No full-text available
To read the full-text of this research,
you can request a copy directly from the authors.
Monitoring Vegetation Systems in the Great Plains with ERTS
... Over the years, a myriad of indices have been proposed for a wide variety of applications. For example, the normalized difference vegetation index (NDVI) (Rouse et al. 1974) is a measure of plant health, while the analytical burned area index (ABAI) makes it easy to distinguish between burned and healthy forest areas. In most cases, these indices are either directly derived from spectral reflectance properties or determined through extensive field studies, experiments and numerical optimization techniques. ...
... In view of the heavy use of spectral indices in multispectral remote sensing applications Mouafik et al. 2024;Tran, Reef, and Zhu 2022;Zeng et al. 2020), this work introduces a novel index, the linear ratio index (LRI), a generalization of the popular normalized difference, ratio and difference indices (Jordan 1969;Rouse et al. 1974;Tucker 1979). Specifically, the generalization is achieved by extending the normalized difference index to a weighted linear sum of all available spectral bands in both the numerator and denominator. ...
... Most spectral indices are based on the early normalized difference, ratio and difference indices (Jordan 1969;Rouse et al. 1974;Tucker 1979), which are calculated as shown in Equation 1-Equation 3. c a 2 R m�l and c b 2 R m�l are the spectral input bands where m denotes the height and l denotes the width of the bands. I nd , I r and I d correspond to the normalized difference, ratio and difference index, respectively. ...
Unmanned aerial vehicles, equipped with multispectral imaging systems, as well as publicly available datasets, have fueled various research in remote sensing applications, including precision agriculture, land cover mapping or even camouflage detection. Many of these applications make use of spectral indices, such as normalized difference or ratio indices, created by merging multiple raw bands. These indices typically provide a direct indication of certain physical surface properties, like plant health, nitrogen content or leaf area index, and are determined by studying spectral reflectance properties or using optimization techniques. Given the heavy use and utility of such indices, this work introduces a novel generalization of the normalized difference, ratio and difference indices, the linear ratio index (LRI), a ratio of two linear functions of all available bands. In addition, an optimization approach for the LRI is presented, which incorporates complexity reduction strategies that enable optimization using only a subset of all available bands and reduced parameter precision, thereby ensuring parameter readability. The LRI and its optimization are thoroughly investigated in the context of camouflage detection in tactical reconnaissance scenarios by optimizing a six-band and a two-band LRI using the eXtended Multispectral Dataset for Camouflage Detection (MUDCAD-X). For comparison with traditional spectral index optimization approaches, the resulting linear ratio indices (LRIs) are evaluated against all raw bands and an optimized normalized difference index and an optimized ratio index. The evaluation shows that the optimized LRIs provide the best overall results in terms of visibility and detectability of camouflaged targets. This could indicate a general superiority of the LRI over established indices optimized by testing band permutations, making the LRI a promising candidate for further investigation in other remote sensing applications where it could also outperform traditional index optimization approaches. Therefore, the software code for optimizing the LRI has been made publicly available for further exploitation, requiring only an adapted optimization criterion to support any other use case. Furthermore, as with most spectral indices, the LRIs obtained in this study have negligible computational overhead and, under the right conditions, can be directly integrated into any existing camouflage detection system.
... Finally, we assessed spatial agreement (Guerschman et al. 2009, Nagler et al. 2003) Surrogate Cellulose Absorption Index (SWIR2/SWIR1) EVI2 (Z. Jiang et al. 2008) Enhanced Vegetation Index 2 2.5 * ((NIR -Red)/(NIR +2.4 * Red + 1)) MNDWI (Xu 2006) Modified Normalized Difference Water Index (Green -SWIR1)/(Green + SWIR1) NBR (Key and Benson 2006) Normalized Burn Ratio (NIR -SWIR2)/(NIR + SWIR2) NDMI (McDonald, Gemmell, and Lewis 1998) Normalized Difference Moisture Index (NIR -SWIR2)/(NIR + SWIR2) NDVI (Rouse et al. 1974) Normalized Difference Vegetation Index (NIR -Red)/(NIR + Red) NDWI (Gao 1996) Normalized Difference Water Index (NIR -Green)/(NIR + Green) SAVI (Huete 1988) Soil Adjusted Vegetation Index ((1 + L) * (NIR -Red))/(NIR + Red + L) between our map and three existing products (CGLS-LC100, MCD12Q1, and MapBiomas) by resampling them to match our resolution and reclassifying their legends to our Level-1 scheme (Supplementary Materials, Tables S1-S3). ...
Northeast Brazil (NEB), about three times the area of Spain, hosts >90% of Brazil’s drylands along with tropical rain- and dry forests. Climate variability, 45–60% cloud cover, and scarce reference data limit land use and land cover (LULC) mapping accuracy to ~80% across much of the region. Here, we introduce NEB’s first context-specific LULC framework, using phenologically timed annual MODIS mosaics (2000–2020) with <0.5% pixel gaps and minimal seasonal bias. Ecoregions were individually classified using customized random forest (RF) models with 56 features – including linear spectral unmixing fractions – prior to NEB-wide integration. Binary masks excluding non-mangrove pixels during RF training significantly improved mangrove-rainforest separation. Our two-tier classification scheme uniquely distinguishes NEB shrublands nationally, aligns with global datasets (7 Level-1 classes), and preserves ecoregion detail (16 Level-2 classes). Validated against >10,000 independent points, the 2018 NEB-wide map achieved 90.5% overall accuracy at Level-1. At Level-2, ecoregional accuracies were 95.9% (Amazon), 94.3% (Atlantic Forest), 89.4% (Cerrado), and 87.9% (Caatinga). Per-pixel spatial agreement with national and global datasets ranged from 29–70%. Between the 2000 and 2020 endpoints, ~540,000 km² of NEB underwent LULC changes, based on pixel counts. Forest declined 22%, grasslands 68%, and agriculture expanded 140% – roughly 10 million soccer fields – mainly in the Cerrado MaToPiBa (Maranhão, Tocantins, Piauí, Bahia) frontier. Meanwhile, encroachment around protected areas intensified, particularly in the Amazon. This open-access product (http://www.dsr.inpe.br/DSR/laboratorios/LAF) sets a benchmark for LULC mapping in global dryland-forest mosaics, positioning NEB as a model for data-driven land management.
... In the context of warming and humidification, climate factors such as precipitation and temperature have different impacts on vegetation growth (Horion et al., 2013). The Normalized Difference Vegetation Index (NDVI) first proposed by Rouse (1973) in 1973 effectively represents changes in vegetation and ecosystem parameters and sensitively reflects changes in climate factors (Gao & Dennis, 2001;Horion et al., 2013). Among these climate factors, Liu et al. (2016) found that in other arid and semi-arid regions, the dominant factors influencing vegetation changes are temperature and precipitation. ...
The study of seasonal-scale climate-vegetation coupling mechanisms is important for coordinating desertification control and climate adaptation. Taking the Mu Us Sandy Land (MUSL) as a case study, we gathered meteorological data from 1959 to 2019 (including maximum temperature, minimum temperature, and precipitation) for seasonal analysis. We conducted M–K significance and mutation analysis, Morlet wavelet periodicity analysis and correlation analysis and investigated the effects of various seasonal and annual climate factors on NDVI using NDVI values collected from 1999 to 2019. The results indicate the following: (1) Both the maximum and minimum temperatures in the MUSL exhibit an upward trend across all four seasons. Precipitation in autumn shows a decreasing trend, while in spring, summer, and winter, it increases, leading to an overall rise in precipitation. (2) The maximum and minimum temperatures in MUSL experienced a mutation in the 1980 and 2000, respectively, while precipitation underwent a mutation in the 1980 and 2019. After these mutations, both temperature and precipitation exhibited an overall upward trend. (3) The first primary cycle for both the maximum and minimum temperatures is 18 years, while the first primary cycle for precipitation is 8 years. (4) The impact of the climate in MUSL on vegetation is as follows: precipitation > temperature.
... Crop parameter extraction was performed using time series of the Normalized Difference Vegetation Index (NDVI) [38], derived from Sentinel-2 imagery with a spatial resolution of 10 m and a revisit time of 5 days [39]. These satellite images were integrated with land use maps to confirm the crop types irrigated by each system. ...
This study presents a robust methodology for the indirect estimation of groundwater abstraction for irrigation at the scale of individual wells, addressing a key gap in data-scarce agricultural settings. The approach combines NDVI time series, crop water requirement modelling, and spatial analysis of irrigation systems within a GIS environment. A soil water balance model was applied to Homogeneous Units of Analysis, and irrigation requirements were estimated using an ensemble approach accounting for key sources of uncertainty related to phenology detection, soil moisture at sowing (%SAW), and irrigation system efficiency. A spatial linkage algorithm was developed to associate individual wells with the irrigated areas they supply. Sensitivity analysis demonstrated that 10% increases in %SAW resulted in abstraction reductions of up to 1.98%, while 10% increases in irrigation efficiency reduced abstractions by an average of 6.48%. These findings support the inclusion of both parameters in the ensemble, generating eight abstraction estimates per well. Values ranged from 33,000 to 115,000 m 3 for the 2023 season. Validation against flowmeter data confirmed the method's reliability, with an R 2 of 0.918 and an RMSE equivalent to 9.3% of the mean observations. This approach offers an accurate, spatially explicit estimation of groundwater abstractions without requiring direct metering and offers a transferable, cost-effective tool to improve groundwater accounting and governance in regions with limited monitoring infrastructure.
... The geology of the Chianti area was simplified into fourteen major groups based on lithology type and age. The Normalized Difference Vegetation Index (NDVI; Rouse et al., 1973) and the Normalized Difference Water Index (NDWI; McFeeters, 1996) were derived from remote-sensing data. The NDVI is useful to understand the distribution of vegetation and provides information about the relation between vegetation cover and bare soil. ...
Ensuring an efficient Extra Virgin Olive Oil (EVOO) traceability is fundamental to support a sustainable produced food. To date assessing geographical origin of EVOO is a challenging issue, especially if the authenticity is evaluated based on objective parameters beyond subjectivity or paper certifications. Consequently, technical approaches are becoming increasingly complex, such as the use of radiogenic 87Sr/86Sr to link the soil of the origin to the EVOO. We present a novel database of geological and organic 87Sr/86Sr values (n = 133) from Tuscany, using newly analyzed samples and literature data, to establish the first comprehensive bioavailable Sr isotope baseline for this region. We show that the 87Sr/86Sr of EVOO is a powerful fingerprint if we consider the olive mill processes. To this end a two-component mixing approach based on olive fruits and tap water was used to assess the contribution of different sources of 87Sr/86Sr to EVOO. The isoscape of bioavailable 87Sr/86Sr was generated using a novel geoinformatics framework for a representative Tuscan territory with an high quality standard EVOO production. Results show that the 87Sr/86Sr values of Tuscany EVOOs range from 0.70854 to 0.70974. The median value, equal to 0.70911, is higher than Tunisian (0.70861) and northern Spanish (0.70837) EVOOs. The proof of concept shown in this research is highly relevant for geographic EVOO traceability as it allows a complete evaluation of the critical path in using the Sr isotope signature for provenance study.
... Values closer to 0.5 represent coffee plants with low vigor, which may be a physiological response to some kind of constraint. We calculated the NDVI through the difference in reflectance between the NIR (near infrared) and Red bands divided by the sum of the NIR and Red bands according to equation 1, proposed by (Rouse et al., 1974). ...
Soils of the Cerrados (Brazilian Savanna) are deep, well-structured, and well-drained, with flat to gently undulating terrain that favors mechanization for coffee cultivation. However, these soils are susceptible to compaction. This study aimed to assess the effect of mechanization on the physical characteristics of an Oxisol under irrigated coffee cultivation in the Alto Paranaíba-Minas Gerais State. We selected eight areas with different cultivars and years of Arabica coffee plantation, sampling five positions: right soil under the tree crown (RSC), right tractor lines (RTL), interrows (IR), left tractor lines (LTL), and left soil under the tree crown (LSC) at layers of 0.00-0.10, 0.10-0.20, 0.20-0.30, and 0.30-0.40 m. We conducted principal component analysis (PCA) and analysis of variance, comparing means through Tukey’s test (p<0.05). The PCA selected three principal components (PC1, PC2, and PC3) composed of 12 physico-chemical properties from a total of 27 evaluated. Total porosity (TP), mean penetration resistance (PRmean), volumetric moisture (θ) at 100 kPa (θ 100 kPa) and 300 kPa (θ 300 kPa) tensions, particle density (PD), and granulometric fractions (clay, fine sand, and coarse sand) were among the most influential attributes. Total porosity and PRmean demonstrated the existence of compaction in the tractor wheel tracks, particularly in the 0.00-0.20 m layer. The 3.5-year-old plantation did not show significant variations in these properties. The θ 100 kPa and θ 300 kPa were higher in the compacted areas, indicating increased water retention but potentially limiting aeration. Clay content increased with depth, while sand fractions decreased, influencing the soil susceptibility to compaction. The vigor of coffee plants, as identified by satellite images (NDVI), could not be fully associated with the physical constraints of the subsurface, as even areas with low vigor did not consistently correlate with poor physical properties in laboratory analyses. These findings highlight the complex interplay between soil physical properties and coffee plant performance, emphasizing the need for comprehensive management strategies in mechanized coffee cultivation.
... The resulting chlorophyll distribution map reveals significantly elevated concentrations, reaching a maximum of 39 mg m − 3 , in coral reefs and adjacent waters due to the presence of symbiotic and coralline algae (Varunan and Shanmugam 2021) surrounded by coral reefs, while the rest of the region displays notably very low concentrations. In Figure 12(c), the Normalized Difference Vegetation Index (NDVI) is computed using the red (684 nm) and NIR (704 nm) wavelength (Rouse et al. 1974). The 704 nm band lies within the red-edge transition region, making it particularly sensitive to changes in chlorophyll contents. ...
Unmanned Aerial Systems (UAS) equipped with push broom hyperspectral imaging (HSI) sensors offer unique advantages for high-resolution monitoring of inland and coastal aquatic environments. However, accurate retrieval of water-leaving radiance from UAS-based HSI data is challenged by atmospheric path effects, such as molecular and aerosol scattering, which significantly impact observed radiance and necessitate a robust atmospheric correction method. This study introduces Hycor (HYperspectral atmospheric CORrection), an atmospheric correction algorithm designed specifically for UAS-based hyperspectral data. Hycor leverages in-situ atmospheric measurements to accurately retrieve water-leaving radiance. It incorporates a novel pressure correction scheme for Rayleigh Optical Thickness (ROT) and employs a pixel-wise, image-based aerosol estimation method tailored to the lower altitudes typical of UAS deployments. Validation against in-situ data in turbid coastal waters demonstrated Hycor’s effectiveness in reducing radiance deviations and improving water-quality metrics, such as chlorophyll and turbidity. Statistical comparisons across wavelengths showed significant accuracy improvements. At shorter wavelengths (413–560 nm), initial radiance deviations from in-situ data ranged from 25.8% to 70.3%, reduced to 7.8%–20.2% with Hycor. At longer wavelengths (670–865 nm), where initial deviations were higher due to complex water reflectance and minimal atmospheric boundary signals, Hycor reduced these deviations from 83.0%–1166.7% to 26.1%–99.5%. Overall, Hycor’s corrections enable more accurate retrieval of spectral water-leaving radiances, particularly at shorter wavelengths, enhancing UAS-based HSI’s capacity to assess water quality in aquatic environments. This advancement lays the groundwork for real-time, high-precision UAS-based HSI applications in water colour remote sensing.
... Excess green index (ExG) Rouse et al., 1974 Normalized difference red edge index (NDRE) Barnes et al. (2000) R, G, B, RE, and NIR represent the red, green, blue, red edge, and near infrared bands, respectively in the above formulas. environment for the 2nd ratoon (CVs3), untested cultivar in tested crop/ environment for the 3rd ratoon (CVs4), and untested cultivar in untested crop/environment (CVs5) (Fig. 2). ...
Yield and its components are the important traits for plant breeders to select the best genotypes in the breeding programs. However, traditional measurements of these traits across genotypes and environments are labor-intensive and time-consuming, as hundreds or even thousands of plots need to be estimated. A yield trial was carried out using seven sugarcane cultivars planted in a randomized complete block design with four replications for two ratoon crops to estimate sugarcane yield and its components using unoccupied aerial systems (UAS)-based high throughput phenotyping (HTP) and to compare the traditional method with UAS-based yield components in discriminating ability to assess sugarcane yield via a path coefficient analysis. UAS platforms mounted with sensors were flown over the trial. The result shows that UAS-derived plant height (PH) showed a strong relationship with the ground measured PH (R 2 = 0.89, RMSE = 0.15 m). Likewise, an accurate millable stalk height (MSH) estimation, using UAS-derived PH as a predictor, was observed (R 2 = 0.54, RMSE = 0.15 m). Canopy height model (CHM)-derived canopy cover (CC) appeared to be a promising feature to indirectly select or to predict for stalk number (SN) (R 2 = 0.69, RMSE = 10,975 stalks ha − 1). Based on a path coefficient analysis, UAS-based yield components performed equally to or slightly underperformed the traditional method. Traditionally , SN was the largest contributor to cane yield. Similarly, CC and CHM were the important components for UAS-based yield components. Additionally, the yield prediction model using UAS-derived canopy features with five cross validation schemes (CVs) revealed that model accuracy increased as association between predictor variables with a responding variable increased. The present study shows that random forest outperformed (higher r and lower RMSE) the linear regression models (stepwise, lasso, and ridge) in all CVs. The linear regressions were off when they were used to predict the performance of cultivars in untested crop/environments (CVs2 and CVs5), while a higher accuracy was observed when using random forest in those CVs. More importantly , the accuracy of all models reduced when they were tested in untested crop/environments (CVs2 and CVs5), indicating the challenge of using a prediction model applied to new environments.
... (c) Spatial analysis, land cover classification and landscape heterogeneity assessment First, we extracted the normalized difference vegetation index (NDVI) for each point where a recorder was located. This metric is used in remote sensing to assess vegetation density and greenness based on the reflection of light [29]. To classify land cover, we applied the Corine LandCover classification scheme (the most used land cover system in the country for land cover classification) to categorize satellite imagery obtained from the PlanetScope satellite constellation (Planet Labs) for the year 2020, with a spatial resolution of 3 m (1:10 000). ...
As agriculture continues to expand in tropical regions, effectively preserving biodiversity will rely not only on protected areas but also on sustainable practices within agricultural landscapes. Studying biodiversity changes associated with landscape management is essential for refining practices that support ecosystem resilience and species conservation, but collecting the data required to draw strong conclusions remains challenging because of the high spatial and temporal resolution needed. In this context, passive acoustic monitoring (PAM) offers a valuable solution by enabling researchers to gather continuous, high-resolution biotic signals over time. Using PAM, our objective was to examine how changes in landscape characteristics, specifically heterogeneity and composition, correlate with soundscape patterns including acoustic activity and beta diversity. We collected data across 52 000 ha in the Magdalena River Valley, Colombia, a biodiversity hotspot significantly transformed by palm oil monocultures. We contrasted soundscape data, including acoustic activity and soundscape turnover, with landscape metrics derived from Geographical Information Systems analysed satellite imagery, focusing on landscape composition and configuration. Our analysis showed that compositional and heterogeneity-related landscape variables, such as the proportion of natural cover (NC) and patch shape, were associated with differences in acoustic activity and soundscape homogenization. Specifically, patches with uniform shapes and a lower NC correspond to more homogeneous soundscapes with higher acoustic activity. In contrast, patches with irregular shapes and a higher NC were linked to more heterogeneous soundscapes and lower acoustic activity. By linking soundscape patterns with landscape metrics, we highlight the importance of retaining natural habitat features within productive areas to support acoustic diversity, and by extension, ecological resilience.
This article is part of the theme issue ‘Acoustic monitoring for tropical ecology and conservation’.
... Aplicações derivadas do sensoriamento remoto em estudos da paisagem utilizando índices de estrutura da vegetação, por meio de imagens, são novas ferramentas que auxiliem em estudos com finalidade de acompanhar e compreender processos em níveis regionais à globais, ou seja, avaliar mudanças nas paisagens (SOARES-FILHO, 1998;LUZ, 2002). O NDVI, desenvolvido por Rouse et al. (1973), tem como importância a capacidade de monitorar as mudanças sazonais e interanuais. O NDVI é preciso ao analisar as alterações sofridas pela cobertura vegetal ao longo do tempo (LIMA et al., 2015), sendo o mais utilizado em estudos com a cobertura vegetal, por detectar as condições da vegetação e sua dinâmica têmporoespacial, facilitando o monitoramento sazonal e variações de longo prazo (WANG et al., 2003). ...
The regional landscape encompassed by Rio Grande basin, on Western Bahia, has on its Chapadas, in the erosive retreat fronts, the Evergreen Valley forest between the mosaics composed of forest and savanna phytophysiognomies. Therefore, this study intends to evaluate the spatial distribution of the Evergreen Valley forest occurrence, what are the conditions that influence the local landscape, and investigate the possible changes in this scenario at a spatial-temporal intermission. The methods was based on the use of products from the mission SRTM to the development of the geomorphological maps of the areas where the Evergreen forest is found on the landscape, around the river basin, towards the use of NDVI, to compare the variations on vegetation cover during 40 years, since 1975. Moreover, a stratigraphic profile of the site was done in order to obtain information about the local geological structure, and a land profile under the values of NDVI to assess the vegetative strength at the Evergreen forest area throughout the length of the stain. The stratigraphic profile indicated the presence of low porosity rocks along the forest occurrence altimetry, indicating a favorable geomorphological condition to its development.
... Numerous research articles focus on urban ecology assessment, including the monitoring of built-up and vegetation [26,27], urban heat islands (UHIs) [28,29], water resource management [30], air quality regulation [31], and biodiversity monitoring [32]. These studies underscore the effectiveness of remote sensing methods in urban ecology monitoring [33,34], employing various indices such as NDVI [35], LST [36], BI [37], EVI [38], NDBI [39], SAVI [40], and MNDWI [41]. However, Xu [42] introduced the remote sensing based ecological index (RSEI) to observe and evaluate regional ecological conditions. ...
Assessing the ecological environmental quality (EEQ) is crucial for protecting the environment. Dhaka's rapid, unplanned urbanization, driven by economic and social growth, poses significant eco-environmental challenges. Spatiotemporal ecological and environmental quality changes were assessed using remote sensing based ecological index (RSEI) maps derived from Landsat images (1993, 2003, 2013, and 2023). RSEI was based on four indicators-greenness (NDVI), heat index (LST), dryness (NDBSI), and wetness (LSM). Landsat 5 TM and 8 OLI/TIRS images were processed on Google Earth Engine (GEE), with principal component analysis (PCA) applied to determine RSEI. The findings showed a decline in the overall RSEI (1993-2023), with low-and very low-quality areas increasing by about 39% and high-and very high-quality areas decreasing by 24% of the total area. NDBSI and LST were negatively correlated with RSEI, except in 1993, while NDVI and LSM were generally positive but negative in 1993. The global Moran's I (0.88-0.93) indicated strong spatial correlation in the distribution of EEQ across Dhaka. LISA cluster maps showed high-high clusters in the northeast and east, while low-low clusters were concentrated in the northwest. This research examines the degradation of ecological conditions over time in Dhaka and provides valuable insights for policymakers to address environmental issues and improve future ecological management.
... The combination of the normalised difference formulation with the regions exhibiting the highest chlorophyll absorption and reflectance renders it a suitable tool for a wide range of conditions. However, saturation may occur in areas of dense vegetation when LAI (leaf area index) values are high (Rouse et al., 1973). ...
The existence of an extensive Gräberstraße-type necropolis in the Roman city of Segobriga is confirmed by the funerary-type structures located 2,400 m from the city and by the excavation of five funerary monuments located along its main entrance/exit road. The inscriptions, sculptures and architectural remains of funerary character exhumed prove, in addition, its use by members of the higher social classes, including wealthy freedmen. Until now we did not know the spatial structuring of the monumenta and their relationship with each other and with the road. This information is vital to know the internal topographic organisation and the constructive density of the necropolis. Geophysical surveys with ground penetrating radar (GPR) and multispectral images captured with unmanned aerial vehicles (UAV) have recently been carried out in order to improve our knowledge in this field. They have been developed within the framework of an ongoing research project to study the northern suburb. The objective of these surveys was to identify new funerary monuments not visible on the surface along the route of the road. This paper analyses the methodology and processing of the two techniques used. It also evaluates their comparative applicability to detect buried remains in calcareous soils. The data obtained indicate the presence of mausoleums on both sides of the roadway according to the Italic model of funerary viae. Those located in the first line form two continuous rows, while isolated monuments are located at the rear. This model prevailed in the cemetery areas of the Western Roman Empire from the end of the 1st century BC onwards.
... NDVI [47] ρ nir (·)−ρ r (·) ρ nir (·)+ρ r (·) ...
This document presents a low-cost, open-source, robust, and user-friendly Unmanned Aerial System for precision agriculture tasks. The proposed methodology for data collection and image processing is flexible and adaptable to most basic systems. Besides, a new vegetation index is defined for temperature estimation on vegetation without thermal imagery as usually done by other related systems. The system also features a control algorithm that is robust against external disturbances. The output information is used then to estimate the vegetation's temperature. The experiments presented in this work are enclosed to corn fields.
... [−1, + 1] ( Rouse et al., 1974 ) Green Normalized Difference Vegetation Index Gitelson et al. (1996) Generalized Difference Vegetation Index ...
... 10.1029/2024JG008421 Measures green vegetation health and density (Rouse et al., 1974). ...
Wetland ecosystems are critical to global carbon and nitrogen cycles. This study leverages unmanned aerial system (UAS)‐based hyperspectral imaging to quantify soil organic matter (SOM), total carbon (C), and total nitrogen (N) in moderately to densely vegetated salt marshes at the Virginia Coast Reserve Long‐Term Ecological Research (VCR‐LTER) site. We utilized elastic net (ENet) regression and gradient‐boosted regression trees (GBRT) within a hybrid modeling framework to predict these soil properties using features from the visible to near‐infrared (VNIR) and shortwave infrared (SWIR) spectral ranges. Validated through a 1,000‐iteration bootstrap analysis, the hybrid model demonstrated robust predictive capabilities. The model achieved mean normalized root mean square error of 0.118 for SOM, 0.127 for C, and 0.138 for N, with corresponding mean R2 values of 0.874, 0.865, and 0.822, respectively. These outcomes highlight the efficacy of integrating advanced statistical methods with high‐resolution remote sensing data to enhance soil property estimation in ecologically sensitive areas.
... Gitelson et al. (2003),Rouse et al. (1974) e Miranda et al. (2020. ...
Technological advancements have reduced geographical barriers, demanding rapid adaptation across all sectors, including the use of remotely piloted aircraft (RPAs), commonly known as drones, which have been widely applied in areas such as urban and agricultural monitoring. In municipalities like Jataí-GO, where agribusiness is predominant, the use of RPAs for measuring vegetative indices (VIs) brings benefits for more precise and sustainable agricultural practices. However, the cost of some RPAs limits their broader adoption, as many devices can exceed R$ 160,000 (Brazilian currency). This research is experimental and aimed to develop techniques for using rotary-wing drones, which are more affordable than other models available on the market, to generate vegetation indices for mapping and monitoring commercial grain crops. The methodology consisted of: 1) field surveys in soybean planting areas; 2) acquisition of images from the Sentinel-2 satellite and the drone; 3) processing of images captured by the Phantom 4 PRO drone, equipped with a MAPIR Survey 3W camera; and 4) analysis of correlations between the VIs obtained by the drone and Sentinel-2 in two areas on the campus of the Federal University of Jataí (UFJ), for validation. Data collection included the use of a high-precision Trimble R4s GNSS for georeferencing. The results show a strong correlation between the VIs calculated using drone and Sentinel-2 images for soybean crops, with coefficients of determination (R²) exceeding 0.72 for VARI and 0.73 for NDVI. Plot 001 stood out for its uniformity, achieving high coefficients of determination, reinforcing the effectiveness of the geotechnologies employed. In more heterogeneous areas, such as plot 002, the VIs revealed differences, particularly with the VARI index, which proved less efficient for mixed cultivation environments. The data confirms that VIs generated by cost-effective drones can indicate planting variations, demonstrating the feasibility of their application in the agricultural sector without significant investments.
... The urban greening map was generated by means of the normalized difference vegetation index (NDVI) applied to CBERS-4A images, previously subjected to an atmospheric correction using the Dark-Object Subtraction (DOS) method [53,54]. This index, proposed by [55], is a metric meant to quantify biomass, vegetation health, and density. Thus, the NDVI is also capable of highlighting the presence or absence of vegetation, calculated from the normalized difference between the red (highly absorbed by healthy vegetation to fuel photosynthesis and create chlorophyll) and near-infrared (which is strongly reflected by healthy plants) spectral bands [56]. ...
Analyzing the population’s access to ecosystem services offered by urban greening constitutes a measure of environmental justice, as it directly affects the quality of life and health of the population living in cities. This article is committed to proposing a geoenvironmental model in a geographic information system (GIS), envisaged to estimate the share of urban forests and green spaces in territorial planning units (TPUs), corresponding to neighborhoods of a pilot city, using high-spatial-resolution images of the China–Brazil Earth Resources Satellite (CBERS-4A) and the normalized difference vegetation index (NDVI). These data were combined by means of a Boolean analysis with social vulnerability indicators assessed from census data related to income, education, housing, and sanitation. This model ultimately aims to identify priority areas for urban afforestation in the context of environmental justice and is thus targeted to improve the inhabitants’ quality of life. The municipality of Goiânia, the capital of Goiás state, located in the Brazilian Central–West Region, was chosen as the study area for this experiment. Goiânia presents 19.5% of its urban territory (82.36 km2) covered by vegetation. The analyses indicate an inequity in the distribution of urban forest patches and green areas in this town, where 7.8% of the total TPUs have low priority, 28.2% have moderate to low priority, 42.2% have moderate to high priority, and 21.8% have high priority for urban afforestation. This urban greening imbalance is particularly observed in its most urbanized central nuclei, associated with a peripheralization of social vulnerability. These findings are meant to support initiatives towards sound territorial planning processes designed to promote more sustainable and equal development to ensure environmental justice and combat climate change.
... The calculations were performed using the R programme. The NDVI was calculated according to the formula by Rouse et al. (1973). ...
Given the increasing global demand for sustainable agricultural practices, there is a growing need to evaluate the effectiveness of governance mechanisms. This paper presents a case study analysis of voluntary sustainability standards (VSS) and their impact on maintaining soil health in the context of soybean production, specifically in the Brazilian Savannah (Cerrado biome). The sustainability of soybean production certified by VSS ProTerra and Roundtable on Responsible Soy was evaluated on 35 farms, considering factors such as land use, deforestation, cultivation methods, pesticide usage, and their effects on soil health. The assessment of these factors was conducted through a comprehensive methodology that included field visits, soil sampling and laboratory analysis, remote sensing techniques using satellite imagery, and structured interviews with farm managers. VSS are private governance mechanisms that establish quality standards to be followed in various areas. The study shows that the standards are generally respected on certified farms and, in particular, excluding deforestation. The VSS promote incremental improvements within the overall context of large-scale, business-as-usual agriculture by promoting practices that enhance soil fertility, reduce erosion, and optimise input use. These actions can contribute to stronger soil health, boosting resilience, and productivity. The urgency of reconciling food production with climate change mitigation and adaptation will increase interest in and demand for sustainable agriculture certification in the coming decades. Therefore, the monitoring and verification of the effectiveness of those standards, as shown in our study, are fundamental to provide true benefits, transparency, and confidence to the market.
... The NDVI is widely recognized as an effective indicator of vegetation growth status and canopy coverage, exhibiting a linear or near-linear relationship with green leaf density, photosynthetically active radiation, vegetation productivity, and plant biomass [29]. In this study, NDVI values were calculated from the selected Landsat satellite imagery using ENVI 5.6 software, and the vegetation activity levels were subsequently classified. ...
Vegetation restoration in seismically active regions involves complex interactions between geological hazards and ecological processes. Understanding the spatiotemporal patterns of vegetation recovery is critical for assessing disaster evolution, evaluating mitigation effectiveness, and guiding ecological resilience planning. This study investigates post-earthquake vegetation dynamics in the Chutou Gully watershed, located in the 12 May 2008 Wenchuan earthquake zone, using NDVI data from 2000 to 2022. Results reveal a sharp decline in vegetation cover following the earthquake, followed by a steady recovery trend, with NDVI values projected to return to pre-earthquake levels by 2030. Degradation was concentrated in debris flow channels, while more stable adjacent slopes exhibited stronger recovery. Over time, the area of poorly restored vegetation significantly declined, indicating increased ecosystem resilience. The findings highlight the need for site-specific ecological restoration strategies tailored to localized recovery conditions. This study provides valuable insights for disaster mitigation agencies, ecological planners, and local governments working in mountainous hazard-prone regions, and contributes to the long-term sustainability of ecosystems in disaster-prone areas.
... Vegetation indices indicate the health status of plants and can be specific to a particular biotic or abiotic stress (Table 1). There are many vegetation indices, but the most commonly used vegetation index for assessing drought stress is the Normalized Difference Vegetation Index (NDVI) (Figure 3) [163]. For assessing water deficit stress, indices derived from the ratio and difference in reflectance in the visible (VIS), near-infrared (NIR), and shortwave infrared (SWIR) spectral regions are commonly utilized [164]. ...
In the course of climate change, drought is becoming one of the most important abiotic stress factors in agroecosystems and significantly affects agricultural productivity. Common bean (Phaseolus vulgaris L.), one of the most important legumes with a high protein content for human consumption, is very sensitive to water deficit. Thus, it is important to understand the physiological and developmental effects of water deficit on the bean. Thanks to technological advances, traditional phenotyping methods have evolved towards high-throughput phenotyping (HTP), which utilizes various imaging technologies for rapid and non-destructive monitoring of plant traits. This review examines the effects of water deficit on bean morphology (roots, leaves, stems, and generative organs), physiology (photosynthesis, antioxidant activity, phytohormones), and gene expression. We will also describe the HTP techniques used to quantify this water deficit-induced response through different imaging techniques and evaluate their applicability for the generation of reliable phenotypic data and the selection of drought-tolerant genotypes for further breeding and genetic progress.
... The remote sensing method, NDVI, tracks vegetation dynamics. It is computed using canopy reflectance in the near-infrared and infrared bands and is less reliant on soil characteristics [21]. We used the United States Geological Survey (USGS) [22] data server to obtain a retrospective time series of the NDVI with a monthly temporal resolution. ...
Malnutrition is viewed as one of climate change’s five most considerable adverse health impacts. This study, from a drought-and famine-prone food insecure setting in the Rift Valley of southern Ethiopia, aims to quantify the possible causal effect of climate variation on women’s nutritional status through its effect on the normalized difference vegetation index (NDVI), a proxy measure for crop production, and household food security. Using a cohort study design, we ensured a temporal relationship between the main exposures preceding the mediator and the outcome. Women living in 904 households from nine randomly selected subsistence farming in rural Kebeles, the lowest administrative unit in the Boricha district in Sidama, were visited quarterly to collect nutritional status (outcome variable), household food security status (HHFS), and sociodemographic information. Climate data (rainfall and temperature) was obtained from the Google Earth Engine. Generalized structural equation modeling (GSEM) was used to measure the association between rains, the NDVI, and women’s nutritional status after adjusting for the mediation effect of HHFS. The analysis adjusted the clustering effect of Kebele and the household. The study showed that the NDVI and HHFS directly affected women’s body mass index. Moreover, household heads who attended primary education, total energy expenditure of women, and household wealth were positively associated with women’s BMI. On the other hand, older women and women who were not members of a community-based health insurance had a lower BMI. Climate variability, NDVI, and household food security could be causally linked to women’s nutritional status, suggesting that rural people depending on rain-fed subsidence farming for crop production are vulnerable to the impact of climate variability.
... So far, there have been hundreds of vegetation indices proposed both domestically and internationally. However, the majority of these indices incorporate both visible light and near-infrared bands [31][32][33][34]. At present, low-cost consumer-grade UAVs, typically equipped with RGB cameras, are more commonly used in practical applications. ...
Low-cost unmanned aerial vehicle (UAV) visible light remote sensing provides new opportunities for plant community monitoring, but its practical deployment in different ecosystems is still limited by the lack of standardized vegetation index (VI) optimization for multi-species coverage extraction. This study developed a universal method integrating four VIs—Excess Green Index (EXG), Visible Band Difference Vegetation Index (VDVI), Red-Green Ratio Index (RGRI), and Red-Green-Blue Vegetation Index (RGBVI)—to bridge UAV imagery with plant communities. By combining spectral separability analysis with machine learning (SVM), we established dynamic thresholds applicable to crops, trees, and shrubs, achieving cross-species compatibility without multispectral data. The results showed that all VIs achieved robust vegetation/non-vegetation discrimination (Kappa > 0.84), with VDVI being more suitable for distinguishing vegetation from non-vegetation. The overall classification accuracy for different vegetation types exceeded 92.68%, indicating that the accuracy is considerable. Crop coverage extraction showed a minimum segmentation error of 0.63, significantly lower than that of other vegetation types. These advances enable high-resolution vegetation monitoring, supporting biodiversity assessment and ecosystem service quantification. Our research findings track the impact of plant communities on the ecological environment and promote the application of UAVs in ecological restoration and precision agriculture.
قدمت هذه الدراسة تحليلًا معمقًا لتقييم حالة الغطاء النباتي وتقييم محتوى الرطوبة في التربة لتقدير ظاهرة الجفاف الزراعي في حوض وادي تثليث بالمملكة العربية السعودية، مستفيدة من التطورات الهائلة في تقنيات الاستشعار عن بعد (Remote Sensing) ونظم المعلومات الجغرافية(GIS) ,إذ يبرز حوض وادي تثليث كمنطقة دراسة نموذجية لتأثرها المتزايد بالجفاف، حيث شهد تزايدًا في وتيرة وشدة السنوات الجافة منذ بداية القرن الماضي، مع تباين في التأثير يزداد حدة في الأجزاء الأكثر قحولة. الهدف المحوري للدراسة تقييم تأثير مؤشر رطوبة التربة في تقدير الجفاف الزراعي في حوض وادي تثليث، في فترتين زمنيتين مختلفين ( 2015م و 2025م ) بفاصل زمني 10 سنوات ،تم الاعتماد بشكل أساسي على صور الأقمار الصناعية لاندسات (Landsat 8)، وتم التركيز على فصل الربيع نظرًا لكونه فترة النشاط البيولوجي الأقصى للغطاء النباتي. لتحقيق هذا الهدف، استُخدمت مجموعة من المؤشرات البيئية الفعًالة، بما في ذلك: مؤشر الغطاء النباتي الطبيعي(NDVI)، مؤشر حالة النباتات(VCI)، مؤشر حرارة السطح(TCI)، ومؤشر صحة النبات المركّب (VHI)تمثل هذه المؤشرات أدوات لا غنى عنها لرصد وتقييم التغيرات المرتبطة بالجفاف. والتي أظهرت تدهورًا كبيرًا في حالة الغطاء النباتي بين الفترتين المدروسة. فبينما كانت المساحة المتأثرة بالجفاف الشديد أو المتدني في عام 2015 تبلغ حوالي 14.3% من إجمالي مساحة الحوض، قفزت هذه النسبة إلى 31.8% في عام 2025، مما يعكس تدهورًا واضحًا في صحة الغطاء النباتي. كما كشفت مؤشرات الجفاف الحراري (TCI) عن تفاقم الوضع، حيث ارتفعت مساحة الأراضي التي تعاني من ظروف حرارية سيئة جدًا بشكل هائل من 2.1% في 2015 إلى 53% في 2025. هذه الأرقام تُشير بوضوح إلى أن ما يقرب من نصف مساحة الوادي أصبحت تُعاني من إجهاد حراري شديد، مما يُساهم في تفاقم ظاهرة الجفاف الزراعي. كما أن الغطاء النباتي الذي يعاني من نقص في رطوبة التربة يصبح أكثر عرضة للتأثر بالتغيرات المناخية مثل ارتفاع درجات الحرارة والجفاف .وقد أظهرت الدراسة علاقة قوية وواضحة بين ازدياد مناطق الجفاف وتراجع حالة وصحة الغطاء النباتي في المنطقة العامل الأساسي في تقدير الجفاف الزراعي بمنطقة الدراسة.
Forest ecosystems are vital for biodiversity, climate regulation, and ecosystem services. Their resilience depends not only on species diversity but also on intraspecific variation—the genetic and phenotypic differences within species—which underpins adaptive capacity to environmental change. However, large-scale, continuous monitoring of intraspecific variation remains challenging. Here, we present a remote sensing approach using Sentinel-2 time series of five vegetation indices as proxies for pigment content, canopy structure, and water content to detect intraspecific variation in seven tree species across a broad environmental gradient in Switzerland. Using pure-species plot data from the Swiss National Forest Inventory, we decomposed variation into spatial, temporal, and spatiotemporal components. We found that spatial variation dominated in evergreen species (48–86%), while temporal variation was more pronounced in deciduous species (56–82%), reflecting their stronger seasonality. These findings demonstrate that species-specific Sentinel-2 time series can effectively track intraspecific variation, providing a scalable method for forest monitoring. This approach opens new pathways for studying forest adaptation, informing management strategies, and guiding species selection for conservation under changing climate conditions.
The Mississippi River Bird‐foot Delta (MRBD) has long been at risk of deterioration due to Relative Sea Level Rise (RSLR), yet information on historical spatial distribution in wetland gain and loss remains limited. Using a Random Forest algorithm in Google Earth Engine, we extract wetland area from multiple Landsat images spanning 1990–2022. Data are integrated with sediment load, wave dynamics, sea level, and surface elevation to analyze drivers of wetland gain and loss. Results indicate a minor net change of only 1.21 km², with a total gain of 160.83 km² and a total loss of 159.62 km². Overall stability of wetland area masks significant regional variability, with notable wetland expansion in the interior and substantial losses along eastern and southeastern margins. Sediment diversion toward the interior of the delta lead to distributaries narrowing (Main Pass and Pass a Loutre) that further hindered sediment‐laden water transport into deltaic margins. Wetland dynamics along the edges were closely linked to wave action, with large‐scale retreat in northern (4.0 ± 9.9 m/yr), eastern (58.0 ± 48.2 m/yr), and southeastern (38.6 ± 15.8 m/yr) regions, while progradation in the southern (13.6 ± 10.1 m/yr) and western areas (7.4 ± 19.4 m/yr). Fluvial sediments significantly impact wetland growth with 1‐year lag. Vertical accretion of wetlands exceeds RSLR, indicating equilibrium along vertical dimension but are affected by lateral dynamics driven by wave and fluvial sediment inputs. In conclusion, the MRBD is abandoning the distal parts to wave erosion, while focusing on building wetlands in the interior to create a more compact delta.
In protected areas of the Brazilian savannas (Cerrado), Land Surface Phenology (LSP) is influenced by both precipitation and fire, but the nature of these relationships remains unexplored. Here, we assessed the impacts of precipitation and fire on LSP metrics derived from the Normalized Difference Vegetation Index (NDVI) at Emas National Park (ENP). Using TIMESAT, along with the 250-m Moderate Resolution Imaging Spectroradiometer (MODIS) MOD13Q1 and 30-m Harmonized Landsat Sentinel (HLS) products, we investigated these effects in both grassland and woodland areas. To evaluate the effects of precipitation, we identified the driest and wettest seasonal cycles between 2002 and 2023 and analyzed the relationships between accumulated rainfall during the rainy season and each of the 13 TIMESAT metrics. To assess the effects of fire, three major events were examined: 1 September 2005 (affecting 45% of the park’s area), 12 August 2010 (90%), and 10 July 2021 (21%). The burned grassland area and the subsequent vegetation recovery following the 2021 event were analyzed in detail using a non-burned control site and LSP metrics extracted from the HLS product, covering both pre- and post-disturbance cycles. The results indicated that the metrics most positively correlated to precipitation were Amplitude (AMP), End of Season (EOS), Large and Small Seasonal Integrals (LSI and SSI), and Rate of Increase at the Beginning of the Season (RIBS). The highest correlation coefficients were found in woodland areas, which were less affected by fire disturbance than grassland areas. Similar trends were observed in the behavior of AMP, EOS, and SSI in response to both precipitation and fire, with fire exerting a stronger influence. By decoupling the fire effects from rainfall influence using the control site, we identified Base Level (BL), SSI, EOS, AMP, and Values at the End and Start of the Season (VES and VSS), as the metrics most sensitive to fire and subsequent vegetation recovery in burned areas. The effects of fire were evident for most metrics, both during the disturbance cycle and in the post-fire cycle. Our study underscores the importance of combining MODIS and HLS time series to understand vegetation phenology in the Cerrado.
Understanding the spatial variability of soil erodibility and its associated indices across different land uses is critical for sustainable land use planning and management. Traditional methods for measuring these variables are often time-consuming and costly. To address this, the study employed digital soil mapping (DSM) and machine learning (ML) models as efficient and cost-effective alternatives to predict soil erodibility and its indices, including clay ratio, critical level of organic matter, crust formation, dispersion ratio, and soil aggregate stability. 50 soil surface samples (0–20 cm depth) were collected from forest, agricultural, and pasture land uses. Soil physicochemical properties were determined through laboratory analyses. The study utilized Multiple Linear Regression (MLR) and machine learning models, including Random Forest (RF), Support Vector Machine (SVM), Artificial Neural Network (ANN), and an ensemble of the four single models. These models were trained using the repeated tenfold cross-validation method and evaluated based on root mean square error (RMSE), mean absolute error (MAE), and coefficient of determination (R²). The results demonstrated that the ANN model outperformed others in predicting soil erodibility (R² = 0.98, MAE = 0.00341, RMSE = 0.0031. The SVM and RF models also performed well, with SVM achieving R² = 0.93, MAE = 0.00541, RMSE = 0.0038, and RF achieving R² = 0.87, MAE = 0.0037, RMSE = 0.00557 for soil erodibility prediction. The superior performance of ANN is attributed to its ability to model complex, non-linear interactions among variables influencing soil erodibility. Nonetheless, challenges such as data quality requirements and the risk of overfitting highlight the need for careful model calibration. The spatial prediction of soil erodibility across land uses revealed distinct patterns. Forest soils exhibited the lowest mean erodibility values (0.0313 t ha⁻¹ h MJ⁻¹ mm⁻¹), reflecting their higher resistance to erosion due to better soil structure and organic matter content. In contrast, agricultural land uses recorded the highest mean erodibility values (0.0320 t ha⁻¹ h MJ⁻¹ mm⁻¹), likely due to frequent tillage and reduced vegetation cover, which increase erosion susceptibility. Among soil types, Calcaric Cambisols were identified as the most erosion-prone, while Lithic Leptosols were the least susceptible, attributed to differences in soil texture, structure, and organic matter content. Finally, the basin was classified based on soil erodibility classes. The analysis showed that 81.18% of the basin (covering 546.6 km²) falls under the less erodible class, highlighting the basin’s overall resilience to erosion. In conclusion, the study demonstrates that machine learning-based models can accurately predict soil erodibility and its indices. The resulting maps provide a valuable baseline for land use planning, natural resource management, and decision-making processes.
Above-ground biomass (AGB) is an important factor in crop yield. However, most AGB estimation methods for crops with conspicuous spikes, such as rice and sorghum, can achieve high accuracy during the vegetative stage but low accuracy during the reproductive stage. In this study, we explored an AGB estimation model throughout the entire growth period. Firstly, we divided the growth period of crops into two stages—before heading and after heading—and adopted different strategies according to the characteristics of the different stages. Before heading, we estimated AGB by multiplying the multi-spectral vegetation index (VI) and the crop canopy height (H) square. After heading, we added spectral absorption characteristic parameters to characterize spike biomass and used a multiple linear regression model. This model can accurately estimate AGB in both rice and sorghum throughout the entire growth period, which has a coefficient of determination (R2) above 0.88 and the relative root mean square error (rRMSE) below 20.13% in both crops. Compared with the direct estimation of AGB throughout the entire growth period using H2 × VI, this model effectively improved the accuracy of AGB estimation for crops with conspicuous spikes in the reproductive stage, which can provide reliable information for evaluating crop growth at plot scale.
Sugarcane yield prediction plays a pivotal role in enabling farmers to monitor crop development and optimize cultivation practices, guiding harvesting operations for sugar mills. In this study, we established three experimental fields, which were planted with three main sugarcane cultivars in Guangxi, China, respectively, implementing a multi-gradient fertilization design with 39 plots and 810 sampling grids. Multispectral imagery was acquired by unmanned aerial vehicles (UAVs) during five critical growth stages: mid-tillering (T1), late-tillering (T2), mid-elongation (T3), late-elongation (T4), and maturation (T5). Following rigorous image preprocessing (including stitching, geometric correction, and radiometric correction), 16 VIs were extracted. To identify yield-sensitive vegetation indices (VIs), a spectral feature selection criterion combining gray relational analysis and correlation analysis (GRD-r) was proposed. Subsequently, three supervised learning algorithms—Gradient Boosting Decision Tree (GBDT), Random Forest (RF), and Support Vector Machine (SVM)—were employed to develop both single-stage and multi-stage yield prediction models. Results demonstrated that multi-stage models consistently outperformed their single-stage counterparts. Among the single-stage models, the RF model using T3-stage features achieved the highest accuracy (R2 = 0.78, RMSEV = 7.47 t/hm2). The best performance among multi-stage models was obtained using a GBDT model constructed from a combination of DVI (T1), NDVI (T2), TDVI (T3), NDVI (T4), and SRPI (T5), yielding R2 = 0.83 and RMSEV = 6.63 t/hm2. This study highlights the advantages of integrating multi-temporal spectral features and advanced machine learning techniques for improving sugarcane yield prediction, providing a theoretical foundation and practical guidance for precision agriculture and harvest logistics.
Pastoral activities are an essential part of the cultural and ecological landscape of Central Italy. This traditional practice supports local economies, maintains biodiversity, and contributes to the sustainable use of natural resources. Understanding livestock behavior in response to environmental variability is essential for improving grazing management and animal welfare and ensuring the sustainability of these systems. This study evaluated the movement patterns of sheep grazing on pastures with differing vegetation indices in the Sibillini Mountains. Twenty lactating ewes foraging on two different pastures were monitored from June to October 2023 using GPS collars and accelerometers. GPS tracks were segmented using the Expectation Maximization Binary Clustering (EmBC) method to characterize movement behaviors, such as foraging, traveling, and resting. The NDVI was used to characterize vegetation dynamics, showing notable differences between the two pastures and across the grazing season. Additive mixed models were used to analyze data, accounting for individual variability and temporal autocorrelation in the sample. The results suggest that variations in the NDVI influence grazing behavior, with sheep in areas of lower vegetation density exhibiting increased movement during foraging. These findings provide valuable insights for optimizing grazing practices and promoting sustainable land use.
Resumo Diante da urgência em implementar ações contra o desmatamento e a fragmentação florestal, os sistemas agroflorestais (SAF) têm ganhado destaque como medida para recuperação e conservação da biodiversidade, promovendo os benefícios associados aos serviços ecossistêmicos. Para a avaliação e o monitoramento de paisagens degradadas em processo de regeneração, os índices de vegetação são amplamente utilizados, devido à sua capacidade de aferir propriedades qualitativas e quantitativas da cobertura vegetal. Neste contexto, este trabalho aplica o Índice de Vegetação por Diferença Normalizada (NDVI) com o objetivo de analisar, ao longo do ano de 2022, a resposta vegetativa no Assentamento Nova Esperança I, localizado no município de São José dos Campos (SP), que apresenta experiências com SAF. Verificou-se que as áreas florestadas e as parcelas com SAF apresentaram os maiores valores de NDVI da área de estudo, além de sofrerem a menor redução do índice durante o período de estiagem. Os resultados sugerem que os SAF são mais resilientes às variações de pluviosidade, favorecendo a manutenção da cobertura vegetal, e que o método adotado é uma ferramenta eficaz para a avaliação de sistemas agroflorestais. Palavras-chave: Sistemas Agroflorestais (SAF); NDVI; áreas protegidas; serviços ecossistêmicos; sensoriamento remoto. Analysis of agroforestry systems by vegetation spectral index in rural settlement Abstract Given the urgency of implementing actions against deforestation and forest fragmentation, Agroforestry Systems (SAF) have gained prominence as a strategy for the recovery and conservation of biodiversity, promoting the benefits associated with ecosystem services. For the assessment and monitoring of degraded landscapes undergoing regeneration, vegetation indices are widely used due to their ability to measure both qualitative and quantitative aspects of vegetation cover. In this context, this study applies the Normalized Difference Este trabalho está licenciado com uma Licença Creative Commons-Atribuição 4.0 Internacional. Rev. NERA | Presidente Prudente, SP | v. 28, n. 2 | e9985 | 2025.
Kubu Raya Regency is one of the areas that has a peat ecosystem in it. The peat ecosystem has a role and function in mitigating climate change because it has the ability to store quite high carbon reserves. However, peat ecosystems often experience degradation and changes in land cover which can contribute carbon emissions to the atmosphere. Remote sensing is a technology that can be used to detect changes in land cover and use in Kubu Raya Regency. Therefore, this research aims to detect changes in land cover and using remote sensing technology and assess the level of accuracy of the detection results. Analysis of changes in land cover and use from 2000 - 2023 was obtained by guided classification using the Random Forest (RF) algorithm which involves various vegetation, water and built-up land indices. The research results show that there is a decrease in forest land area from 2000 to 2023 amounting to 106,542 ha. The forest area in 2000 was 524,359 ha, while in 2023 it will be 417,817 ha. The results of accuracy measurements show an overall accuracy (OA) value of 98.84% with a kappa statistic of 0.98. It is hoped that the results of these findings will provide an initial picture of the condition of the ecosystem in Kubu Raya Regency, most of which is a peat ecosystem, as a consideration in formulating peat ecosystem conservation policies.
This study evaluates the effectiveness of combining remote sensing techniques
with the Random Forest algorithm for estimating the Periodic Annual Increment (PAI)
in a dry tropical forest located within the Caatinga biome in northeastern Brazil. The
analysis integrates forest inventory data collected from permanent plots monitored between 2011 and 2019 with Landsat satellite imagery processed through the Google Earth Engine platform. By incorporating surface reflectance and vegetation indices, the approach significantly improved the accuracy of productivity estimates while reducing the costs and efforts associated with traditional field-based methods. The Random Forest model achieved a strong performance (R2 = 0.8867; RMSE = 0.87), and its predictions were further refined using post-processing correction factors. These results demonstrate the potential of data-driven modeling to support forest monitoring and sustainable management practices, especially in ecosystems vulnerable to the impacts of climate change.
When a program synthesis task starts from an ambiguous specification, the synthesis process often involves an iterative specification refinement process. We introduce the Programming by Navigation Synthesis Problem, a new synthesis problem adapted specifically for supporting iterative specification refinement in order to find a particular target solution. In contrast to prior work, we prove that synthesizers that solve the Programming by Navigation Synthesis Problem show all valid next steps ( Strong Completeness ) and only valid next steps ( Strong Soundness ). To meet the demands of the Programming by Navigation Synthesis Problem, we introduce an algorithm to turn a type inhabitation oracle (in the style of classical logic) into a fully constructive program synthesizer. We then define such an oracle via sound compilation to Datalog. Our empirical evaluation shows that this technique results in an efficient Programming by Navigation synthesizer that solves tasks that are either impossible or too large for baselines to solve. Our synthesizer is the first to guarantee that its specification refinement process satisfies both Strong Completeness and Strong Soundness .
Nos estudos referentes ao processo de desertificação, o índice de vegetação constitui um dado importante para apreender a dinâmica ambiental do domínio morfoclimático das caatingas expressa na cobertura vegetal, decorrente da sazonalidade climática e da pressão ambiental. Assim, propõe-se, por meio deste estudo, analisar a evolução espaço-temporal do NDVI nos períodos chuvoso e seco dos anos de 2001 a 2016, para estabelecer a susceptibilidade ambiental à desertificação através da elaboração de uma modelagem ambiental. Em decorrência do caráter semiárido do clima e estágios avançados de deterioração ambiental, selecionou-se o município de Canudos, situado no norte do estado da Bahia, como área de estudo. Empregaram-se produtos MOD13, oriundos do sensor MODIS, para aplicar o NDVI e, posteriormente, integrar os dados em ambiente SIG mediante o uso da lógica fuzzy. Identificou-se uma dimensão espacial acentuada das classes com os menores índices de vegetação para o período seco e chuvoso, o que configura estágios avançados de deterioração, pois a biomassa não se recompõe em meio às precipitações pluviométricas. Em áreas de Depressão Periférica e Interplanálticas, o padrão de chuvas não causou mudanças significativas na biomassa, devido à intensa pressão ambiental que resultou em deterioração. Em função disso, a Susceptibilidade severa é expressamente extensa, por decorrer em 51,9% das terras.
A expansão de monoculturas em larga escala na Amazônia tem acelerado as transformações no uso e cobertura da terra, ameaçando florestas e os modos de produção locais. Este estudo analisou mudanças na cobertura florestal no nordeste do Pará (2018–2024) utilizando imagens Sentinel-2 e o algoritmo Random Forest, identificando um aumento de 1.016% no desmatamento entre 2021 e 2024, o que corresponde a 21,5% da área de estudo. A principal conversão observada ocorreu em florestas secundárias, que foram transformadas em grandes áreas contínuas preparadas para agricultura. Esse padrão contrasta com a tradicional agricultura de roçado praticada na região, indicando uma forte pressão sobre os recursos florestais. Os resultados reforçam a necessidade de políticas públicas eficazes para o monitoramento, fiscalização e proteção das florestas remanescentes.
Iraq struggles with rising temperatures while managing a lack of precipitation, increased dry spells, and facing water shortages and land degradation, along with recurring dust storms. Extreme climate changes significantly affect environmental stability, agricultural yield, and overall sustainability maintenance. The research aims to examine climate change in the southern regions of Iraq and its impact on land degradation and vegetation growth. The research uses global meteorological data combined with satellite imagery to study climatic parameter transformations in southern Iraq from 1981 to 2020 and their consequences on water balance, vegetation growth, and land quality. The research analyses MODIS Vegetation Indices (MOD13) together with 20 satellite images throughout Iraq, from 2000 to 2020. Key climatic variables demonstrate time-dependent and geographic changes across Iraq between 1981 and 2020, impacting water balance and vegetation maintenance while leading to land degradation. The research findings demonstrate concerning temperature growth that ranges from o.76 to 1.62°C per decade, because this rapid temperature increase worsens environmental destruction. Rain levels have been decreasing throughout the years, except in the second decade, which shows a slightly higher rainfall rate. Most of the region receives between 105.25 to 110, 13 mm of the mean annual rainfall. The results revealed that the decline in rainfall level causes a loss in water balance of 169.72 million. Cubic meters in the third decade and 169.66 million. Cubic meters in the fourth decade. The reduced precipitation has led to rising evapotranspiration losses that amounted to-50.32 million m³ in the first decade, followed by 109.35 million m³ in the second decade, and finally reaching 119.66 million m³ in the third decade. The increased aridity index forces greater adverse impacts on vegetation density, which leads to faster land degradation and desertification. The widespread destruction of natural lands has reached more than 98% because of desertification processes and water shortages. The rising climate change dangers to the ecosystems require immediate adaptations for combating desertification and enhancing land administration methods.
This study investigated the efficacy of Sentinel-1 radar and Sentinel-2 optical data to classify Acacia cyclops and A. mearnsii species for each month of a year using the Extreme Gradient Boosting classifier. Sentinel-2 bands and their derivative indices yielded modest overall accuracies (69–77%) in detecting Acacia species across months. Comparable accuracies were obtained (75–79%) by adding Sentinel-1 radar data. The producer’s accuracies varied with month for both Acacia species (60–65%) when using Sentinel-2 products. Adding radar data improved these accuracies for nearly all months by 4–32%. In all cases, better accuracies were obtained in summer and autumn months. Variable importance comparison revealed that the Sentinel-2 visible bands, RedEdge bands and their derivative indices to be the highest contributors in the identification of the Acacia species. Although the radar data showed more importance in distinguishing Acacia from the other land cover groups than from each other, they did not improve the classification accuracies significantly. The inability of radar to differentiate the Acacia species was attributed to the lack of distinctive structural variation between the two species. The findings of this study show the importance of data acquisition time in the classification effort while more research is needed to exploit radar data.
Land use change in agriculture and forestry is a key sector in the IPCC reports on climate change, as it significantly impacts greenhouse gas emissions and carbon sequestration. Advances in remote sensing technology and new satellite generations provide opportunities for more frequent and detailed monitoring of land cover. This study focuses on analyzing and evaluating the effectiveness of machine learning models, including Random Forest (RF), Boosted Tree (BT), and Support Vector Machine (SVM), for land cover classification in Dak Nong. Sentinel-2 MSI and ALOS World 3D data were used in machine learning classification models. Results indicate that RF is the most effective classification model, achieving the highest overall accuracy of 78.6% with strong stability, and Kappa value of 0.75. BT classifier also performed well on dry-season imagery, while SVM exhibited lower accuracy due to its sensitivity to parameter settings. The findings highlight the importance of integrating multi-seasonal imagery with spectral indices and topographic data to improve classification accuracy in complex landscapes as well as their potential application to support AFOLU-related emissions inventory.
The prediction of soil moisture conditions using multispectral data from unmanned aerial vehicles (UAVs) has advantages over ground measurements in terms of costs and monitoring range. However, the prediction accuracy for moisture conditions using spectral data alone is low. In this study, relationships between water deficits and phenotypic characteristics in oats were evaluated and used to develop a UAV multispectral-based water prediction model. The vegetation indices NDRE (Normalized Difference Red Edge), CIG (Chlorophyll Index), and MCARI (Modified Chlorophyll Absorption in Reflectance Index) were highly correlated with oat yield. Based on a multipath analysis in the structural equation modeling framework, irrigation (p < 0.01), leaf area index (LAI) (p < 0.001), and SPAD (p < 0.001) had direct positive effects on NDRE. Three distinct machine learning approaches—linear regression (LR), random forest (RF), and artificial neural network (ANN) were employed to establish predictive models between the Normalized Difference Red Edge Index (NDRE) and soil water content (SWC). The linear regression model showed moderate correlation (R2 = 0.533). Machine learning approaches demonstrated markedly superior performance (RF: R2 = 0.828; ANN: R2 = 0.810). Nonlinear machine learning algorithms (RF and ANN) significantly outperform conventional linear regression in estimating SWC from spectral vegetation indices.
Forests provide essential ecosystem services, including biodiversity conservation, climate regulation, and livelihoods for millions of people worldwide. This study provides a comprehensive analysis of land-use and land-cover (LULC) changes with a focus on forest cover changes in Huế, central Vietnam, over the period from 1988 to 2022. Huế is a region of ecological and cultural significance, home to diverse forest ecosystems that play a critical role in water regulation, flood mitigation, and soil stabilization. The province’s forests also support rich biodiversity and provide vital resources for local livelihoods. By leveraging time-series Landsat observations and employing the continuous change detection and classification—spectral mixture analysis method, we synthesized multi-decadal geospatial data to track and categorize forest dynamics. The results indicate substantial LULC changes, highlighted by a significant reduction in stable forest cover from 58.3% in 1993 to 48.9% in 2022, accompanied by an increase in degraded forests from 11.7% to 18.0%. Peak forest loss was recorded at 1.5% by the end of 2013. The study discusses economic expansion, infrastructure development, climate variability, and agricultural intensification as key drivers of forest cover change. The findings underscore the importance of sustainable land management practices and provide actionable insights to inform policy development, particularly in regions with complex socio-economic and ecological interactions.
This paper presents a novel approach for vegetation stress assessment using a combination of Short-Wave Infrared (SWIR) and the Red, Green, and Blue bands of the 8-band multispectral (MS) images from the WorldView-3 satellite. The method aims to identify stressed vegetation based on changes in water content within plant leaves. Initially, the RGB image is created from the Red, Green, and Blue bands, while the SWIR image is resampled to ensure pixel-wise correspondence with the RGB image. This process allows accurate representation of RGB pixels in the SWIR domain. Furthermore, the Silhouette Coefficient method is used on the SWIR pixels to determine the optimal number of clusters (k) for the subsequent k-Means clustering step. The Silhouette Coefficient method evaluates the cohesion and separation of clusters before applying k-Means clustering on the SWIR pixels. The SWIR band’s sensitivity to leaf water content enables effective crop health assessment, as it reflects the physiological response of stomatal closure in stressed plants. The method is tested in experimental vineyards (Vitis vinifera L.), with the last two clusters used to pseudo-colour the RGB image, highlighting stress areas in yellow. Additionally, an Unmanned Aerial Vehicle (UAV) equipped with high-resolution visible-spectrum (RGB) and Thermal Infrared (TIR) imaging was deployed to capture the area shortly after the satellite image acquisition. Despite differences in resolution, satellite, and UAV images produced consistent stress detection results. The proposed method demonstrates the potential of integrating SWIR and RGB images for precision agriculture applications, offering a robust framework for assessing and monitoring crop health based on real-time satellite imagery. It contributes to the ongoing efforts in developing remote sensing techniques for efficient crop management and resource optimization.
Soil nutrient status assessment is a key aspect of crop management. Unlike the labor- and time-intensive conventional approach, precision farming techniques are expanding to ensure the uniformity of soil nutrients, enhance production, and alleviate economic pressure. In this study, the potentials of visible and near-infrared spectroscopy (Vis-NIRS), as non-imaging technology and multispectral imagery mounted on unmanned aerial vehicle (UAV) to predict plant-available (AP) and total phosphorus (TP) (P) were studied and compared. Soil samples were taken from a long-term experiment with contrasting fertilization treatments, and their spectra were recorded. Additionally, drone multispectral images were taken before and after soil tillage and seedbed preparation. The predicted available P content by Vis-NIRS was characterized by a cross-validation determination coefficient of R2cv = 0.82 and validation determination coefficient of R2v = 0.74, whereas the root mean square error for cross-validation (RMSEcv) and validation (RMSEv) were, respectively, 11.23 and 14.09 mg kg−1. The random forest (RF) model based on the textural and spectral features from multispectral images taken after seedbed preparation had the highest performances to predict plant-available P (R2v = 0.68, RMSEv = 13.65 mg kg−1, and RPIQv = 2.98), whereas the lowest prediction accuracy was obtained for total P prediction model after seedbed preparation (R2v = 0.40, RMSEv = 67.91, and RPIQv = 0.6). The effective wavelengths were around 450, 580, and 700 nm for predicting the available P fraction. Before soil tillage, the vegetation indices ranked high in the RF prediction models for available phosphorus (AP) and TP as compared to those developed after using tillage image-derived indices. In contrast, red-edge, red, and green bands, in addition to texture indices, were the most important predictors of soil available P following seedbed preparation. Our study suggests that soil tillage and seedbed preparation incorporate vegetation cover and alter soil roughness, resulting in a more homogeneous, smoother surface and higher accuracy for soil P prediction using UAV multispectral imagery.
Enhancing the spatial resolution of gypsiferous soil detection, as a valuable baseline information layer, is beneficial for investigating agroecological processes and tackling land degradation in semi-arid environments. This study evaluates the performance of PRISMA (PRecursore IperSpettrale della Missione Applicativa) and EnMAP (Environmental Mapping and Analysis Program) satellites in estimating soil gypsum content and compares models trained on satellite imagery versus lab data. To this end, 242 bare-soil samples were collected from southeast Iran. Gypsum content was measured using acetone precipitation, and spectral reflectance was acquired using the ASD (Analytical Spectral Devices)-Fieldspec 3 spectroradiometer. The gypsum content was retrieved by optical data using three approaches: narrowband indices, spectral absorption features, and machine learning (ML) algorithms. Four machine learning algorithms, including PLSR (Partial Least Squares Regression), RF (Random Forest), SVR (Support Vector Regression), and GPR (Gaussian Process Regression), achieved excellent performance (RPD > 2.5). The results showcased that the difference soil index (DSI) achieved the highest R² scores of 0.96 (ASD), 0.79 (PRISMA), and 0.84 (EnMAP), slightly outperforming the normalized difference gypsum ratio (NDGI) and ratio soil index (RSI). Comparing the shape indices’, the slope parameter (SLP) index outperformed the half-area parameter (HAP) index. PRISMA, with SVR (R² ≥ 0.83), and EnMAP, with PLSR (R² ≥ 0.85), demonstrated that hyperspectral satellites proved reliable in detecting gypsum content, yielding results comparable to ASD with detailed algorithms.
ResearchGate has not been able to resolve any references for this publication.