Search Results (359)

Precision irrigation plays a crucial role in managing crop production in a sustainable and environmentally friendly manner. This study builds on the results of the GreenWaterDrone project, aiming to estimate, in real time, the actual water requirements of crop fields using the crop water stress index, integrating infrared canopy temperature, air temperature, relative humidity, and thermal and near-infrared imagery. To achieve this, a state-of-the-art aerial micrometeorological station (AMMS), equipped with an infrared thermal sensor, temperature–humidity sensor, and advanced multispectral and thermal cameras is mounted on an unmanned aerial system (UAS), thus minimizing crop field intervention and permanently installed equipment maintenance. Additionally, data from satellite systems and ground micrometeorological stations (GMMS) are integrated to enhance and upscale system results from the local field to the regional level. The research was conducted over two years of pilot testing in the municipality of Trifilia (Peloponnese, Greece) on pilot potato and watermelon crops, which are primary cultivations in the region. Results revealed that empirical irrigation applied to the rhizosphere significantly exceeded crop water needs, with over-irrigation exceeding by 390% the maximum requirement in the case of potato. Furthermore, correlations between high-resolution remote and proximal sensors were strong, while associations with coarser Landsat 8 satellite data, to upscale the local pilot field experimental results, were moderate. By applying a comprehensive model for upscaling pilot field results, to the overall Trifilia region, project findings proved adequate for supporting sustainable irrigation planning through simulation scenarios. The results of this study, in the context of the overall services introduced by the project, provide valuable insights for farmers, agricultural scientists, and local/regional authorities and stakeholders, facilitating improved regional water management and sustainable agricultural policies. Full article

The efficient and precise identification of urban slums is a significant challenge for urban planning and sustainable development, as their morphological diversity and complex spatial distribution make it difficult to use traditional remote sensing inversion methods. Current deep learning (DL) methods mainly face challenges such as limited receptive fields and insufficient sensitivity to spatial locations when integrating multi-source remote sensing data, and high-quality datasets that integrate multi-spectral and geoscientific indicators to support them are scarce. In response to these issues, this study proposes a DL model (coordinate-attentive U²-DeepLab network [CAU²DNet]) that integrates multi-source remote sensing data. The model integrates the multi-scale feature extraction capability of U²-Net with the global receptive field advantage of DeepLabV3+ through a dual-branch architecture. Thereafter, the spatial semantic perception capability is enhanced by introducing the CoordAttention mechanism, and ConvNextV2 is adopted to optimize the backbone network of the DeepLabV3+ branch, thereby improving the modeling capability of low-resolution geoscientific features. The two branches adopt a decision-level fusion mechanism for feature fusion, which means that the results of each are weighted and summed using learnable weights to obtain the final output feature map. Furthermore, this study constructs the São Paulo slums dataset for model training due to the lack of a multi-spectral slum dataset. This dataset covers 7978 samples of 512 × 512 pixels, integrating high-resolution RGB images, Normalized Difference Vegetation Index (NDVI)/Modified Normalized Difference Water Index (MNDWI) geoscientific indicators, and POI infrastructure data, which can significantly enrich multi-source slum remote sensing data. Experiments have shown that CAU²DNet achieves an intersection over union (IoU) of 0.6372 and an F1 score of 77.97% on the São Paulo slums dataset, indicating a significant improvement in accuracy over the baseline model. The ablation experiments verify that the improvements made in this study have resulted in a 16.12% increase in precision. Moreover, CAU²DNet also achieved the best results in all metrics during the cross-domain testing on the WHU building dataset, further confirming the model’s generalizability. Full article

Climate change has intensified drought stress, threatening global food security by affecting sensitive crops like maize (Zea mays). This study evaluated the potential of Antarctic fungal endophytes (Penicillium chrysogenum and P. brevicompactum) to enhance maize drought tolerance under field conditions with different irrigation regimes. Drought stress reduced soil moisture to 59% of field capacity. UAV-based multispectral imagery monitored plant physiological status using vegetation indices (NDVI, NDRE, SIPI, GNDVI). Inoculated plants showed up to two-fold higher index values under drought, indicating improved stress resilience. Physiological analysis revealed increased photochemical efficiency (0.775), higher chlorophyll and carotenoid contents (45.54 mg/mL), and nearly 80% lower lipid peroxidation in inoculated plants. Lower proline accumulation suggested better water status and reduced osmotic stress. Secondary metabolites such as phenolics, flavonoids, and anthocyanins were elevated, particularly under well-watered conditions. Antioxidant enzyme activity shifted: SOD, CAT, and APX were suppressed, while POD activity increased, indicating reprogrammed oxidative stress responses. Yield components, including cob weight and length, improved significantly with inoculation under drought. These findings demonstrate the potential of Antarctic endophytes to enhance drought resilience in maize and underscore the value of integrating microbial biotechnology with UAV-based remote sensing for sustainable crop management under climate-induced water scarcity. Full article

Non-destructive monitoring of chlorophyll content through Soil Plant Analysis Development (SPAD) values is essential for precision agriculture in water-limited regions. However, current estimation methods using spectral information alone face significant limitations in sensitivity and transferability under variable irrigation conditions. While integrating canopy structural parameters with spectral data represents a promising solution, systematic investigation of this approach throughout the entire growth cycle of spring wheat under different irrigation regimes remains limited. This study evaluated three machine learning algorithms (Random Forest, Support Vector Regression, and Multi-Layer Perceptron) for SPAD estimation in spring wheat cultivated in the Hetao Irrigation District. Using a split-plot experimental design with two irrigation treatments (conventional: four irrigations; limited: two irrigations) and five nitrogen levels (0–300 kg·ha⁻¹), we analyzed ten vegetation indices derived from Unmanned Aerial Vehicle (UAV) multispectral imagery, with and without Leaf Area Index (LAI) integration, across six growth stages. Results demonstrated that incorporating LAI significantly improved SPAD estimation accuracy across all algorithms, with Random Forest exhibiting the most substantial enhancement (R² increasing from 0.698 to 0.842, +20.6%; RMSE decreasing from 5.025 to 3.640, −27.6%). Notably, LAI contributed more significantly to SPAD estimation under limited irrigation conditions (R² improvement: +17.6%) compared to conventional irrigation (+11.0%), indicating its particular value for chlorophyll monitoring in water-stressed environments. The Green Normalized Difference Vegetation Index (GNDVI) emerged as the most important predictor (importance score: 0.347), followed by LAI (0.213), confirming the complementary nature of spectral and structural information. These findings provide a robust framework for non-destructive SPAD estimation in spring wheat and highlight the importance of integrating canopy structural information with spectral data, particularly in water-limited agricultural systems. Full article

The outdoor spectral detection of winter jujube quality is affected by complex ambient light and surface heterogeneity, resulting in limited inversion accuracy. To address this problem, this study proposes a correction method for outdoor spectral inversion based on the bidirectional polarization reflectance distribution function (BPDF) model. It was used to enhance the detection accuracy of water content and soluble solid (SSC) content of winter jujube. Experimentally, 900–1750 nm hyperspectral data of ripe winter jujube samples were collected at non-polarization and 0°, 45°, 90°, and 135° polarization azimuths. The spectra were inverted using four semi-empirical BPDF models, Nadal–Breon, Litvinov, Maignan and Xie–Cheng, and the corrected spectra were obtained by mean fusion. The quality prediction models are subsequently combined with the competitive adaptive reweighting algorithm (CARS) and partial least squares (PLS). The results showed that the modified spectra significantly optimized the prediction performance. The prediction set correlation coefficients (Rp) of the water content and SSC models were improved by 10–30% compared with the original spectra. The percentage of models with RPIQ values greater than 2 increased from 40% to 60%. Among them, the Litvinov model performs outstandingly in the direction of no polarization and 135° polarization, with the highest Rp of 0.8829 for water content prediction and RPIQ of 2.54. The Xie–Cheng model has an RPIQ of 2.64 for SSC prediction at 90° polarization, which shows the advantage of sensitivity to the deeper constituents. The different models complemented each other in multi-polarization scenarios. The Nadal–Breon model was suitable for epidermal reflection-dominated scenarios, and the Maignan model efficiently coupled epidermal and internal moisture characteristics through the moisture sensitivity index. The study verifies the effectiveness of the spectral correction method based on the BPDF model for outdoor quality detection of winter jujube, which provides a new path for the spectral detection of agricultural products in complex environments. In the future, it is necessary to further optimize the dynamic adjustment mechanism of the model parameters and improve the ability of environmental interference correction by combining multi-source data fusion. Full article

Cultivating crops in the hot, arid conditions of the Arabian Peninsula often requires irrigation with brackish water, which exposes plants to salinity and heat stress. Timely, cost-effective monitoring of plant health can significantly enhance crop management. In this context, remote sensing techniques offer promising alternatives. This study evaluates several low-cost, ground-level remote sensing methods and compares them with benchmark analytical techniques for assessing salt stress in two economically important woody species, moringa and pomegranate. The species were irrigated under three salinity levels: low (2 dS m⁻¹), medium (5 dS m⁻¹), and high (10 dS m⁻¹). Remote sensing tools included RGB, multispectral, and thermal cameras mounted on selfie sticks for canopy imaging, as well as portable leaf pigment and chlorophyll fluorescence meters. Analytical benchmarks included sodium (Na) accumulation, carbon isotope composition (δ¹³C), and nitrogen (N) concentration in leaf dry matter. As salinity increased from low to medium, canopy temperatures, vegetation indices, and δ¹³C values rose. However, increasing salinity from medium to high levels led to a rise in Na accumulation without further significant changes in other remote sensing and analytical parameters. In moringa and across the three salinity levels, the Normalized Difference Red Edge (NDRE) and leaf chlorophyll content on an area basis showed significant correlations with δ¹³C (r = 0.758, p < 0.001; r = 0.423, p < 0.05) and N (r = 0.482, p < 0.01; r = 0.520, p < 0.01). In pomegranate, the Normalized Difference Vegetation Index (NDVI) and chlorophyll were strongly correlated with δ¹³C (r = 0.633, p < 0.01 and r = 0.767, p < 0.001) and N (r = 0.832, p < 0.001 and r = 0.770, p < 0.001). Remote sensing was particularly effective at detecting plant responses between low and medium salinity, with stronger correlations observed in pomegranate. Full article

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. Full article

Soybean cultivation plays a crucial role in the global food system, providing raw materials for both the food and feed industries. To enhance cultivation efficiency, plant biostimulants are used to improve metabolism and stimulate growth. A key aspect of modern cultivation is the ability to rapidly and non-invasively assess crop status. One such method involves the use of drones equipped with multispectral cameras. This paper presents the results of an experimental study on soybean cultivation involving a natural biostimulant in the form of Epilobium angustifolium extract (commonly known as fireweed) and a commercial seaweed-based biostimulant, Kelpak. The research was conducted at an experimental farm in eastern Poland. The effectiveness of the preparations was evaluated using a drone-mounted multispectral camera. Changes in the values of selected spectral indices were analyzed: the Normalized Difference Red Edge Index (NDRE), the Leaf Chlorophyll Index (LCI), and the Optimized Soil-Adjusted Vegetation Index (OSAVI). The study included a control group treated with pure water. Mathematical and statistical analyses of the mean values and standard deviations of the indices were conducted. The results demonstrated that multispectral scanning allows for the detection of significant differences between the effects of the E. angustifolium extract, the seaweed-based biostimulant, and the water control. These findings confirm the utility of this method for assessing the effectiveness of biostimulant applications in soybean cultivation. Full article

Estimating wheat traits based on spectral reflectance measurements and machine learning remains challenging due to the large datasets required for model training and testing. To overcome this limitation, a simulated dataset was generated using the radiative transfer model (RTM) PROSAIL and inverted based on an artificial neural network (ANN). Field experiments were conducted in Eastern Austria to measure spectral reflectance and destructively sample plants to measure the wheat traits plant area index (PAI), nitrogen yield (NY), canopy water content (CWC), and above-ground dry matter (AGDM). Four ANN-based RTM inversion models were setup, which varied in their spectral resolution, hyperspectral or multispectral, and the inclusion or exclusion of background soil spectra correction. The models were also compared to a simple vegetation index approach using Normalized Difference Vegetation Index (NDVI) and Normalized Difference Red-Edge (NDRE). The RTM inversion model with hyperspectral input data and background soil spectra correction was the best among all tested models for estimating wheat traits during the vegetative developmental stages (PAI: R² = 0.930, RRMSE = 17.9%; NY: R² = 0.908, RRMSE = 14.4%; CWC: R² = 0.967, RRMSE = 17.0%) as well as throughout the whole growing season (PAI: R² = 0.845, RRMSE = 27.7%; CWC: R² = 0.884, RRMSE = 20.0%; AGDM: R² = 0.960, RRMSE = 13.7%). Many models presented in this study provided suitable estimations of the relevant wheat traits PAI, NY, CWC, and AGDM for application in agronomy, breeding, and crop sciences in general. Full article

This study aimed to address the challenge of monitoring and managing soil moisture in dryland agriculture with supplemental irrigation under increasingly extreme climate conditions. Using unmanned aerial vehicles (UAVs) equipped with hyperspectral sensors, we collected imagery of wheat fields on Kinmen Island at various growth stages. The Modified Perpendicular Drought Index (MPDI) was calculated to quantify soil drought conditions. Simultaneously, soil samples were collected to measure the actual soil moisture content. These datasets were used to develop a Gradient Boosting Regression (GBR) model to estimate soil moisture across the entire field. The resulting AI-based model can guide decisions on the timing and scale of supplemental irrigation, ensuring water is applied only when needed during crop growth. Furthermore, MPDI values and wheat spike samples were used to construct another GBR model for yield prediction. When applying MPDI values from multispectral imagery collected at a similar stage in the following year, the model achieved a prediction accuracy of over 90%. The proposed approach offers a reliable solution for enhancing the resilience and productivity of dryland crops under climate stress and demonstrates the potential of integrating remote sensing and machine learning in precision water management. Full article

A thorough understanding of the consequences of urbanization can be significantly advanced by examining urban environmental dynamics at high spatial and temporal resolutions. This study evaluates eco-environmental quality and investigates the underlying drivers of urban greening within the functional units of Haikou, a tropical coastal city located on Hainan Island, China, using advanced techniques from Landsat and Google Earth imagery. Ecological index and land use change analyses were conducted using Landsat 5 (TM) imagery for 2010 and Landsat 8 (OLI) imagery for 2020. In addition, Google Earth imagery was used to interpret the driving factors influencing urban functional units (UFUs) in 2010 and 2020. Spatial and temporal environmental changes were quantitatively assessed. Multi-spectral Landsat 8 data at a 30 m resolution were used to construct a remote sensing ecological index (RSEI) to assess Haikou’s ecological condition. Land use impacts on eco-environmental quality were evaluated through RSEI values from 2010 to 2020, showing that eco-environmental quality improved over time, revealing a gradual improvement over time. Land use across 190 UFUs from 2010 to 2020 was categorized into five types: trees and shrubs, herbs, built-up areas, sandy lands, and water bodies. The primary drivers of greening percentage in each UFU were identified as housing prices, maintenance duration, and construction age. The most significant changes in land cover type were observed in the herb areas. Similarly, maintenance duration emerged as the most influential factor driving changes in urban green space (UGS). In conclusion, this study offers valuable insights for future urban planning and improvements in eco-environmental quality in Haikou, Hainan Island, China. Full article

Floods caused by extreme weather events critically impact human and natural systems. Remote sensing can be a very useful tool in mapping these impacts. However, processing and analyzing satellite imagery covering extensive periods is computationally intensive and time-consuming, especially when data from different sensors need to be integrated, hampering its operational use. To address this issue, the present study focuses on mapping flooded areas and analyzing the impacts of the 2023 Storm Daniel flood in the Thessaly region (Greece), utilizing Earth Observation and GIS methods. The study uses multiple Sentinel-1, Sentinel-2, and Landsat 8/9 satellite images based on backscatter histogram statistics thresholding for SAR and Modified Normalized Difference Water Index (MNDWI) for multispectral images to delineate the extent of flooded areas triggered by the 2023 Storm Daniel in Thessaly region (Greece). Cloud computing on the Google Earth Engine (GEE) platform is utilized to process satellite image acquisitions and track floodwater evolution dynamics until the complete drainage of the area, making the process significantly faster. The study examines the usability and transferability of the approach to evaluate flood impact through land cover, linear infrastructure, buildings, and population-related geospatial datasets. The results highlight the vital role of the proposed approach of integrating remote sensing and geospatial analysis for effective emergency response, disaster management, and recovery planning. Full article

Precision irrigation requires reliable estimates of crop evapotranspiration (ET) using site-specific crop and weather data inputs. Such estimates are needed at high resolutions which have been minimally explored for heterogeneous crops such as orchards. In addition, weather information for estimating ET is very often selected from sources that do not represent conditions like heterogeneous site-specific conditions. Therefore, a study was conducted to map geospatial ET and transpiration (T) of a high-density modern apple orchard using high-resolution aerial imagery, as well as to quantify the impact of site-specific weather conditions on the estimates. Five campaigns were conducted in the 2020 growing season to acquire small unmanned aerial system (UAS)-based thermal and multispectral imagery data. The imagery and open-field weather data (solar radiation, air temperature, wind speed, relative humidity, and precipitation) inputs were used in a modified energy balance (UASM-1 approach) extracted from the Mapping ET at High Resolution with Internalized Calibration (METRIC) model. Tree trunk water potential measurements were used as reference to evaluate T estimates mapped using the UASM-1 approach. UASM-1-derived T estimates had very strong correlations (Pearson correlation [r]: 0.85) with the ground-reference measurements. Ground reference measurements also had strong agreement with the reference ET calculated using the Penman–Monteith method and in situ weather data (r: 0.89). UASM-1-based ET and T estimates were also similar to conventional Landsat-METRIC (LM) and the standard crop coefficient approaches, respectively, showing correlation in the range of 0.82–0.95 and normalized root mean square differences [RMSD] of 13–16%. UASM-1 was then modified (termed as UASM-2) to ingest a locally calibrated leaf area index function. This modification deviated the components of the energy balance by ~13.5% but not the final T estimates (r: 1, RMSD: 5%). Next, impacts of representative and non-representative weather information were also evaluated on crop water uses estimates. For this, UASM-2 was used to evaluate the effects of weather data inputs acquired from sources near and within the orchard block on T estimates. Minimal variations in T estimates were observed for weather data inputs from open-field stations at 1 and 3 km where correlation coefficients (r) ranged within 0.85–0.97 and RMSD within 3–13% relative to the station at the orchard-center (5 m above ground level). Overall, the results suggest that weather data from within 5 km radius of orchard site, with similar topography and microclimate attributes, when used in conjunction with high-resolution aerial imagery could be useful for reliable apple canopy transpiration estimation for pertinent site-specific irrigation management. Full article

Satellite microwave-sounding radiometer data assimilation under clear-sky conditions typically requires the exclusion of precipitation-affected field-of-view (FOV) regions. However, the traditional scatter index (SI) and cloud liquid water path (CLWP)-based precipitation sounding algorithms from earlier NOAA microwave sounders are built on window channels which are not available from FY-3C/D MWTS-II. To address this limitation, this study establishes a nonlinear relationship between multispectral visible/infrared data from the FY-2F geostationary satellite and microwave sounding channels using an artificial intelligence (AI)-driven approach. The methodology involves three key steps: (1) The spatiotemporal integration of FY-2F VISSR-derived products with NOAA-19 AMSU-A microwave brightness temperatures was achieved through the GEO-LEO pixel fusion algorithm. (2) The fused observations were used as a training set and input into a random forest model. (3) The performance of the RF_SI method was evaluated by using individual cases and time series observations. Results demonstrate that the RF_SI method effectively captures the horizontal distribution of microwave scattering signals in deep convective systems. Compared with those of the NOAA-19 AMSU-A traditional SI and CLWP-based precipitation sounding algorithms, the accuracy and sounding rate of the RF_SI method exceed 94% and 92%, respectively, and the error rate is less than 3%. Also, the RF_SI method exhibits consistent performance across diverse temporal and spatial domains, highlighting its robustness for cross-platform precipitation screening in microwave data assimilation. Full article

The Cheremskyi Nature Reserve, situated in the Volyn region of Ukraine, constitutes a pivotal element of the European ecological network, distinguished by its distinctive mosaic of peatlands, bogs, and floodplain forests. This study utilizes Sentinel-2 satellite imagery and the Google Earth Engine (GEE) to assess the spatiotemporal patterns of various vegetation indices (NDVI, EVI, SAVI, MSAVI, GNDVI, NDRE, NDWI) from 2017 to 2024. The study aims to select the most suitable combination of vegetation spectral indices for future research. The analysis reveals significant negative trends in NDVI, SAVI, MSAVI, GNDVI, and NDRE, indicating a decline in vegetation health, while NDWI shows a positive trend, suggesting an increased vegetation water content. Correlation analysis underscores robust interrelationships among the indices, with NDVI and SAVI identified as the most significant through random forest feature importance analysis. Principal component analysis (PCA) further elucidates the primary axes of variability, emphasizing the complex interplay between vegetation greenness and moisture content. The findings underscore the utility of multi-index analyses in enhancing predictive capabilities for ecosystem monitoring and support targeted conservation strategies for the sustainable management of the Cheremskyi Nature Reserve. Full article