Monitoring Invasive Plant Species Using Hyperspectral Remote Sensing Data

Deep learning in terrestrial conservation biology

Biodiversity is being lost at an unprecedented rate on Earth. As a first step to more effectively combat this process we need efficient methods to monitor biodiversity changes. Recent technological advance can provide powerful tools (e.g. camera traps, digital acoustic recorders, satellite imagery, social media records) that can speed up the collection of biological data. Nevertheless, the processing steps of the raw data served by these tools are still painstakingly slow. A new computer technology, deep learning based artificial intelligence, might, however, help. In this short and subjective review I oversee recent technological advances used in conservation biology, highlight problems of processing their data, shortly describe deep learning technology and show case studies of its use in conservation biology. Some of the limitations of the technology are also highlighted.

Detecting the Minimum Limit on Wheat Stripe Rust in the Latent Period Using Proximal Remote Sensing Coupled with Duplex Real-Time PCR and Machine Learning

Wheat stripe rust (WSR) is an airborne disease that causes severe damage to wheat. The rapid and early detection of WSR is essential for the prevention and control of this disease. The minimum detection limit (MDL) is one of the most important characteristics of quantitative methods that can be used to determine the scope and applicability of a measurement technique. Three wheat cultivars were inoculated with Puccinia striiformis f.sp. tritici (Pst), and a spectrometer was used to collect the canopy hyperspectral data, and the Pst content was obtained via a duplex real-time polymerase chain reaction (PCR) during the latent period, respectively. The disease index (DI) and molecular disease index (MDI) were calculated. The regression tree algorithm was used to determine the MDL of the Pst based on hyperspectral feature parameters. The logistic, IBK, and random committee algorithms were used to construct the classification model based on the MDL. The results showed that when the MDL was 0.7, IBK had the best recognition accuracy. The optimal model, which used the spectral feature R_2nd.dv ((the second derivative of the original hyperspectral value)) and the modeling ratio 2:1, had an accuracy of 91.67% on the testing set and 90.67% on the 10-fold cross-validation. Thus, during the latent period, the MDL of Pst was determined using hyperspectral technology as 0.7.

From UAV to PlanetScope: Upscaling fractional cover of an invasive species Rosa rugosa

Invasive plant species pose a direct threat to biodiversity and ecosystem services. Among these, Rosa rugosa has had a severe impact on Baltic coastal ecosystems in recent decades. Accurate mapping and monitoring tools are essential to quantify the location and spatial extent of invasive plant species to support eradication programs. In this paper we combined RGB images obtained using an Unoccupied Aerial Vehicle, with multispectral PlanetScope images to map the extent of R. rugosa at seven locations along the Estonian coastline. We used RGB-based vegetation indices and 3D canopy metrics in combination with a random forest algorithm to map R. rugosa thickets, obtaining high mapping accuracies (Sensitivity = 0.92, specificity = 0.96). We then used the R. rugosa presence/absence maps as a training dataset to predict the fractional cover based on multispectral vegetation indices derived from the PlanetScope constellation and an Extreme Gradient Boosting algorithm (XGBoost). The XGBoost algorithm yielded high fractional cover prediction accuracies (RMSE = 0.11, R² = 0.70). An in-depth accuracy assessment based on site-specific validations revealed notable differences in accuracy between study sites (highest R² = 0.74, lowest R² = 0.03). We attribute these differences to the various stages of R. rugosa invasion and the density of thickets. In conclusion, the combination of RGB UAV images and multispectral PlanetScope images is a cost-effective method to map R. rugosa in highly heterogeneous coastal ecosystems. We propose this approach as a valuable tool to extend the highly local geographical scope of UAV assessments into wider areas and regional evaluations.

Detecting and distinguishing between apicultural plants using UAV multispectral imaging

Detecting and distinguishing apicultural plants are important elements of the evaluation and quantification of potential honey production worldwide. Today, remote sensing can provide accurate plant distribution maps using rapid and efficient techniques. In the present study, a five-band multispectral unmanned aerial vehicle (UAV) was used in an established beekeeping area on Lemnos Island, Greece, for the collection of high-resolution images from three areas where Thymus capitatus and Sarcopoterium spinosum are present. Orthophotos of UAV bands for each area were used in combination with vegetation indices in the Google Earth Engine (GEE) platform, to classify the area occupied by the two plant species. From the five classifiers (Random Forest, RF; Gradient Tree Boost, GTB; Classification and Regression Trees, CART; Mahalanobis Minimum Distance, MMD; Support Vector Machine, SVM) in GEE, the RF gave the highest overall accuracy with a Kappa coefficient reaching 93.6%, 98.3%, 94.7%, and coefficient of 0.90, 0.97, 0.92 respectively for each case study. The training method used in the present study detected and distinguish the two plants with great accuracy and results were confirmed using 70% of the total score to train the GEE and 30% to assess the method's accuracy. Based on this study, identification and mapping of Thymus capitatus areas is possible and could help in the promotion and protection of this valuable species which, on many Greek Islands, is the sole foraging plant of honeybees.

Escape from the garden: spreading, effects and traits of a new risky invasive ornamental plant (Gaillardia aristata Pursh)

Ornamental plants constitute a major source of invasive species.Gaillardia aristata(great blanketflower) is planted worldwide and its escape has been reported in several European countries without ecological impact assessment on the invasive potential. As there is a markedly spreading population with invasive behaviour in Hungary, we aimed to reveal the distribution, impacts and traits ofG. aristata. We gathered occurrence data outside the gardens in Hungary, based on literature, unpublished observations by experts and our own records. We investigated the impacts of an extended population, where the species invaded sandy old-fields within a 25 km2area. Here, we compared the species richness, diversity, community composition and height of invaded and uninvaded vegetation. Furthermore, we evaluated the traits potentially associated with the invasiveness ofG. aristatain comparison with other herbaceous invasive species in the region. We found thatG. aristataoccurred mostly by casual escapes, but naturalised and invasive populations were also detected in considerable numbers.G. aristatausually appeared close to gardens and ruderal habitats, but also in semi-natural and natural grasslands and tended to spread better in sandy soils. We found lower plant species richness and Shannon diversity in the invaded sites and the invasion ofG. aristatasignificantly influenced the composition of the plant community. The trait analyses revealed that the invasive potential ofG. aristatais backed by a wide germination niche breadth, extremely long flowering period, small shoot-root ratio (large absorption and gripping surface), large seeds (longer persistence) and dispersal by epizoochory of grazing livestock (mostly by sheep), probably helping the species’ survival and spreading in the disturbed, species-poor, sandy, open habitats. These functional traits, as well as the ornamental utilisation, may act together with the aridisation of the climate and the changing land-use practices (e.g. abandoned, disturbed sites) in the success ofG. aristata. We raise awareness of the rapid transition ofG. aristatafrom ornamental plant to casual alien and then to invasive species in certain environmental conditions (i.e. sandy soils, species-poor communities, human disturbances), although it seems to be not a strong ecosystem transformer so far. Nonetheless, banning it from seed mixtures, developing eradication strategy and long-term monitoring of this species would be important to halt its spreading in time.

Phenotypic variation from waterlogging in multiple perennial ryegrass varieties under climate change conditions

Identifying how various components of climate change will influence ecosystems and vegetation subsistence will be fundamental to mitigate negative effects. Climate change-induced waterlogging is understudied in comparison to temperature and CO2. Grasslands are especially vulnerable through the connection with global food security, with perennial ryegrass dominating many flood-prone pasturelands in North-western Europe. We investigated the effect of long-term waterlogging on phenotypic responses of perennial ryegrass using four common varieties (one diploid and three tetraploid) grown in atmospherically controlled growth chambers during two months of peak growth. The climate treatments compare ambient climatological conditions in North-western Europe to the RCP8.5 climate change scenario in 2050 (+2°C and 550 ppm CO2). At the end of each month multiple phenotypic plant measurements were made, the plants were harvested and then allowed to grow back. Using image analysis and principal component analysis (PCA) methodologies, we assessed how multiple predictors (phenotypic, environmental, genotypic, and temporal) influenced overall plant performance, productivity and phenotypic responses. Long-term waterlogging was found to reduce leaf-color intensity, with younger plants having purple hues indicative of anthocyanins. Plant performance and yield was lower in waterlogged plants, with tetraploid varieties coping better than the diploid one. The climate change treatment was found to reduce color intensities further. Flooding was found to reduce plant productivity via reductions in color pigments and root proliferation. These effects will have negative consequences for global food security brought on by increased frequency of extreme weather events and flooding. Our imaging analysis approach to estimate effects of waterlogging can be incorporated into plant health diagnostics tools via remote sensing and drone-technology.

Spatial distribution assessment of invasive alien species Amorpha fruticosa L. by UAV-based on remote sensing in the Special Nature Reserve Obedska Bara, Serbia

The Obedska Bara Special Nature Reserve is one of the oldest protected areas in the world, also enlisted as an Important Bird Area, Ramsar and UNESCO world heritage site. False indigo bush (Amorpha fruticosa L.) represents an invasive alien species which is significantly deteriorating the biodiversity of the Obedska Bara Special Nature Reserve in Serbia. Mapping of A. fruticosa, using an unmanned aerial vehicle and GIS tools, showed that in meadows, pastures, ponds and wetland areas, A. fruticosa covered 85 ha or 11% of the area. However, coverage was uneven, and the most overgrown areas were some meadows (up to 35%), while flooded areas and areas where human impact is significant, as on pastures, were not so affected (1-3%). The most susceptible parts were forest edges. Active management practices, such as cattle grazing and topsoil tarping, and occasional moving, gave positive effects in A. fruticosa, but also other invasive terrestrial plant species spreading control in the reserve. This has also been confirmed by the UAV survey and mapping, which has proven to be an effective method for A. fruticosa monitoring over large areas.

Squirrel Search Optimization with Deep Transfer Learning-Enabled Crop Classification Model on Hyperspectral Remote Sensing Imagery

With recent advances in remote sensing image acquisition and the increasing availability of fine spectral and spatial information, hyperspectral remote sensing images (HSI) have received considerable attention in several application areas such as agriculture, environment, forestry, and mineral mapping, etc. HSIs have become an essential method for distinguishing crop classes and accomplishing growth information monitoring for precision agriculture, depending upon the fine spectral response to the crop attributes. The recent advances in computer vision (CV) and deep learning (DL) models allow for the effective identification and classification of different crop types on HSIs. This article introduces a novel squirrel search optimization with a deep transfer learning-enabled crop classification (SSODTL-CC) model on HSIs. The proposed SSODTL-CC model intends to identify the crop type in HSIs properly. To accomplish this, the proposed SSODTL-CC model initially derives a MobileNet with an Adam optimizer for the feature extraction process. In addition, an SSO algorithm with a bidirectional long-short term memory (BiLSTM) model is employed for crop type classification. To demonstrate the better performance of the SSODTL-CC model, a wide-ranging experimental analysis is performed on two benchmark datasets, namely dataset-1 (WHU-Hi-LongKou) and dataset-2 (WHU-Hi-HanChuan). The comparative analysis pointed out the better outcomes of the SSODTL-CC model over other models with a maximum of 99.23% and 97.15% on test datasets 1 and 2, respectively.

Demystifying the Differences between Structure-from-MotionSoftware Packages for Pre-Processing Drone Data

With the increased availability of low-cost, off-the-shelf drone platforms, drone data become easy to capture and are now a key component of environmental assessments and monitoring. Once the data are collected, there are many structure-from-motion (SfM) photogrammetry software options available to pre-process the data into digital elevation models (DEMs) and orthomosaics for further environmental analysis. However, not all software packages are created equal, nor are their outputs. Here, we evaluated the workflows and output products of four desktop SfM packages (AgiSoft Metashape, Correlator3D, Pix4Dmapper, WebODM), across five input datasets representing various ecosystems. We considered the processing times, output file characteristics, colour representation of orthomosaics, geographic shift, visual artefacts, and digital surface model (DSM) elevation values. No single software package was determined the “winner” across all metrics, but we hope our results help others demystify the differences between the options, allowing users to make an informed decision about which software and parameters to select for their specific application. Our comparisons highlight some of the challenges that may arise when comparing datasets that have been processed using different parameters and different software packages, thus demonstrating a need to provide metadata associated with processing workflows.

Study on the Classification Method of Rice Leaf Blast Levels Based on Fusion Features and Adaptive-Weight Immune Particle Swarm Optimization Extreme Learning Machine Algorithm

Leaf blast is a disease of rice leaves caused by the Pyricularia oryzae. It is considered a significant disease is affecting rice yield and quality and causing economic losses to food worldwide. Early detection of rice leaf blast is essential for early intervention and limiting the spread of the disease. To quickly and non-destructively classify rice leaf blast levels for accurate leaf blast detection and timely control. This study used hyperspectral imaging technology to obtain hyperspectral image data of rice leaves. The descending dimension methods got rice leaf disease characteristics of different disease classes, and the disease characteristics obtained by screening were used as model inputs to construct a model for early detection of leaf blast disease. First, three methods, ElasticNet, principal component analysis loadings (PCA loadings), and successive projections algorithm (SPA), were used to select the wavelengths of spectral features associated with leaf blast, respectively. Next, the texture features of the images were extracted using a gray level co-occurrence matrix (GLCM), and the texture features with high correlation were screened by the Pearson correlation analysis. Finally, an adaptive-weight immune particle swarm optimization extreme learning machine (AIPSO-ELM) based disease level classification method is proposed to further improve the model classification accuracy. It was also compared and analyzed with a support vector machine (SVM) and extreme learning machine (ELM). The results show that the disease level classification model constructed using a combination of spectral characteristic wavelengths and texture features is significantly better than a single disease feature in terms of classification accuracy. Among them, the model built with ElasticNet + TFs has the highest classification accuracy, with OA and Kappa greater than 90 and 87%, respectively. Meanwhile, the AIPSO-ELM proposed in this study has higher classification accuracy for leaf blast level classification than SVM and ELM classification models. In particular, the AIPSO-ELM model constructed with ElasticNet+TFs as features obtained the best classification performance, with OA and Kappa of 97.62 and 96.82%, respectively. In summary, the combination of spectral characteristic wavelength and texture features can significantly improve disease classification accuracy. At the same time, the AIPSO-ELM classification model proposed in this study has sure accuracy and stability, which can provide a reference for rice leaf blast disease detection.

Applying a Complex Integrated Method for Mapping and Assessment of the Degraded Ecosystem Hotspots from Romania

To meet the global challenges of climate change and human activity pressure on biodiversity conservation, it has become vital to map such pressure hotspots. Large areas, such as nation-wide regions, are difficult to map from the point of view of the resources needed for such mapping (human resources, hard and soft resources). European biodiversity policies have focused on restoring degraded ecosystems by at least 10% by 2020, and new policies aim to restore up to 30% of degraded ecosystems by 2030. In this study, methods developed and applied for the assessment of the degradation state of the ecosystems in a semi-automatic manner for the entire Romanian territory (238,391 km²) are presented. The following ecosystems were analyzed: forestry, grassland, rivers, lakes, caves and coastal areas. The information and data covering all the ecoregions of the Romania (~110,000 km²) were analyzed and processed, based on GIS and remote sensing techniques. The largest degraded areas were identified within the coastal area (49.80%), grassland ecosystems (38.59%) and the cave ecosystems (2.66%), while 27.64% of rivers ecosystems were degraded, followed by 8.52% of forest ecosystems, and 14.05% of lakes ecosystems. This analysis can contribute to better definition of the locations of the most affected areas, which will yield a useful spatial representation for future ecological reconstruction strategy.

The Use of an Unmanned Aerial Vehicle for Tree Phenotyping Studies

A strip of 20th-century landscape woodland planted alongside a 17th to mid-18th century ancient and semi-natural woodland (ASNW) was investigated by applied aerial spectroscopy using an unmanned aerial vehicle (UAV) with a multispectral image camera (MSI). A simple classification approach of normalized difference spectral index (NDSI), derived using principal component analysis (PCA), enabled the identification of the non-native trees within the 20th-century boundary. The tree species within this boundary, classified by NDSI, were further segmented by the machine learning segmentation method of k-means clustering. This combined innovative approach has enabled the identification of multiple tree species in the 20th-century boundary. Phenotyping of trees at canopy level using the UAV with MSI, across 8052 m2, identified black pine (23%), Norway maple (19%), Scots pine (12%), and sycamore (19%) as well as native trees (oak and silver birch, 27%). This derived data was corroborated by field identification at ground-level, over an area of 6785 m2, that confirmed the presence of black pine (26%), Norway maple (30%), Scots pine (10%), and sycamore (14%) as well as other trees (oak and silver birch, 20%). The benefits of using a UAV, with an MSI camera, for monitoring tree boundaries next to a new housing development are demonstrated.

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.