Search Results (38,201)

With global climate change, urbanization, and agricultural resource limitations, precision agriculture and crop monitoring are crucial worldwide. Integrating multi-source remote sensing data with deep learning enables accurate crop mapping, but selecting optimal network architectures remains challenging. To improve remote sensing-based fruit planting classification and support orchard management and rural revitalization, this study explored feature selection and network optimization. We proposed an improved CF-EfficientNet model (incorporating FGMF and CGAR modules) for fruit planting classification. Multi-source remote sensing data (Sentinel-1, Sentinel-2, and SRTM) were used to extract spectral, vegetation, polarization, terrain, and texture features, thereby constructing a high-dimensional feature space. Feature selection identified 13 highly discriminative bands, forming an optimal dataset, namely the preferred bands (PBs). At the same time, two classification datasets—multi-spectral bands (MS) and preferred bands (PBs)—were constructed, and five typical deep learning models were introduced to compare performance: (1) EfficientNetB0, (2) AlexNet, (3) VGG16, (4) ResNet18, (5) RepVGG. The experimental results showed that the EfficientNetB0 model based on the preferred band performed best in terms of overall accuracy (87.1%) and Kappa coefficient (0.677). Furthermore, a Fine-Grained Multi-scale Fusion (FGMF) and a Condition-Guided Attention Refinement (CGAR) were incorporated into EfficientNetB0, and the traditional SGD optimizer was replaced with Adam to construct the CF-EfficientNet architecture. The results indicated that the improved CF-EfficientNet model achieved high performance in crop classification, with an overall accuracy of 92.6% and a Kappa coefficient of 0.830. These represent improvements of 5.5 percentage points and 0.153, compared with the baseline model, demonstrating superiority in both classification accuracy and stability. Full article

The escalating pressure on water resources in agricultural regions has become a catalyst for water conflicts. The adoption of innovative approaches to estimate actual evapotranspiration (ETa) offers potential solutions to mitigate conflicts related to water usage. This research presents the application of a remote sensing-based methodology for estimating actual evapotranspiration (ETa) based on a two-source energy balance model (TSEB) for riparian vegetation in Nebraska, US using the Spatial EvapoTranspiration Modeling Interface (SETMI). Estimated results through SETMI and field data using the eddy covariance system (EC) considering the period 2008–2013 were used to validate the energy balance components and ETa. Modeled energy balance components showed a strong correlation to the ground data from EC, with ET presenting R2 equal to 0.96 and RMSE of 0.73 mm.d⁻¹. In 2012, the lowest adjusted crop coefficient (Kcadj) values were observed across all land covers, with a mean value of 0.49. The years 2013 and 2012, due to the dry conditions, recorded the highest accumulated ETa values (706 mm and 664 mm, respectively). Soybeans and corn exhibited the highest ETa values, recording 699 mm and 773 mm, respectively. Corn and soybeans, together accounting for a substantial portion of the land cover at 15% and 3%, respectively, play a significant role. Given that most fields cultivating these crops are irrigated, both pumped groundwater and surface water directly impact the water source of the Republican River. The SETMI model has generated appropriate estimated daily ETa values, thereby affirming the model’s utility as a tool for assisting water management and decision-makers in riparian zones. Full article

The main objective of the current work is to evaluate the effect of adding biochar obtained by pyrolysis of a mixture of greenhouse waste to agricultural soil, measuring its effectiveness as an amendment. A mixture of broccoli, zucchini, and tomato plant residues was pyrolyzed in a lab-scale reactor at 450 °C, obtaining a biochar yield of 35.6%. No carrier gas was used in the process. A thorough characterization of the biochar obtained was performed, including elemental and proximal analysis, density, pH, electrical conductivity, cation exchange capacity, surface area, and metal content. Since the raw material had a high percentage of ash (approximately 20%), the resulting biochar contained around 50% inorganic matter, with potassium and calcium being the major metals detected (10–11%). This biochar had a 29% fixed carbon content, a high heating value of 11.5 MJ kg⁻¹, a cation exchange capacity of 477 mmol kg⁻¹, and an electrical conductivity of 16 mS cm⁻¹.The biochar was mixed with greenhouse soil and fertilizer to form a substrate to grow bean seeds, the crop selected for the study. Different experiments were carried out, varying the biochar, fertilizer, and soil percentages. By adding 0.5% biochar to a substrate containing 1% fertilizer, the bean production was increased by 24.5%. It is worth noting that by adding only 0.5% biochar to soil, the bean production reached higher values than when adding 1% fertilizer. Biochar produced from the studied biomass improved the productivity of agricultural soils. The avoidance of selective collection by farmers as well as the non-use of carrier gas in the pyrolysis process made the implementation of the pyrolysis system in situ easier. Consequently, this research has great potential for practical application in modest agricultural areas. Full article

This study evaluated the potential of chicken by-products (hearts, gizzards, and skin) as functional raw materials for protein–fat emulsions to partially replace animal fat in pâtés. Five variants of pâté (PV1–PV5) were prepared, including a control without emulsion and four samples with increasing emulsion levels. Emulsions were formulated from chicken by-product mixtures and vegetable oil with potato starch, sodium bicarbonate, and salt to improve solubility and viscosity. The chemical composition of by-product mixtures varied with organ ratio: heart-rich mixtures supplied higher protein, supporting emulsion stability, whereas skin-rich mixtures contributed more fat for texture. Emulsion composition ranged from 6.6–8.1% protein, 19.1–28.4% fat, and 56.7–66.9% moisture. Functional properties depended on formulation balance: water-holding (58–67%), fat retention (70–83%), emulsifying capacity (50–62%), and stability (47–55%). Variant 5 achieved the most favorable combination of composition, stability, and viscosity. In pâtés, emulsion addition reduced protein and fat but increased ash and carbohydrate contents (p < 0.05), improving hydration and stability. Fat retention rose up to 83% and emulsion stability up to 62%. Drip loss declined markedly from 9.2% in the control to 3.6% in Variant 5, while yield stress decreased by 25%, producing softer, more spreadable products. Sensory evaluation favored emulsion-containing samples, with PV-5 scoring highest in texture and appearance. TBARS values rose with the amount of emulsion due to higher PUFA, but acid numbers increased more slowly, indicating reduced hydrolytic rancidity. Overall, pâté with 25% of emulsion offered the best balance of technological performance, sensory quality, and lipid stability, highlighting chicken by-products as sustainable emulsifiers in pâté production. Full article

In the lower and middle sections of the Yangtze River Basin Region (YRBR) in China, challenges posed by climate change and delayed harvesting of preceding crops have hindered the timely sowing of wheat, leading to an increasing prevalence of late-sown wheat fields. This trend has emerged as a significant impediment to achieving high and stable production of wheat in this area. During the growing seasons of 2022–2023 and 2023–2024, an unmanned aerial vehicle (UAV)-based multispectral camera was used to monitor different wheat materials at various growth stages under normal sowing treatment (M1) and late sowing with increased plant density (M2). By assessing yield loss, the wheat tolerance to late sowing was quantified and categorized. The correlation between the differential vegetation indices (D-VIs) and late sowing resistance was examined. The findings revealed that the J2-Logistic model demonstrated optimal classification performance. The precision values of stable type, intermediate type, and sensitive type were 0.92, 0.61, and 1.00, respectively. The recall values were 0.61, 0.92, and 1.00. The mean average precision (mAP) of the model was 0.92. This study proposes a high-throughput and low-cost evaluation method for wheat tolerance to late sowing, which can provide a rapid predictive tool for screening suitable varieties for late sowing and facilitating late-sown wheat breeding. Full article

Planting concrete is a composite material used for erosion control on roadbed side slopes. However, excessive concrete thickness creates an unfavorable environment that prevents the survival of some grass species. This study aims to optimize the thickness and grass species of planting concrete. The stress scenarios of planting concrete, including pedestrian loads and frost heave stress, were analyzed. The maximum internal stress under pedestrian loads and the frost heave stress during freezing were determined using finite element analysis and frost heave tests, respectively. Nine groups of planting concrete specimens with different porosities and water–cement ratios were prepared and tested. The measured compressive and splitting tensile strengths were compared with the maximum stress of planting concrete to determine the optimal mix proportion. Using the optimal mix, planting concrete specimens with three thicknesses were prepared, and six common grass species were selected for planting experiments. Vegetation coverage, plant height, root length, root number, and root biomass were measured for each grass species at three thicknesses to determine the optimal thickness and grass species. The results show that the maximum tensile stress of planting concrete under pedestrian loads and frost heave stress is 0.86 MPa. The optimal porosity and water–cement ratio are determined to be 30% and 0.33, respectively. Ryegrass exhibits the highest vegetation coverage and plant height, thereby determining that ryegrass is the optimal grass species. Planting concrete of 4 cm thickness demonstrates the best root development, thereby determining that 4 cm is the optimal thickness. These findings provide a scientific basis for optimizing ecological slope protection with planting concrete. Full article

Accurate and timely crop yield estimation is essential for effective agricultural management and global food security, particularly for winter wheat. This study aimed to assess the effectiveness of EnMAP hyperspectral imagery in combination with machine learning and deep learning models for winter wheat yield prediction in Hungary. Using EnMAP images from February and May 2023, along with ground truth yield data from four fields, we derived 10 distinct vegetation indices. Random Forest, Gradient Boosting, and Multilayer Perceptron algorithms were employed, and model performance was evaluated using Mean Absolute Error (MAE) and Coefficient of Determination (R²) values. The results consistently demonstrated that integrating multi-temporal data significantly enhanced predictive accuracy, with the MLP model achieving an R² of 0.79 and an MAE of 0.27, notably outperforming single-date predictions. Shortwave infrared (SWIR) indices were particularly critical for early-season yield estimations. This research highlights the substantial potential of hyperspectral data and advanced machine learning techniques in precision agriculture, emphasizing the promising role of future missions such as CHIME in further refining and expanding yield estimation capabilities. Full article

Heracleum persicum Desf. ex Fischer, a species of the Apiaceae family, is endemic to Iran and has been historically utilized as a spice, condiment, and medicinal plant. The plant produces seeds that represent a potential new source of vegetable oil. In this study, the oil from these seeds was extracted using a solvent, and its physical, chemical, and nutritional properties were investigated. The oil extraction yield was determined to be 12.62%. Oleic acid (61.11%) and linoleic acid (25.84%) were identified as the predominant fatty acids in the extracted oil. Among its phytosterols, beta-sitosterol (65.6%) and stigmasterol (14.0%) were the most abundant. Furthermore, this oil exclusively contained alpha-tocopherol at a relatively high concentration (1610.9 ppm). The chlorophyll and carotenoid contents of the extracted oil were 28.34 mg/kg and 4.95 mg/kg, respectively. Regarding its nutritional indices, the atherogenic index, thrombogenic index, and hypocholesterolemic to hypercholesterolemic ratio were 0.13, 0.24, and 9.77, respectively. In conclusion, considering its unique oil composition and qualitative characteristics, this oil holds promise as a novel source of vegetable oil and a valuable byproduct of Heracleum persicum. Full article

While prior studies on LULC change in the Ewa region of O’ahu Hawai’i have explored the policy implications and the rapid infrastructure changes on land use, very few studies have attempted to fully integrate both of these changes in a comprehensive, long-term study of island geographies. Most of the past work has focused on general trends or short-term fluctuations, without considering the play of nuanced interactions between urbanization policies, transit-oriented development, and constraints of Hawai’i’s finite land resources. To fill these gaps, this study examines LULC changes in Ewa, Honolulu between 2002 and 2022, which emphasizes the impacts of strategic urban policies and infrastructure development, such as the Honolulu Skyline Rail Transit System. Using Landsat 7 satellite imagery and random forest machine learning classifier, in Google Earth Engine, LULC is classified into urban, forest, vegetation, barren, and water with classification accuracy of over 85%. The results highlight trends of significant urban growth especially after 2010, and highlight key issues of tension between housing demands and environmental sustainability in O’ahu. This study highlights the potential of integrated remote sensing and policy analysis for informing sustainable development in land-constrained island settings, and advocates for planning frameworks that more effectively balance growth, ecosystem stewardship, and community welfare. Full article

Post-fire soil and vegetation changes can intensify erosion and sediment yield by altering the factors controlling the runoff–infiltration balance. Erosion barriers (EBs) are widely used in hydrological and forest restoration to mitigate erosion, reduce sediment transport, and promote vegetation recovery. However, precise spatial assessments of their effectiveness remain scarce, requiring validation through operational methodologies. This study evaluates the impact of EB on post-fire vegetation recovery at two temporal and spatial scales: (1) Remotely Piloted Aircraft System (RPAS) imagery, acquired at high spatial resolution but limited to a single acquisition date coinciding with the field flight. These data were captured using a MicaSense RedEdge-MX multispectral camera and an RGB optical sensor (SODA), from which NDVI and vegetation height were derived through aerial photogrammetry and digital surface models (DSMs). (2) Sentinel-2 satellite imagery, offering coarser spatial resolution but enabling multi-temporal analysis, through NDVI time series spanning four consecutive years. The study was conducted in the area of the Luna Fire (northern Spain), which burned in July 2015. A paired sampling design compared upstream and downstream areas of burned wood stacks and control sites using NDVI values and vegetation height. Results showed slightly higher NDVI values (0.45) upstream of the EB (p < 0.05), while vegetation height was, on average, ~8 cm lower than in control sites (p > 0.05). Sentinel-2 analysis revealed significant differences in NDVI distributions between treatments (p < 0.05), although mean values were similar (~0.32), both showing positive trends over four years. This study offers indirect insight into the functioning and effectiveness of EB in post-fire recovery. The findings highlight the need for continued monitoring of treated areas to better understand environmental responses over time and to inform more effective land management strategies. Full article

Under global warming, drought frequency and its severity have risen notably, posing considerable challenges to vegetation growth. Central Asia (CA), recognized as the largest non-zonal arid zone globally, features dryland ecosystems that are particularly vulnerable to drought stress. This research examines how plant life in CA reacts to prolonged dry spells by analyzing multiple datasets, including drought indices and satellite-derived NDVI measurements, spanning four decades (1982–2022). This study also delves into the compound impact of drought, revealing how its influence on vegetation unfolds through both cumulative stress and delayed ecological responses. Based on the research results, the vegetation coverage in CA exhibited a notable rising tendency from 1982 to 1998. Specifically, it increased at a rate of 4 × 10⁻³ per year (p < 0.05). On the other hand, the direction of this trend shifted to a downward one during the period from 1999 to 2022. During this latter phase, the vegetation coverage decreased at a rate of −4 × 10⁻³ per year (p > 0.05). Vegetation changes in the study area underwent a fundamental reversal around 1998, shifting from widespread greening during 1982–1998 to persistent browning during 1999–2022. Specifically, 98.6% of the region underwent pronounced summer drought stress, which triggered a substantial rise in vegetation browning. The vegetation response to the accumulated and lagged effects of drought varied across seasons, with summer exhibiting the strongest sensitivity, followed by spring and autumn. The lagged effect of drought predominantly influences the vegetation during the growing season and spring, affecting 59.44% and 79.27% of CA, respectively. In contrast, the accumulated effect of drought is more prominent in summer and autumn, affecting 54.92% and 56.52% of CA. These insights offer valuable guidance for ecological restoration initiatives and sustainable management of dryland ecosystems. Full article

Chrysanthemum (Chrysanthemum morifolium Ramat.), a typical short-day plant (SDP), relies on photoperiod and light quality signals to regulate flowering and growth. Red light interruptions inhibit its flowering, whereas supplemental blue light can counteract this inhibitory effect. To investigate how “high-blue/low-red” mixed light (RBL) regulates chrysanthemum flowering and growth, we treated ‘Gaya Glory’ plants with 4 h of supplemental or night-interruptional RBL (S-RBL4 or NI-RBL4, 0 or 30 ± 3 μmol m⁻² s⁻¹ PPFD) under 10 h short-day and 13 h long-day conditions (SD10 and LD13; white light, WL; 300 ± 5 μmol m⁻² s⁻¹ PPFD), recorded as SD10, SD10 + S-RBL4, SD10 + NI-RBL4, LD13, LD13 + S-RBL4, and LD13 + NI-RBL4, respectively. Under SD10 conditions, S-RBL4 promoted flowering and enhanced nutritional quality, whereas NI-RBL4 suppressed flowering. Under LD13 conditions, both treatments alleviated flowering inhibition, with S-RBL4 exhibiting a more pronounced inductive effect. Chrysanthemums displayed superior vegetative growth and physiological metabolism under LD13 compared to SD10, as evidenced by higher photosynthetic efficiency, greater carbohydrate accumulation, and more robust stem development. Furthermore, S-RBL4 exerted a stronger regulatory influence than NI-RBL4 on photosynthetic traits, the activities of sugar metabolism-related enzymes, and gene expression. The photoperiodic flowering of chrysanthemum was coordinately regulated by the photoreceptor-mediated and sugar-induced pathways: CmCRY1 modulated the expression of florigenic genes (CmFTLs) and anti-florigenic gene (CmAFT) to transmit light signals, while S-RBL4 activated sucrose-responsive flowering genes CmFTL1/2 through enhanced photosynthesis and carbohydrate accumulation, thereby jointly regulating floral initiation. The anti-florigenic gene CmTFL1 exhibited dual functionality—its high expression inhibited flowering and promoted lateral branch and leaf growth, but only under sufficient sugar availability, indicating that carbohydrate status modulates its functional activity. Full article

The Xujiahe Formation (FM) is a significant source rock layer in the Sichuan Basin. In recent years, a growing number of scholars believe that the shale gas potential of the Xujiahe Formation is equally substantial, with the first member of the formation being the richest resource. The deposition of Member (Mbr) 1 of Xujiahe FM represents the first and most extensive transgression event within the entire Xujiahe Formation. This study investigates the sedimentary environment and organic matter (OM) enrichment mechanisms of the dark mud shales in the Mbr1 of Xujiahe FM on the southeastern margin of the Sichuan Basin, utilizing methods such as elemental geochemistry and organic geochemistry analyses. The results indicate that these dark mud shales possess a relatively high OM abundance, averaging 2.20% and reaching a maximum of 6.22%. The OM is primarily Type II₂ to Type III. Furthermore, the paleoclimate during the Mbr1 period in the study area was warm and humid with lush aquatic vegetation. Intense weathering and ample precipitation transported large amounts of nutrients into the lacustrine/marine basin, promoting the growth and reproduction of algae and terrestrial plants. Correlation analysis between the Total Organic Carbon (TOC) content and various geochemical proxies in the Mbr1 mud shales suggests that OM enrichment in the study area was primarily controlled by the climate and sedimentation rate; substantial OM accumulation occurred only with abundant terrigenous OM input and a relatively high sedimentation rate. Redox conditions, primarily productivity, and terrigenous detrital input acted as secondary factors, collectively modulating OM enrichment. Event-driven transgressions also played an important role in creating conditions favorable for OM preservation. Synthesizing the influence of these multiple factors on OM enrichment, this study proposes two distinct composite models for OM enrichment, dominated by climate and sedimentation rate. Full article

Understanding the relationship between vegetation transpiration and root-zone soil moisture is essential for assessing eco-hydrological processes under global change. However, past studies often looked at only one side, and traditional field observations have the limitations of high cost and poor spatial–temporal continuity. Using daily GLDAS Catchment data from 2004 to 2023, this study investigates the spatiotemporal patterns and interactions between vegetation transpiration and root-zone soil moisture in Fujian Province. The results show that transpiration decreased before 2016 and increased thereafter temporally, with an overall spatial decline. In contrast, the root-zone soil moisture increased before 2016 and then decreased temporally, showing overall spatial growth with significant heterogeneity. A strong negative correlation was found between vegetation transpiration and root-zone soil moisture, particularly in summer and autumn. Among them, vegetation transpiration strongly influenced soil moisture, with increases (or decreases) in transpiration corresponding to decreases (or increases) in soil moisture. Moreover, transpiration changes preceded those in soil moisture, and a significant resonance relationship with a 1- to 2-year cycle was identified. These findings offer insights into the vegetation–soil moisture dynamics in humid subtropical regions, supporting eco-hydrological management under climate change. Full article

Ensuring the structural continuity and completeness of road networks in high-resolution remote sensing imagery remains a major challenge for current deep learning methods, especially under conditions of occlusion caused by vegetation, buildings, or shadows. To address this, we propose a novel post-processing enhancement framework that improves the connectivity and accuracy of initial road extraction results produced by any segmentation model. The method employs a dual-stream encoder architecture, which jointly processes RGB images and preliminary road masks to obtain complementary spatial and semantic information. A core component is the MAF (Multi-Modal Attention Fusion) module, designed to capture fine-grained, long-range, and cross-scale dependencies between image and mask features. This fusion leads to the restoration of fragmented road segments, the suppression of noise, and overall improvement in road completeness. Experiments on benchmark datasets (DeepGlobe and Massachusetts) demonstrate substantial gains in precision, recall, F1-score, and mIoU, confirming the framework’s effectiveness and generalization ability in real-world scenarios. Full article