular enzyme production, that prompts the observed decline in more complex carbon compounds (e.g., cellulose and lignin). Furthermore, a metabolic response to drought appeared to condition (biologically and physically) the soil, notably through the production of polysaccharides, particularly in experimental plots that had been pre-exposed to a short-term drought. This hysteretic response, in addition to an observed drought-related decline in phosphorus concentration, may have been responsible for a comparatively modest CO 2 efflux following wet-up in drought plots relative to control plots.

54 ENVIRONMENTAL SCIENCES↗

BOREAS TE-9 NSA Photosynthetic Capacity and Foliage Nitrogen Data

The Boreal Ecosystem-Atmospheric Study (BOREAS) TE-9 (Terrestrial Ecology) team collected several data sets related to chemical and photosynthetic properties of leaves in boreal forest tree species. This data set describes the spatial and temporal relationship between foliage nitrogen concentration and photosynthetic capacity in the canopies of black spruce, jack pine, and aspen located within the Northern Study Area (NSA). The data were collected from June to September 1994 and are useful for modeling the vertical distribution of carbon fixation for different forest types in the boreal forest. The data are available in tabular ASCII files. The data files are available on a CD-ROM (see document number 20010000884), or from the Oak Ridge National Laboratory (ORNL) Distributed Active Archive Center (DAAC).

Hall, Forrest G.↗

The influence of hydrological variability on inherent water use efficiency in forests of contrasting composition, age, and precipitation regimes in the Pacific Northwest

The Pacific Northwest (PNW) region of the United States has some of the most productive forests in the world. As precipitation regimes may shift with changing climate in this area, droughts are predicted to increase in both frequency and degree of severity, which will have a significant impact on already drought-prone ecosystems. When modeling ecosystem responses to drought, it is important to consider the physiology of individual tree species since the variations in drought sensitivity among species is easily overlooked when plants are characterized using broad plant functional types. In this report we explore the use of inherent water-use efficiency as an index of drought sensitivity in semi-arid young and mature ponderosa pine forests and a mesic mature Douglas-fir forest in the PNW. Summer maximum of an evapotranspiration-based WUE (WUE i ) was 2.5 times higher in young and mature pines in semi-arid climate than Douglas-fir in mesic climate (12.2 and 11.3 versus 4.7 g C kPa per kg H 2 O, respectively). In contrast, annually averaged WUE i was similar among the sites (2.8 g C kPa per kg H 2 O for pines and 2.4 g C kPa per kg H 2 O for Douglas-fir). The effect of drought stress on WUE i was most pronounced in young pine, followed by mature pine and Douglas-fir (32, 11, and 6% increase in WUE i per % decline in soil water content, respectively) which reflect differences in age-related ecosystem structure (root system, stem capacitance, and soil water holding capacity). Among sites, the responses of WUEi to climate variability were largely driven by changes in evapotranspiration (ET) compared to gross primary productivity (GPP). However, in areas where evaporation is the primary component of ET, such as the open canopy ponderosa forests of the PNW, the contribution of soil processes to ET can overshadow the reaction of vegetation transpiration (T) to changes in water availability. In these cases, utilizing a transpiration-based WUE (WUE i_T ) in vegetation models will yield a more accurate representation of plant activity during drought. These results highlight the importance of incorporating differences in species- and age-related WUEi in models in diverse forest types at regional and global scales to improve predictions in ecosystem responses to climate change.

54 ENVIRONMENTAL SCIENCES↗

Isoprene photochemistry over the Amazon rainforest

Isoprene photooxidation is a major driver of atmospheric chemistry over forested regions. Isoprene reacts with hydroxyl radicals (OH) and molecular oxygen to produce isoprene peroxy radicals (ISOPOO). These radicals can react with hydroperoxyl radicals (HO2) to domi-nantly produce hydroxyhydroperoxides (ISOPOOH). They can also react with nitric oxide (NO) to largely produce methyl vinyl ketone (MVK) and methacrolein (MACR). Unimolecular isomerization and bimolecular reactions with organic peroxy radicals are also possible. There is uncertainty about the relative importance of each of these pathways in the atmosphere and possible changes because of anthropogenic pollution. Herein, measurements of ISOPOOH and MVK + MACR concentrations are reported over the central region of the Amazon basin during the wet season. The research site, downwind of an urban region, intercepted both background and polluted air masses during the GoAmazon2014/5 Experiment. Under background conditions, the confidence interval for the ratio of the ISOPOOH concentration to that of MVK + MACR spanned 0.4–0.6. This result implies a ratio of the reaction rate of ISOPOO with HO2 to that with NO of approximately unity. A value of unity is significantly smaller than simulated at present by global chemical transport models for this important, nominally low-NO, forested region of Earth. Under polluted conditions, when the concentrations of reactive nitrogen compounds were high (>1 ppb), ISOPOOH concentrations dropped below the instrumental detection limit (<60 ppt). This abrupt shift in isoprene photooxidation, sparked by human activities, speaks to ongoing and possible future changes in the photochemistry active over the Amazon rainforest.

Liu, Yingjun↗

Predicting Airport Runway Configurations for Decision-Support Using Supervised Learning

One of the most challenging tasks for air traffic controllers is runway configuration management (RCM). It deals with the optimal selection of runways to operate on (for arrivals and departures) based on traffic, surface wind speed, wind direction, other environmental variables, noise constraints, and several other airport-specific factors. It affects the efficiency of the National Airspace System (NAS) and both surface and airspace operations can benefit from better understanding future runway configurations. In this paper, we present a comprehensive implementation of predictive models for runway configuration estimation from large volumes of historical data. Specifically, operational data from two full years (2018 and 2019) is collected, analyzed, and fused together to build the data product used in this work. The data set differs from prior work in the field in terms of its scope, resolution, and variety of factors collected and considered. Meteorological data is collected from two different sources – current weather conditions from METAR (Meteorological Terminal Aviation Routine Weather Report) and forecast weather conditions from Localized Aviation MOS Program (LAMP). Operational data from the Federal Aviation Administration (FAA) Aviation System Performance Metrics (ASPM) related to scheduled and actual number of arrivals and departures, average taxi times, etc. are collected. NASA’s Sherlock Data Warehouse is used to identify critical information such as go-arounds, and other events that might impact RCM decision-making. All data is collected and aggregated over 15-minute intervals throughout the two years. This provides a resolution like the timescales that might be necessary for runway configuration management decision-making. A variety of supervised learning algorithms are tested including Support Vector Machine, Random Forest, Gradient Boosting, etc. including tuning of the model hyperparameters. The modeling process is applied and presented on two representative U.S. airports – Charlotte Douglas International Airport (KCLT) and Denver International Airport (KDEN). The two airports present different levels of complexity in terms of the total number of configurations used and provide a balanced perspective on the generalizability of the developed approach to other airports in the NAS. Initial results are promising (F1 score of 0.91 at KCLT and 0.83 at KDEN) for data in the test set. The final paper will contain a comprehensive comparison between different models and model building strategies as well as further refined results. Most important predictors for each airport will be identified along with a discussion and recommendations on adapting the framework to other scenarios.

Tejas G Puranik↗

Can a void mimic the Λ in ΛCDM?

We investigate Lemaítre-Tolman-Bondi (LTB) models, whose early time evolution and bang time are homogeneous and the distance-redshift relation and local Hubble parameter are inherited from the ΛCDM model. We show that the obtained LTB models and the ΛCDM model predict different relative local expansion rates and that the Hubble functions of the models diverge increasingly with redshift. The LTB models show tension between low redshift baryon acoustic oscillation and supernova observations and including Lyman-α forest or cosmic microwave background observations only accentuates the better fit of the ΛCDM model compared to the LTB model. The result indicates that additional degrees of freedom are needed to explain the observations, for example by renouncing spherical symmetry, homogeneous bang time, negligible effects of pressure, or the early time homogeneity assumption.

79 ASTRONOMY AND ASTROPHYSICS↗

Synergistic Ecoclimate Teleconnections from Forest Loss in Different Regions Structure Global Ecological Responses

Forest loss in hotspots around the world impacts not only local climate where loss occurs, but also influences climate and vegetation in remote parts of the globe through ecoclimate teleconnections. The magnitude and mechanism of remote impacts likely depends on the location and distribution of forest loss hotspots, but the nature of these dependencies has not been investigated. We use global climate model simulations to estimate the distribution of ecologically-relevant climate changes resulting from forest loss in two hotspot regions: western North America (wNA), which is experiencing accelerated dieoff, and the Amazon basin, which is subject to high rates of deforestation. The remote climatic and ecological net effects of simultaneous forest loss in both regions differed from the combined effects of loss from the two regions simulated separately, as evident in three impacted areas. Eastern South American Gross Primary Productivity (GPP) increased due to changes in seasonal rainfall associated with Amazon forest loss and changes in temperature related to wNA forest loss. Eurasia's GPP declined with wNA forest loss due to cooling temperatures increasing soil ice volume. Southeastern North American productivity increased with simultaneous forest loss, but declined with only wNA forest loss due to changes in VPD. In conclusion, our results illustrate the need for a new generation of local-to-global scale analyses to identify potential ecoclimate teleconnections, their underlying mechanisms, and most importantly, their synergistic interactions, to predict the responses to increasing forest loss under future land use change and climate change.

54 ENVIRONMENTAL SCIENCES↗

Designing and Evaluating NASA SPoRT Center’s DustTracker-AI Model for Detecting Dust in NASA/NOAA Geostationary Satellite Imagery

- Near real-time identification of airborne dust in satellite imagery is important for mitigating the adverse effects of dust storms on human activities. - False color Red-Green-Blue (RGB) imagery has been used for dust detection, but it has limitations and can be difficult to interpret. - The NASA Short-term Research and Transition (SPoRT) center has developed a night-time dust detection random forest (NT-DustTracker-AI, Berndt et al. 2021) model using NASA/NOAA Geostationary Operational Environmental Satellite-16 (GOES-16) Advanced Baseline Imager (ABI) infrared imagery as inputs. - The SPoRT center has partnered with the NOAA National Weather Service to evaluate the model for use in weather forecasting operations, and preliminary results have been positive. - The SPoRT center has expanded the model to cover both day and night, continuing to use infrared imagery as inputs. This new model, known as DustTracker-AI, has shown good agreement with available dust observations

Robert A. Junod↗

Relating ground truth collection to model sensitivity

The importance of collecting high quality ground truth before a SAR mission over a forested area is two fold. First, the ground truth is used in the analysis and interpretation of the measured backscattering properties; second, it helps to justify the use of a scattering model to fit the measurements. Unfortunately, ground truth is often collected based on visual assessment of what is perceived to be important without regard to the mission itself. Sites are selected based on brief surveys of large areas, and the ground truth is collected by a process of selecting and grouping different scatterers. After the fact, it may turn out that some of the relevant parameters are missing. A three-layer canopy model based on the radiative transfer equations is used to determine, before hand, the relevant parameters to be collected. Detailed analysis of the contribution to scattering and attenuation of various forest components is carried out. The goal is to identify the forest parameters which most influence the backscattering as a function of frequency (P-, L-, and C-bands) and incident angle. The influence on backscattering and attenuation of branch diameters, lengths, angular distribution, and permittivity; trunk diameters, lengths, and permittivity; and needle sizes, their angular distribution, and permittivity are studied in order to maximize the efficiency of the ground truth collection efforts. Preliminary results indicate that while a scatterer may not contribute to the total backscattering, its contribution to attenuation may be significant depending on the frequency.

Amar, Faouzi↗

An ecologically-constrained deep learning model for tropical leaf phenology monitoring using PlanetScope satellites

In tropical forests, leaf phenology signals leaf-on/off status and exhibits considerable variability across scales from a single tree-crown to the entire forest ecosystem. Such phenology signals importantly regulate large-scale biogeochemical cycles and regional climate. PlanetScope CubeSats data with a 3-m resolution and near-daily global coverage provide an unprecedented opportunity to monitor both fine- and ecosystem-scale phenology variability along large environmental gradients. However, a scalable method that accurately characterizes leaf phenology from PlanetScope with biophysically meaningful metrics remains lacking. Here we developed an index-guided, ecologically constrained autoencoder (IG-ECAE) method to automatically derive a deciduousness metric (i.e. percentage of tree canopies with leaf-off status within an image pixel) from PlanetScope. The IG-ECAE first estimated the reflectance spectra of leafy/leafless canopies based on their spectral indices characteristics, then used the derived reflectance spectra to guide an autoencoder deep learning method with additional ecological constraints to refine the reflectance spectra, and finally used linear spectral unmixing to estimate the relative abundance of leafless canopies (or deciduousness) per PlanetScope image pixel. We tested the IG-ECAE method at 16 tropical forest sites spanning multiple continents and a large precipitation gradient (1470-2819 mm year -1 ). Among these sites, we evaluated the PlanetScope-derived deciduousness with corresponding measures derived from WorldView-2 (n=9 sites) and local phenocams (n=9 sites). Our results show that PlanetScope-derived deciduousness agrees: 1) with that derived from WorldView-2 at the patch level (90m×90m) with r 2 =0.89 across all sites; and 2) with that derived from phenocams to quantify ecosystem-scale seasonality with r 2 ranging from 0.62-0.96. These results demonstrate the effectiveness and scalability of IG-ECAE in characterizing the wide variability in deciduousness across scales from pixels to forest ecosystems, and from a single date to the full annual cycle, indicating the potential for using high-resolution satellites to track the large-scale phenological patterns and response of tropical forests to climate change.

54 ENVIRONMENTAL SCIENCES↗

Application of Machine Learning and Data Augmentation Algorithms in the Discovery of Metal Hydrides for Hydrogen Storage

The development of efficient and sustainable hydrogen storage materials is a key challenge for realizing hydrogen as a clean and flexible energy carrier. Among various options, metal hydrides offer high volumetric storage density and operational safety, yet their application is limited by thermodynamic, kinetic, and compositional constraints. In this work, we investigate the potential of machine learning (ML) to predict key thermodynamic properties—equilibrium plateau pressure, enthalpy, and entropy of hydride formation—based solely on alloy composition using Magpie-generated descriptors. We significantly expand an existing experimental dataset from ~400 to 806 entries and assess the impact of dataset size and data augmentation, using the PADRE algorithm, on model performance. Models including Support Vector Machines and Gradient Boosted Random Forests were trained and optimized via grid search and cross-validation. Results show a marked improvement in predictive accuracy with increased dataset size, while data augmentation benefits are limited to smaller datasets and do not improve accuracy in underrepresented pressure regimes. Furthermore, clustering and cross-validation analyses highlight the limited generalizability of models across different material classes, though high accuracy is achieved when training and testing within a single hydride family (e.g., AB2). The study demonstrates the viability and limitations of ML for accelerating hydride discovery, emphasizing the importance of dataset diversity and representation for robust property prediction.

augmentation↗

First detection of cosmic microwave background lensing and Lyman- α forest bispectrum

We present the first detection of a correlation between the Lyman-α forest and cosmic microwave background gravitational lensing. For each Lyman-α forest in SDSS-III/BOSS DR12, we correlate the one-dimensional power spectrum with the cosmic microwave background lensing convergence on the same line of sight from Planck. This measurement constitutes a position-dependent power spectrum, or a squeezed bispectrum, and quantifies the nonlinear response of the Lyman-α forest power spectrum to a large-scale overdensity. The signal is measured at 5σ and is consistent with the expectation of the standard ΛCDM cosmological model. We measure the linear bias of the Lyman-α forest with respect to the dark matter distribution and constrain a combination of nonlinear terms including the nonlinear bias. This new observable provides a consistency check for the Lyman-α forest as a large-scale structure probe and tests our understanding of the relation between intergalactic gas and dark matter. In the future, it could be used to test hydrodynamical simulations and calibrate the relation between the Lyman-α forest and dark matter.

79 ASTRONOMY AND ASTROPHYSICS↗

Detection of Diversion in a Realistic Heat Pipe Microreactor Using Supervised Machine Learning

Microreactors (MRs) pose new challenges for international safeguards. Here, their small size and mass reproducibility make them ideal for deployment in greater numbers and in remote locations, making the job of safeguards inspectors more challenging. Machine learning (ML) is currently being applied to many fields to augment human performance and increase automation; in particular, ML could be used to provide insight for international inspectors to help detect the diversion of nuclear fuel from MR cores. Four ML model types (k-nearest neighbors, decision tree, random forest, and histogram-based gradient boosted ensemble) were trained on integrated flux and critical control drum angle data generated with Serpent 2 for a realistic heat pipe MR design, achieving nearly 100% binary classification accuracy of nominal and diversion core configurations by the end of 1 full power year for three of the four model types. Regression model variants were also trained, using the same input data, for predicting the number of fuel pins diverted. Root-mean-square errors below 5% of the total number of fuel pins were achieved by the 1 full power year mark for all models.

22 - GENERAL STUDIES OF NUCLEAR REACTORS↗

Upland forest retreat lags behind sea‐level rise in the mid‐Atlantic coast

Abstract Ghost forests consisting of dead trees adjacent to marshes are striking indicators of climate change, and marsh migration into retreating coastal forests is a primary mechanism for marsh survival in the face of global sea‐level rise. Models of coastal transgression typically assume inundation of a static topography and instantaneous conversion of forest to marsh with rising seas. In contrast, here we use four decades of satellite observations to show that many low‐elevation forests along the US mid‐Atlantic coast have survived despite undergoing relative sea‐level rise rates (RSLRR) that are among the fastest on Earth. Lateral forest retreat rates were strongly mediated by topography and seawater salinity, but not directly explained by spatial variability in RSLRR, climate, or disturbance. The elevation of coastal tree lines shifted upslope at rates correlated with, but far less than, contemporary RSLRR. Together, these findings suggest a multi‐decadal lag between RSLRR and land conversion that implies coastal ecosystem resistance. Predictions based on instantaneous conversion of uplands to wetlands may therefore overestimate future land conversion in ways that challenge the timing of greenhouse gas fluxes and marsh creation, but also imply that the full effects of historical sea‐level rise have yet to be realized.

Biodiversity & Conservation↗

Landscape‐scale lidar analysis of aboveground biomass distribution in secondary Brazilian Atlantic Forest

Abstract Secondary forests account for more than half of tropical forests and represent a growing carbon sink, but rates of biomass accumulation vary by a factor of two or more even among plots in the same landscape. To better understand the drivers of this variability, we used airborne lidar to measure forest canopy height and estimate biomass over 4529 ha at Serra do Conduru Park in Southern Bahia, Brazil. We measured trees in 30 georeferenced field plots (0.25‐ha each) to estimate biomass using allometry. Then we estimated aboveground biomass density ( ABD ) across the lidar study area using a statistical model developed from our field plots. This model related the 95th percentile of the distribution of lidar return heights to ABD . We overlaid this map of ABD on a Landsat‐derived forest age map to determine rates of biomass accumulation. We found rapid initial biomass regeneration (~6 Mg/ha yr), which slowed as forests aged. We also observed high variability in both height and biomass across the landscape within forests of similar age. Nevertheless, a regression model that accounted for spatial autocorrelation and included forest age, slope, and distance to roads or open areas explained 62 and 77 percent of the landscape variation in ABD and canopy height, respectively. Thus, while there is high spatial heterogeneity in forest recovery, and the drivers of this heterogeneity warrant further investigation, we suggest that a relatively simple set of predictor variables is sufficient to explain the majority of variance in both height and ABD in this landscape.

Becknell, Justin M.↗

Machine Learning Analysis of Hydrologic Exchange Flows and Transit Time Distributions in a Large Regulated River

Hydrologic exchange between river channels and adjacent subsurface environments is a key process that influences water quality and ecosystem function in river corridors. High-resolution numerical models were often used to resolve the spatial and temporal variations of exchange flows, which are computationally expensive. In this study, we adopt Random Forest (RF) and Extreme Gradient Boosting (XGB) approaches for deriving reduced order models of hydrologic exchange flows and associated transit time distributions, with integrated field observations (e.g., bathymetry) and hydrodynamic simulation data (e.g., river velocity, depth). The setup allows an improved understanding of the influences of various physical, spatial, and temporal factors on the hydrologic exchange flows and transit times. The predictors also contain those derived using hybrid clustering, leveraging our previous work on river corridor system hydromorphic classification. The machine learning-based predictive models are developed and validated along the Columbia River Corridor, and the results show that the top parameters are the thickness of the top geological formation layer, the flow regime, river velocity, and river depth; the RF and XGB models can achieve 70% to 80% accuracy and therefore are effective alternatives to the computational demanding numerical models of exchange flows and transit time distributions. Each machine learning model with its favorable configuration and setup have been evaluated. The transferability of the models to other river reaches and larger scales, which mostly depends on data availability, is also discussed.

97 MATHEMATICS AND COMPUTING↗

Assessing impacts of canopy 3D structure on chlorophyll fluorescence radiance and radiative budget of deciduous forest stands using DART

Although remote sensing (RS) of solar-induced chlorophyll fluorescence (SIF) is increasingly used as a valuable source of information about vegetation photosynthetic activity, the RS SIF observations are significantly influenced by canopy-specific structural features (i.e., canopy architecture including leaf area index and presence of woody components), atmospheric conditions during their acquisition (e.g., proportion of direct and diffuse irradiance) and observational geometric configurations (e.g., sun and viewing directions). Radiative transfer (RT) models have the potential to provide a better understanding of the canopy structural effects on the SIF emission and RS signals. Here, we used the DART model to assess the daily influence, from morning to evening, of forest 3D architecture on SIF nadir radiance, emission, escape factor and nadir yield of eight 100 m × 100 m forest study plots established in a temperate deciduous forest of the Smithsonian Environmental Research Center (Edgewater, MD, USA). The 3D architecture of each plot was derived from airborne LiDAR. DART simulations of these 3D forest plots and their 1D (i.e., vertical profile of sun-adapted and shade-adapted leaves) and 0D (i.e., homogeneous layer of sun-adapted leaves above an homogeneous layer of shade-adapted leaves) abstractions were compared to assess the relative errors (ε1D−3D and ε0D−3D) associated with horizontal and vertical structural heterogeneity, respectively. Forest 3D structure, especially horizontal heterogeneity, had a great influence on forest nadir SIF radiance, resulting in ε1D−3D up to 55% at 8:00 and 18:00 (i.e., for oblique sun directions). The key indicators of this impact, in the descending order of importance, were the SIF escape factor (ε1D−3D up to 40%), the attenuation of incident photosynthetically active radiation (ε1D−3D less than 5%), and the SIF emission yield (ε1D−3D less than 2%). The influence of forest architecture on the nadir SIF escape factor and SIF yield (ε1D−3D up to 40%) varied over time, with differences in forest stand structure, and per spectral domain, being always larger between 640 and 700 nm than between 700 and 850 nm. In addition, woody elements demonstrated a large influence on forest SIF radiance due to their “shading” effect (ε up to 17%) and their “blocking” effect (ε ≈ 10%), both of them higher for far-red than for red SIF. These results underline the importance of 3D forest canopy architecture, especially 2D heterogeneity, and inclusion of woody elements in RT modeling used for interpretation of the RS SIF signal, and subsequently for the estimation of gross primary production and detection of vegetation stress.

Omar Regaieg↗

Assessing the Use of SAR/Optical Data Fusion and TensorFlow for Improved Mangrove Mapping

Mangrove forests are found in intertidal zones of tropical regions around the world and provide important ecological and economic benefits – they are considered carbon sequesters, habitats for flora and fauna, and natural barriers to hurricanes and tsunamis. Wood from mangrove forests are used as fuel and building materials in surrounding coastal communities, therefore promoting local livelihoods. Despite the importance of these ecosystems, mangrove forests have historically been degraded in natural processes such as severe weather, and anthropogenic factors like conversion to agriculture and aquaculture. This study assesses change in mangrove forests in Nigeria and Mozambique from 2015 to 2018 using SAR and optical data fusion. Due to frequent cloud cover over the study area, SAR and optical data is fused to obtain gap-free imagery without clouds. Landsat-8 OLI and Sentinel-1 imagery is fused with TensorFlow, an open source platform used in developing machine learning models. The resulting images are classified to discriminate mangrove forest cover from other land cover types, and change is estimated using image differencing. Understanding the rates and magnitude of mangrove change across space and time can aid in identifying priority areas for forest regeneration, and can help construct sustainable management practices for the future.

Strattman, Katherine↗