Grassland Monitoring Research Articles

Classification of grassland conditions using a hyperspectral camera and deep learning

ABSTRACT Grassland is the most widespread vegetation type in terrestrial ecosystem, but it has been threatened by degradation in recent years. Developing an operational species detection model is necessary for achieving grassland monitoring and making management plans. Therefore, this study aims to quickly and accurately classify grassland species based on hyperspectral imaging (HSI) technology and deep learning algorithms. In the present study, 16,200 hyperspectral data are collected from grassland samples over a period of 3 years using a hyperspectral imager, with a wavelength range of 400–1000 nm. Second, the hyperspectral data are preprocessed by the multiple scatter correction and mean normalization, improving the quality of input data and thereby enhancing modelling capabilities. Finally, four models are established, including temporal convolutional neural network (TempCNN), recurrent neural network with long short-term memory (LSTM-RNN), Transformer, and support vector machines (SVM). The results show that the preprocessed data have stronger modelling ability than the original data, and the classification performance of the model is ranked in descending order as Transformer, LSTM-RNN, TempCNN, and SVM. Among them, the classification performance of Medicago sativa L. in the TempCNN is superior to other combinations. The LSTM-RNN achieved accuracy of 1 for Agropyron cristatum var. pectinatum and Leymus chinensis (Trin.) Tzvel. The accuracy of both the Transformer and SVM for Leymus chinensis (Trin.) Tzvel. and Lotus corniculatus L. is 1. The results indicate the effectiveness and robustness of the proposed hyperspectral imaging technology combined with deep learning model, which has well classification performance for specific forage varieties.

A novel remote sensing method for monitoring Large-Scale grassland aboveground Biomass: The case study of grassland key belt in the Tibetan Plateau

The harsh climate and vast terrain of the Tibetan Plateau present significant challenges for large-scale remote sensing monitoring of grasslands, particularly in regions where the variation patterns of aboveground biomass (AGB) are influenced by high spatial complexity and pronounced environmental variability, further complicating the monitoring and estimation processes. To address this pressing issue, we propose a novel concept called the “grassland key belt,” which utilizes localized studies to reflect regional dynamics. Using AGB estimation in this key belt as a case study, we analyzed the gradient changes in AGB across different elevations. To achieve this, we used a bit-depth & residual quantization method for mining radiometric information from remote sensing images and integrated multimodal features, including remote sensing, terrain, and climate data, to accurately estimate AGB and generate an AGB distribution map. The experimental results demonstrate significant estimation accuracy, with an R2 of 0.8728 and an RMSE of 17.4799 g/m2. The study reveals an increasing trend in AGB as elevation decreases, with southern regions exhibiting higher AGB due to superior hydrothermal conditions. Notably, the southeastern grasslands display the highest AGB, consistent with previous studies, thus validating the reliability of the “grassland key belt” concept. This research advances the application of remote sensing technologies for monitoring vegetation dynamics in challenging environments, providing valuable insights for sustainable ecosystem management.

A 30-m annual grassland dataset from 1991 to 2020 for Inner Mongolia, China

Grassland is a widely distributed land use type that provides essential resources for livestock production and serves as a crucial ecosystem component. Over the past decades, grassland has significantly degraded and shrunk due to climate change and human activities, with ongoing changes in its area. This study utilized the Google Earth Engine (GEE) and the Res-UNet++ model to analyze the phenological and spectral characteristics of grasslands in Landsat images for long-term annual monitoring. Additionally, the LandTrendr algorithm was utilized to correct long-term time series data for grasslands, yielding a map of grassland distribution in Inner Mongolia from 1991 to 2020. The results indicate that the overall spatial accuracy from 1991 to 2020 exceeded 96%, with a Kappa coefficient over 0.92, demonstrating high monitoring accuracy. In particular, the 2019 grassland monitoring area showed high consistency with data from the Third National Land Survey (TNLS), with a coefficient of determination (R^2) reaching 0.97, reflecting the high accuracy and reliability.

Classification of major species in the sericite-Artemisia desert grassland using hyperspectral images and spectral feature identification.

The species composition of and changes in grassland communities are important indices for inferring the number, quality and community succession of grasslands, and accurate monitoring is the foundation for evaluating, protecting, and utilizing grassland resources. Remote sensing technology provides a reliable and powerful approach for measuring regional terrain information, and the identification of grassland species by remote sensing will improve the quality and effectiveness of grassland monitoring. Ground hyperspectral images of a sericite-Artemisia desert grassland in different seasons were obtained with a Soc710 VP imaging spectrometer. First-order differential processing was used to calculate the characteristic parameters. Analysis of variance was used to extract the main species, namely, Seriphidium transiliense (Poljak), Ceratocarpus arenarius L., Petrosimonia sibirica (Pall), bare land and the spectral characteristic parameters and vegetation indices in different seasons. On this basis, Fisher discriminant analysis was used to divide the samples into a training set and a test set at a ratio of 7:3. The spectral characteristic parameters and vegetation indices were used to identify the three main plants and bare land. The selection of parameters with significant differences (P < 0.05) between the recognition objects effectively distinguished different land features, and the identification parameters also differed due to differences in growth period and species. The overall accuracy of the recognition model established by the vegetation index decreased in the following order: June (98.87%) > September (91.53%) > April (90.37%). The overall accuracy of the recognition model established by the feature parameters decreased in the following order: September (89.77%) > June (88.48%) > April (85.98%). The recognition models based on vegetation indices in different months are superior to those based on feature parameters, with overall accuracies ranging from 1.76% to 9.40% higher. Based on hyperspectral image data, the use of vegetation indices as identification parameters can enable the identification of the main plants in sericite-Artemisia desert grassland, providing a basis for further quantitative classification of the species in community images.

Convolutional transformer attention network with few-shot learning for grassland degradation monitoring using UAV hyperspectral imagery

ABSTRACT In recent years, the desertification of grasslands has increased due to various factors, including both global warming and human activities. It is an essential basis for grassland degradation monitoring to monitor the dynamic change of desert grassland vegetation communities and distribution statistics. Although unmanned aerial vehicle (UAV) remote sensing images have allowed us to achieve dynamic real-time grassland monitoring, the distribution of desert grassland ground objects can be random and narrow, thus increasing the difficulty of sample labelling of remote sensing imagery. Therefore, to reduce the number of samples required for the model, this research proposes a convolutional transformer attention network (CTAN) to identify desert grassland ground objects and validate it on a self-collected desert grassland dataset. The network utilizes the transformer model to enhance its learning of global pixels so that it suppresses the transmission of background pixels within the network. Furthermore, the edge convolution module is designed to strengthen the network’s learning for edge pixels, improving its identification effect. The results show that the network provides 97.22% of overall accuracy (OA), 94.35% of average accuracy (AA), and 0.9398 of Kappa for ground object recognition in desert grassland. The model improves OA by 2.36–9.85% points compared to methods in the same field and 0.8–6.35% points compared to methods in hyperspectral imagery classification. The experimental results show the superior performance of the CTAN model for recognizing desert grassland objects, which helps the management and restoration of desert grasslands.

Multidecadal grassland fractional cover time series retrieval for Germany from the Landsat and Sentinel-2 archives

Time series data provided by the Sentinel-2 and Landsat satellite missions offer manifold opportunities for grassland monitoring. The high intra-annual observation density of Sentinel-2 combined with the continuous long-term data record of Landsat enable analyses at seasonal, annual, and decadal scales. Fractional cover estimates of photosynthetic vegetation (PV), non-photosynthetic vegetation (NPV), and soil provide essential information to describe grassland conditions and processes. Yet, retrieving consistent grassland fractional cover time series from Landsat and Sentinel-2 imagery represents a major challenge. In this study, we implemented a multisensor spectral unmixing approach for retrieving multidecadal (i.e., 1984 to 2021) fractional cover time series of PV, NPV, and soil for Germany's permanent grasslands from the Landsat and Sentinel-2 archives. The spectral consistency of Landsat 5/7/8 and Sentinel-2A/B imagery as well as the coherency of a Sentinel-2-based spectral library to be used across Landsat and Sentinel-2 sensors served as the foundation for implementing the unmixing approach. We then employed regression-based unmixing using synthetic training data from spectral libraries for developing spatially and temporally generalized models. Applying these models to the Landsat and Sentinel-2 data facilitated multidecadal fractional cover mapping at a national-scale. We evaluated the quality of our multidecadal grassland fractional cover time series using statistical validation and linear correspondence analysis. The statistical validation was based on a multitemporal reference dataset spanning 2017 to 2021, derived from very high-resolution (VHR) imagery. Landsat 7/8- and Sentinel-2A/B-derived fractions showed similar Mean Absolute Errors (MAEs), i.e., 0.067 and 0.08 for PV, 0.149 and 0.15 for NPV, and 0.135 and 0.129 for soil. Linear correspondence analysis confirmed consistent PV and NPV fractional cover estimates among Landsat and Sentinel-2 sensors, suggesting similar errors beyond the statistical validation period. However, higher errors and weaker linear correspondence pointed to remaining uncertainties in soil fractional cover estimates. We further showed that the differences in spatial and spectral resolutions, i.e., the pixel size and the number of spectral bands, between Landsat and Sentinel-2 had a minor effect and were well mitigated by the spectral unmixing approach. We finally illustrated the value of the dense time series available for more recent years for describing seasonal trajectories of grassland conditions and land use intensities, as well as the use of the entire time series for analyzing long-term grassland dynamics based on annual fraction anomalies. Our study emphasizes the efficacy of generalized multisensor spectral unmixing approaches for retrieving consistent PV, NPV, and soil cover fractions across space, time, and sensors, providing a valuable means for grassland monitoring.

Using Remote Sensing Vegetation Indices for the Discrimination and Monitoring of Agricultural Crops: A Critical Review

The agricultural sector is currently confronting multifaceted challenges such as an increased food demand, slow adoption of sustainable farming, a need for climate-resilient food systems, resource inequity, and the protection of small-scale farmers’ practices. These issues are integral to food security and environmental health. Remote sensing technologies can assist precision agriculture in effectively addressing these complex problems by providing farmers with high-resolution lenses. The use of vegetation indices (VIs) is an essential component of remote sensing, which combines the variability of spectral reflectance value (derived from remote sensing data) with the growth stage of crops. A wide array of VIs can be used to classify the crops and evaluate their state and health. However, precisely this high number leads to difficulty in selecting the best VI and their combination for specific objectives. Without thorough documentation and analysis of appropriate VIs, users might find it difficult to use remote sensing data or obtain results with very low accuracy. Thus, the objective of this review is to conduct a critical analysis of the existing state of the art on the effective use of VIs for the discrimination and monitoring of several important agricultural crops (wheat, corn, sunflower, soybean, rape, potatoes, and forage crops), grasslands and meadows. This data could be highly useful for all the stakeholders involved in agricultural activities. The current review has shown that VIs appear to be suitable for mapping and monitoring agricultural crops, forage crops, meadows and pastures. Sentinel-1 and Sentinel-2 data were the most utilized sources, while some of the frequently used VIs were EVI, LAI, NDVI, GNDVI, PSRI, and SAVI. In most of the studies, an array of VIs needed to be employed to achieve a good discrimination of crops or prediction of yields. The main challenges in using VIs are related to the variation of the spectral characteristics during the vegetation period and to the similarities of the spectral signatures of various crops and semi-natural meadows. Thus, further studies are needed to establish appropriate models for the use of satellite data that would prove to have greater accuracy and provide more relevant information for the efficient monitoring of agricultural crops.

Grassland Monitoring Based on Geobotanical, Ground, Spectrometric, and Satellite Data

Grassland Monitoring Based on Geobotanical, Ground, Spectrometric, and Satellite Data

A wireless triboelectric sensing system with polygonal synchronous driven by bipolar electromagnetic generators for wide wind speed monitoring

The change of wind speed has an important impact on the ecological balance in the wind-eroded grassland. Using the wind speed monitoring technology can promote the sustainable management of grasslands, but commercial wind speed sensors pose certain challenges to energy consumption. Here, a self-powered wide wind speed sensor (SWSS) is proposed, consisting of polygonal cam synchronous driven triboelectric nanogenerator and stereoscopic electromagnetic nanogenerator. The circumferential array cam drive mechanism and the double-optimized silicone film realize the synergistic enhancement effect of force-electric coupling, which makes the synchronous sensing unit output wind speed signals with high sensitivity and up to 0.991 linearity. In addition, at 8 m/s wind speed, the transducer unit with the three-dimensional magnetic field enhanced layout and the energy capture unit with the semi-cylindrical blade designed for installation angle jointly achieved a power output of 69.35 mW, and the energy conversion efficiency reached 6.91 %. Owing to the intermittency of wind energy, the energy closed loop is realized through solar-assisted energy supply and energy management technology. In short, the design, optimization and integration of SWSS provide an innovative strategy for wide wind speed monitoring and sustainable management of wind-eroded grassland.

2 Satellite-Based Decision Support Tools to Assist Grazing Cattle Production

Abstract Grasslands cover approximately 40.5% of the surface of the earth and 80% of agriculturally productive land. After forests, grasslands are the primary carbon sink source and the most used feed source for livestock production. Regularly monitoring grasslands assures efficient management and sustainability of pasture-based production systems. Conventional ground-based methods to monitor grassland production and management rely on field measurements, which are time-consuming and usually restricted to small-scale assessment. Using satellite information allows for large-scale monitoring of grasslands and capturing the spatial variability of the land surface with high temporal resolution. Various methods for grassland monitoring based on satellite data can be applied, such as classifications, correlations/regression analyses, and time series analyses. Depending on the purpose of the application, these methods are sometimes combined to derive grassland management and production information. The ability of satellite-based data to quantify vegetation characteristics depends on the type of sensor and instrumentation features, such as spectral, radiometric, spatial, and temporal resolution, polarization, and angularity. The models to estimate grassland biomass based on remote sensing have been chiefly focused on optical systems. The spectral reflectance of raw bands and vegetation indices were used as proxies to investigate spatial and temporal patterns of grassland production. Optical (multispectral or hyperspectral) sensors are passive and require sunlight, so they depend highly on the weather (cloud) and light conditions. Thus, there has been increasing interest in active sensors, such as Synthetic Aperture Radar (SAR) and Light Detection and Ranging (LIDAR) sensors, which are not constrained due to clouds but are more complex. Using satellite data in combination with field measurements has commonly yielded regression models (e.g., linear, power, logarithmic, multiple linear) for estimating grassland biomass or biophysical characteristics (e.g., chlorophyll, leaf area index) of different types of grasslands. The exponential evolution of digital computers has pushed forward machine learning-based regression methods to estimate biomass. Random forest, support vector machines, and artificial neural networks are the most used algorithms. The possibility of accurate mapping and monitoring of biomass and nutritional attributes of grasslands based on satellite provides essential insights into the decision support system for pasture management. A better understanding of the nitrogen status of pastures, forage biomass, and its nutritive value is instrumental in livestock and forage management. Timely prediction of these variables can help improve decision-making by grazing land managers on, for instance, the adjustment of stocking rate or adequate supplementation to match the needs of animals toward more sustainable production. Future use of satellite-based grazing models in tandem with ruminant nutrition models will enable to development of decision-support tools to assist with many aspects of livestock production in diverse environmental conditions and accounting for temporal variability. (FAPESP #2020/14367-7)

Remote Sensing Classification of Temperate Grassland in Eurasia Based on Normalized Difference Vegetation Index (NDVI) Time-Series Data

The Eurasian temperate grassland is the largest temperate grassland ecosystem and vegetation transition zone globally. The spatiotemporal distribution and changes of grassland types are vital for grassland monitoring and management. However, there is currently a lack of a unified classification method and standard distribution map of Eurasian temperate grassland types. The Normalized Difference Vegetation Index (NDVI) from remote sensing data is commonly used in grassland monitoring. In this paper, the Accumulated Rate of NDVI Change Index (ARNCI) was proposed to characterize the annual NDVI trend of different temperate grassland types, and four transitional categories were introduced to account for the overlap between them. Based on survey data on the distribution of Eurasian temperate grassland types in the 1980s, the study area was divided into three sub-regions: Northern China, Central Asia, and Mongolia. Regionally, pixel-based ARNCI maps in the 1980s and 1990s were successfully calculated from using NOAA’s AVHRR NDVI time-series products. The ARNCI classification thresholds for different sub-regions were determined, and classification experiments and validation were conducted for each sub-region. The overall accuracies of grasslands types classification for Northern China, Central Asia, and Mongolia in the 1980s were 75.3%, 64.2%, and 84.6%, respectively, which demonstrated that there were variations in classification accuracy in the three sub-regions, and the overall performance was favorable. Finally, distribution maps of Eurasian temperate grassland types in the 1980s and 1990s were obtained, and the spatiotemporal changes of grassland types were analyzed and discussed. The ARNCI method is simple to operate and easy to obtain data, and it can be conveniently used in grassland type classification. The maps firstly address the lack of remote sensing classification maps of Eurasian temperate grassland types, and provide a promising tool for monitoring grassland degradation, management, and utilization.

Integrated vegetation cover of typical steppe in China based on mixed decomposing derived from high resolution remote sensing data

Grasslands represent the largest ecosystem in China, accurate and efficient extraction of its integrated vegetation cover (IVC) plays a crucial role in supporting policy decisions. This study presented a method for grassland monitoring via IVC derived from high-resolution satellite data. Taking the multispectral data of Gaofen-1 (GF-1) and Gaofen-6 (GF-6) with 16 m resolution as the main data source, vegetation cover of six representative regions was assessed based on mixed-pixel decomposition model. Using grassland vegetation cover and ratio of grassland area, the IVC in each site was calculated and verified against ground-measured sample data. The results showed that the IVC of grassland was closely related to vegetation habitat driven by regional hydrothermal regime. Yichang grassland, dominated with warm-temperate shrub tussock type, had the highest IVC (80.06 %) due to its favorable hydrothermal conditions. For the main grassland types in Hulunbuir and Gansu Province (temperate meadow steppe and temperate typical steppe), the IVC was 79.38 % and 58.46 %, respectively. In both Xilin-Gol and Nagqu, vegetation cover decreased gradually from east to west, and the IVC was merely 42.83 % and 42.61 %, respectively. Both regions are endowed with less hydrothermal resources to different degrees. Alxa, with a predominately temperate desert landscape, had the lowest IVC of 15.58 % where precipitation is extremely scarce. Based on the grass species of measured samples, the dominant species and biodiversity of different grassland types in Gansu Province and Hulunbuir Municipality of Inner Mongolia Autonomous Region were analyzed. The results showed that the meadow grassland has the richest biodiversity. The temperate mountain meadows in Gansu Province have a high species diversity, with a total of 90 grass species, and the lowland meadows in Hulunbuir have a total of 49 grass species. This study utilizes high-resolution data to conduct large-scale vegetation monitoring, which is a viable alternative for efficient assessment of steppe ecology.

基于注意力网络的无人机高光谱草原鼠洞的识别研究

Rat-hole area and number of rat holes are indicators of the level of degradation and rat damage in grassland environments. However, rat-hole monitoring has consistently relied on manual ground surveys, leading to extremely low efficiency and accuracy. In this paper, a convolutional block attention module (CBAM) model suitable for rat-hole recognition in desert grassland monitoring, called grassland monitoring-CBAM, is proposed that comprehensively incorporates unmanned aerial vehicle hyperspectral remote-sensing technology and deep-learning methods. Validation results show that the overall accuracy and Kappa coefficient of the model were 99.35% and 98.90%, which were 3.96% and 3.35% higher, respectively, than those of the basic model. This study represents a breakthrough in the intelligent interpretation of rat holes and provides technical support for the subsequent rapid interpretation of grassland rat holes and rat damage evaluation. It also provides a solution for the fine classification and quantitative inversion of similar landscape features.

Multi-Temporal Hyperspectral Classification of Grassland Using Transformer Network.

In recent years, grassland monitoring has shifted from traditional field surveys to remote-sensing-based methods, but the desired level of accuracy has not yet been obtained. Multi-temporal hyperspectral data contain valuable information about species and growth season differences, making it a promising tool for grassland classification. Transformer networks can directly extract long-sequence features, which is superior to other commonly used analysis methods. This study aims to explore the transformer network's potential in the field of multi-temporal hyperspectral data by fine-tuning it and introducing it into high-powered grassland detection tasks. Subsequently, the multi-temporal hyperspectral classification of grassland samples using the transformer network (MHCgT) is proposed. To begin, a total of 16,800 multi-temporal hyperspectral data were collected from grassland samples at different growth stages over several years using a hyperspectral imager in the wavelength range of 400-1000 nm. Second, the MHCgT network was established, with a hierarchical architecture, which generates a multi-resolution representation that is beneficial for grass hyperspectral time series' classification. The MHCgT employs a multi-head self-attention mechanism to extract features, avoiding information loss. Finally, an ablation study of MHCgT and comparative experiments with state-of-the-art methods were conducted. The results showed that the proposed framework achieved a high accuracy rate of 98.51% in identifying grassland multi-temporal hyperspectral which outperformed CNN, LSTM-RNN, SVM, RF, and DT by 6.42-26.23%. Moreover, the average classification accuracy of each species was above 95%, and the August mature period was easier to identify than the June growth stage. Overall, the proposed MHCgT framework shows great potential for precisely identifying multi-temporal hyperspectral species and has significant applications in sustainable grassland management and species diversity assessment.

Robotic monitoring of grasslands: a dataset from the EU Natura2000 habitat 6210* in the central Apennines (Italy)

Despite the remarkable growth of the global market for robotics, robotic monitoring of habitats is still an understudied topic. This is true, among others, for the species-rich EU Annex I habitat “6210 - Semi-natural grasslands and scrubland facies on calcareous substrates”. This habitat is typically surveyed by human operators. In this work, we present a dataset concerning relevés performed through the quadrupedal robot ANYmal C. The dataset contains information from three plots, which include the robot state, videos, and images acquired to assess the habitat conservation status. Additionally, a collection of videos and pictures about two typical and one early warning species of habitat 6210 is also presented. This database is publicly available in the provided Zenodo repository and will aid researchers in several fields. Robot state information can be used by engineers to validate their algorithms, while data gathered by the robot can be used to design new methodologies and new metrics to assess the habitat conservation status or train/test classifiers (e.g. neural networks) for plant classification.

Beyond "greening" and "browning": Trends in grassland ground cover fractions across Eurasia that account for spatial and temporal autocorrelation.

Grassland ecosystems cover up to 40% of the global land area and provide many ecosystem services directly supporting the livelihoods of over 1 billion people. Monitoring long-term changes in grasslands is crucial for food security, biodiversity conservation, achieving Land Degradation Neutrality goals, and modeling the global carbon budget. Although long-term grassland monitoring using remote sensing is extensive, it is typically based on a single vegetation index and does not account for temporal and spatial autocorrelation, which means that some trends are falsely identified while others are missed. Our goal was to analyze trends in grasslands in Eurasia, the largest continuous grassland ecosystems on Earth. To do so, we calculated Cumulative Endmember Fractions (annual sums of monthly ground cover fractions) derived from MODIS 2002-2020 time series, and applied a new statistical approach PARTS that explicitly accounts for temporal and spatial autocorrelation in trends. We examined trends in green vegetation, non-photosynthetic vegetation, and soil ground cover fractions considering their independent change trajectories and relations among fractions over time. We derived temporally uncorrelated pixel-based trend maps and statistically tested whether observed trends could be explained by elevation, land cover, SPEI3, climate, country, and their combinations, all while accounting for spatial autocorrelation. We found no statistical evidence for a decrease in vegetation cover in grasslands in Eurasia. Instead, there was a significant map-level increase in non-photosynthetic vegetation across the region and local increases in green vegetation with a concomitant decrease in soil fraction. Independent environmental variables affected trends significantly, but effects varied by region. Overall, our analyses show in a statistically robust manner that Eurasian grasslands have changed considerably over the past two decades. Our approach enhances remote sensing-based monitoring of trends in grasslands so that underlying processes can be discerned.

Remote sensing as a tool of biological conservation and grassland monitoring in mountain areas of Southeastern Kazakhstan

Grassland degradation, as a worldwide phenomenon, has economic and bio-conservation aspects. Degradation of mountain grasslands severely impacts the stability of ecosystems in fragile mountain environments and may destroy the habitats of many endemic and endangered species. One of the significant triggers of mountain grassland degradation, along with the possible consequences of climate change, is massive overgrazing. Overgrazing may seriously influence the ecosystem since it results in plant composition changes, soil erosion, water regime disturbances, etc., up to the disappearance of the entire ecosystem. It is crucial to have a reliable and cost-effective instrument for the ecosystem assessment of remote and hardly accessible mountain areas supported by accurate methods of vegetation parameter estimation since the vegetation cover is first to react to externally driven disturbances. The current study was conducted in the Dzungarian Alatau Mountains, inhabited by the rare and endemic anuran amphibian Ranodon sibiricus (Kessler, 1886). The project of the Conservation International Foundation (CIF/326/21) was aimed at the strategy of species conservation. The current study emphasises estimating the overgrazing risks for the amphibian population. More than two hundred ground measurements were done within the Upper Koksu Forestry and adjacent areas to provide representative data on the vegetation parameters. We tested a series of spectral indices related to vegetation biophysical parameters. We found the DWSI, GrNDVI, IRECI and NDI45 indices to provide the best correlations and reasonable accuracy for remote measurements of above-ground biomass, grass cover, and unpalatable grass content. Sentinel-2 data with the red-edge bands, in most cases, provided better performance. Our study confirmed that the use of a single criterion (like above-ground biomass) might result in a serious underestimation of grassland degradation. Data obtained from field surveys and satellite information analysis allowed the evaluation of the optimal grazing load for the Upper Koksu Forestry and provided recommendations for the Action Plan on the Conservation of Ranodon sibiricus.

Grassland cover declined in Southern Africa but increased in other African subcontinents in early twenty-first century

The African continent has the most extensive grassland cover in the world, providing valuable ecosystem services. African grasslands, like other continental grasslands, are prone to various anthropogenic disturbances and climate, and require data-driven monitoring for efficient functioning and service delivery. Yet, knowledge of how the African grassland cover has changed in the past years is lacking, especially at the subcontinent level, due to lack of relevant long-term, Africa-wide observations and experiments. In this study, we used Moderate Resolution Imaging Spectroradiometer (MODIS) Land Cover Type (MCD12Q1) data spanning 2001 to 2017 to conduct land use land cover (LULC) change analyses and map grassland distribution in Africa. Specifically, we assessed the changes in grassland cover across and within African subcontinents over three periods (2001-2013, 2013-2017, and 2001-2017). We found that the African grassland cover was 16,777,765.5 km2, 16,999,468.25 km2, and 16,968,304.25 km2 in 2001, 2013, and 2017, respectively. There were net gain (1.32%) and net loss (- 0.19%) during 2001-2013 and 2013-2017 periods, respectively, and the annual rate of change during these periods were 0.11% and - 0.05%, respectively. Generally, the African grassland cover increased by 1.14% (0.07% per annum) over the entire study period (2001-2017) at the expense of forestland, cropland, and built-up areas. The East and West African grassland cover reduced by 0.07% (- 0.02% per annum) and 1.35% (- 0.34% per annum), respectively from 2013 to 2017 but increased in other periods. On the other hand, the grassland cover in North and Central Africa increased throughout the three periods while that of Southern Africa decreased over the three periods. Overall, the net gains in the grassland cover of other African subcontinents offset the loss in Southern Africa and promoted the overall gain across Africa. This study underscores the need for continuous monitoring of African grasslands and the causes of their changes for efficient delivery of ecosystem services.

Remote sensing as a tool of biological conservation and grassland monitoring in mountain areas of Southeastern Kazakhstan

Grassland degradation, as a worldwide phenomenon, has economic and bio-conservation aspects. Degradation of mountain grasslands severely impacts the ecosystem stability in fragile mountain environments and may destroy habitats of many endemic and endangered species. One of the significant triggers of mountain grassland degradation, along with possible consequences of climate change, is massive overgrazing. Overgrazing may seriously influence the ecosystem since it results in plant composition changes, soil erosion, water regime disturbances, etc., up to the disappearance of the entire ecosystem. It is crucial to have a reliable and cost-effective instrument for the ecosystem assessment of remote and hardly accessible mountain areas supported with accurate methods of the vegetation parameters estimation since the vegetation cover is first to react to externally driven disturbances. The current study was conducted in Dzungarian Alatau Mountains, inhabited by the rare and endemic anuran amphibian Ranodon sibiricus, Kessler, 1886. The project of the Conservation International Foundation (CIF/326/21) was aimed at the strategy of this species conservation. The current study emphasises estimating the overgrazing risks for the amphibian population. More than two hundred ground measurements were done within the Upper Koksu Forestry and adjacent areas to provide representative data on the vegetation parameters. We tested a series of spectral indices related to vegetation biophysical parameters. We found DWSI, GrNDVI, IRECI and NDI45 indices to provide the best correlations and reasonable accuracy for remote measurements of above-ground biomass, grasscover and unpalatable grass content. Sentinel-2 data with the red-edge bands, in most cases, provided better performance. Our study confirmed the use of a single criterion (like above-ground biomass) might result in a serious underestimation of grassland degradation. Data obtained from field survey and satellite information analysis allowed the evaluation of the optimal grazing load for the Upper Koksu Forestry and provided recommendations for the Action Plan on the conservation of Ranodon sibiricus.

Identification and Classification of Small Sample Desert Grassland Vegetation Communities Based on Dynamic Graph Convolution and UAV Hyperspectral Imagery.

Desert steppes are the last barrier to protecting the steppe ecosystem. However, existing grassland monitoring methods still mainly use traditional monitoring methods, which have certain limitations in the monitoring process. Additionally, the existing deep learning classification models of desert and grassland still use traditional convolutional neural networks for classification, which cannot adapt to the classification task of irregular ground objects, which limits the classification performance of the model. To address the above problems, this paper uses a UAV hyperspectral remote sensing platform for data acquisition and proposes a spatial neighborhood dynamic graph convolution network (SN_DGCN) for degraded grassland vegetation community classification. The results show that the proposed classification model had the highest classification accuracy compared to the seven classification models of MLP, 1DCNN, 2DCNN, 3DCNN, Resnet18, Densenet121, and SN_GCN; its OA, AA, and kappa were 97.13%, 96.50%, and 96.05% in the case of only 10 samples per class of features, respectively; The classification performance was stable under different numbers of training samples, had better generalization ability in the classification task of small samples, and was more effective for the classification task of irregular features. Meanwhile, the latest desert grassland classification models were also compared, which fully demonstrated the superior classification performance of the proposed model in this paper. The proposed model provides a new method for the classification of vegetation communities in desert grasslands, which is helpful for the management and restoration of desert steppes.