Vegetation Index NDVI Research Articles

Estimating Switchgrass Biomass Yield and Lignocellulose Composition from UAV-Based Indices

Innovative methods for estimating commercial-scale switchgrass yields and feedstock quality are essential to optimize harvest logistics and biorefinery efficiency for sustainable aviation fuel production. This study utilized vegetation indices (VIs) derived from multispectral images to predict biomass yield and lignocellulose concentrations of advanced bioenergy-type switchgrass cultivars (“Liberty” and “Independence”) under two N rates (28 and 56 kg N ha−1). Field-scale plots were arranged in a randomized complete block design (RCBD) and replicated three times at Urbana, IL. Multispectral images captured during the 2021–2023 growing seasons were used to extract VIs. The results show that linear and exponential models outperformed partial least square and random forest models, with mid-August imagery providing the best predictions for biomass, cellulose, and hemicellulose. The green normalized difference vegetation index (GNDVI) was the best univariate predictor for biomass yield (R2 = 0.86), while a multivariate combination of the GNDVI and normalized difference red-edge index (NDRE) enhanced prediction accuracy (R2 = 0.88). Cellulose was best predicted using the NDRE (R2 = 0.53), whereas hemicellulose prediction was most effective with a multivariate model combining the GNDVI, NDRE, NDVI, and green ratio vegetation index (GRVI) (R2 = 0.44). These findings demonstrate the potential of UAV-based VIs for the in-season estimation of biomass yield and cellulose concentration.

Assessment of the Current Soil-ecological Condition of the Reclamation Sites in the Mountain Taiga Subzone of Kuzbass

The soil-ecological condition of the sites after reclamation was analyzed and an attempt was made to demonstrate that it is possible to use NDVI vegetation index values as an additional tool for its assessment. It was found that in the areas where organ-accumulative embryozems dominate in the soil cover structure (more than 85 %) their soil-ecological condition is characterized as satisfactory (from 22 to 29 %). It was revealed that NDVI vegetation index for the reclamation sites (average value from three images for 2024) above 0.3 indicates the soil-ecological condition after reclamation of disturbed lands as satisfactory. It is concluded that the application of NDVI index as an indicator of soil-ecological condition of reclamation sites is possible, but for more accurate information it is necessary to create a database of long-term studies based on instrumental methods in the field.

АНАЛИЗ ПРАКТИЧЕСКИХ ВОЗМОЖНОСТЕЙ ПРИМЕНЕНИЯ БЕСПИЛОТНЫХ ЛЕТАТЕЛЬНЫХ АППАРАТОВ В СЕЛЬСКОМ ХОЗЯЙСТВЕ

The purpose of the study is to analyze the practical possibilities of using unmanned aerial vehicles in agriculture. The review carried out in this paper contains useful information for understanding the essence and possibilities of using unmanned aerial vehicles in solving agricultural problems. The areas of application of unmanned aerial vehicles for monitoring waterlogging or drought, detecting diseases of agricultural crops, mapping soil properties, the degree of ripening, crop yields, etc. are shown. Technological aspects are considered, which include technical characteristics, spatial and temporal resolution for the measurement devices used, as well as atmospheric conditions. . The main types of unmanned aerial vehicles are identified, their characteristics are given, advantages and disadvantages are shown, the potential is revealed in terms of a gradual increase in the number of functions. In practice, three types of UAV platforms are used. Fixed-wing UAVs have an airfoil that creates the lift needed to lift off the ground, fly through the air, and reach a certain speed. Helicopters have a set of horizontally rotating blades attached to a central mast to create lift and push the craft in different directions. Multicopters are rotorcraft with multiple sets of horizontally rotating blades (4-8) capable of providing lift and control of the craft. The necessary hardware elements for solving agricultural problems are described. A comparison of the main types of digital cameras that are used in monitoring fields with plants is carried out. The main system for monitoring crops using unmanned aerial vehicles is described. The conversion of the measured data into the type of information (NDVI vegetation index) was used, which shows the characteristics of the state of plants in the controlled agricultural area. UAV imaging is still costly and there are problems with satellite imagery due to cloudiness. Progress in the development of devices is associated with a reduction in weight, an increase in payload, an increase in stability and controllability during flight.

NDVI of crops as a remote indicator of arable soils quality

The quality of arable soils largely determines the productivity of agricultural crops and the economic efficiency of their cultivation. The purpose of this work is to analyze the relationship between intra-field heterogeneity of crops and vertical heterogeneity of soil skeletality based on a test corn field in Kabardino-Balkaria. The NDVI vegetation index, calculated from Sentinel-2 satellite imagery, was used as an indicator of crop condition. Soil skeletality was determined by dry sieving. It has been established that the value of the NDVI index of crops on a test field can serve as the basis for indirect detection of vertical heterogeneity of agronomically important soil properties. To obtain reliable information, accurate timing of obtaining NDVI values and the crop cultivated in the field is necessary. The indicator reliability of different crops is determined by their phenology and the thickness of the potential root layer. The geography of agronomically important soil properties on the test field does not correlate with the areas of the traditionally compiled soil map. Spatial variation in corn yield on the test field (range 23%) correlates with variation in the soil skeletal profile. To use NDVI values as an indicator of spatial variation in agronomically important soil properties, it is necessary to take into account the type of crop cultivated, careful selection of the date for obtaining NDVI, as well as the availability of a priori expert knowledge about the limiting soil factors in the field, the specific phenology and agrotechnology of crop cultivation.

Spatial Phenology and Rice Productivity Estimation Based on Vegetation Indices in Wargasetra Village Using Planet Fusion Satellite Imagery

Rice is a primary food commodity globally, particularly in Indonesia, where West Java Province produces more than half of the country’s yield. While traditional methods continue to be used, remote sensing technology now provides fast and cost-effective insights into rice production. Planet Fusion satellite imagery is used in this research and offers cloud-free multispectral imagery with a 3-meter spatial resolution for an entire year. This research examined the rice crops in Wargasetra Village using three vegetation indices—NDVI, GNDVI, and EVI—to determine rice crops’ phenology and estimate the rice productivity using the Ordinary Least Square (OLS) equation. Rice crops are cultivated biannually in Wargasetra Village. GNDVI was suited for mapping the age distribution of rice crops (with an average r 2 of 0.892), while NDVI was most suitable for productivity estimation (with an r 2 of 0.678). The results showed that around 90% of Wargasetra’s paddy fields have high productivity (5.30–5.95 tons/ha). This highlights the potential of remote sensing technology in enhancing rice crop analysis and making informed agricultural decisions.

Prediction of Oil Palm Plantation Block Productivity Based On Canopy Area And Vegetation Index Using Multispectral Aerial Photographs

The demands of productivity and efficiency of oil palm plantations can be met by implementing Precision Farming (PF), where production analysis is carried out on a narrower area. Currently, yield evaluation or harvest results are carried out based on block area (25-100 Ha). The diverse information in one block is standardized, potentially eliminating detailed information that is useful for management. This study aims to develop an empirical estimation model of oil palm plantation productivity per harvest day through the canopy area approach and oil palm vegetation index with multispectral camera technology. The oil palm productivity estimation method is carried out by comparing the processing results using the Normalized Difference Vegetation Index and Atmospherically Resistant Vegetation Index transformation algorithms. The basis for estimation is per Harvesting Collection Point, namely an area of ± 0.3 ha. The results showed: 1) NDVI, NDRE are strongly and very strongly correlated with FFB production; 2) canopy area has a strong relationship to FFB production; 3) NDVI vegetation index values are strongly correlated with FFB production. The productivity estimation equation from NDRE value: y = 3621.9x – 1153.8, the productivity estimation equation based on canopy area: y = 0.5479x – 717.08, and the productivity estimation equation based on NDVI: y = 11.639x – 9709.2

Robust vegetation detection using RGB colour composites and isoclust classification of the Landsat TM image

The paper presents the application of ArcGIS for environmental modelling of the landscapes in northern Iceland (17.00°W–23.00°W, 64.30°N–67.00°N). The aim was to explore the vegetation distribution by NDVI and ISOCLUST classification of the land cover types. Data include the Landsat TM image. Freely available satellite remote sensing data from the Landsat mission have been processed by GIS to deliver information on land cover types from image classification and NDVI vegetation index. Landsat products provide geospatial data on regional scale with moderate temporal (weekly) and spatial (30–10 m) resolution, making them useful for environmental monitoring and landscape studies. The tools include the ArcGIS software used for raster processing. Data processing was performed in the three steps: 1) comparative analysis of the visualized sixteen band combinations to assess the distinguishability of vegetation and other land cover types in colour composites; 2) computed NDVI standardized vegetation index; 3) unsupervised classification of the Landsat TM by the ISOCLUST algorithm. Large glaciers Hofsjökull and Langjökull were detected on various colour composites, and the visibility of the water/land borders is assessed (Blöndulón lake), agricultural areas near the Varmahlíð, vegetated areas around the Akrahreppur municipality. Computing the NDVI and using ISOCLUST by ArcGIS software enabled to distinguish various land cover types and map landscapes in the study area. The computed NDVI shown the presence and condition of vegetation, that is, a relative biomass in the area of northern Iceland. The NDVI was used based on the contrast of the two channels from a multispectral Landsat TM raster data.

Integration of geoelectric methods and remote sensing in assessing the environment state in the area of impact of ecologically hazardous objects

Relevance. The need for comprehensive assessment of environmental components in the zones of ecologically hazardous industrial facilities impact, which enables to operatively identify the spatial structure of technogenic pollution. Aim. Chemical pollution assessment of the geological environment in the zones of industrial objects impact, based on the combined use of remote sensing and ground-based geoelectric methods. Objects. Sources of pollution during the production of mineral fertilizers (phosphogypsum dumps, sulfur storage). Methods. The author has developed a complex of methods, consisting of multispectral space imaging (Sentinel-2 satellite images) and ground-based geoelectric researches: water surface resistivity measurements, natural electric field potential imaging, vertical electrical sounding. According to satellite image data (vegetation indices NDVI, NBR, SWVI), technogenic geosystems modifications are distinguished, characterizing different levels of chemical pollution (TM-1, TM-2 and natural geosystem). Within the modification zones, geoelectrical studies are carried out to assess the depth of contamination. Results. In the zone of phosphogypsum dumps impact, two technogenic modifications were distinguished, with a total area of 83.3 hectares, characterized by a statistically significant decrease in the values of vegetation indices compared to the average level. Based on the results of vertical electrical sounding, it was established that the depth of contamination in the TM-1 zone reaches up to 20 m, in the TM-2 zone – up to 2.5 m. The migration of contaminated substances from the dumps occurs with surface drain. In the zone of impact of the sulfur storage, the area of pollution, specified with vegetation indices, covers two hectares. According to the results of the natural electric field method and vertical electrical sounding, the flow of pollution from the sulfur storage site penetrates into groundwater, which is discharged in the TM-1 zone, causing the death of vegetation. In the TM-2 zone, contamination is registered only in the ground aquifer. The developed set of methods enables to quickly and relatively comprehensively diagnose the state of the undergoing technogenic impacts geological environment.

Estimating Carbon Stock in Unmanaged Forests Using Field Data and Remote Sensing

Unmanaged forest ecosystems play a critical role in addressing the ongoing climate and biodiversity crises. As there is no commercial interest in monitoring the health and development of such inaccessible habitats, low-cost assessment approaches are needed. We used a method combining RGB imagery acquired using an Unmanned Aerial Vehicle (UAV), Sentinel-2 data, and field surveys to determine the carbon stock of an unmanaged forest in the UNESCO World Heritage Site wilderness area Dürrenstein-Lassingtal in Austria. The entry-level consumer drone (DJI Mavic Mini) and freely available Sentinel-2 multispectral datasets were used for the evaluation. We merged the Sentinel-2 derived vegetation index NDVI with aerial photogrammetry data and used an orthomosaic and a Digital Surface Model (DSM) to map the extent of woodland in the study area. The Random Forest (RF) machine learning (ML) algorithm was used to classify land cover. Based on the acquired field data, the average carbon stock per hectare of forest was determined to be 371.423 ± 51.106 t of CO2 and applied to the ML-generated class Forest. An overall accuracy of 80.8% with a Cohen’s kappa value of 0.74 was achieved for the land cover classification, while the carbon stock of the living above-ground biomass (AGB) was estimated with an accuracy within 5.9% of field measurements. The proposed approach demonstrated that the combination of low-cost remote sensing data and field work can predict above-ground biomass with high accuracy. The results and the estimation error distribution highlight the importance of accurate field data.

Monitoring of Heracleum sosnowskyi Manden Using UAV Multisensors: Case Study in Moscow Region, Russia

Detection and mapping of Sosnowsky’s hogweed (HS) using remote sensing data have proven effective, yet challenges remain in identifying, localizing, and eliminating HS in urban districts and regions. Reliable data on HS growth areas are essential for monitoring, eradication, and control measures. Satellite data alone are insufficient for mapping the dynamics of HS distribution. Unmanned aerial vehicles (UAVs) with high-resolution spatial data offer a promising solution for HS detection and mapping. This study aimed to develop a method for detecting and mapping HS growth areas using a proposed algorithm for thematic processing of multispectral aerial imagery data. Multispectral data were collected using a DJI Matrice 200 v2 UAV (Dajiang Innovation Technology Co., Shenzhen, China) and a MicaSense Altum multispectral camera (MicaSense Inc., Seattle, WA, USA). Between 2020 and 2022, 146 sites in the Moscow region of the Russian Federation, covering 304,631 hectares, were monitored. Digital maps of all sites were created, including 19 digital maps (orthophoto, 5 spectral maps, and 13 vegetation indices) for four experimental sites. The collected samples included 1080 points categorized into HS, grass cover, and trees. Student’s t-test showed significant differences in vegetation indices between HS, grass, and trees. A method was developed to determine and map HS-growing areas using the selected vegetation indices NDVI > 0.3, MCARI > 0.76, user index BS1 > 0.10, and spectral channel green > 0.14. This algorithm detected HS in an area of 146.664 hectares. This method can be used to monitor and map the dynamics of HS distribution in the central region of the Russian Federation and to plan the required volume of pesticides for its eradication.

Modelling bluetongue and African horse sickness vector (Culicoides spp.) distribution in the Western Cape in South Africa using random forest machine learning.

Culicoides biting midges exhibit a global spatial distribution and are the main vectors of several viruses of veterinary importance, including bluetongue (BT) and African horse sickness (AHS). Many environmental and anthropological factors contribute to their ability to live in a variety of habitats, which have the potential to change over the years as the climate changes. Therefore, as new habitats emerge, the risk for new introductions of these diseases of interest to occur increases. The aim of this study was to model distributions for two primary vectors for BT and AHS (Culicoides imicola and Culicoides bolitinos) using random forest (RF) machine learning and explore the relative importance of environmental and anthropological factors in a region of South Africa with frequent AHS and BT outbreaks. Culicoides capture data were collected between 1996 and 2022 across 171 different capture locations in the Western Cape. Predictor variables included climate-related variables (temperature, precipitation, humidity), environment-related variables (normalised difference vegetation index-NDVI, soil moisture) and farm-related variables (livestock densities). Random forest (RF) models were developed to explore the spatial distributions of C. imicola, C. bolitinos and a merged species map, where both competent vectors were combined. The maps were then compared to interpolation maps using the same capture data as well as historical locations of BT and AHS outbreaks. Overall, the RF models performed well with 75.02%, 61.6% and 74.01% variance explained for C. imicola, C. bolitinos and merged species models respectively. Cattle density was the most important predictor for C. imicola and water vapour pressure the most important for C. bolitinos. Compared to interpolation maps, the RF models had higher predictive power throughout most of the year when species were modelled individually; however, when merged, the interpolation maps performed better in all seasons except winter. Finally, midge densities did not show any conclusive correlation with BT or AHS outbreaks. This study yielded novel insight into the spatial abundance and drivers of abundance of competent vectors of BT and AHS. It also provided valuable data to inform mathematical models exploring disease outbreaks so that Culicoides-transmitted diseases in South Africa can be further analysed.

Effect of Transient Waterlogging Stress on Growth, Physiology and Yield of Cowpea (Vigna unguiculata L.) in Semi-Arid Region

Cowpea cultivation during rainy season is highly affected by the waterlogging stress due to unpredicted high-intensity rains. The studies on assessment of waterlogging effect on different growth stages of cowpea are necessary for planning mitigation strategies. Hence study was conducted during kharif (June to September) 2022 under factorial randomized block design (FRCBD) set up. The first factor consisted of seven waterlogging durations (3 to 15 days), and second factor was three growth stages of cowpea (15 DAE; Days after emergence, 25 DAE and at 50% flowering). The results revealed that regardless of growth stages, growth and yield attributes were drastically decreased with increased duration of waterlogging. The highest plant height (25.07 cm), number of branches plant–1 (5.33) and leaf area (205.27 cm2 plant–1), and number of pods plant–1 (4.27), pod length (15.24 cm), number of seeds pod–1 (14.27), grain (6.27 g plant–1) and haulm yield (15.62 g plant–1) were recorded with 3 days of waterlogging, whereas lowest values were reported with 15 days of waterlogging. Regarding growth stages, highest growth, and yield attributes were recorded with waterlogging during 50% flowering, followed by 25 DAE and 15 DAE. Moreover, the correlation study indicated that physiological parameters such as leaf protein content (r = 0.95) and Normalized Difference Vegetation Index NDVI (r = 0.97) were positively related to grain yield. It was found that, cowpea is sensitive to high-intensity waterlogging (beyond 3–5 days) especially during the early growth stage (15 DAE).

Predicting wheat yield gap and its determinants combining remote sensing, machine learning, and survey approaches in rainfed Mediterranean regions of Morocco

Wheat plays a crucial role in Morocco’s food security, economic stability, and livelihoods of farming communities. Assessing key vegetation indices (as yield predictors), along with understanding potential yield, yield gap, and major determinants for this gap at regional and national scales, is vital for improving food security with resilience in variable climatic conditions. Analysing the yield gap and its causes during drought and optimal weather conditions can reduce crop failure risks and enhance productivity specially in variable rainfed production systems. This study aimed to develop scalable methodology to predict field- and landscape-level yield and yield gaps for wheat and their underlying causes examplifying Morocco’s rainfed production environment combining remote sensing, machine learning, and ground information. By analysing six vegetation indices (EVI2, CGVI, MSR, NDVI, OSAVI, and RVI) derived from Sentinel-2 satellite imagery (10 m resolution) over three successive growing seasons (2018–2019, 2019–2020, and 2020–2021), the study employed advanced vegetation index models for accurate prediction of wheat yields and yield gaps at plot and on a larger regional scale within the Rabat-Sale-Kenitra region. To identify the determinants of yield gap, climate and soil datasets were merged with crop management information and the random forest model was fine-tuned and assessed for each season and cumulatively. The findings highlighted that RVI, GCVI, and NDVI vegetation indices were particularly effective in predicting wheat yields, showing the highest R2 and the lowest prediction errors (RMSE). Such predictive methodologies are crucial for policymakers to proactively plan and mitigate risk minimization and adaption plans at regional and national levels. The models predicted rainfed potential yields of 5.99, 1.53, and 4.66 t ha−1, with corresponding yield gap of 3.38, 0.73, and 1.58 t ha−1 for the seasons of 2018/2019 (favorable); 2019/2020 (drought) and 2020/2021 (favorable), respectively. Across three periods, critical factors determining yield include soil moisture, total rainfall during the crop growing period, evapotranspiration, and soil texture and carbon content. To minimize drought risks and maximize benefits during variable rainfall conditions, it is essential to implement pre-season drought forecasts, customize seeding dates based on soil moisture, adopt technologies that enhance soil moisture retention, and utilize climate-adapted farming practices in the semi-arid and arid rainfed regions.

Использование индексов вегетации в почвенно-ландшафтом картографировании и агроэкологической оценке

In this work, the possibilities of using remote sensing data to clarify the contours of soil differences were evaluated. It was found that visualization of mean annual vegetation indices NDVI allows to specify actual information on the contours of productivity zones. The use of this approach allows clarifying the boundaries of soil differences and identifying the actual boundaries of lithogenic lands with different productivity. It was found that the average annual NDVI in the linear model is related to the content of physical clay, with R2=0.26, the highest NDVI values are observed on soils of medium-loamy and heavy loamy composition in conditions of excessive moisture in the foothills of the Krasnodar Territory with average annual precipitation of more than 850 mm. Keywords: VEGETATION INDICES, REMOTE SENSING DATA, LAND PRODUCTIVITY, AGRO-ECOLOGICAL ASSESSMENT

Identification Leaves of Ulmus pumila L., Tilia cordata Mill. and Acer campestre L. Using Vegetation Indices

The aim of the research was to identify a group of vegetation indices (VIs) for species identification. The objects of research were leaves of Ulmus pumila L., Tilia cordata Mill. and Acer campestre L. Hyperspectral imaging (HSI) was carried out under artificial lighting in laboratory conditions using a Cubert UHD-185 hyperspectral camera. A technique was developed for the automated selection of pure spectral profiles from hyperspectral images by setting a double barrier specified by intervals of PSSR and NDVI VIs. A total of 80 VIs was calculated. A statistical analysis of the data was carried out for their representativeness. To determine VIs, the value of which is most dependent on the species characteristics of trees, analysis of variance (ANOVA) and principal component analysis (PCA) methods were used. Research has shown that the PCA method is effective and sufficient to identify the group of VIs characterized by the greatest dispersion in relation to tree species. The PCA carried out for pairs of tree species made it possible to identify a group of vegetation indices, the value of which to the greatest extent depends on species characteristics. These are Carter2, CI2, CRI4, GMI2, mSR2, NDVI2, OSAVI2, SR1, Carter4, Datt2, SR6, Datt, DD, Maccioni, MTC.

Geotechnologies in Biophysical Analysis through the Applicability of the UAV and Sentinel-2A/MSI in Irrigated Area of Common Beans: Accuracy and Spatial Dynamics

The applicability of remote sensing enables the prediction of nutritional value, phytosanitary conditions, and productivity of crops in a non-destructive manner, with greater efficiency than conventional techniques. By identifying problems early and providing specific management recommendations in bean cultivation, farmers can reduce crop losses, provide more accurate and adequate diagnoses, and increase the efficiency of agricultural resources. The aim was to analyze the efficiency of vegetation indices using remote sensing techniques from UAV multispectral images and Sentinel-2A/MSI to evaluate the spectral response of common bean (Phaseolus vulgaris L.) cultivation in different phenological stages (V4 = 32 DAS; R5 = 47 DAS; R6 = 60 DAS; R8 = 74 DAS; and R9 = 89 DAS, in 99 days after sowing—DAS) with the application of doses of magnesium (0, 250, 500, and 1000 g ha−1). The field characteristics analyzed were mainly chlorophyll content, productivity, and plant height in an experimental area by central pivot in the midwest region of Brazil. Data from UAV vegetation indices served as variables for the treatments implemented in the field and were statistically correlated with the crop’s biophysical parameters. The spectral response of the bean crop was also detected through spectral indices (NDVI, NDMI_GAO, and NDWI_GAO) from Sentinel-2A/MSI, with spectral resolutions of 10 and 20 m. The quantitative values of NDVI from UAV and Sentinel-2A/MSI were evaluated by multivariate statistical analysis, such as principal components (PC), and cophenetic correlation coefficient (CCC), in the different phenological stages. The NDVI and MCARI vegetation indices stood out for productivity prediction, with r = 0.82 and RMSE of 330 and 329 kg ha−1, respectively. The TGI had the best performance in terms of plant height (r = 0.73 and RMSE = 7.4 cm). The best index for detecting the relative chlorophyll SPAD content was MCARI (r = 0.81; R2 = 0.66 and RMSE = 10.14 SPAD), followed by NDVI (r = 0.81; R2 = 0.65 and RMSE = 10.19 SPAD). The phenological stage with the highest accuracy in estimating productive variables was R9 (Physiological maturation). GNDVI in stages R6 and R9 and VARI in stage R9 were significant at 5% for magnesium doses, with quadratic regression adjustments and a maximum point at 500 g ha−1. Vegetation indices based on multispectral bands of Sentinel-2A/MSI exhibited a spectral dynamic capable of aiding in the management of bean crops throughout their cycle. PCA (PC1 = 48.83% and PC2 = 39.25%) of the satellite multiple regression model from UAV vs. Sentinel-2A/MSI presented a good coefficient of determination (R2 = 0.667) and low RMSE = 0.12. UAV data for the NDVI showed that the Sentinel-2A/MSI samples were more homogeneous, while the UAV samples detected a more heterogeneous quantitative pattern, depending on the development of the crop and the application of doses of magnesium. Results shown denote the potential of using geotechnologies, especially the spectral response of vegetation indices in monitoring common bean crops. Although UAV and Sentinel-2A/MSI technologies are effective in evaluating standards of the common bean crop cycle, more studies are needed to better understand the relationship between field variables and spectral responses.

INVESTIGATION OF THE PROCESSES OF ECOLOGICAL AND ECOSYSTEM CHANGES IN WATER BODIES USING UAV DATA

In recent years, the water landscapes of inland rivers have been subjected to significant an- thropogenic impacts exceeding the limits of their self-healing ability. Traditional methods of monitoring ge- oecological parameters - sampling of water in the field with subsequent laboratory analysis - require signif- icant financial and time costs. Traditional methods allow assessing the ecological state of the entire water- course not spatially, but pointwise. In this research, sensors on board the UAV measured solar radiation reflected from the surface of the water and used image data from different camera ranges. The combina- tion of images used was based on a common methodology for identifying key features, and a geographic information system (GIS) modelling approach was used for spatially analyze the distribution and interaction of environmental features. In addition, research the ecological condition of the Yertis River and the quality of water discharged after the municipal wastewater treatment facilities of Ust-Kamenogorsk city into the Yertis River, the data from the DJI Phantom 4 RTK/multispectral drone was processed and the normalized vegetation index NDVI, normalised water level difference index NDWI, water chromaticness index CI, tur- bidity index NDTI and chlorophyll concentration index "a" were calculated. The results obtained can serve as a basis for scientific analysis of the environmental conditions of the researching area, including for learning the processes of eutrophication and other changes in the environment.

USING MACHINE LEARNING ALGORITHMS FOR NATURAL HABITATS ASSESSMENT

The potential of AI to process and interpret large volumes of data can provide researchers with a powerful tool to understand and monitor biodiversity on a global scale. In this paper we aimed to identify dominant individual plant species in natural protected habitats. Mapping the dominant species from the targeted natural habitats was followed by testing machine learning algorithm for differentiating similar species using satellite images. In the end we validated the data generated by machine learning algorithms through extensive field observations. Using the Sentinel-2 mission 10m resolution data and comprehensive field mapping we managed to see different phenology variations between diverse types of plant communities. Using the NDVI and NDII vegetation indexes and Random Forest algorithm during the dominant species phenology stages for each consecutive 10-day periods between May 1st and September 10th, revealed distinct responses to climate fluctuations and environmental factors. The natural habitats different signatures are strongly influenced by their ecological and conservation status and are not yet suitable for identification, but could help improve AI’s automatic detection for multiannual analysis if a favorable conservation trend is reached. The main achievement of the proposed methodology is the ability to differentiate between different species of deciduous trees, with machine learning training accuracy generally exceeding 95% and classification accuracy surpassing 90%.

Comparison of Citrus Leaf Water Content Estimations Based on the Continuous Wavelet Transform and Fractional Derivative Methods

Citrus tangerines are famous fruits worldwide, and monitoring the water content of citrus leaves is highly important for citrus production. However, there are still challenges in quantitatively estimating the water content of citrus leaves using hyperspectral technology, and the random noise generated during spectral acquisition and the overlapping peaks in the sensitive band of the citrus leaf water content will affect estimation accuracy. To solve these problems and further explore the roles of the continuous wavelet transform (CWT) and fractional-order derivative (FOD) in the estimation of citrus leaf water content, this study intends to use of CWT and FOD to decompose the original spectrum, and then compare the correlation between the original spectrum and leaf water content to explore whether the decomposition treatment has improved the correlation between spectrum and leaf moisture content. Then, the successive projections algorithm (SPA) was used to select feature bands and combine spectral vegetation indices. Partial least squares regression (PLSR) was used to construct water-content inversion models for citrus leaves, and the inversion accuracies of two commonly used spectral preprocessing methods were compared. The results indicate that (1) the CWT can improve the sensitivity of the spectrum to the citrus leaf water content to a certain extent, and the inversion accuracy of the CWT is approximately 5% greater than that of the FOD. (2) On the basis of the CWT and FOD methods, the inversion accuracy of the citrus leaf water content based on SPA screening increased by 9.61% and 9.29%, respectively, compared with the original spectrum. (3) Under CWT decomposition, Scale4 of the Gaus1 wavelet was screened by the SPA, and the inversion model of citrus leaf water content was constructed by combining the spectral vegetation index NDVI with the best results. The R-squared (R2) and root mean square error (RMSE) values were 0.7491 and 0.0284, respectively, which were both 0.0138 greater than those of the best inversion model for the FOD R2. In conclusion, the CWT-SPA combined with the spectral vegetation index can improve the sensitivity of the spectrum to the citrus leaf water content, eliminate a large amount of redundant data, and enhance the prediction ability and stability of the citrus leaf water content.

Intercropped Soybean Plant Population in a Coffee Plantation and Its Effects on Agronomic Parameters and Geospatial Information

Coffee farming has high land use value, which can result in economic losses without proper land use planning. Intercropping has improved coffee production by providing an alternative income source to producers, especially in the crop formation phase. The objective of this study was to evaluate productivity, growth, and geospatial data in different soybean plant populations intercropped with coffee. The experiment was conducted at the Federal University of Uberlândia, in Monte Carmelo, Minas Gerais, Brazil. It had an experimental randomized block design with five treatments: the control (no soybeans); 80 thousand plants ha−1; 160 thousand plants ha−1; 240 thousand plants ha−1; and 320 thousand plants ha−1. Productive and vegetative characteristics of coffee and soybeans were evaluated, as well as the NDVI and GNDI vegetation indices. The mass of 1000 grains of soybean reached its peak (178.96 g) with a population of 222 thousand plants of soybean ha−1. The maximum soybean productivity of 102.78 bags ha−1 was obtained in the population of 185 thousand plants soybean ha−1. An increasing population of 240–320 thousand plants ha−1 soybean between coffee rows reduced soybean yield due to reduced light, causing plant lodging. The biometric parameters of the coffee trees did not change, which was evidenced by high normalized and green normalized difference vegetation indices (NDVI and GNDVI, respectively). Therefore, it is concluded that the use of soybeans between the coffee trees does not affect the vegetative and productive parameters of the coffee tree, making the use of the intercrop viable.