Comparison of Support Vector Machine and Random Forest Algorithms for Invasive and Expansive Species Classification Using Airborne Hyperspectral Data

Capacity and capability of remote sensing to inform invasive plant species management in the Pacific Islands region

The Pacific Islands region is home to several of the world's biodiversity hotspots, yet its unique flora and fauna are under threat because of biological invasions. These invasions are likely to proliferate as human activity increases and large-scale natural disturbances unfold, exacerbated by climate change. Remote sensing data and techniques provide a feasible method to map and monitor invasive plant species and inform invasive plant species management across the Pacific Islands region. We used case studies taken from literature retrieved from Google Scholar, 3 regional agencies' digital libraries, and 2 online catalogs on invasive plant species management to examine the uptake and challenges faced in the implementation of remote sensing technology in the Pacific region. We synthesized remote sensing techniques and outlined their potential to detect and map invasive plant species based on species phenology, structural characteristics, and image texture algorithms. The application of remote sensing methods to detect invasive plant species was heavily reliant on species ecology, extent of invasion, and available geospatial and remotely sensed image data. However, current mechanisms that support invasive plant species management, including policy frameworks and geospatial data infrastructure, operated in isolation, leading to duplication of efforts and creating unsustainable solutions for the region. For remote sensing to support invasive plant species management in the region, key stakeholders including conservation managers, researchers, and practitioners; funding agencies; and regional organizations must invest, where possible, in the broader geospatial and environmental sector, integrate, and streamline policies and improve capacity and technology access.

Improvement of evapotranspiration simulation study in the Hailar River basin under the influence of vegetation dynamics

In arid and semi-arid areas with <400 mm of precipitation, evapotranspiration (ET) accounts for about 80% of precipitation and is the main water consumer in the watershed. However, vegetation greening in recent years will increase ET and exacerbate the aridity of the area by affecting soil moisture in the root system. Vegetation changes are regional and spatially heterogeneous, therefore, in order to characterize ET changes under vegetation dynamics, it is necessary to expand the spatial scale of ET simulation. However, widely used evapotranspiration simulation models, such as the Shuttleworth-Wallace model (SW model), are deficient in reflecting the direct and indirect effects of vertical (i.e., soil depths) and horizontal (i.e., vegetation dynamics) directions. Based on field sampling and constructed structural equation model (SEM), we found that vegetation dynamics affect evapotranspiration not only directly, but also indirectly by affecting soil moisture at different depths. On this basis, we defined the weighting coefficients of 0.85 and 0.15 for grassland vegetation zones, 0.3, 0.15, 0.20, 0.25, 0.10 for forest-grass interspersed zones, and 0.20, 0.55, 0.25 for forested zones, respectively, based on the SEM results. Different soil moisture weighting coefficients were defined within different vegetation type zones and the improved SW model is called S-W-α. Comparing the simulation results with the measured data, S-W-α improved the ET simulation accuracy in this region by 33.92% and the improved ET spatial trend can respond to the dynamic changes of vegetation. Replacing the ET module in the Block-wise use of TOPMODEL and Muskingum-Cunge method mode (BTOP model) with the modified S-W-α, the results show that the simulation accuracy of the improved model is increased by 25%, and the Nash is higher than 75% for both the rate period and the validation period, which realizes the extension of the model from the point scale to the basin scale. The modified model may provide technical support for simulation of evapotranspiration and management of ecosystem health in ecologically fragile areas.

Machine Learning Enabled Photoacoustic Spectroscopy for Noninvasive Assessment of Breast Tumor Progression In Vivo: A Preclinical Study

Breast cancer is a dreaded disease affecting women the most in cancer-related deaths over other cancers. However, early diagnosis of the disease can help increase survival rates. The existing breast cancer diagnosis tools do not support the early diagnosis of the disease. Therefore, there is a great need to develop early diagnostic tools for this cancer. Photoacoustic spectroscopy (PAS), being very sensitive to biochemical changes, can be relied upon for its application in detecting breast tumors in vivo. With this motivation, in the current study, an aseptic chamber integrated photoacoustic (PA) probe was designed and developed to monitor breast tumor progression in vivo, established in nude mice. The device served the dual purpose of transporting tumor-bearing animals to the laboratory from the animal house and performing PA experiments in the same chamber, maintaining sterility. In the current study, breast tumor was induced in the nude mice by MCF-7 cells injection and the corresponding PA spectra at different time points (day 0, 5, 10, 15, and 20) of tumor progression in vivo in the same animals. The recorded photoacoustic spectra were subsequently preprocessed, wavelet-transformed, and subjected to filter-based feature selection algorithm. The selected top 20 features, by minimum redundancy maximum relevance (mRMR) algorithm, were then used to build an input feature matrix for machine learning (ML)-based classification of the data. The performance of classification models demonstrated 100% specificity, whereas the sensitivity of 95, 100, 92.5, and 85% for the time points, day 5, 10, 15, and 20, respectively. These results suggest the potential of PA signal-based classification of breast tumor progression in a preclinical model. The PA signal contains information on the biochemical changes associated with disease progression, emphasizing its translational strength toward early disease diagnosis.

Using Unmanned Aerial Vehicles to Evaluate Revegetation Success on Natural Gas Pipelines

The Appalachian region of the United States has experienced significant growth in the production of natural gas. Developing the infrastructure required to transport this resource to market creates significant disturbances across the landscape, as both well pads and transportation pipelines must be created in this mountainous terrain. Midstream infrastructure, which includes pipeline rights-of-way and associated infrastructure, can cause significant environmental degradation, especially in the form of sedimentation. The introduction of this non-point source pollutant can be detrimental to freshwater ecosystems found throughout this region. This ecological risk has necessitated the enactment of regulations related to midstream infrastructure development. Weekly, inspectors travel afoot along new pipeline rights-of-way, monitoring the re-establishment of surface vegetation and identifying failing areas for future management. The topographically challenging terrain of West Virginia makes these inspections difficult and dangerous to the hiking inspectors. We evaluated the accuracy at which unmanned aerial vehicles replicated inspector classifications to evaluate their use as a complementary tool in the pipeline inspection process. Both RGB and multispectral sensor collections were performed, and a support vector machine classification model predicting vegetation cover were made for each dataset. Using inspector defined validation plots, our research found comparable high accuracy between the two collection sensors. This technique displays the capability of augmenting the current inspection process, though it is likely that the model can be improved further. The high accuracy thus obtained suggests valuable implementation of this widely available technology in aiding these challenging inspections.

A rapid and accurate method of mapping invasive Tamarix genotypes using Sentinel-2 images

Background

The management of invasive Tamarix genotypes depends on reliable and accurate information of their extent and distribution. This study investigated the utility of the multispectral Sentinel-2 imageries to map infestations of the invasive Tamarix along three riparian ecosystems in the Western Cape Province of South Africa.

Methods

The Sentinel-2 image was acquired from the GloVis website (http://glovis.usgs.gov/). Random forest (RF) and support vector machine (SVM) algorithms were used to classify and estimate the spatial distribution of invasive Tamarix genotypes and other land-cover types in three riparian zones viz. the Leeu, Swart and Olifants rivers. A total of 888 reference points comprising of actual 86 GPS points and additional 802 points digitized using the Google Earth Pro free software were used to ground-truth the Sentinel-2 image classification.

Results

The results showed the random forest classification produced an overall accuracy of 87.83% (with kappa value of 0.85), while SVM achieved an overall accuracy of 86.31% with kappa value of 0.83. The classification results revealed that the Tamarix invasion was more rampant along the Olifants River near De Rust with a spatial distribution of 913.39 and 857.74 ha based on the RF and SVM classifiers, respectively followed by the Swart River with Tamarix coverage of 420.06 ha and 715.46 hectares, respectively. The smallest extent of Tamarix invasion with only 113.52 and 74.27 hectares for SVM and RF, respectively was found in the Leeu River. Considering the overall accuracy of 85% as the lowest benchmark for a robust classification, the results obtained in this study suggests that the SVM and RF classification of the Sentinel-2 imageries were effective and suitable to map invasive Tamarix genotypes and discriminate them from other land-cover types.

The Influence of Data Density and Integration on Forest Canopy Cover Mapping Using Sentinel-1 and Sentinel-2 Time Series in Mediterranean Oak Forests

Forest canopy cover (FCC) is one of the most important forest inventory parameters and plays a critical role in evaluating forest functions. This study examines the potential of integrating Sentinel-1 (S-1) and Sentinel-2 (S-2) data to map FCC in the heterogeneous Mediterranean oak forests of western Iran in different data densities (one-year datasets vs. three-year datasets). This study used very high-resolution satellite images from Google Earth, gridded points, and field inventory plots to generate a reference dataset. Based on it, four FCC classes were defined, namely non-forest, sparse forest (FCC = 1–30%), medium-density forest (FCC = 31–60%), and dense forest (FCC > 60%). In this study, three machine learning (ML) models, including Random Forest (RF), Support Vector Machine (SVM), and Classification and Regression Tree (CART), were used in the Google Earth Engine and their performance was compared for classification. Results showed that the SVM produced the highest accuracy on FCC mapping. The three-year time series increased the ability of all ML models to classify FCC classes, in particular the sparse forest class, which was not distinguished well by the one-year dataset. Class-level accuracy assessment results showed a remarkable increase in F-1 scores for sparse forest classification by integrating S-1 and S-2 (10.4% to 18.2% increased for the CART and SVM ML models, respectively). In conclusion, the synergetic use of S-1 and S-2 spectral temporal metrics improved the classification accuracy compared to that obtained using only S-2. The study relied on open data and freely available tools and can be integrated into national monitoring systems of FCC in Mediterranean oak forests of Iran and neighboring countries with similar forest attributes.

Identifying Key Environmental Factors for Paulownia coreana Habitats: Implementing National On-Site Survey and Machine Learning Algorithms

Monitoring and preserving natural habitats has become an essential activity in many countries today. As a native tree species in Korea, Paulownia coreana has periodically been surveyed in national ecological surveys and was identified as an important target for conservation as well as habitat monitoring and management. This study explores habitat suitability models (HSMs) for Paulownia coreana in conjunction with national ecological survey data and various environmental factors. Together with environmental variables, the national ecological survey data were run through machine learning algorithms such as Artificial Neural Network and Decision Tree & Rules, which were used to identify the impact of individual variables and create HSMs for Paulownia coreana, respectively. Unlike other studies, which used remote sensing data to create HSMs, this study employed periodical on-site survey data for enhanced validity. Moreover, localized environmental resources such as topography, soil, and rainfall were taken into account to project habitat suitability. Among the environment variables used, the study identified critical attributes that affect the habitat conditions of Paulownia coreana. Therefore, the habitat suitability modelling methods employed in this study could play key roles in planning, monitoring, and managing plants species in regional and national levels. Furthermore, it could shed light on existing challenges and future research needs.

An Automatic Procedure for Forest Fire Fuel Mapping Using Hyperspectral (PRISMA) Imagery: A Semi-Supervised Classification Approach

Natural vegetation provides various benefits to human society, but also acts as fuel for wildfires. Therefore, mapping fuel types is necessary to prevent wildfires, and hyperspectral imagery has applications in multiple fields, including the mapping of wildfire fuel types. This paper presents an automatic semisupervised machine learning approach for discriminating between wildfire fuel types and a procedure for fuel mapping using hyperspectral imagery (HSI) from PRISMA, a recently launched satellite of the Italian Space Agency. The approach includes sample generation and pseudolabelling using a single spectral signature as input data for each class, unmixing mixed pixels by a fully constrained linear mixing model, and differentiating sparse and mountainous vegetation from typical vegetation using biomass and DEM maps, respectively. Then the procedure of conversion from a classified map to a fuel map according to the JRC Anderson Codes is presented. PRISMA images of the southern part of Sardinia, an island off Italy, were considered to implement this procedure. As a result, the classified map obtained an overall accuracy of 87% upon validation. Furthermore, the stability of the proposed approach was tested by repeating the procedure on another HSI acquired for part of Bulgaria and we obtained an overall stability of around 84%. In terms of repeatability and reproducibility analysis, a degree of confidence greater than 95% was obtained. This study suggests that PRISMA imagery has good potential for wildfire fuel mapping, and the proposed semisupervised learning approach can generate samples for training the machine learning model when there is no single go-to dataset available, whereas this procedure can be implemented to develop a wildfire fuel map for any part of Europe using LUCAS land cover points as input.

Airborne HySpex Hyperspectral Versus Multitemporal Sentinel-2 Images for Mountain Plant Communities Mapping

Climate change and anthropopression significantly impact plant communities by leading to the spread of expansive and alien invasive plants, thus reducing their biodiversity. Due to significant elevation gradients, high-mountain plant communities in a small area allow for the monitoring of the most important environmental changes. Additionally, being a tourist attraction, they are exposed to direct human influence (e.g., trampling). Airborne hyperspectral remote sensing is one of the best data sources for vegetation mapping, but flight campaign costs limit the repeatability of surveys. A possible alternative approach is to use satellite data from the Copernicus Earth observation program. In our study, we compared multitemporal Sentinel-2 data with HySpex airborne hyperspectral images to map the plant communities on Tatra Mountains based on open-source R programing implementation of Random Forest and Support Vector Machine classifiers. As high-mountain ecosystems are adapted to topographic conditions, the input of Digital Elevation Model (DEM) derivatives on the classification accuracy was analyzed and the effect of the number of training pixels was tested to procure practical information for field campaign planning. For 13 classes (from rock scree communities and alpine grasslands to montane conifer and deciduous forests), we achieved results in the range of 76–90% F1-score depending on the data set. Topographic features: digital terrain model (DTM), normalized digital surface model (nDSM), and aspect and slope maps improved the accuracy of HySpex spectral images, transforming their minimum noise fraction (MNF) bands and Sentinel-2 data sets by 5–15% of the F1-score. Maps obtained on the basis of HySpex imagery (2 m; 430 bands) had a high similarity to maps obtained on the basis of multitemporal Sentinel-2 data (10 m; 132 bands; 11 acquisition dates), which was less than one percentage point for classifications based on 500–1000 pixels; for sets consisting of 50–100 pixels, Random Forest (RF) offered better accuracy.

U-shaped deep-learning models for island ecosystem type classification, a case study in Con Dao Island of Vietnam

The monitoring of ecosystem dynamics utilises time and resources from scientists and land-use managers, especially in wetland ecosystems in islands that have been affected significantly by both the current state of oceans and human-made activities. Deep-learning models for natural and anthropogenic ecosystem type classification, based on remote sensing data, have become a tool to potentially replace manual image interpretation. This study proposes a U-Net model to develop a deep learning model for classifying 10 island ecosystems with cloud- and shadow-based data using Sentinel-2, ALOS and NOAA remote sensing data. We tested and compared different optimiser methods with two benchmark methods, including support vector machines and random forests. In total, 48 U-Net models were trained and compared. The U-Net model with the Adadelta optimiser and 64 filters showed the best result, because it could classify all island ecosystems with 93 percent accuracy and a loss function value of 0.17. The model was used to classify and successfully manage ecosystems on a particular island in Vietnam. Compared to island ecosystems, it is not easy to detect coral reefs due to seasonal ocean currents. However, the trained deep-learning models proved to have high performances compared to the two traditional methods. The best U-Net model, which needs about two minutes to create a new classification, could become a suitable tool for island research and management in the future.

Classifying Forest Structure of Red-Cockaded Woodpecker Habitat Using Structure from Motion Elevation Data De-Rived from sUAS Imagery

Small unmanned aerial systems (sUAS) and relatively new photogrammetry software solutions are creating opportunities for forest managers to perform spatial analysis more efficiently and cost-effectively. This study aims to identify a method for leveraging these technologies to analyze vertical forest structure of red-cockaded woodpecker habitat in Montgomery County, Texas. Traditional sampling methods would require numerous hours of ground surveying and data collection using various measuring techniques. Structure from Motion (SfM), a photogrammetric method for creating 3-D structure from 2-D images, provides an alternative to relatively expensive LIDAR sensing technologies and can accurately model the high level of complexity found within our study area’s vertical structure. DroneDeploy, a photogrammetry processing app service, was used to post-process and create a point cloud, which was later further processed into a Canopy Height Model (CHM). Using supervised, object-based classification and comparing multiple classifier algorithms, classifications maps were generated with a best overall accuracy of 84.8% using Support Vector Machine in ArcGIS Pro software. Appropriately sized training sample datasets, correctly processed elevation data, and proper image segmentation were among the major factors impacting classification accuracy during the numerous classification iterations performed.

Mapping Invasive Plant Species with Hyperspectral Data Based on Iterative Accuracy Assessment Techniques

Recent developments in computer hardware made it possible to assess the viability of permutation-based approaches in image classification. Such approaches sample a reference dataset multiple times in order to train an arbitrary number of machine learning models while assessing their accuracy. So-called iterative accuracy assessment techniques or Monte-Carlo-based approaches can be a useful tool when it comes to assessment of algorithm/model performance but are lacking when it comes to actual image classification and map creation. Due to the multitude of models trained, one has to somehow reason which one of them, if any, should be used in the creation of a map. This poses an interesting challenge since there is a clear disconnect between algorithm assessment and the act of map creation. Our work shows one of the ways this disconnect can be bridged. We calculate how often a given pixel was classified as given class in all variations of a multitude of post-classification images delivered by models trained during the iterative assessment procedure. As a classification problem, a mapping of Calamagrostis epigejos, Rubus spp., Solidago spp. invasive plant species using three HySpex hyperspectral datasets collected in June, August and September was used. As a classification algorithm, the support vector machine approach was chosen, with training hyperparameters obtained using a grid search approach. The resulting maps obtained F1-scores ranging from 0.87 to 0.89 for Calamagrostis epigejos, 0.89 to 0.97 for Rubus spp. and 0.99 for Solidago spp.

Classifying Crop Types Using Two Generations of Hyperspectral Sensors (Hyperion and DESIS) with Machine Learning on the Cloud

Advances in spaceborne hyperspectral (HS) remote sensing, cloud-computing, and machine learning can help measure, model, map and monitor agricultural crops to address global food and water security issues, such as by providing accurate estimates of crop area and yield to model agricultural productivity. Leveraging these advances, we used the Earth Observing-1 (EO-1) Hyperion historical archive and the new generation DLR Earth Sensing Imaging Spectrometer (DESIS) data to evaluate the performance of hyperspectral narrowbands in classifying major agricultural crops of the U.S. with machine learning (ML) on Google Earth Engine (GEE). EO-1 Hyperion images from the 2010–2013 growing seasons and DESIS images from the 2019 growing season were used to classify three world crops (corn, soybean, and winter wheat) along with other crops and non-crops near Ponca City, Oklahoma, USA. The supervised classification algorithms: Random Forest (RF), Support Vector Machine (SVM), and Naive Bayes (NB), and the unsupervised clustering algorithm WekaXMeans (WXM) were run using selected optimal Hyperion and DESIS HS narrowbands (HNBs). RF and SVM returned the highest overall producer’s, and user’s accuracies, with the performances of NB and WXM being substantially lower. The best accuracies were achieved with two or three images throughout the growing season, especially a combination of an earlier month (June or July) and a later month (August or September). The narrow 2.55 nm bandwidth of DESIS provided numerous spectral features along the 400–1000 nm spectral range relative to smoother Hyperion spectral signatures with 10 nm bandwidth in the 400–2500 nm spectral range. Out of 235 DESIS HNBs, 29 were deemed optimal for agricultural study. Advances in ML and cloud-computing can greatly facilitate HS data analysis, especially as more HS datasets, tools, and algorithms become available on the Cloud.

Densely Connected Pyramidal Dilated Convolutional Network for Hyperspectral Image Classification

Recently, with the extensive application of deep learning techniques in the hyperspectral image (HSI) field, particularly convolutional neural network (CNN), the research of HSI classification has stepped into a new stage. To avoid the problem that the receptive field of naive convolution is small, the dilated convolution is introduced into the field of HSI classification. However, the dilated convolution usually generates blind spots in the receptive field, resulting in discontinuous spatial information obtained. In order to solve the above problem, a densely connected pyramidal dilated convolutional network (PDCNet) is proposed in this paper. Firstly, a pyramidal dilated convolutional (PDC) layer integrates different numbers of sub-dilated convolutional layers is proposed, where the dilated factor of the sub-dilated convolution increases exponentially, achieving multi-sacle receptive fields. Secondly, the number of sub-dilated convolutional layers increases in a pyramidal pattern with the depth of the network, thereby capturing more comprehensive hyperspectral information in the receptive field. Furthermore, a feature fusion mechanism combining pixel-by-pixel addition and channel stacking is adopted to extract more abstract spectral–spatial features. Finally, in order to reuse the features of the previous layers more effectively, dense connections are applied in densely pyramidal dilated convolutional (DPDC) blocks. Experiments on three well-known HSI datasets indicate that PDCNet proposed in this paper has good classification performance compared with other popular models.

Smart Agriculture Cloud Using AI Based Techniques

This research proposes a generic smart cloud-based system in order to accommodate multiple scenarios where agriculture farms using Internet of Things (IoTs) need to be monitored remotely. The real-time and stored data are analyzed by specialists and farmers. The cloud acts as a central digital data store where information is collected from diverse sources in huge volumes and variety, such as audio, video, image, text, and digital maps. Artificial Intelligence (AI) based machine learning models such as Support Vector Machine (SVM), which is one of many classification types, are used to accurately classify the data. The classified data are assigned to the virtual machines where these data are processed and finally available to the end-users via underlying datacenters. This processed form of digital information is then used by the farmers to improve their farming skills and to update them as pre-disaster recovery for smart agri-food. Furthermore, it will provide general and specific information about international markets relating to their crops. This proposed system discovers the feasibility of the developed digital agri-farm using IoT-based cloud and provides solutions to problems. Overall, the approach works well and achieved performance efficiency in terms of execution time by 14%, throughput time by 5%, overhead time by 9%, and energy efficiency by 13.2% in the presence of competing smart farming baselines.

Classification Efficacy Using K-Fold Cross-Validation and Bootstrapping Resampling Techniques on the Example of Mapping Complex Gully Systems

The availability of aerial and satellite imageries has greatly reduced the costs and time associated with gully mapping, especially in remote locations. Regardless, accurate identification of gullies from satellite images remains an open issue despite the amount of literature addressing this problem. The main objective of this work was to investigate the performance of support vector machines (SVM) and random forest (RF) algorithms in extracting gullies based on two resampling methods: bootstrapping and k-fold cross-validation (CV). In order to achieve this objective, we used PlanetScope data, acquired during the wet and dry seasons. Using the Normalized Difference Vegetation Index (NDVI) and multispectral bands, we also explored the potential of the PlanetScope image in discriminating gullies from the surrounding land cover. Results revealed that gullies had significantly different (p < 0.001) spectral profiles from any other land cover class regarding all bands of the PlanetScope image, both in the wet and dry seasons. However, NDVI was not efficient in gully discrimination. Based on the overall accuracies, RF’s performance was better with CV, particularly in the dry season, where its performance was up to 4% better than the SVM’s. Nevertheless, class level metrics (omission error: 11.8%; commission error: 19%) showed that SVM combined with CV was more successful in gully extraction in the wet season. On the contrary, RF combined with bootstrapping had relatively low omission (16.4%) and commission errors (10.4%), making it the most efficient algorithm in the dry season. The estimated gully area was 88 ± 14.4 ha in the dry season and 57.2 ± 18.8 ha in the wet season. Based on the standard error (8.2 ha), the wet season was more appropriate in gully identification than the dry season, which had a slightly higher standard error (8.6 ha). For the first time, this study sheds light on the influence of these resampling techniques on the accuracy of satellite-based gully mapping. More importantly, this study provides the basis for further investigations into the accuracy of such resampling techniques, especially when using different satellite images other than the PlanetScope data.

Comparison of Random Forest, Support Vector Machines, and Neural Networks for Post-Disaster Forest Species Mapping of the Krkonoše/Karkonosze Transboundary Biosphere Reserve

Mountain forests are exposed to extreme conditions (e.g., strong winds and intense solar radiation) and various types of damage by insects such as bark beetles, which makes them very sensitive to climatic changes. Therefore, continuous monitoring is crucial, and remote-sensing techniques allow the monitoring of transboundary areas where a common policy is needed to protect and monitor the environment. In this study, we used Sentinel-2 and Landsat 8 open data to assess the forest stands classification of the UNESCO Krkonoše/Karkonosze Transboundary Biosphere Reserve, which is undergoing dynamic changes in recovering woodland vegetation due to an ecological disaster that led to damage and death of a large portion of the forests. Currently, in this protected area, dry big trunks and branches coexist with naturally occurring young forests. This heterogeneity generates mixes, which hinders the automation of classification. Thus, we used three machine learning algorithms—Random Forest (RF), Support Vector Machine (SVM), and Artificial Neural Network (ANN)—to classify dominant tree species (birch, beech, larch and spruce). The best results were obtained for the SVM RBF classifier, which offered an average median F1-score that oscillated around 67.2–91.5% depending on the species. The obtained maps, which were based on multispectral satellite images, were also compared with classifications made for the same area on the basis of hyperspectral APEX imagery (288 spectral bands with three-meter resolution), indicating high convergence in the recognition of woody species.

Machine-Learning Classification of Soil Bulk Density in Salt Marsh Environments

Remotely sensed data from both in situ and satellite platforms in visible, near-infrared, and shortwave infrared (VNIR–SWIR, 400–2500 nm) regions have been widely used to characterize and model soil properties in a direct, cost-effective, and rapid manner at different scales. In this study, we assess the performance of machine-learning algorithms including random forest (RF), extreme gradient boosting machines (XGBoost), and support vector machines (SVM) to model salt marsh soil bulk density using multispectral remote-sensing data from the Landsat-7 Enhanced Thematic Mapper Plus (ETM+) platform. To our knowledge, use of remote-sensing data for estimating salt marsh soil bulk density at the vegetation rooting zone has not been investigated before. Our study reveals that blue (band 1; 450–520 nm) and NIR (band 4; 770–900 nm) bands of Landsat-7 ETM+ ranked as the most important spectral features for bulk density prediction by XGBoost and RF, respectively. According to XGBoost, band 1 and band 4 had relative importance of around 41% and 39%, respectively. We tested two soil bulk density classes in order to differentiate salt marshes in terms of their capability to support vegetation that grows in either low (0.032 to 0.752 g/cm³) or high (0.752 g/cm³ to 1.893 g/cm³) bulk density areas. XGBoost produced a higher classification accuracy (88%) compared to RF (87%) and SVM (86%), although discrepancies in accuracy between these models were small (<2%). XGBoost correctly classified 178 out of 186 soil samples labeled as low bulk density and 37 out of 62 soil samples labeled as high bulk density. We conclude that remote-sensing-based machine-learning models can be a valuable tool for ecologists and engineers to map the soil bulk density in wetlands to select suitable sites for effective restoration and successful re-establishment practices.

An Evaluation of Pixel- and Object-Based Tree Species Classification in Mixed Deciduous Forests Using Pansharpened Very High Spatial Resolution Satellite Imagery

Quality tree species information gathering is the basis for making proper decisions in forest management. By applying new technologies and remote sensing methods, very high resolution (VHR) satellite imagery can give sufficient spatial detail to achieve accurate species-level classification. In this study, the influence of pansharpening of the WorldView-3 (WV-3) satellite imagery on classification results of three main tree species (Quercus robur L., Carpinus betulus L., and Alnus glutinosa (L.) Geartn.) has been evaluated. In order to increase tree species classification accuracy, three different pansharpening algorithms (Bayes, RCS, and LMVM) have been conducted. The LMVM algorithm proved the most effective pansharpening technique. The pixel- and object-based classification were applied to three pansharpened imageries using a random forest (RF) algorithm. The results showed a very high overall accuracy (OA) for LMVM pansharpened imagery: 92% and 96% for tree species classification based on pixel- and object-based approach, respectively. As expected, the object-based exceeded the pixel-based approach (OA increased by 4%). The influence of fusion on classification results was analyzed as well. Overall classification accuracy was improved by the spatial resolution of pansharpened images (OA increased by 7% for pixel-based approach). Also, regardless of pixel- or object-based classification approaches, the influence of the use of pansharpening is highly beneficial to classifying complex, natural, and mixed deciduous forest areas.

Hyperspectral Imaging for Identification of an Invasive Plant Mikania micrantha Kunth

Mile-a-minute weed (Mikania micrantha Kunth) is considered as one of top 100 most dangerous invasive species in the world. A fast and accurate detection technology will be needed to identify M. micrantha. It will help to mitigate the extensive ecologic and economic damage on our ecosystems caused by this alien plant. Hyperspectral technology fulfills the above requirement. However, when working with hyperspectral images, preprocessing, dimension reduction, and classifier are fundamental to achieving reliable recognition accuracy and efficiency. The spectral data of M. micrantha were collected using hyperspectral imaging in the spectral range of 450-998 nm. A different combination of preprocessing methods, principal component analysis (for dimension reduction), and three classifiers were used to analyze the collected hyperspectral images. The results showed that a combination of Savitzky-Golay (SG) smoothing, principal component analysis (PCA), and random forest (RF) achieved an accuracy (A) of 88.71%, an average accuracy (AA) of 88.68%, and a Kappa of 0.7740 with an execution time of 9.647 ms. In contrast, the combination of SG, PCA and a support vector machine (SVM) resulted in a weaker performance in terms of A (84.68%), AA(84.66%), and Kappa (0.6934), but with less execution time (1.318 ms). According to the requirements for specific identification accuracy and time cost, SG-PCA-RF and SG-PCA-SVM might represent two promising methods for recognizing M. micrantha in the wild.

Exploring PRISMA Scene for Fire Detection: Case Study of 2019 Bushfires in Ben Halls Gap National Park, NSW, Australia

Precursore IperSpettrale della Missione Applicativa (Hyperspectral Precursor of the Application Mission, PRISMA) is a new hyperspectral mission by the ASI (Agenzia Spaziale Italiana, Italian Space Agency) mission launched in 2019 to measure the unique spectral features of diverse materials including vegetation and forest disturbances. In this study, we explored the potential use of this new sensor PRISMA for active wildfire characterization. We used the PRISMA hypercube acquired during the Australian bushfires of 2019 in New South Wales to test three detection techniques that take advantage of the unique spectral features of biomass burning in the spectral range measured by PRISMA. The three methods—the CO2-CIBR (continuum interpolated band ratio), HFDI (hyperspectral fire detection index) and AKBD (advanced K band difference)—were adapted to the PRISMA sensor’s characteristics and evaluated in terms of performance. Classification techniques based on machine learning algorithms (support vector machine, SVM) were used in combination with the visual interpretation of a panchromatic sharpened PRISMA image for validation. Preliminary analysis showed a good overall performance of the instrument in terms of radiance. We observed that the presence of the striping effect in the data can influence the performance of the indices. Both the CIBR and HFDI adapted for PRISMA were able to produce a detection rate spanning between 0.13561 and 0.81598 for CO2-CIBR and that between 0.36171 and 0.88431 depending on the chosen band combination. The potassium emission index turned out to be inadequate for locating flaming in our data, possibly due to multiple factors such as striping noise and the spectral resolution (12 nm) of the PRISMA band centered at the potassium emission.

Comparison of Support Vector Machines and Random Forests for Corine Land Cover Mapping

Land cover information is essential in European Union spatial management, particularly that of invasive species, natural habitats, urbanization, and deforestation; therefore, the need for accurate and objective data and tools is critical. For this purpose, the European Union’s flagship program, the Corine Land Cover (CLC), was created. Intensive works are currently being carried out to prepare a new version of CLC+ by 2024. The geographical, climatic, and economic diversity of the European Union raises the challenge to verify various test areas’ methods and algorithms. Based on the Corine program’s precise guidelines, Sentinel-2 and Landsat 8 satellite images were tested to assess classification accuracy and regional and spatial development in three varied areas of Catalonia, Poland, and Romania. The method is dependent on two machine learning algorithms, Random Forest (RF) and Support Vector Machine (SVM). The bias of classifications was reduced using an iterative of randomized training, test, and verification pixels. The ease of the implementation of the used algorithms makes reproducing the results possible and comparable. The results show that an SVM with a radial kernel is the best classifier, followed by RF. The high accuracy classes that can be updated and classes that should be redefined are specified. The methodology’s potential can be used by developers of CLC+ products as a guideline for algorithms, sensors, and the possibilities and difficulties of classifying different CLC classes.

Performance and Feasibility of Drone-Mounted Imaging Spectroscopy for Invasive Aquatic Vegetation Detection

Invasive plants are non-native species that can spread rapidly, leading to detrimental economic, ecological, or environmental impact. In aquatic systems such as the Sacramento-San Joaquin River Delta in California, USA, management agencies use manned aerial vehicles (MAV) imaging spectroscopy missions to map and track annual changes in invasive aquatic plants. Advances in unmanned aerial vehicles (UAV) and sensor miniaturization are enabling higher spatial resolution species mapping, which is promising for early detection of invasions before they spread over larger areas. This study compared maps made from UAV-based imaging spectroscopy with the manned airborne imaging spectroscopy-derived maps that are currently produced for monitoring invasive aquatic plants in the Sacramento-San Joaquin Delta. Concurrent imagery was collected using the MAV mounted HyMap sensor and the UAV mounted Nano-Hyperspec at a wetland study site and classification maps generated using random forest models were compared. Classification accuracies were comparable between the Nano- and HyMap-derived maps, with the Nano-derived map having a slightly higher overall accuracy. Additionally, the higher resolution of the Nano imagery allowed detection of patches of water hyacinth present in the study site that the HyMap could not. However, it would not be feasible to operate the Nano as a replacement to HyMap at scale despite its improved detection capabilities due to the high costs associated with overcoming area coverage limitations. Overall, UAV-based imaging spectroscopy provides comparable or improved capability, and we suggest it could be used to supplement existing monitoring programs by focusing on target areas of high ecologic or economic priority.

Intra-Annual Variabilities of Rubus caesius L. Discrimination on Hyperspectral and LiDAR Data

The study was focused on a plant native to Poland, the European dewberry Rubus caesius L., which is a species with the ability to become excessively abundant within its original range, potentially causing significant changes in ecosystems, including biodiversity loss. Monitoring plant distributions over large areas requires mapping that is fast, reliable, and repeatable. For Rubus, different types of data were successfully used for classification, but most of the studies used data with a very high spectral resolution. The aim of this study was to indicate, using hyperspectral and Light Detection and Ranging (LiDAR) data, the main functional trait crucial for R. caesius differentiation from non-Rubus. This analysis was carried out with consideration of the seasonal variability and different percentages of R. caesius in the vegetation patches. The analysis was based on hyperspectral HySpex images and Airborne Laser Scanning (ALS) products. Data were acquired during three campaigns: early summer, summer, and autumn. Differentiation based on Linear Discriminate Analysis (LDA) and Non-Parametric Multivariate Analysis of Variance (NPMANOVA) analysis was successful for each of the analysed campaigns using optical data, but the ALS data were less useful for identification. The analysis indicated that selected spectral ranges (VIS, red-edge, and parts of the NIR and possibly SWIR ranges) can be useful for differentiating R. caesius from non-Rubus. The most useful indices were ARI1, CRI1, ARVI, GDVI, CAI, NDNI, and MRESR. The obtained results indicate that it is possible to classify R. caesius using images with lower spectral resolution than hyperspectral data.

Tree Species Classification in Mixed Deciduous Forests Using Very High Spatial Resolution Satellite Imagery and Machine Learning Methods

Spatially explicit information on tree species composition is important for both the forest management and conservation sectors. In combination with machine learning algorithms, very high-resolution satellite imagery may provide an effective solution to reduce the need for labor-intensive and time-consuming field-based surveys. In this study, we evaluated the possibility of using multispectral WorldView-3 (WV-3) satellite imagery for the classification of three main tree species (Quercus robur L., Carpinus betulus L., and Alnus glutinosa (L.) Geartn.) in a lowland, mixed deciduous forest in central Croatia. The pixel-based supervised classification was performed using two machine learning algorithms: random forest (RF) and support vector machine (SVM). Additionally, the contribution of gray level cooccurrence matrix (GLCM) texture features from WV-3 imagery in tree species classification was evaluated. Principal component analysis confirmed GLCM variance to be the most significant texture feature. Of the 373 visually interpreted reference polygons, 237 were used as training polygons and 136 were used as validation polygons. The validation results show relatively high overall accuracy (85%) for tree species classification based solely on WV-3 spectral characteristics and the RF classification approach. As expected, an improvement in classification accuracy was achieved by a combination of spectral and textural features. With the additional use of GLCM variance, the overall accuracy improved by 10% and 7% for RF and SVM classification approaches, respectively.

Special Issue “Hyperspectral Remote Sensing of Agriculture and Vegetation”

The advent of up-to-date hyperspectral technologies, and their increasing performance both spectrally and spatially, allows for new and exciting studies and practical applications in agriculture (soils and crops) and vegetation mapping and monitoring atregional (satellite platforms) andwithin-field (airplanes, drones and ground-based platforms) scales. Within this context, the special issue has included eleven international research studies using different hyperspectral datasets (from the Visible to the Shortwave Infrared spectral region) for agricultural soil, crop and vegetation modelling, mapping, and monitoring. Different classification methods (Support Vector Machine, Random Forest, Artificial Neural Network, Decision Tree) and crop canopy/leaf biophysical parameters (e.g., chlorophyll content) estimation methods (partial least squares and multiple linear regressions) have been evaluated. Further, drone-based hyperspectral mapping by combining bidirectional reflectance distribution function (BRDF) model for multi-angle remote sensing and object-oriented classification methods are also examined. A review article on the recent advances of hyperspectral imaging technology and applications in agriculture is also included in this issue. The special issue is intended to help researchers and farmers involved in precision agriculture technology and practices to a better comprehension of strengths and limitations of the application of hyperspectral measurements for agriculture and vegetation monitoring. The studies published herein can be used by the agriculture and vegetation research and management communities to improve the characterization and evaluation of biophysical variables and processes, as well as for a more accurate prediction of plant nutrient using existing and forthcoming hyperspectral remote sensing technologies.

Submerged macrophyte assessment in rivers: An automatic mapping method using Pléiades imagery

Submerged macrophyte monitoring is a major concern for hydrosystem management, particularly for understanding and preventing the potential impacts of global change on ecological functions and services. Macrophyte distribution assessments in rivers are still primarily realized using field monitoring or manual photo-interpretation of aerial images. Considering the lack of applications in fluvial environments, developing operational, low-cost and less time-consuming tools able to automatically map and monitor submerged macrophyte distribution is therefore crucial to support effective management programs. In this study, the suitability of very fine-scale resolution (50 cm) multispectral Pléiades satellite imagery to estimate submerged macrophyte cover, at the scale of a 1 km river section, was investigated. The performance of nonparametric regression methods (based on two reliable and well-known machine learning algorithms for remote sensing applications, Random Forest and Support Vector Regression) were compared for several spectral datasets, testing the relevance of 4 spectral bands (red, green, blue and near-infrared) and two vegetation indices (the Normalized Difference Vegetation Index, NDVI, and the Green-Red Vegetation Index, GRVI), and for several field sampling configurations. Both machine learning algorithms applied to a Pléiades image were able to reasonably well predict macrophyte cover in river ecosystems with promising performance metrics (R² above 0.7 and RMSE around 20%). The Random Forest algorithm combined to the 4 spectral bands from Pléiades image was the most efficient, particularly for extreme cover values (0% and 100%). Our study also demonstrated that a larger number of fine-scale field sampling entities clearly involved better cover predictions than a smaller number of larger sampling entities.

Introducing GEOBIA to Landscape Imageability Assessment: A Multi-Temporal Case Study of the Nature Reserve “Kózki”, Poland

Geographic object-based image analysis (GEOBIA) is a primary remote sensing tool utilized in land-cover mapping and change detection. Land-cover patches are the primary data source for landscape metrics and ecological indicator calculations; however, their application to visual landscape character (VLC) indicators was little investigated to date. To bridge the knowledge gap between GEOBIA and VLC, this paper puts forward the theoretical concept of using viewpoint as a landscape imageability indicator into the practice of a multi-temporal land-cover case study and explains how to interpret the indicator. The study extends the application of GEOBIA to visual landscape indicator calculations. In doing so, eight different remote sensing imageries are the object of GEOBIA, starting from a historical aerial photograph (1957) and CORONA declassified scene (1965) to contemporary (2018) UAV-delivered imagery. The multi-temporal GEOBIA-delivered land-cover patches are utilized to find the minimal isovist set of viewpoints and to calculate three imageability indicators: the number, density, and spacing of viewpoints. The calculated indicator values, viewpoint rank, and spatial arrangements allow us to describe the scale, direction, rate, and reasons for VLC changes over the analyzed 60 years of landscape evolution. We found that the case study nature reserve (“Kózki”, Poland) landscape imageability transformed from visually impressive openness to imageability due to the impression of several landscape rooms enclosed by forest walls. Our results provide proof that the number, rank, and spatial arrangement of viewpoints constitute landscape imageability measured with the proposed indicators. Discussing the method’s technical limitations, we believe that our findings contribute to a better understanding of land-cover change impact on visual landscape structure dynamics and further VLC indicator development.

Multi-Temporal Sentinel-2 Data in Classification of Mountain Vegetation

The electromagnetic spectrum registered via satellite remote sensing methods became a popular data source that can enrich traditional methods of vegetation monitoring. The European Space Agency Sentinel-2 mission, thanks to its spatial (10–20 m) and spectral resolution (12 spectral bands registered in visible-, near-, and mid-infrared spectrum) and primarily its short revisit time (5 days), helps to provide reliable and accurate material for the identification of mountain vegetation. Using the support vector machines (SVM) algorithm and reference data (botanical map of non-forest vegetation, field survey data, and high spatial resolution images) it was possible to classify eight vegetation types of Giant Mountains: bogs and fens, deciduous shrub vegetation, forests, grasslands, heathlands, subalpine tall forbs, subalpine dwarf pine scrubs, and rock and scree vegetation. Additional variables such as principal component analysis (PCA) bands and selected vegetation indices were included in the best classified dataset. The results of the iterative classification, repeated 100 times, were assessed as approximately 80% median overall accuracy (OA) based on multi-temporal datasets composed of images acquired through the vegetation growing season (from late spring to early autumn 2018), better than using a single-date scene (70%–72% OA). Additional variables did not significantly improve the results, showing the importance of spectral and temporal information themselves. Our study confirms the possibility of fully available data for the identification of mountain vegetation for management purposes and protection within national parks.

Machine Learning for Gully Feature Extraction Based on a Pan-Sharpened Multispectral Image: Multiclass vs. Binary Approach

Gullies reduce both the quality and quantity of productive land, posing a serious threat to sustainable agriculture, hence, food security. Machine Learning (ML) algorithms are essential tools in the identification of gullies and can assist in strategic decision-making relevant to soil conservation. Nevertheless, accurate identification of gullies is a function of the selected ML algorithms, the image and number of classes used, i.e., binary (two classes) and multiclass. We applied Linear Discriminant Analysis (LDA), Support Vector Machine (SVM), and Random Forest (RF) on a Systeme Pour l’Observation de la Terre (SPOT-7) image to extract gullies and investigated whether the multiclass (m) approach can offer better classification accuracy than the binary (b) approach. Using repeated k-fold cross-validation, we generated 36 models. Our findings revealed that, of these models, both RFb (98.70%) and SVMm (98.01%) outperformed the LDA in terms of overall accuracy (OA). However, the LDAb (99.51%) recorded the highest producer’s accuracy (PA) but had low corresponding user’s accuracy (UA) with 18.5%. The binary approach was generally better than the multiclass approach; however, on class level, the multiclass approach outperformed the binary approach in gully identification. Despite low spectral resolution, the pan-sharpened SPOT-7 product successfully identified gullies. The proposed methodology is relatively simple, but practically sound, and can be used to monitor gullies within and beyond the study region.