Search Results (51)

Utilizing remote sensing models to monitor apple orchards facilitates the industrialization of agriculture and the sustainable development of rural land resources. This study enhanced the DeepLabv3+ model to achieve superior performance in apple orchard identification by incorporating ResNet, optimizing the algorithm, and adjusting hyperparameter configuration using the PIE-Engine cloud platform. GF-6 PMS images were used as the data source, and Qixia City was selected as the case study area for demonstration. The results indicate that the accuracies of apple orchard identification using the proposed DeepLabv3+_34, DeepLabv3+_50, and DeepLabv3+_101 reached 91.17%, 92.55%, and 94.37%, respectively. DeepLabv3+_101 demonstrated superior identification performance for apple orchards compared with ResU-Net and LinkNet, with an average accuracy improvement of over 3%. The identified area of apple orchards using the DeepLabv3+_101 model was 629.32 km², accounting for 31.20% of Qixia City’s total area; apple orchards were mainly located in the western part of the study area. The innovation of this research lies in combining image annotation and object-oriented methods during training, improving annotation efficiency and accuracy. Additionally, an enhanced DeepLabv3+ model was constructed based on GF-6 satellite images and the PIE-Engine cloud platform, exhibiting superior performance in feature expression compared with conventional machine learning classification and recognition algorithms. Full article

The wildland–urban interface (WUI) has been a global phenomenon, yet parameter threshold determination remains a persistent challenge in this field. In China, a significant research gap exists in the development of WUI mapping methodology. This study proposes a novel mapping approach that delineates the WUI by integrating both vegetation and building environment perspectives. GaoFen 1 Panchromatic Multi-spectral Sensor (GF1-PMS) imagery was leveraged as the data source. Building location was extracted using object-oriented and hierarchical classification techniques, and the pixel dichotomy method was employed to estimate fractional vegetation coverage (FVC). Building location and FVC were used as input for the WUI mapping. In this methodology, the threshold of FVC was determined by incorporating the remote sensing characteristics of the WUI types, whereas the buffer range of vegetation was refined through sensitivity analysis. The proposed method demonstrated high applicability in Anning City, achieving an overall accuracy of 88.56%. The total WUI area amounted to 49,578.05 ha, accounting for 38.08% of Anning City’s entire area. Spatially, the intermix WUI was predominantly distributed in the Taiping sub-district of Anning City, while the interface WUI was mainly concentrated in the Bajie sub-district of Anning City. MODIS fire spots from 2003 to 2022 were primarily clustered in the Qinglong sub-district, Wenquan sub-district, and Caopu sub-district of Anning City. Our findings indicated a spatial overlap between the WUI and fire-prone areas in Anning City. This study presents an effective methodology for threshold determination and WUI mapping, making up for the scarcity of mapping methodologies in China. Moreover, our approach offers valuable insights for a wise decision in fire risk. Full article

This research investigates the ultrasonic pulse velocity (UPV) and mechanical performance of epoxy-based polymer mortar (PM) reinforced with discrete fiber types to enhance structural behavior and promote sustainable construction practices. Four fiber types, polypropylene (PPF), natural date palm leaf fiber (DPL), glass fiber (GF), and carbon fiber (CF), were incorporated at varying volume fractions (0.5%, 1.0%, and 1.5%) into PM matrices. A total of thirteen mixtures, including a fiber-free control, were prepared. UPV testing was conducted prior to mechanical testing to evaluate internal quality and homogeneity, followed by compressive and flexural strength tests to assess structural performance. The results demonstrated that fiber type and dosage significantly influenced fiber-reinforced PM (FRPM) behavior. UPV values showed strong positive correlations with compressive strength for PPF, DPL, and CF, confirming UPV’s role as a non-destructive quality indicator. GF at 0.5% yielded the highest compressive strength (54.4 MPa), while CF and GF at 1.5% provided the greatest flexural enhancements (15 MPa), indicating improved ductility and energy absorption. Quadratic regression models were developed to predict strength responses as functions of fiber dosage. Although statistical significance was not achieved due to limited sample size, models for PPF and CF exhibited strong predictive reliability. Natural fibers such as DPL demonstrated moderate performance while offering environmental advantages through local renewability and low embodied energy. The study concludes that low fiber dosages, particularly 0.5%, enhance mechanical performance and material efficiency in FRPMs. The findings underscore the potential of FRPM as a durable and sustainable alternative to traditional cementitious materials. Full article

Mei (Prunus mume Sieb. et Zucc.) is a rare woody species that flowers in winter, yet its large-scale propagation is limited by the variable ability of cuttings to form adventitious roots (ARs). In this study, two cultivars were compared: P. mume ‘Xiangxue Gongfen’ (GF), which roots readily, and P. mume ‘Zhusha Wanzhaoshui’ (ZS), which is more recalcitrant. Detailed anatomical observations revealed that following cutting, the basal region expanded within 7 days, callus tissues had appeared by 14 days, and AR primordia emerged between 28 and 35 days. Notably, compared to the recalcitrant cultivar ZS, the experimental cultivar GF exhibited significantly enhanced callus tissue formation and AR primordia differentiation. Physiological analyses showed that the initial IAA concentration was highest at day 0, whereas cytokinin (tZR) and gibberellin (GA1) levels peaked at 14 days, with ABA gradually decreasing over time, resulting in increased IAA/tZR and IAA/GA1 ratios during the rooting process. Transcriptomic profiling across these time points identified significant upregulation of key genes (e.g., PmPIN3, PmLOG2, PmCKX5, PmIAA13, PmLAX2, and PmGA2OX1) and transcription factors (PmWOX4, PmSHR, and PmNAC071) in GF compared to ZS. Moreover, correlation analyses revealed that PmSHR expression is closely associated with IAA and tZR levels. Overexpression of PmSHR in tobacco further validated its role in enhancing lateral root formation. Together, these findings provide comprehensive insights into the temporal, hormonal, and genetic regulation of AR formation in P. mume, offering valuable strategies for improving its propagation. Full article

Natural resources (NRs) are important for the operation of any economy and are crucial for preserving environmental quality. However, the persistent utilization of NRs has led to a severe deterioration of environmental quality. This presents a vulnerability to the steadiness of the ecosystem, emphasizing the urgent requirement to achieve a harmonious equilibrium concerning the utilization of NRs and the conservation of environmental quality. Environmental taxes (ETs), green finance (GF), and the cultivation of a proficient workforce dedicated to achieving sustainable development are essential for attaining equilibrium and advancing the Sustainable Development Goals (SDGs). We aim to investigate the impact of NR, ET, GF, and the human capital index (HCI) on environmental pollution (PM_2.5, CH₄, CO₂, and N₂O) in the G20 countries from 2000 to 2022. This study employs a novel and cutting-edge MMQR methodology, offering distinct perspectives that diverge from the conclusions of previous research. The study’s findings suggest that excessive use of NRs contributes to the degradation of environmental quality. ET, GF, and economic growth help to improve environmental quality, but HCI has a harmful impact. The paper proposes that the establishment and enforcement of environmental regulations are crucial for attaining ecological integrity and meeting SDGs 7, 12, and 13. Full article

Remote sensing technology plays an important role in woodland identification. However, in mountainous areas with complex terrain, accurate extraction of woodland boundary information still faces challenges. To address this problem, this paper proposes a multiple mixed attention U-Net (MMA-U-Net) semantic segmentation model using 2015 and 2022 GF-1 PMS images as data sources to improve the ability to extract the boundary features of Picea schrenkiana var. tianschanica forest. The U-Net architecture serves as its underlying network, and the feature extraction ability of the Picea schrenkiana var. tianschanica is improved by adding hybrid attention CBAM and replacing the original skip connection with the DCA module to improve the accuracy of the model segmentation. The results show that on the remote sensing dataset with GF-1 PMS images, compared with the original U-Net and other models, the accuracy of the multiple mixed attention U-Net model is increased by 5.42%–19.84%. By statistically analyzing the spatial distribution of Picea schrenkiana var. tianschanica as well as their changes, the area was 3471.38 km² in 2015 and 3726.10 km² in 2022. Combining the predicted results with the DEM data, it was found that the Picea schrenkiana var. tianschanica were most distributed at an altitude of 1700–2500 m. The method proposed in this study can accurately identify Picea schrenkiana var. tianschanica and provides a theoretical basis and research direction for forest monitoring. Full article

The use of satellite data to estimate PM_2.5 is an appropriate approach for long-term, substantial monitoring and assessment. To estimate PM_2.5, the majority of the algorithms now in use utilize the top-of-atmosphere (TOA) reflectance or aerosol optical depth (AOD) derived from scalar satellite data. However, there is relatively little research on the retrieval of PM_2.5 using multi-angle polarized data. With its directional polarimetric camera (DPC), the Chinese new-generation satellite Gaofen 5B (henceforth referred to as GF-5B) offers a unique opportunity to close this gap in multi-angle polarized observation data. In this research, we utilized TOA data from the DPC payload and applied the gradient boosting machine method to simulate the impact of the observation angle, wavelength, and polarization information on the accuracy of PM_2.5 retrieval. We identified the optimal conditions for the effective estimation of PM_2.5. The quantitative results indicated that, under these optimal conditions, the PM_2.5 concentrations retrieved by GF-5B showed a strong correlation with the ground-based data, achieving an R² of 0.9272 and an RMSE of 7.38 µg·m⁻³. By contrast, Himawari-8’s retrieval accuracy under similar data conditions consisted of an R² of 0.9099 and RMSE of 7.42 µg·m⁻³, indicating that GF-5B offers higher accuracy. Furthermore, the retrieval results in this study demonstrated an R² of 0.81 when compared to the CHAP dataset, confirming the feasibility and effectiveness of the use of GF-5B for PM_2.5 retrieval and providing support for PM_2.5 estimation through multi-angle polarized data. Full article

Accurate forecasting of high-resolution particulate matter 2.5 (PM_2.5) levels is essential for the development of public health policy. However, datasets used for this purpose often contain missing observations. This study presents a two-stage approach to handle this problem. The first stage is a multivariate spatial time series (MSTS) model, used to generate forecasts for the sampled spatial units and to impute missing observations. The MSTS model utilizes the similarities between the temporal patterns of the time series of the spatial units to impute the missing data across space. The second stage is the high-resolution prediction model, which generates predictions that cover the entire study domain. The second stage faces the big N problem giving rise to complex memory and computational problems. As a solution to the big N problem, we propose a Gaussian Markov random field (GMRF) for innovations with the Matérn covariance matrix obtained from the corresponding Gaussian field (GF) matrix by means of the stochastic partial differential equation (SPDE) method and the finite element method (FEM). For inference, we propose Bayesian statistics and integrated nested Laplace approximation (INLA) in the R-INLA package. The above approach is demonstrated using daily data collected from 13 PM_2.5 monitoring stations in Jakarta Province, Indonesia, for 1 January–31 December 2022. The first stage of the model generates PM_2.5 forecasts for the 13 monitoring stations for the period 1–31 January 2023, imputing missing data by means of the MSTS model. To capture temporal trends in the PM_2.5 concentrations, the model applies a first-order autoregressive process and a seasonal process. The second stage involves creating a high-resolution map for the period 1–31 January 2023, for sampled and non-sampled spatiotemporal units. It uses the MSTS-generated PM_2.5 predictions for the sampled spatiotemporal units and observations of the covariate’s altitude, population density, and rainfall for sampled and non-samples spatiotemporal units. For the spatially correlated random effects, we apply a first-order random walk process. The validation of out-of-sample forecasts indicates a strong model fit with low mean squared error (0.001), mean absolute error (0.037), and mean absolute percentage error (0.041), and a high R² value (0.855). The analysis reveals that altitude and precipitation negatively impact PM_2.5 concentrations, while population density has a positive effect. Specifically, a one-meter increase in altitude is linked to a 7.8% decrease in PM_2.5, while a one-person increase in population density leads to a 7.0% rise in PM_2.5. Additionally, a one-millimeter increase in rainfall corresponds to a 3.9% decrease in PM_2.5. The paper makes a valuable contribution to the field of forecasting high-resolution PM_2.5 levels, which is essential for providing detailed, accurate information for public health policy. The approach presents a new and innovative method for addressing the problem of missing data and high-resolution forecasting. Full article

Nowadays, trace metal contamination within urban atmospheres is a significant and concerning global issue. In the present study, two synanthropic bird species, namely, the feral pigeon (Columba livia f. domestica) and the rook (Corvus frugilegus), were employed as bioindicators to assess the atmospheric trace metal pollution in Iasi City, Romania. The concentrations of Ni, Pb, Cd, Co, Cr, and Cu were determined through high-resolution continuum source graphite furnace atomic absorption spectrometry (HR-CS GF-AAS) of various tissues, including the liver, kidney, lung, heart, muscle, and bone, of feral pigeons and rooks collected in Iasi City. The order of trace metal concentrations in the tissues of feral pigeons and rooks in Iasi City was similar: Cu > Pb > Ni > Cd > Cr > Co. However, trace element values in most tissues were higher in the rook samples than in feral pigeon ones, except for Co, which had elevated levels in feral pigeon renal and cardiac tissues, and Cu, which registered the highest concentrations in feral pigeon liver and kidney tissues. While not statistically significant, Pb concentration values in the PM₁₀ fraction of atmospheric particles positively correlated with Pb concentrations in rook kidney samples (p = 0.05). The concentration levels of Cd, Pb, and Ni in the PM₁₀ fraction of air particles showed a positive correlation with Cd levels in the samples of pigeon heart and rook liver, kidney, and heart, Pb levels in the samples of pigeon kidney, heart, and muscle and rook liver and bone, and Ni levels in the samples of pigeon liver, kidney, and bone and rook liver, muscle, and bone, respectively. Full article

A panchromatic and multispectral sensor (PMS) and a wide-field-of-view (WFV) sensor were fitted aboard the Gaofen6 (GF6) satellite, which was launched on 2 June 2018. This study used the Landsat9-Operational Land Imager 2 and Sentinel2-Multispectral Instrument as reference sensors to perform radiometric cross-calibration on GF6-PMS and WFV data at the Dunhuang calibration site. The four selected sensor images were all acquired on the same day. The results indicate that: the calibration results between different reference sensors can be controlled within 3%, with the maximum difference from the official coefficients being 8.78%. A significant difference was observed between the coefficients obtained by different reference sensors when spectral band adjustment factor (SBAF) correction was not performed; from the two sets of validation results, the maximum mean relative difference in the near-infrared band was 9.46%, with the WFV sensor showing better validation results. The validation of calibration coefficients based on synchronous ground observation data and the analysis of the impact of different SBAF methods on the calibration results indicated that Landsat9 is more suitable as a reference sensor for radiometric cross-calibration of GF6-PMS and WFV. Full article

Early identification of acute gout is crucial, enabling healthcare professionals to implement targeted interventions for rapid pain relief and preventing disease progression, ensuring improved long-term joint function. In this study, we comprehensively explored the potential early detection of gout flares (GFs) based on nurses’ chief complaint notes in the Emergency Department (ED). Addressing the challenge of identifying GFs prospectively during an ED visit, where documentation is typically minimal, our research focused on employing alternative Natural Language Processing (NLP) techniques to enhance detection accuracy. We investigated GF detection algorithms using both sparse representations by traditional NLP methods and dense encodings by medical domain-specific Large Language Models (LLMs), distinguishing between generative and discriminative models. Three methods were used to alleviate the issue of severe data imbalances, including oversampling, class weights, and focal loss. Extensive empirical studies were performed on the Gout Emergency Department Chief Complaint Corpora. Sparse text representations like tf-idf proved to produce strong performances, achieving F1 scores higher than 0.75. The best deep learning models were RoBERTa-large-PM-M3-Voc and BioGPT, which had the best F1 scores for each dataset, with a 0.8 on the 2019 dataset and a 0.85 F1 score on the 2020 dataset, respectively. We concluded that although discriminative LLMs performed better for this classification task when compared to generative LLMs, a combination of using generative models as feature extractors and employing a support vector machine for classification yielded promising results comparable to those obtained with discriminative models. Full article

This study focuses on optimizing precipitation forecast induced by tropical cyclones (TCs) in the Northwest Pacific region, with lead times ranging from 6 to 72 h. The research employs deep learning models, such as U-Net, UNet3+, SE-Net, and SE-UNet3+, which utilize precipitation forecast data from the Global Forecast System (GFS) and real-time GFS environmental background data using a U-Net structure. To comprehensively make use of the precipitation forecasts from these models, we additionally use probabilistic matching (PM) and simple averaging (AVR) in rainfall prediction. The precipitation data from the Global Precipitation Measurement (GPM) Mission serves as the rainfall observation. The results demonstrate that the root mean squared errors (RMSEs) of U-Net, UNet3+, SE-UNet, SE-UNet3+, AVR, and PM are lowered by 8.7%, 10.1%, 9.7%, 10.0%, 11.4%, and 11.5%, respectively, when compared with the RMSE of the GFS TC precipitation forecasts, while the mean absolute errors are reduced by 9.6%, 11.3%, 9.0%, 12.0%, 12.8%, and 13.0%, respectively. Furthermore, the neural network model improves the precipitation threat scores (TSs). On average, the TSs of U-Net, UNet3+, SE-UNet, SE-UNet3+, AVR, and PM are raised by 12.8%, 21.3%, 19.3%, 20.7%, 22.5%, and 22.9%, respectively, compared with the GFS model. Notably, AVR and PM outperform all other individual models, with PM’s performance slightly better than AVR’s. The most important feature variables in optimizing TC precipitation forecast in the Northwest Pacific region based on the UNet-based neural network include GFS precipitation forecast data, land and sea masks, latitudinal winds at 500 hPa, and vertical winds at 500 hPa. Full article

Mangroves as an important blue carbon ecosystem have a unique ability to sequester and store large amounts of carbon. The height of mangrove forest is considered to be a critical factor in evaluating carbon sink capacity. However, considering the highly complicated nature of the mangrove system, accurate estimation of mangrove species height is challenging. Gaofen-2 (GF-2) panchromatic and multispectral sensor (PMS), Gaofen-3 (GF-3) SAR images, and unmanned aerial vehicle-light detection and ranging (UAV-LiDAR) data have the capability to capture detailed information about both the horizontal and vertical structures of mangrove forests, which offer a cost-effective and reliable approach to predict mangrove species height. To accurately estimate mangrove species height, this study obtained a variety of characteristic parameters from GF-2 PMS and GF-3 SAR data and utilized the canopy height model (CHM) derived from UAV-LiDAR data as the observed data of mangrove forest height. Based on these parameters and the random forest (RF) regression algorithm, the mangrove species height result had a root-mean-square error (RMSE) of 0.91 m and an R² of 0.71. The Kandelia obovate (KO) exhibited the tallest tree height, reaching a maximum of 9.6 m. The polarization features, HH, VV, and texture feature, mean_1 (calculated based on the mean value of blue band in GF-2 image), had a reasonable correlation with canopy height. Among them, the most significant factor in determining the height of mangrove forest was HH. In areas where it is difficult to conduct field surveys, the results provided an opportunity to update access to acquire forest structural attributes. Full article

Water eutrophication poses a dual threat to ecological and human well-being. Gaining insight into the intricate dynamics of phytoplankton bloom phenology holds paramount importance in comprehending the complexities of aquatic ecosystems. Remote sensing technologies have gained attention for mapping algal blooms (ABs) effectively, but distinguishing them from aquatic vegetation (AV) remains challenging due to their similar spectral characteristics. To address this issue, we propose a meticulous three-step methodology for AB mapping employing long-term Landsat imagery. Initially, a multi-index decision tree model (DTM) is deployed to identify the vegetation signal (VS) encompassing both AV and ABs. Subsequently, the annual maximum growth range of AV is precisely delineated using vegetation presence frequency (VPF) in conjunction with normal and low water level imagery. Lastly, ABs are accurately extracted by inversely intersecting VS and AV. The performance of our approach is thoroughly validated using the interclass correlation coefficient (ICC) based on a Gaofen-2 Panchromatic Multi-spectral (GF-2 PMS) image, demonstrating strong consistency with notable values of 0.822 longitudinally, 0.771 latitudinally, and 0.797 overall. The method is applied to Landsat images from 1984 to 2022 to quantify the spatial distribution and temporal variations of ABs in Yuqiao Reservoir—a significant national water body spanning a vast area of 135 km² in China. Our findings reveal a pervasive and uneven dispersion of ABs, predominantly concentrated in the northern sector. Notably, the intensity of ABs experienced an initial surge from 1984 to 2008, followed by a subsequent decline from 2014 to 2022. Importantly, anthropogenic activities, such as fish cage culture, alongside pollution stemming from nearby industrial and agricultural sources, exert a profound influence on the dynamics of water eutrophication. Fortunately, governmental initiatives focused on water purification exhibit commendable efficacy in mitigating the ecological burden on reservoirs and upholding water quality. The methodological framework presented in this study boasts remarkable precision in AB extraction and exhibits considerable potential in addressing the needs of aquatic ecosystems. Full article

Forest ecosystems depend on species of tree variety. Remote sensing for obtaining large-scale spatial distribution information of tree species diversity is a geoscience research hotspot to overcome the limitations of conventional tree species diversity survey approaches. Airborne LiDAR or synergy with airborne optical imagery has been used to model and estimate tree species diversity for specific forest communities, with many revealing results. However, the data collection for such research is costly, the breadth of monitoring findings is limited, and obtaining information on the geographical pattern is challenging. To this end, we propose a method for mapping forest tree species diversity by synergy satellite optical remote sensing and satellite-based LiDAR based on the spectral heterogeneity hypothesis and structural variation hypothesis to improve the accuracy of the remote sensing monitoring of forest tree species diversity while considering data cost. The method integrates horizontal spectral variation from GF-1/PMS image data with vertical structural variation from ICESat-2 spot data to estimate the species diversity of trees. The findings reveal that synergistic horizontal spectral variation and vertical structural variation overall increase tree species diversity prediction accuracy compared to a single remote sensing variation model. The synergistic approach improved Shannon and Simpson indices prediction accuracy by 0.06 and 0.04, respectively, compared to the single horizontal spectral variation model. The synergistic model, single vertical structural variation model, and single horizontal spectral variation model were the best prediction models for Shannon, Simpson, and richness indices, with R² of 0.58, 0.62, and 0.64, respectively. This research indicates the potential of synergistic satellite-based LiDAR and optical remote sensing in large-scale forest tree species diversity mapping. Full article