Search

In the lower Florida Keys, the endangered Florida Key deer and numerous other wildlife species inhabit a vulnerable island environment susceptible to storm surges and rising seawater due to low elevation and flat terrain. Timely and reliable assessment of vegetation damage from natural disasters, such as Hurricane Irma, is crucial for effective habitat management. The study’s overall objective is to examine Hurricane Irma’s impact on vegetation on No Name Key, Florida, using remote sensing. The study relates the area change in vegetation obtained from remote sensing analysis to Florida Key deer population changes following the storm. The methodology involved performing a thematic change detection analysis using the following data sources: (1) aerial multispectral images (for pre- and post-Hurricane), (2) airborne lidar data (for pre- and post-Hurricane), (3) an existing vegetation map, and (4) soil data. A Support Vector Machine (SVM) image classification algorithm was applied to pre- and post-storm input image stacks to create pre- and post-Hurricane Irma vegetation maps. We were then able to obtain the area change information (for various vegetation categories) by performing the change detection analysis of the 2 SVM-classified images. The differences in areas following the storm were calculated for 7 affected vegetation types. Using the area change information following Hurricane Irma, we estimated the number of deer supported by the storm-affected vegetation. These estimated deer numbers, based on the area differences in post-Hurricane Irma vegetation types, were compared to observed deer numbers collected during the post-Hurricane Irma Texas A&M Natural Resources Institute (NRI) deer field survey. The results showed the following: mangroves had the largest negative area changes (area loss), followed by pinelands, hardwoods/hammocks, developed areas, and buttonwoods. Freshwater marshes had the largest positive area changes (area gain). The deer's preferred vegetation areas had decreased post-Hurricane Irma, resulting in a reduced deer population compared to pre-storm numbers. The predicted number of the Key deer post-Hurricane Irma fell within a 95% confidence interval of the observed deer population from the post-storm field survey. The study findings and techniques could be applied to study climate change impact, especially sea level rise. This methodology can be valuable in assessing the impact of storms on other wildlife species in similar environments. The applications and methodology are especially relevant considering the increasing frequency and intensity of storm surges and the accelerating rate of sea level rise.

Savanna ecosystems across the globe have experienced substantial changes in their vegetation composition. These changes can be attributed to three main processes: (1) encroachment, which refers to the expansion of woody plants into open areas, (2) thicketization, which is characterized by the growth of sub-canopy woody plants, and (3) disturbance, defined here as the removal of woodland cover due to both natural forces and human activities. In this study, we utilized Landsat surface reflectance data and Sentinel-1 SAR data to track the progression of these process from 1996 to 2022 in the significantly modified Post Oak Savannah ecoregion of Central Texas. Our methodology employs an ensemble classification algorithm, which combines the results of multiple models, to develop a more precise predictive model, along with the spectral–temporal segmentation algorithm LandTrendr in Google Engine (GEE). Our ensemble classification algorithms demonstrated high overall accuracies of 94.3 and 96.5% for 1996 and 2022, respectively, while our LandTrendr vegetation map exhibited an overall accuracy of 80.4%. The findings of our study reveal that 9.7% of the overall area experienced encroachment of woody plants into open area, while an additional 6.8% of the overall area has transitioned into a thicketized state due to the growth of sub-canopy woody plants. Furthermore, 5.7% of the overall area encountered woodland disturbance leading to open areas. Our findings suggest that these processes advanced unevenly throughout the region, resulting in the coexistence of three prominent plant communities that appear to have long-term stability: a dense deciduous shrubland in the southern region, as well as a thicketized oak woodland and open area mosaic in the central and northern regions. The successional divergence observed in these plant communities attests to the substantial influence of human modification on the landscape. This study demonstrates the potential of integrating passive optical multispectral data and active SAR data to accurately map large-scale ecological processes.

To effectively combat the re-infestation of boll weevils (Anthonomus grandis L.) in cotton fields, it is necessary to address the detection of volunteer cotton (VC) plants (Gossypium hirsutum L.) in rotation crops such as corn (Zea mays L.) and sorghum (Sorghum bicolor L.). The current practice involves manual field scouting at the field edges, which often leads to the oversight of VC plants growing in the middle of fields alongside corn and sorghum. As these VC plants reach the pinhead squaring stage (5–6 leaves), they can become hosts for boll weevil pests. Consequently, it becomes crucial to detect, locate, and accurately spot-spray these plants with appropriate chemicals. This paper focuses on the application of YOLOv5m to detect and locate VC plants during the tasseling (VT) growth stage of cornfields. Our results demonstrate that VC plants can be detected with a mean average precision (mAP) of 79% at an Intersection over Union (IoU) of 50% and a classification accuracy of 78% on images sized 1207 × 923 pixels. The average detection inference speed is 47 frames per second (FPS) on the NVIDIA Tesla P100 GPU-16 GB and 0.4 FPS on the NVIDIA Jetson TX2 GPU, which underscores the relevance and impact of detection speed on the feasibility of real-time applications. Additionally, we show the application of a customized unmanned aircraft system (UAS) for spot-spray applications through simulation based on the developed computer vision (CV) algorithm. This UAS-based approach enables the near-real-time detection and mitigation of VC plants in corn fields, with near-real-time defined as approximately 0.02 s per frame on the NVIDIA Tesla P100 GPU and 2.5 s per frame on the NVIDIA Jetson TX2 GPU, thereby offering an efficient management solution for controlling boll weevil pests.

The Ice, Cloud, and Land Elevation Satellite-2 (ICESat-2) provides an extraordinary opportunity to support global large-scale forest carbon mapping, but further research is needed in order to obtain wall-to-wall forest aboveground biomass (AGB) maps with this technology. The effects of vegetation structure on the performance of canopy height and AGB modeling using ICESat-2 photon-counting light detection and ranging (LiDAR) data in Mediterranean forest areas have not been previously studied in the literature. In this study, we combined recent ICESat-2 vegetation (ATL08) data, Airborne Laser Scanning (ALS)- and field-based estimates, and a multi-sensor earth observation composite for extrapolation of AGB estimates and AGB mapping. A diverse gradient of forest Mediterranean ecosystems, distributed over 19,744.15 km2 of forest area in the region of Extremadura (Spain), with different species and structural complexity forming 5 different forest types (3 Quercus spp. dominated and 2 Pinus spp. dominated forests), was used to (i) evaluate the precision of ICESat-2 canopy height estimations, (ii) develop ICESat-2-based AGB models, and (iii) generate a spatially continuous prediction of AGB by using data from the satellite missions Sentinel-1 (S1), Sentinel-2 (S2), Phased Array L-band Synthetic Aperture Radar (ALOS2/PALSAR2), and Shuttle Radar Topography Mission (SRTM). First, ALS- and ICESat-2-derived metrics that best described canopy height (p98 and rh98, respectively) were compared at the ATL08 segment level. Second, ALS-based AGB values were derived at the ATL08 segment scale. Third, ALS-based AGB estimates at the ICESat-2 segment level were used as dependent variables to fit ICESat-2-based AGB models. Fourth, a multi-sensor approach was then implemented to predict ICESat-2-derived AGB, by means of a Random Forest (RF) modeling technique, with predictors retrieved from S1, S2, ALOS2/PALSAR2, and SRTM. Finally, RF was used to generate wall-to-wall AGB maps that were compared with field-, ALS- and ICESat-2-based observations. The agreement between the ALS- and ICESat-2-derived metrics related to the canopy height distribution was higher for Pinus spp. forest than for the Quercus spp-dominated forests. The ICESat-2-based AGB models yielded model efficiency (Mef) values between 0.56 and 0.80, with a RMSE ranging from 7.76 to 17.71 Mg ha−1 and rRMSE from 19.04 to 55.21%. The multi-sensor RF models provided the following results when compared with the ICESat-2- and ALS-based AGB observations: R2 values of 0.63 and 0.64, and RMSE values of 11.10 Mg ha−1(rRMSE = 28.15%) and 12.28 Mg ha−1 (rRMSE = 31.45%), respectively, and an approximately unbiased result (0.03 Mg ha−1 and 0.09 Mg ha−1). When applied to the field-based validation data set (4th Spanish National Forest Inventory (SNFI-4) plots = 508), the RF-derived AGB model showed a relatively lower predictive capacity (R2 = 0.45), a higher RMSE value (25.88 Mg ha−1) and slightly biased results (−1.47 Mg ha−1), especially for larger field-derived AGB intervals. The results of this study serve to provide an initial quantitative assessment of the ICESat-2 ATL08 data for large-scale AGB estimation. The findings suggest that a multi-sensor approach may be feasible for extrapolating ICESat-2-derived AGB estimates over areas where field or ALS reference data are not available.

The feral or volunteer cotton (VC) plants when reach the pinhead squaring phase (5–6 leaf stage) can act as hosts for the boll weevil (Anthonomus grandis L.) pests. The Texas Boll Weevil Eradication Program (TBWEP) employs people to locate and eliminate VC plants growing by the side of roads or fields with rotation crops but the ones growing in the middle of fields remain undetected. In this paper, we demonstrate the application of computer vision (CV) algorithm based on You Only Look Once version 5 (YOLOv5) for detecting VC plants growing in the middle of corn fields at three different growth stages (V3, V6 and VT) using unmanned aircraft systems (UAS) remote sensing imagery. All the four variants of YOLOv5 (s, m, l, and x) were used and their performances were compared based on classification accuracy, mean average precision (mAP) and F1-score. It was found that YOLOv5s could detect VC plants with maximum classification accuracy of 98% and mAP of 96.3% at V6 stage of corn while YOLOv5s and YOLOv5m resulted in the lowest classification accuracy of 85% and YOLOv5m and YOLOv5l had the least mAP of 86.5% at VT stage on images of size 416 × 416 pixels. The developed CV algorithm has the potential to effectively detect and locate VC plants growing in the middle of corn fields as well as expedite the management aspects of TBWEP.

Plastic shopping bags are often discarded as litter and can be carried away from roadsides and become tangled on cotton plants in farm fields. This rubbish plastic can end up in the cotton at the gin if not removed before harvest. These bags may not only cause problems in the ginning process but might also become embedded in cotton fibers, reducing the quality and marketable value. Therefore, detecting, locating, and removing the bags before the cotton is harvested is required. Manually detecting and locating these bags in cotton fields is a tedious, time-consuming, and costly process. To solve this, this paper shows the application of YOLOv5 to detect white and brown colored plastic bags tangled at three different heights in cotton plants (bottom, middle, top) using Unmanned Aircraft Systems (UAS)-acquired Red, Green, Blue (RGB) images. It was found that an average white and brown bag could be detected at 92.35% and 77.87% accuracies and a mean average precision (mAP) of 87.68%. Similarly, the trained YOLOv5 model, on average, could detect 94.25% of the top, 49.58% of the middle, and only 5% of the bottom bags. It was also found that both the color of the bags (p < 0.001) and their height on cotton plants (p < 0.0001) had a significant effect on detection accuracy. The findings reported in this paper can help in the autonomous detection of plastic contaminants in cotton fields and potentially speed up the mitigation efforts, thereby reducing the amount of contaminants in cotton gins.

Forest canopy cover is an essential biophysical parameter of ecological significance, especially for characterizing woodlands and forests. This research focused on using data from the ICESat-2/ATLAS spaceborne lidar sensor, a photon-counting altimetry system, to map the forest canopy cover over a large country extent. The study proposed a novel approach to compute categorized canopy cover using photon-counting data and available ancillary Landsat images to build the canopy cover model. In addition, this research tested a cloud-mapping platform, the Google Earth Engine (GEE), as an example of a large-scale study. The canopy cover map of the Republic of Türkiye produced from this study has an average accuracy of over 70%. Even though the results were promising, it has been determined that the issues caused by the auxiliary data negatively affect the overall success. Moreover, while GEE offered many benefits, such as user-friendliness and convenience, it had processing limits that posed challenges for large-scale studies. Using weak or strong beams’ segments separately did not show a significant difference in estimating canopy cover. Briefly, this study demonstrates the potential of using photon-counting data and GEE for mapping forest canopy cover at a large scale.

NASA’s Ice, Cloud, and land Elevation Satellite-2 (ICESat-2) provides exceptional opportunities for characterizing the structure of ecosystems through the acquisition of along-track, three-dimensional observations. Focusing on canopy cover as a fundamental parameter for assessing forest conditions, the overall goal of this study was to establish a framework for generating a gridded 30 m canopy cover product with ICESat-2. Specifically, our objectives were to (1) Determine and compare ICESat-2-derived canopy cover with airborne lidar-derived and the 2016 National Land Cover Database (NLCD) cover product estimates, and (2) Evaluate a methodology for wall-to-wall mapping of canopy cover. Using two Southern US sites, the Sam Houston National Forest (SHNF) in south-east Texas and the Solon Dixon Forestry Education Center (SDFEC) in southern Alabama, four measures of canopy cover estimated with ICESat-2′s Land-Vegetation Along-Track Product, or ATL08, were evaluated at the 30 m pixel scale. Comparisons were made using spatially coinciding NLCD pixels and airborne lidar-derived reference canopy cover. A suite of Landsat and Landsat-derived parameters were then used as predictors to model and map each measure of canopy cover with Random Forests (RF), and their accuracies were assessed and compared. Correlations (r) between ICESat-2-derived and airborne lidar canopy cover at the pixel scale ranged from 0.57 to 0.78, and R2 up to 0.81 was produced between NLCD and ICESat-2-derived canopy cover. RF models developed for extrapolating ICESat-2-derived canopy cover estimate yielded R2 values between 0.50 and 0.61 (RMSEs between 16% and 20%) when evaluated with airborne lidar-derived canopy cover. With a demonstrated capability of ICESat-2 to estimate vegetation biophysical parameters, the findings serve to support the spatially comprehensive mapping of other vegetation attributes, especially forest aboveground biomass, and contribute to the development of an up-to-date gridded canopy cover product.

Abstract Traditional phenotyping methods, coupled with genetic mapping in segregating populations, have identified loci governing complex traits in many crops. Unoccupied aerial systems (UAS)‐based phenotyping has helped to reveal a more novel and dynamic relationship between time‐specific associated loci with complex traits previously unable to be evaluated. Over 1,500 maize (Zea mays L.) hybrid row plots containing 280 different replicated maize hybrids from the Genomes to Fields (G2F) project were evaluated agronomically and using UAS in 2017. Weekly UAS flights captured variation in plant heights during the growing season under three different management conditions each year: optimal planting with irrigation (G2FI), optimal dryland planting without irrigation (G2FD), and a stressed late planting (G2LA). Plant height of different flights were ranked based on importance for yield using a random forest (RF) algorithm. Plant heights captured by early flights in G2FI trials had higher importance (based on Gini scores) for predicting maize grain yield (GY) but also higher accuracies in genomic predictions which fluctuated for G2FD (−0.06∼0.73), G2FI (0.33∼0.76), and G2LA (0.26∼0.78) trials. A genome‐wide association analysis discovered 52 significant single nucleotide polymorphisms (SNPs), seven were found consistently in more than one flights or trial; 45 were flight or trial specific. Total cumulative marker effects for each chromosome's contributions to plant height also changed depending on flight. Using UAS phenotyping, this study showed that many candidate genes putatively play a role in the regulation of plant architecture even in relatively early stages of maize growth and development.

Globally, native semiarid grasslands and savannas have experienced a densification of woody plant species—leading to a multitude of environmental, economic, and cultural changes. These encroached areas are unique in that the diversity of tree species is small, but at the same time the individual species possess diverse phenological responses. The overall goal of this study was to evaluate the ability of very high resolution drone imagery to accurately map species of woody plants encroaching on semiarid grasslands. For a site in the Edwards Plateau ecoregion of central Texas, we used affordable, very high resolution drone imagery to which we applied maximum likelihood (ML), support vector machine (SVM), random forest (RF), and VGG-19 convolutional neural network (CNN) algorithms in combination with pixel-based (with and without post-processing) and object-based (small and large) classification methods. Based on test sample data (n = 1000) the VGG-19 CNN model achieved the highest overall accuracy (96.9%). SVM came in second with an average classification accuracy of 91.2% across all methods, followed by RF (89.7%) and ML (86.8%). Overall, our findings show that RGB drone sensors are indeed capable of providing highly accurate classifications of woody plant species in semiarid landscapes—comparable to and even greater in some regards to those achieved by aerial and drone imagery using hyperspectral sensors in more diverse landscapes.

Lidar (light detection and ranging) remote sensing technology provides promising tools for 3D characterization of the earth’s surface. In ecosystem studies, lidar derived structural parameters relating to vegetation and terrain have been extensively used in many applications and are rapidly expanding. Yet, most of the lidar applications have focused on tall, woody vegetation in forested environments and less research attention is given to non-forest, short stature vegetation dominated ecosystems. Similar to the lidar developments in forestry, novel methodological approaches and algorithm developments will be necessary to improve estimates of structural and biophysical properties (i.e. biomass and carbon storage) in non-forested short stature environments. Under changing climate scenarios, the latter is particularly useful to improve our understanding of their future role as terrestrial carbon sinks. In an attempt to identify research gaps in airborne lidar remote sensing application in short stature vegetation studies, in this review article we provide a comprehensive overview on the current state of airborne lidar applications. Our focus is mainly on the levels of accuracies and errors reported, as well as the potentials and limitations of the methods applied in these studies. We also provide insights into future research needs and applications in these environments.

National Aeronautics and Space Administration’s (NASA’s) Ice, Cloud, and land Elevation Satellite-2 (ICESat-2) provides rich insights over the Earth’s surface through elevation data collected by its Advanced Topographic Laser Altimeter System (ATLAS) since its launch in September 2018. While this mission is primarily aimed at capturing ice measurements, ICESat-2 also provides data over vegetated areas, offering the capability to gain insights into ecosystem structure and the potential to contribute to the sustainable management of forests. This study involved an examination of the utility of ICESat-2 for estimating forest aboveground biomass (AGB). The objectives of this study were to: (1) investigate the use of canopy metrics for estimating AGB, using data extracted from an ICESat-2 transect over forests in south-east Texas; (2) compare the accuracy for estimating AGB using data from the strong beam and weak beam; and (3) upscale predicted AGB estimates using variables from Landsat multispectral imagery and land cover and canopy cover maps, to generate a 30 m spatial resolution AGB map. Methods previously developed with simulated ICESat-2 data over Sam Houston National Forest (SHNF) in southeast Texas were adapted using actual data from an adjacent ICESat-2 transect over similar vegetation conditions. Custom noise filtering and photon classification algorithms were applied to ICESat-2’s geolocated photon data (ATL03) for one beam pair, consisting of a strong and weak beam, and canopy height estimates were retrieved. Canopy height parameters were extracted from 100 m segments in the along-track direction for estimating AGB, using regression analysis. ICESat-2-derived AGB estimates were then extrapolated to develop a 30 m AGB map for the study area, using vegetation indices from Landsat 8 Operational Land Imager (OLI), National Land Cover Database (NLCD) landcover and canopy cover, with random forests (RF). The AGB estimation models used few canopy parameters and suggest the possibility for applying well-developed methods for modeling AGB with airborne light detection and ranging (lidar) data, using processed ICESat-2 data. The final regression model achieved a R2 and root mean square error (RMSE) value of 0.62 and 24.63 Mg/ha for estimating AGB and RF model evaluation with a separate test set yielded a R2 of 0.58 and RMSE of 23.89 Mg/ha. Findings provide an initial look at the ability of ICESat-2 to estimate AGB and serve as a basis for further upscaling efforts.

Accurate measures of forest structural parameters are essential to forest inventory and growth models, managing wildfires, and modeling of carbon cycle. Terrestrial laser scanning (TLS) fills the gap between tree scale manual measurements and large scale airborne LiDAR measurements by providing accurate below crown information through non-destructive methods. This study developed innovative methods to extract individual tree height, diameter at breast height (DBH), and crown width of trees in East Texas. Further, the influence of scan settings, such as leaf-on/leaf-off seasons, tree distance from the scanner, and processing choices, on the accuracy of deriving tree measurements were also investigated. DBH was retrieved by cylinder fitting at different height bins. Individual trees were extracted from the TLS point cloud to determine tree heights and crown widths. The R-squared value ranged from 0.91 to 0.97 when field measured DBH was validated against TLS derived DBH using different methods. An accuracy of 92% (RMSE = 1.51 m) was obtained for predicting tree heights. The R-squared value was 0.84 and RMSE was 1.08 m when TLS derived crown widths were validated using field measured crown widths. Examples of underestimations of field measured forest structural parameters due to tree shadowing have also been discussed in this study. The results from this study will benefit foresters and remote sensing studies from airborne and spaceborne platforms, for map upscaling or calibration purposes, for aboveground biomass estimation, and prudent decision making by the forest management.

The United States Forest Service Forest Inventory and Analysis (FIA) Program provides a diverse selection of data used to assess the status of the nation’s forests using sample locations dispersed throughout the country. Airborne laser scanning (ALS) systems are capable of producing accurate measurements of individual tree dimensions and also possess the ability to characterize forest structure in three dimensions. This study investigates the potential of discrete return ALS data for modeling forest aboveground biomass (AGBM) and gross volume (gV) at FIA plot locations in the Malheur National Forest, eastern Oregon utilizing three analysis levels: (1) individual subplot (r = 7.32 m); (2) plot, comprising four clustered subplots; and (3) hectare plot (r = 56.42 m). A methodology for the creation of three point cloud-based airborne LiDAR metric sets is presented. Models for estimating AGBM and gV based on LiDAR-derived height metrics were built and validated utilizing FIA estimates of AGBM and gV derived using regional allometric equations. Simple linear regression models based on the plot-level analysis out performed subplot-level and hectare-level models, producing R2 values of 0.83 and 0.81 for AGBM and gV, utilizing mean height and the 90th height percentile as predictors, respectively. Similar results were found for multiple regression models, where plot-level analysis produced models with R2 values of 0.87 and 0.88 for AGBM and gV, utilizing multiple height percentile metrics as predictor variables. Results suggest that the current FIA plot design can be used with dense airborne LiDAR data to produce area-based estimates of AGBM and gV, and that the increased spatial scale of hectare plots may be inappropriate for modeling AGBM of gV unless exhaustive tree tallies are available. Overall, this study demonstrates that ALS data can be used to create models that describe the AGBM and gV of Pacific Northwest FIA plots and highlights the potential of estimates derived from ALS data to augment current FIA data collection procedures by providing a temporary intermediate estimation of AGBM and gV for plots with outdated field measurements.

Spatially continuous estimates of forest aboveground biomass (AGB) are essential to supporting the sustainable management of forest ecosystems and providing invaluable information for quantifying and monitoring terrestrial carbon stocks. The launch of the Ice, Cloud, and land Elevation Satellite-2 (ICESat-2) on September 15th, 2018 offers an unparalleled opportunity to assess AGB at large scales using along-track samples that will be provided during its three-year mission. The main goal of this study was to investigate deep learning (DL) neural networks for mapping AGB with ICESat-2, using simulated photon-counting lidar (PCL)-estimated AGB for daytime, nighttime, and no noise scenarios, Landsat imagery, canopy cover, and land cover maps. The study was carried out in Sam Houston National Forest located in south-east Texas, using a simulated PCL-estimated AGB along two years of planned ICESat-2 profiles. The primary tasks were to investigate and determine neural network architecture, examine the hyper-parameter settings, and subsequently generate wall-to-wall AGB maps. A first set of models were developed using vegetation indices calculated from single-date Landsat imagery, canopy cover, and land cover, and a second set of models were generated using metrics from one year of Landsat imagery with canopy cover and land cover maps. To compare the effectiveness of final models, comparisons with Random Forests (RF) models were made. The deep neural network (DNN) models achieved R2 values of 0.42, 0.49, and 0.50 for the daytime, nighttime, and no noise scenarios respectively. With the extended dataset containing metrics calculated from Landsat images acquired on different dates, substantial improvements in model performance for all data scenarios were noted. The R2 values increased to 0.64, 0.66, and 0.67 for the daytime, nighttime, and no noise scenarios. Comparisons with Random forest (RF) prediction models highlighted similar results, with the same R2 and root mean square error (RMSE) range (15−16 Mg/ha) for daytime and nighttime scenarios. Findings suggest that there is potential for mapping AGB using a combinatory approach with ICESat-2 and Landsat-derived products with DL.

Continuing population growth will result in increasing global demand for food and fiber for the foreseeable future. During the growing season, variability in the height of crops provides important information on plant health, growth, and response to environmental effects. This paper indicates the feasibility of using structure from motion (SfM) on images collected from 120 m above ground level (AGL) with a fixed-wing unmanned aerial vehicle (UAV) to estimate sorghum plant height with reasonable accuracy on a relatively large farm field. Correlations between UAV-based estimates and ground truth were strong on all dates (R2 > 0.80) but are clearly better on some dates than others. Furthermore, a new method for improving UAV-based plant height estimates with multi-level ground control points (GCPs) was found to lower the root mean square error (RMSE) by about 20%. These results indicate that GCP-based height calibration has a potential for future application where accuracy is particularly important. Lastly, the image blur appeared to have a significant impact on the accuracy of plant height estimation. A strong correlation (R2 = 0.85) was observed between image quality and plant height RMSE and the influence of wind was a challenge in obtaining high-quality plant height data. A strong relationship (R2 = 0.99) existed between wind speed and image blurriness.

A plethora of information contained in full-waveform (FW) Light Detection and Ranging (LiDAR) data offers prospects for characterizing vegetation structures. This study aims to investigate the capacity of FW LiDAR data alone for tree species identification through the integration of waveform metrics with machine learning methods and Bayesian inference. Specifically, we first conducted automatic tree segmentation based on the waveform-based canopy height model (CHM) using three approaches including TreeVaW, watershed algorithms and the combination of TreeVaW and watershed (TW) algorithms. Subsequently, the Random forests (RF) and Conditional inference forests (CF) models were employed to identify important tree-level waveform metrics derived from three distinct sources, such as raw waveforms, composite waveforms, the waveform-based point cloud and the combined variables from these three sources. Further, we discriminated tree (gray pine, blue oak, interior live oak) and shrub species through the RF, CF and Bayesian multinomial logistic regression (BMLR) using important waveform metrics identified in this study. Results of the tree segmentation demonstrated that the TW algorithms outperformed other algorithms for delineating individual tree crowns. The CF model overcomes waveform metrics selection bias caused by the RF model which favors correlated metrics and enhances the accuracy of subsequent classification. We also found that composite waveforms are more informative than raw waveforms and waveform-based point cloud for characterizing tree species in our study area. Both classical machine learning methods (the RF and CF) and the BMLR generated satisfactory average overall accuracy (74% for the RF, 77% for the CF and 81% for the BMLR) and the BMLR slightly outperformed the other two methods. However, these three methods suffered from low individual classification accuracy for the blue oak which is prone to being misclassified as the interior live oak due to the similar characteristics of blue oak and interior live oak. Uncertainty estimates from the BMLR method compensate for this downside by providing classification results in a probabilistic sense and rendering users with more confidence in interpreting and applying classification results to real-world tasks such as forest inventory. Overall, this study recommends the CF method for feature selection and suggests that BMLR could be a superior alternative to classical machining learning methods.

This study developed an IPCC (Intergovernmental Panel on Climate Change) compliant method for the estimation of above-ground carbon (AGC) in forest stands using remote sensing technology. A multi-level morphological active contour (MMAC) algorithm was employed to obtain tree-level metrics (tree height (LH), crown radius (LCR), competition index (LCI), and stem diameter (LDBH)) from an airborne LiDAR-derived canopy height model. Seven biomass-based AGC models and 13 volume-based AGC models were developed using a training dataset and validated using a separate validation dataset. Four accuracy measures, mean absolute error (MAE), root-mean-square error (RMSE), percentage RMSE (PRMSE), and root-mean-square percentage error (RMSPE) were calculated for each of the 20 models. These measures were transformed into a new index, accuracy improvement percentage (AIP), for post hoc testing of model performance in estimating forest stand AGC stock. Results showed that the tree-level AGC models explained 84% to 91% of the variance in tree-level AGC within the training dataset. Prediction errors (RMSEs) for these models ranged between 15 ton/ha and 210 ton/ha in mature forest stands, which is equal to an error percentage in the range 6% to 86%. At the stand-level, several models achieved accurate and reliable predictions of AGC stock. Some models achieved 90% to 95% accuracy, which was equal to or superior to the R-squared of the tree-level AGC models. The first recommended model was a biomass-based model using the metrics LDBH, LH, and LCI and the others were volume-based models using LH, LCI, and LCR and LDBH and LH. One metric, LCI, played a critical role in upgrading model performance when banded together with LH and LCR or LDBH and LCR. We conclude by proposing an IPCC-compatible method that is suitable for calculating tree-level AGC and predicting AGC stock of forest stands from airborne LiDAR data.