ai_agent_IP

ai_agent

maintenance

instantTrialDurationMinutes

isBiopharma

enableNewMyJoveSectionDesign

educationFeatures

seoMetaApi

ai_copilot_institution_blacklist

ai_chat_institution_blacklist

freeAccessWindow

ssoRoleCapture

scheduledMaintenanceBanner

joveLabsFeatures

disable_autoplay_for_bots

extended_trial_duration

5 minutes

The authors are grateful to the local communities on Hiiumaa island for their support, especially local farmers who manage coastal wetlands and kept the research team safe and welcomed during fieldwork. The authors thank the networking project for providing filming support: &#34;Supported by Nature &#8211;nature-based solution learning sites for a sustainable Baltic Sea&#34;, especially Toomas Kokovkin and Siiri K&#252;lm, who are working on the project and coordinating the establishment of the Learning Site/Living Lab at the study site used as an example to illustrate this protocol.

<ol>
	<li>Breiman L. Random forests. Mach Learn. 2001;45(1):5-32.</li>
	<li>Guisan A, Zimmermann NE. Predictive habitat distribution models in ecology. Ecol Model. 2000;135(2):147-186.</li>
	<li>Tuxen K et al. Mapping changes in tidal wetland vegetation composition and pattern across a salinity gradient using high spatial resolution imagery. Wetl Ecol Manag. 2011;19(2):141-157.</li>
	<li>Joyce CB, Wade PM. European Wet Grasslands: Biodiversity, Management and Restoration. John Wiley; Chichester, New York, Weinheim; 1998.</li>
	<li>Flores-de-Santiago F et al. Assessing the effect of flight altitude and overlap on orthoimage generation for UAV estimates of coastal wetlands. J Coast Conserv. 2020;24:35.</li>
	<li>Morgan RG et al. Unmanned aerial remote sensing of coastal vegetation: A review. Ann GIS. 2022;28(3):385-399.</li>
	<li>Bannari A et al. A review of vegetation indices. Remote Sens Rev. 1995;13(1-2):95.</li>
	<li>D&#237;az-Delgado R, Lucas R, Hurford C. The Roles of Remote Sensing in Nature Conservation: A Practical Guide and Case Studies. Springer; Cham; 2017.</li>
	<li>Zheng JY et al. Coastal wetland vegetation classification using pixel-based, object-based and deep learning methods based on RGB-UAV. Land. 2022;11(11).</li>
	<li>Horning N et al. Remote Sensing for Ecology and Conservation: A Handbook of Techniques. Oxford University Press; Oxford; 2020.</li>
	<li>Villoslada M et al. Fine scale plant community assessment in coastal meadows using UAV based multispectral data. Ecol Indic. 2020. doi:10.1016/j.ecolind.2019.105979.</li>
	<li>Burkhard B et al. Mapping and assessing ecosystem services in the EU - Lessons learned from the ESMERALDA approach of integration. One Ecosyst. 2018;3:e29153.</li>
	<li>Bhatnagar S et al. A nested drone-satellite approach to monitoring the ecological conditions of wetlands. ISPRS J Photogramm Remote Sens. 2021;174:151-165.</li>
	<li>Nicholson Thomas I et al. Towards a standardised monitoring of ecosystem condition: A literature review on indicators and their data sources. Ecol Indic. 2025;178:113952.</li>
	<li>Scott DB, Frail-Gauthier J, Mudie PJ. Coastal Wetlands of the World: Geology, Ecology, Distribution and Applications. Cambridge University Press; Cambridge, New York; 2014.</li>
	<li>Duarte C et al. The role of coastal plant communities for climate change mitigation and adaptation. Nat Clim Change. 2013;3:961-968.</li>
	<li>Bergamo T et al. Experimental climate change impacts on Baltic coastal wetland plant communities. 2022. doi:10.21203/rs.3.rs-1517117/v1.</li>
	<li>Perillo G et al. Coastal Wetlands: An Integrated Ecosystem Approach. Elsevier; 2018.</li>
	<li>Geary WL et al. A guide to ecosystem models and their environmental applications. Nat Ecol Evol. 2020;4(11):1459-1471.</li>
	<li>Joyce CB. Ecological consequences and restoration potential of abandoned wet grasslands. Ecol Eng. 2014;66:91-102.</li>
	<li>Joyce CB. Plant community dynamics of managed floodplain grasslands: An ordination analysis. In: Joyce CB, Wade PM, editors. European Wet Grasslands: Biodiversity, Management and Restoration. John Wiley; Chichester, New York, Weinheim; 1998. p. 173-191.</li>
	<li>R&#363;si&#326;a S, Spu&#326;&#291;is V. 1630* Boreal Baltic Coastal Meadows. In: Semi-Natural Grasslands. Latvian Nature Conservation Agency; Sigulda; 2017.</li>
	<li>White J. The population structure of vegetation. In: The Population Structure of Vegetation. Springer Netherlands; Dordrecht; 1985. p. 1-14.</li>
	<li>Neyman J. On the two different aspects of the representative method: The method of stratified sampling and the method of purposive selection. J R Stat Soc. 1934;97(4):558.</li>
	<li>Magnussen S. Calibration of a confidence interval for a classification accuracy. Open J For. 2021;11(1):14-36.</li>
	<li>Vehmaa A et al. Harmonization of Nordic coastal marsh habitat classification benefits conservation and management. Ocean Coast Manag. 2024;252:107104.</li>
	<li>Kose M et al. 20 years of Baltic Boreal coastal meadow restoration: Has it been long enough? Restor Ecol. 2020;29.</li>
	<li>Kasari-Toussaint L et al. Challenges and solutions in managing semi-natural grasslands: Insights from Estonia. Biol Conserv. 2026;313:111520.</li>
	<li>Villoslada Peci&#241;a M et al. Country-scale mapping of ecosystem services provided by semi-natural grasslands. Sci Total Environ. 2019;661:212-225.</li>
	<li>K&#246;ster T et al. The management of the coastal grasslands of Estonia. Environ Stud. 2004;10:45-54.</li>
	<li>Burnside NG et al. Use of vegetation classification and plant indicators to assess grazing abandonment in Estonian coastal wetlands. J Veg Sci. 2007;18(5):645-654.</li>
	<li>Ward RD et al. Importance of microtopography in determining plant community distribution in Baltic coastal wetlands. J Coastal Res. 2016;32(5):1062-1070.</li>
	<li>Wolff F et al. RGB vs. multispectral imagery: Mapping aapa mire plant communities with UAVs. Ecol Indic. 2023;148:110140.</li>
	<li>Dale J et al. The use of unmanned aerial vehicles to determine differences in vegetation cover: A tool for monitoring coastal wetland restoration schemes. Remote Sens. 2020;12(24):4022.</li>
	<li>Harris JM, Broussard WP, Nelson JA. Evaluating coastal wetland restoration using drones and high-resolution imagery. Estuaries Coasts. 2024;47(6):1359-1375.</li>
	<li>Maes WH. Practical guidelines for performing UAV mapping flights with snapshot sensors. Remote Sens. 2025;17(4):606.</li>
	<li>Movchan D et al. Collecting and processing drone-based remotely sensed data for use in forest recovery monitoring. J Vis Exp. 2025;(224):e68745.</li>
	<li>Yigitcanlar T et al. Machine learning and remote sensing integration for leveraging urban sustainability: A review and framework. Sustain Cities Soc. 2023;96:104653.</li>
	<li>Kvile K&#216; et al. Drone and ground-truth data collection, image annotation and machine learning: A protocol for coastal habitat mapping and classification. MethodsX. 2024;13:102935.</li>
	<li>Morgan G et al. UAS remote sensing for coastal wetland vegetation biomass estimation: A destructive vs. non-destructive sampling experiment. Remote Sens. 2025;17.</li>
	<li>Datt B. Visible/near infrared reflectance and chlorophyll content in Eucalyptus leaves. Int J Remote Sens. 1999;20(14):2741-2759.</li>
	<li>Lishawa SC et al. Mechanical harvesting effectively controls young Typha spp. invasion and unmanned aerial vehicle data enhances post-treatment monitoring. Front Plant Sci. 2017;8.</li>
	<li>Wu C, Niu Z, Gao S. The potential of the satellite derived green chlorophyll index for estimating midday light use efficiency in maize, coniferous forest and grassland. Ecol Indic. 2012;14(1):66-73.</li>
	<li>Gianelle D, Vescovo L. Determination of green herbage ratio in grasslands using spectral reflectance: Methods and ground measurements. 2007.</li>
	<li>Sripada RP et al. Aerial color infrared photography for determining early in-season nitrogen requirements in corn. Agron J. 2006;98(4):968-977.</li>
	<li>Crippen RE. Calculating the vegetation index faster. Remote Sens Environ. 1990;34(1):71-73.</li>
	<li>Gitelson AA, Kaufman YJ, Merzlyak MN. Use of a green channel in remote sensing of global vegetation from EOS-MODIS. Remote Sens Environ. 1996;58(3):289-298.</li>
	<li>Pinton D et al. A new algorithm for estimating ground elevation and vegetation characteristics in coastal salt marshes from high-resolution UAV-based LiDAR point clouds. Earth Surf Process Landf. 2020;45(14):3687-3701.</li>
	<li>Xing H et al. MSAVI-enhanced CASA model for estimating the carbon sink in coastal wetland area: A case study of Shandong Province. IEEE J Sel Top Appl Earth Obs Remote Sens. 2024;17:19698-19712.</li>
	<li>Haboudane D. Hyperspectral vegetation indices and novel algorithms for predicting green LAI of crop canopies: Modeling and validation in the context of precision agriculture. Remote Sens Environ. 2004;90(3):337-352.</li>
	<li>Yi W et al. An enhanced monitoring method for spatio-temporal dynamics of salt marsh vegetation using Google Earth Engine. Estuar Coast Shelf Sci. 2024;298:108658.</li>
	<li>Rouse JW, Haas RH, Schell JA, Deering DW. Monitoring vegetation systems in the Great Plains with ERTS [conference presentation]. Presented at: Third ERTS-1 Symposium; Washington, DC; 1974. p. 309-317. Available from: https://www.scirp.org/reference/referencespapers?referenceid=1411719 [Last accessed: 11/30/2025].</li>
	<li>Huete AR. A soil-adjusted vegetation index (SAVI). Remote Sens Environ. 1988;25(3):295-309.</li>
	<li>Paul NC et al. Optimized soil adjusted vegetation index mapping of Pune district using Google Earth Engine. Remote Sens Lett. 2025;16(7):728-736.</li>
	<li>Jordan CF. Derivation of leaf-area index from quality of light on the forest floor. Ecology. 1969;50(4):663-666.</li>
	<li>Bergamo TF et al. From UAV to PlanetScope: Upscaling fractional cover of an invasive species Rosa rugosa. J Environ Manage. 2023;336:117693.</li>
	<li>Torres-S&#225;nchez J et al. Multi-temporal mapping of the vegetation fraction in early-season wheat fields using images from UAV. Comput Electron Agric. 2014;103:104-113.</li>
	<li>Batungwanayo P, Vanclooster M, Koropitan AF. Response of seasonal vegetation dynamics to climatic constraints in northeastern Burundi. J Geosci Environ Prot. 2020;8(9):151-181.</li>
	<li>De Swaef T et al. Applying RGB- and thermal-based vegetation indices from UAVs for high-throughput field phenotyping of drought tolerance in forage grasses. Remote Sens. 2021;13(1):147.</li>
	<li>Kataoka T et al. Crop growth estimation system using machine vision [conference presentation]. Presented at: 2003 IEEE/ASME International Conference on Advanced Intelligent Mechatronics (AIM 2003); 2003. 2:b1079-b1083.</li>
	<li>Puppala H et al. Enhanced Green View Index. MethodsX. 2022;9:101824.</li>
	<li>Meyer GE, Neto JC. Verification of color vegetation indices for automated crop imaging applications. Comput Electron Agric. 2008;63(2):282-293.</li>
	<li>Woebbecke DM et al. Color indices for weed identification under various soil, residue, and lighting conditions. Trans ASAE. 1995;38(1):259-269.</li>
	<li>Guijarro M et al. Automatic segmentation of relevant textures in agricultural images. Comput Electron Agric. 2011;75(1):75-83.</li>
	<li>Sonnentag O et al. Digital repeat photography for phenological research in forest ecosystems. Agric For Meteorol. 2012;152:159-177.</li>
	<li>Louhaichi M, Borman MM, Johnson DE. Spatially located platform and aerial photography for documentation of grazing impacts on wheat. Geocarto Int. 2001;16(1):65-70.</li>
	<li>Motohka T et al. Applicability of Green-Red Vegetation Index for remote sensing of vegetation phenology. Remote Sens. 2010;2(10):2369-2387.</li>
	<li>Hunt ER et al. Evaluation of digital photography from model aircraft for remote sensing of crop biomass and nitrogen status. Precis Agric. 2005;6(4):359-378.</li>
	<li>Barr JR, Green MC, DeMaso SJ et al. Detectability and visibility biases associated with using a consumer-grade unmanned aircraft to survey nesting colonial waterbirds. J Field Ornithol. 2018;89(3):242-257.</li>
	<li>Bendig J et al. Combining UAV-based plant height from crop surface models, visible, and near infrared vegetation indices for biomass monitoring in barley. Int J Appl Earth Obs Geoinf. 2015;39:79.</li>
	<li>Tucker CJ. Red and photographic infrared linear combinations for monitoring vegetation. Remote Sens Environ. 1979;8(2):127-150.</li>
	<li>Bock T. How to install R packages from GitHub (step-by-step guide). 2018. Available from: https://www.displayr.com/installing-r-packages-from-github/ [Last accessed: 5/7/2026].</li>
	<li>Hijmans RJ et al. Raster package in R. Version. 2013. Available from: https://mirrors.sjtug.sjtu.edu.cn/cran/web/packages/raster/raster.pdf.</li>
	<li>Mohammed M, Alsunosi R. Effect of selecting validation dataset on building random forest and decision tree models. AlQalam J Med Appl. 2022:470-478.</li>
	<li>Belgiu M, Dr&#259;gu&#355; L. Random forest in remote sensing: A review of applications and future directions. ISPRS J Photogramm Remote Sens. 2016;114:24-31.</li>
	<li>Bergstra J, Bengio Y. Random search for hyper-parameter optimization. J Mach Learn Res. 2012.</li>
	<li>Naidu G, Zuva T, Sibanda EM. A review of evaluation metrics in machine learning algorithms. In: Artificial Intelligence Application in Networks and Systems. Springer International Publishing; Cham; 2023. p. 15-25.</li>
	<li>Manning CD, Raghavan P, Sch&#252;tze H. Introduction to Information Retrieval. Cambridge University Press; 2008.</li>
	<li>Blair DC. Information Retrieval, 2nd ed. C.J. Van Rijsbergen. London: Butterworths; 1979:208 pp. J Am Soc Inf Sci. 1979;30(6):374-375.</li>
	<li>IDB - Index DataBase. Available from: https://www.indexdatabase.de/ [Last accessed: 5/7/2026].</li>
	<li>Sun Z et al. UAVs as remote sensing platforms in plant ecology: Review of applications and challenges. J Plant Ecol. 2021;14(6):1003-1023.</li>
	<li>Mart&#237;nez Prentice R et al. Synergistic use of Sentinel-2 and UAV-derived data for plant fractional cover distribution mapping of coastal meadows with digital elevation models. Biogeosciences. 2024;21(6):1411-1431.</li>
	<li>Makumbura RK et al. A systematic review of unmanned aerial vehicles (UAVs) for coastal ecosystem monitoring. Sci Remote Sens. 2026;13:100438.</li>
</ol>

The authors declare no conflicts of interest. We used Grammarly and QuillBot AI-assisted tools to refine grammar and provide suggestions for improvement.

The critical steps in the protocol are in phase 1, the UAV survey, and in phase 2, fieldwork, where biophysical observations are collected, and the ground truth dataset is compiled. Both are weather-dependent and must be executed in close proximity. And both must yield geospatial datasets with high coordinate precision (1&#8211;3 cm precision was achieved for the case study). The success of vegetation index calculations and the machine learning process directly depends on the data quality of the UAV Survey and ground truth. Crucial steps to achieve UAV-survey map accuracy are described in step 1.4, Post-flight procedure. If post-processing/image geotagging uses RINEX data that is not accessible, an alternative is to use a live RTK base station, which provides real-time GNSS correction signals to the drone during flight (see an example in the video article Movchan et al.37 with an example for setup instructions).
Before data collection, the study site should be visited to gain experiential knowledge of the landscape, identify the plant communities of interest, and determine which biophysical observations can be feasibly collected on-site to describe plant community composition. Because each study location exhibits distinct landscape characteristics and flora shaped by its climate zone, identifying plant species is essential for accurate land cover mapping, as species-specific biochemical, structural, and physiological traits produce unique spectral reflectance signatures. For each sampling quadrat, coordinates should be recorded at all four corners using GNSS/RTK equipment and land&#8209;surveying software, with the quadrat identification code entered and saved. All additional biophysical observations or samples collected within the quadrat must be linked to these coordinates so that every measurement is anchored to the geospatial dataset and can be compiled in a uniform tabulated format for plant community classification and subsequent statistical analyses or ecological modeling. The sampled quadrats are labeled as training points, with community names/codes attached (for example, in this training set, they were OP, LS, US, and TG). Random Forest (RF) then learns the pixel patterns associated with each label. The final result of RF classification is a map displaying the distribution of plant community labels across the study site, based on quadrat training samples provided during fieldwork.
Phases 3 (Vegetation index calculations) and 4 (Supervised classification in R using Random Forest) are interdependent and highly modifiable. For example, Supplementary File 1 lists 19 mathematical formulas for calculating indices from multispectral bands and 23 formulas for recalculating RGB aerial survey data. Nonetheless, as VIs are formulated by researchers, the equations are open source and published in peer-reviewed articles and spectral index databases80. A greater number (than provided) of formulas are available for testing in the machine learning process to classify plant community maps. Changes to the datasets will affect the algorithm&#39;s performance. VIs can be added and omitted to test models. The availability of two final plant community maps, derived from multispectral and RGB-based datasets, provides an opportunity to compare model performances. The RGB model achieved 98.89%, but that does not necessarily mean the sensor is superior to the multispectral sensor, which achieved a lower score. RGB-based data relies on color and height, which can be efficient for classifying landcover maps of structurally diverse habitats9,33. In contrast, multispectral imagery provides more information about plant physiology, not just appearance, and may be superior at distinguishing vegetation types with similar colors and shadow resistance (e.g., NIR light, which plants strongly reflect, can be captured even when they are partly shaded81). Using only RGB sensors is limited by their narrow spectral range (red, green, blue), as subtle biochemical and physiological differences (e.g., chlorophyll content and water stress) may not be detectable without NIR, red&#8209;edge, or hyperspectral bands.
Main limitations of the method may include the costly UAV system and the photogrammetry demonstrated. However, the method is designed so that, to replicate this protocol, a multispectral sensor and an RGB camera can be used interchangeably. To implement this protocol, the eBee X fixed&#8209;wing UAV system equipped with a multispectral and RGB sensor (Sequoia) and the eMotion flight&#8209;management software was used; however, other UAV systems can reproduce the protocol provided if they include a multispectral sensor and/or an RGB camera, a mission&#8209;planning function in the flight&#8209;management software, a 90&#8209;degree nadir camera orientation, and either a user&#8209;accessible flight log for post&#8209;flight geotagging or an RTK capability to record precise image coordinates during flight. Furthermore, non-pilots may subcontract UAV surveys if the contracted pilot meets all legal and operational requirements, a common practice in research, conservation, and environmental monitoring; however, the research team remains responsible for fundamental mission design, including defining the study site and determining survey timing. Therefore, even for non-UAV pilots, it is recommended to familiarize them with the first phase of the protocol. In addition, the demonstrated photogrammetry software can be used to successfully implement the protocol, or it can be licensed for a short period to reduce costs.
A notable advantage of this protocol is its compatibility with both multispectral and standard RGB UAV cameras. It can be adopted by research teams and conservation practitioners with limited budgets and is scalable across regions and institutions, making it suitable for long-term monitoring. This hardware independence ensures the workflow remains future-proof and hardware-agnostic. Because both RGB and multispectral survey data can be used, the workflow supports comparisons across multiple sites, long-term time series&#8212;even when equipment changes&#8212;and the integration of legacy (historical) RGB datasets.
Future improvements to this protocol could incorporate texture metrics derived from high-resolution imagery to better capture structural differences in vegetation. In this context, exploring ensembles of RF models that combine RGB and multispectral imagery may improve classification accuracy. Also, future recommendations for upscaling UAV-derived plant community maps to satellite imagery and coupling this approach with cloud-based platforms would enable large-scale ecosystem modeling82. While UAV data remains essential for capturing the centimeter-scale structural and spectral detail required for accurate community-level mapping, satellite imagery could serve as an additional predictor layer or as broader contextual input. Incorporating satellite&#8209;derived variables into the RF model may enhance its ability to generalize across larger spatial extents and support multi&#8209;scale habitat assessments. This hybrid approach would allow UAV&#8209;based community maps to be nested into a broader landscape perspective, enabling the method to detect regional patterns, prioritize UAV survey locations, and strengthen long&#8209;term monitoring frameworks. Exploring how satellite data can be harmonized with UAV inputs within the RF pipeline represents a research opportunity to expand the scalability and operational utility of the protocol.
Integrating UAV imagery, field surveys, vegetation indices, and AI-assisted classification into a single, reproducible workflow is essential, as it provides the spatial, spectral, and ecological detail required for accurate mapping of low-growing vegetation. UAV-based remote sensing has gained increasing attention in the scientific community and has rapidly evolved into a widely used tool for diverse applications, particularly in coastal environment monitoring83. This method provides a practical guide to a UAV-based, machine-learning-assisted workflow for education and research, intended to support ecological restoration and monitoring natural or semi-natural grasslands in coastal ecosystems.

The goal of this protocol is to provide a practical, step-by-step workflow that combines drone-based (i.e., unmanned aerial vehicle [UAV]-based) photogrammetric survey with on-site biophysical observations as ground-truth data to produce a coastal wetland plant community distribution map. The final output, a land-cover map, is created through a semi-automated machine-learning process (random forest [RF] algorithm)1.
A plant community map is an essential dataset in wetland ecological modeling because it transforms complex vegetation patterns into a spatially explicit, pixel-based representation of habitat structure. This baseline dataset enables modeling of ecological processes (e.g., biomass distribution, species interactions, eco-hydrological responses, nutrient cycles) across a landscape2,3,4.
In addition to the plant community map, following the steps of this protocol produces a collection of geospatial data. Saved as a geographical information system (GIS) project, the dataset can be integrated into a GIS, shared, and used for further ecosystem analysis and decision-making to support management planning and environmental monitoring.
In this method, a UAV survey yields an RGB (i.e., red, green, blue, the three primary colors) and/or a multispectral, geometrically accurate orthomosaic map, along with a digital surface model (DSM), all serving as baseline data5,6. This data is used to calculate vegetation indices (VIs) using orthomosaic maps as inputs to the GIS software&#39;s calculator. To create the final output map, VIs serve as per-pixel predictor variables for RF, transforming the raw spectral information of the orthomosaic into structured inputs for classification7,8. Because VIs are mathematical combinations of spectral bands that highlight vegetation properties reflected by plants and light7, VIs can be used as independent data in ecology to monitor habitat quality and biodiversity, and support ecological modeling8,9. Therefore, VIs are saved as raster maps and included in a GIS project.
To classify and map plant communities in an AI-assisted environment, remotely sensed datasets (e.g., UAV survey maps, DSM, and VIs) must be combined with georeferenced on-site biophysical observations to ensure ecological reliability, reproducibility, and meaningful interpretation10. Such field data serve as ground truth for the RF algorithm to classify habitat-vegetation-cover pixel data in VIs and to predict plant community distribution across a study site (e.g., to create a plant community map)11. In addition to serving as a ground-truth dataset for machine learning, georeferenced observations provide a means to anchor biophysical observations within GIS. This way, the ecological dataset functions as an attribute table, which can be used as environmental variables for ecosystem modeling12,13. On-site data is valuable for evidencing the ecological conditions of a habitat because it is gathered directly within the actual environment under study, providing a realistic and immediate assessment of specific conditions14.
Coastal wetlands are low-energy habitats located in sheltered shoreline areas. Wetland ecosystems are distributed along the coastlines of six continents, excluding Antarctica, playing crucial ecological roles globally, except for ice-covered landscapes in&#160;the extreme polar regions15. The global population growth and industrialization, coastal defenses, and intensification of agricultural practices significantly impact coastal wetlands, causing fragmentation and degradation16,17. These pressures make coastal ecosystems a priority for ecological restoration and conservation worldwide18.
Environmental monitoring and ecosystem modeling of coastal habitats facilitate the evaluation of ecosystem health, the identification of temporal changes, and the assessment of restoration outcomes19. Nonetheless, effective monitoring can be hindered by the dynamic nature of these ecosystems, their restricted accessibility, and the substantial costs of data collection in complex, often remote intertidal zones. In dynamic, hard&#8209;to&#8209;access habitats, vegetation often provides the clearest, most stable signal of ecological change18.
As vegetation is a fundamental basis for habitat formation, classifying plant communities and mapping their distributions provides a critical foundation for ecological assessment and habitat process modeling20,21,22. Coastal wetlands are highly heterogeneous systems, exhibiting significant variation over short distances in elevation, salinity, vegetation structure, hydrology, and sediment characteristics. Due to this complexity, the protocol incorporates stratified quadrat&#160;sampling23 (minimum ten 1 m &#215; 1 m quadrat samples per plant community), which is not only beneficial but methodologically imperative for generating representative ecosystem models and land cover maps24,25.
To illustrate this methodology, a case study was conducted on a microtidal marsh on Hiiumaa Island in the West Estonian archipelago of the Baltic Sea (Figure 1). The Baltic Sea&#39;s coastal landscape, including marshes in sediment-accumulation zones across more than 100,000 islands within the archipelagos, is managed at different levels of intensity26. For biodiversity conservation and restoration, Baltic boreal coastal wetlands are maintained as semi-natural grasslands27,28. Such wet grasslands have regional landscape heritage value, and some, including the case study site, are part of the Natura 2000 network of protected areas. In such areas, to sustain low-growing vegetation, which supports greater biodiversity and provides habitats for wildlife such as waders29, coastal meadows are grazed extensively and/or mown seasonally to maintain open grasslands and prevent them from being overtaken by expansive species, for example, Phragmites australis30. In boreal coastal regions, wetlands managed under conservation measures typically include four key plant communities: Open Pioneer (OP), Lower Shore (LS), Upper Shore (US), and Tall Grass (TG)31. All four occur at the selected case study site. Vascular plant species dominate coastal wet grasslands. The OP indicator species are halophytes: Salicornia europaea (most common height range 3&#8211;30 cm) and Suaeda maritima (10&#8211;50 cm). The LS is dominated by Glaux maritima (3&#8211;25 cm) and Juncus geradii (25&#8211;75 cm). US indicator species are Festuca rubra (15&#8211;90 cm) and Leontodon autumnalis (10&#8211;80 cm), and dominant grasses identify TG: Deschampsia cespitosa (30&#8211;120 cm), Elytrigia repens (30&#8211;120 cm), and Molinia caerulea (50&#8211;180 cm). In addition, typical coastal wetland plants in this climate zone include: Spergularia marina (5&#8211;30 cm), Plantago maritima (10&#8211;30 cm), Triglochin maritima (15&#8211;70 cm), and Agrostis stolonifera (15&#8211;30 cm), which occur across communities.
Coastal wetlands are defined by their low-relief landscapes with subtle microtopographic variations, such as depressions and hummocks, that influence plant community distribution. These landscape features form naturally through processes such as sediment deposition during floods, storm surges, and tidal currents32. These features often lack distinct signatures detectable by coarse aerial imagery, but species composition reflects specific spectral responses that can be recorded and classified33. Commonly, satellite and aircraft aerial mapping provides the geospatial data needed for much ecosystem surveying and modeling to support monitoring and assessment34,35. However, low-altitude drone-based aerial mapping is essential for effectively surveying coastal grasslands. This approach delivers high-resolution data and provides a more detailed photogrammetric record of landscape features, including vegetation distribution patterns and vegetation height models derived from a Digital Surface Model (DSM), thereby improving classification accuracy3.
Compared to alternative approaches, UAV workflows allow flexible scheduling to match phenological stages, minimize cloud interference, and capture structural detail unavailable from satellites36,37. Combined with machine learning (e.g., Random Forest), UAV data support automated pattern detection, object classification, and the extraction of valuable insights from complex datasets that would be overwhelming for humans38. However, on-site ground sampling remains indispensable for supervised learning because&#160;it provides verified labels for training and assessing models, ensuring that models learn correct patterns and that their performance is robust and reliable11,39,40.
This protocol is designed for low-relief ecosystems with low-growing plant communities that are accessible for on-site sampling. The workflow is divided into four distinct phases (Figure 2): (1) UAV-based aerial survey, (2) ground-truth data collection and georeferencing, (3) vegetation index calculations, and (4) supervised classification using Random Forest in the open-source statistical computing environment R. The protocol was implemented using RStudio with the following key packages: terra, sp, sf, rgdal, raster, rsample, MLmetrics, and randomForest.

<table><tbody><tr><td>eBee X&amp;nbsp;</td><td>senseFly/AgEagle</td><td>eBee X, https://www.sensefly.com/drones/ebee-x/</td><td>UAV system eBee X is a professional fixed-wing mapping drone. An alternative mapping drone system can be used</td></tr><tr><td>eMotion</td><td>senseFly/AgEagle</td><td>https://www.sensefly.com/drone-software/emotion/</td><td>Used to plan drone flight missions and manage aerial data. eMotion Software is a complimentary part of the eBeeX drone system</td></tr><tr><td>External hard drive</td><td>Any supplier</td><td>NA</td><td>Size depends on the study area size project size (250 GB - 1TB)</td></tr><tr><td>Fieldwork laptop</td><td>Any supplier</td><td>NA</td><td>a capable, portable machine suitable for field operations and running drone flightlifght management so (Based on eMotion specs:&amp;nbsp; 64-bit Windows 10/11; Intel Core i5/i7 (12th Gen+) or AMD Ryzen 5/7 (&gt;3.5 GHz) - High clock speeds are more important than core count; 16GB Minimum (32GB+ Highly Recommended); Mid-range NVIDIA GTX/RTX (e.g., RTX 3060/4060); NVMe SSD (Required).&amp;nbsp;</td></tr><tr><td>GNSS/RTK system Trimble</td><td>Trimble Inc.&amp;nbsp;</td><td>Model&amp;nbsp; R10</td><td>It has a receiver with land surveying software and spare batteries. Alternative GNSS/RTK systems can also be used.</td></tr><tr><td>Grass shears</td><td>Any supplier</td><td>NA</td><td>biomass sampling (optional)</td></tr><tr><td>Pix4Dmapper&amp;nbsp;</td><td>Pix4D</td><td>https://www.pix4d.com/product/pix4dmapper-photogrammetry-software/</td><td>Photogrammetry software: Pix4Dmapper is available to license on a monthly or annual basis. An alternative photogrammetry software can be used to implement this protocol.</td></tr><tr><td>Plant identification guide</td><td>Any supplier</td><td>NA</td><td>Used to conduct biophysical observations (online, book or print-out local plant ID guides)</td></tr><tr><td>QGIS</td><td>QGIS</td><td>3.44.9 Solothurn</td><td>A free and open-source GIS software, avaliable at https://qgis.org/, alternative GIS software can be used to impliment this protocol</td></tr><tr><td>quadrat frame of 1 m x 1 m&amp;nbsp;</td><td>Any supplier</td><td>NA</td><td>To be used in phase 2 for field work/sampling, i.e. to conduct biophysical observations, can be self-made</td></tr><tr><td>R&amp;nbsp;</td><td>R-Software Services</td><td>version 4.2.0, https://cran.r-project.org&amp;nbsp;</td><td>An open-source a predictito download modelling environment widely used for statistical computing and graphics, data analysis, and predictive modeling.</td></tr><tr><td>RStudio</td><td>R-Software Services</td><td>version 2024.4.0.735, https//posit.co/download/rstudio/&amp;nbsp;</td><td></td></tr><tr><td>Rtools</td><td>R-Software Services</td><td>https://cran.r-project.org/bin/windows/Rtools/</td><td>As some packages may require compilation from source. Key pacages used: terra 1.5 21, sp 1.5 0, sf 1.0 15, rgdal 1.6 6, raster 3.5 15, rsample 1.3 1, MLmetrics 1.1 1, and randomForest 4.7 1.1.</td></tr><tr><td>Scale (battery-operated, levelled, precision &amp;plusmn;1 g)</td><td>Any supplier</td><td>NA</td><td>durable for fieldwork&amp;nbsp;</td></tr><tr><td>Sequoia</td><td>Parrot SA</td><td>Parrot SEQUOIA+</td><td>It is a Multispectral/RGB sensor, to be used in phase 1. RGB and/or multispectral sensor (many professional drones include one or both sensors). To implement this protocol used Parrot SEQUOIA+ (company Parrot SA)</td></tr><tr><td>Soil moisture reader</td><td>Any supplier</td><td>NA</td><td></td></tr><tr><td>UAV forecast weather app</td><td>Any supplier</td><td>NA</td><td>To plan flights used https://www.uavforecast.com/&amp;nbsp;</td></tr><tr><td>WET sensor kit</td><td>Delta T Devices</td><td>WET-UM-1.6</td><td>Soil moisture sensor (optional)</td></tr><tr><td>Workstation</td><td>Any supplier</td><td>NA</td><td>Optimal specification needed for smooth processing of the photogrammetry projects and machine learning in R (specs based on Pix4Dmapper software requirements: Windows 10/11, 64 bits; CPU quad-core or hexa-core Intel i9/Threadripper/Ryzen 9/; GeForce GTX GPU compatible with OpenGL 3.2 and 2 GB RAM; Hard disk: SSD; Large projects (over 500- 1000 images at 14 MP): 32 GB RAM, 60 GB SSD Free Space.</td></tr></tbody></table>

semi-automated method for mapping and classifying boreal coastal wetland plant communities using drone and ground data

Semi-Automated Method for Mapping and Classifying Boreal Coastal Wetland Plant Communities using Drone and Ground Data

Semi-automated plant community mapping bridges the gap between traditional ecological surveys and modern AI-assisted ecosystem monitoring, enabling site survey and monitoring at scales and speeds previously unattainable. Coastal wetlands, dominated by low-growing herbaceous plants, require a drone-based (Unmanned Aerial Vehicle, UAV) photogrammetric survey to achieve higher spatial resolution and greater flexibility in timing. This protocol consists of four phases, namely UAV-based aerial survey, ground-truth data collection and georeferencing, vegetation index calculation, and supervised classification using the random forest (RF) algorithm in R (i.e., AI&#8209;assisted, semi&#8209;automated mapping of plant community distributions using machine&#8209;learning classification). Key R packages used include terra, sp, sf, rgdal, raster, rsample, MLmetrics, randomForest. The emphasis in the second phase is on a traditional ecological survey method&#8212;stratified quadrat ground sampling. Ground sampling serves as ground truthing, providing empirical evidence to ensure the accuracy and reliability of the final map product. Two widely used UAV-mounted sensor types were tested: a multispectral sensor and an RGB camera, yielding 19 multispectral and 27 RGB-based indices, along with an RGB-derived digital surface model (DSM). Plant communities were mapped at a Baltic coastal wetland case study site, and the following algorithm performance results were obtained: using the multispectral dataset, the model achieved an overall accuracy of 92.3% with an out-of-bag (OOB) error of 7.75%; in comparison, the RGB dataset achieved an accuracy exceeding 98% with an OOB error of 1.14%. These results reinforce the suitability of both sensor types. Each phase of the protocol produces georeferenced datasets. These can be compiled into a layered geographical information system (GIS) Project with embedded biophysical field observations, serving as a foundation for complex ecosystem research, such as ecological modeling to forecast impacts and changes. In practice, this GIS Project can serve as a historical record of land cover and support management, environmental restoration planning, and monitoring.

The protocol comprises four integrated phases: Unmanned Aerial Vehicle (UAV) survey, ground-truth data collection, vegetation index computation, and AI-assisted classification and mapping of coastal wetland plant communities. The result is a multilayered geospatial dataset that supports applications in ecology, environmental monitoring, and decision-making for coastal wetland habitat conservation and management.

Semi-automated plant community mapping bridges the gap between traditional ecological surveys and modern AI-assisted ecosystem monitoring, enabling site ...

semi-automated-method-for-mapping-classifying-boreal-coastal-wetland

Research

JoVE Journal

Environment

The use of a needle injection method to inoculate maize and teosinte plants with the biotrophic pathogen Ustilago maydis is described.  The needle injection inoculation method facilitates the controlled delivery of the fungal pathogen in between the plant leaves where the pathogen enters the plant through the formation of appresoria. This method is highly efficient, enabling reproducible inoculations with U. maydis.

A Rapid and Efficient Method for Assessing Pathogenicity of Ustilago maydis on Maize and Teosinte Lines

We provide a technique to preserve intact tree phloem and prepare it for observation.  We create an apparatus called a phloem sandwich that allows for the introduction and observation of arthropods, microbes, and other organisms that inhabit phloem tissues.

Technique for Studying Arthropod and Microbial Communities within Tree Tissues

EPA Method 1615 uses an electropositive filter to concentrate enteroviruses and noroviruses in environmental and drinking waters. This manuscript describes the procedure for collecting samples for Method 1615 analyses.

EPA Method 1615. Measurement of Enterovirus and Norovirus Occurrence in Water by Culture and RT-qPCR. I. Collection of Virus Samples

Here we present a procedure to quantify enterovirus and norovirus in environmental and drinking waters using reverse transcription-quantitative PCR. Mean virus recovery from groundwater with this standardized procedure from EPA Method 1615 was 20% for poliovirus and 30% for murine norovirus.

EPA Method 1615. Measurement of Enterovirus and Norovirus Occurrence in Water by Culture and RT-qPCR. Part III. Virus Detection by RT-qPCR

A protocol to screen for endocrine activity in organic extracts of water samples, including treated wastewater effluent and surface (receiving) water, was adapted using commercially available division-arrested ("freeze and thaw") in vitro transactivation bioassays.

Screening for Endocrine Activity in Water Using Commercially-available In Vitro Transactivation Bioassays

Excavation of plant roots from the field as well as processing of samples into endosphere, rhizosphere, and soil are described in detail, including DNA extraction and data analysis methods. This paper is designed to enable other laboratories to use these techniques for the study of soil, endosphere, and rhizosphere microbiomes.

Isolation and Analysis of Microbial Communities in Soil, Rhizosphere, and Roots in Perennial Grass Experiments

This paper reports the protocol for a rapid identification assay for Bemisia tabaci based on loop-mediated isothermal amplification (LAMP) technology. The protocol requires minimal laboratory training and can, therefore, be implemented on-site at points of entry for plant imports such as seaports and airports.

A Loop-mediated Isothermal Amplification (LAMP) Assay for Rapid Identification of Bemisia tabaci

We developed a method to detect Phytophthora capsici zoospores in water sources using a filter paper DNA extraction method coupled with a loop-mediated isothermal amplification (LAMP) assay that can be analyzed in the field or in the lab.

Detection of Phytophthora capsici in Irrigation Water using Loop-Mediated Isothermal Amplification

A protocol is described to utilize the carbon dioxide in natural gas power plant flue gas to cultivate microalgae in open raceway ponds. Flue gas injection is controlled with a pH sensor, and microalgae growth is monitored with real time measurements of optical density.

Coupling Carbon Capture from a Power Plant with Semi-automated Open Raceway Ponds for Microalgae Cultivation

The Updegraff method is the most widely used method for the cellulose estimation. The main purpose of this demonstration is to provide a detailed Updegraff protocol for estimation of cellulose content in plant biomass samples.

Estimation of Crystalline Cellulose Content of Plant Biomass using the Updegraff Method

Estonian University of Life Sciences.  The protocol comprises four integrated phases: Unmanned Aerial Vehicle (UAV) survey, ground-truth data collection, vegetation index computation, and AI-assisted classification and mapping of coastal wetland plant communities. The result is a multilayered geospatial dataset that supports applications in ecology, environmental monitoring, and decision-making for coastal wetland habitat conservation and management.

Semi-Automated Method for Mapping and Classifying Boreal Coastal Wetland Plant Communities using Drone and Ground Data

Explore More Videos