Search

In this research, we propose a deep learning model employing gated recurrent units (GRUs) for the transmission spectrum prediction, and computational inverse designing of all-optical plasmonic devices (AOPDs), which may a crucial role in the precise fabrication process of photonic integrated circuits (PICs). This shift from a conventional simulation-based design to a GRU-based model offers a significant advantage in terms of accuracy and precision. The technique facilitates the intricate design process by simulating the propagation of Surface Plasmon Polaritons (SPPs) within the plasmonic structures of AOPDs. The forward modeling approach presented here demonstrates a substantial improvement in computational efficiency over the finite-difference time-domain method, adeptly forecasting transmission spectra characterized through the analysis of various geometrical parameters. The inverse modeling process infers the necessary design parameters to produce specific transmission spectra, markedly expediting the design process and eclipsing the time-intensive nature of traditional optimization methods. With a prediction loss (MSE) of 0.168 and 0.9217, this research substantiates the efficacy of GRUs in streamlining the forward and inverse design processes of AOPDs for integration into PICs. [ABSTRACT FROM AUTHOR]

Electricity is essential for keeping power networks balanced between supply and demand, especially since it costs a lot to store. The article talks about different deep learning methods that are used to guess how much green energy different Asian countries will produce. The main goal is to make reliable and accurate predictions that can help with the planning of new power plants to meet rising demand. There is a new deep learning model called the Green-electrical Production Ensemble (GP-Ensemble). It combines three types of neural networks: convolutional neural networks (CNNs), gated recurrent units (GRUs), and feedforward neural networks (FNNs). The model promises to improve prediction accuracy. The 1965–2023 dataset covers green energy generation statistics from ten Asian countries. Due to the rising energy supply-demand mismatch, the primary goal is to develop the best model for predicting future power production. The GP-Ensemble deep learning model outperforms individual models (GRU, FNN, and CNN) and alternative approaches such as fully convolutional networks (FCN) and other ensemble models in mean squared error (MSE), mean absolute error (MAE) and root mean squared error (RMSE) metrics. This study enhances our ability to predict green electricity production over time, with MSE of 0.0631, MAE of 0.1754, and RMSE of 0.2383. It may influence laws and enhance energy management. [ABSTRACT FROM AUTHOR]

Movement is a key means by which animals cope with variable environments. As they move, animals construct individual niches composed of the environmental conditions they experience. Niche axes may vary over time and covary with one another as animals make tradeoffs between competing needs. Seasonal migration is expected to produce substantial niche variation as animals move to keep pace with major life history phases and fluctuations in environmental conditions. Here, we apply a time-ordered principal component analysis to examine dynamic niche variance and covariance across the annual cycle for four species of migratory crane: common crane (Grus grus, n = 20), demoiselle crane (Anthropoides virgo, n = 66), black-necked crane (Grus nigricollis, n = 9), and white-naped crane (Grus vipio, n = 9). We consider four key niche components known to be important to aspects of crane natural history: enhanced vegetation index (resources availability), temperature (thermoregulation), crop proportion (preferred foraging habitat), and proximity to water (predator avoidance). All species showed a primary seasonal niche "rhythm" that dominated variance in niche components across the annual cycle. Secondary rhythms were linked to major species-specific life history phases (migration, breeding, and nonbreeding) as well as seasonal environmental patterns. Furthermore, we found that cranes' experiences of the environment emerge from time-dynamic tradeoffs among niche components. We suggest that our approach to estimating the environmental niche as a multidimensional and time-dynamical system of tradeoffs improves mechanistic understanding of organism-environment interactions. [ABSTRACT FROM AUTHOR]

The Florida sandhill crane (Antigone canadensis pratensis) is a state‐threatened non‐migratory subspecies. Our understanding of adult crane survival in Florida, USA, is unclear, as it relies on decades‐old unpublished data of birds residing in natural areas. Since that time, the loss of natural habitat precipitated cranes using urbanized areas such as suburban lawns and roadside verges for foraging and loafing. Contemporary studies are needed to properly guide crane management and conservation efforts. We addressed this knowledge gap by estimating the annual survival rate for sandhill cranes in 12 central Florida counties. We used a live‐dead capture‐recapture multistate model, monitoring 118 adult cranes from June 2017 to May 2023; 76 were color‐banded and 42 were tagged with Global System for Mobile Communications (GSM) transmitters. Fifteen cranes died during the study, with vehicle strikes (n = 9) being the most prevalent identified source of mortality. Overall, the annual survival probability was estimated at 0.79 (95% credibility interval = 0.75–0.84). Using the subset of GSM‐tagged cranes, we observed no influence of urbanization on annual survival rate (βurbanization gradient = 0.007, 95% credibility interval = −0.008, 0.022). The adult survival rates we observed are lower than reported for other populations of sandhill cranes in North America that are considered stable or growing. [ABSTRACT FROM AUTHOR]

Fossil bird eggs from the Pleistocene of the Americas are rare. Previous records include Uruguay, Bermuda, California (USA) and Mexico, including reports of complete fossil eggs from extinct puffin (Fratercula dowi) from California, Tinamou (Tinamidae indet.) from Uruguay, Brown Pelican (Pelecanus occidentalis) from Bermuda and Sandhill Crane (Grus canadensis) from México. The fossil record of flamingos in Mexico is restricted to palaeolakes in Central Mexico, which is very interesting because the current distribution of flamingos in North America is restricted to some areas of the Southeastern United States and Yucatan Peninsula, which are far from palaeontological sites. We report a fossil flamingo egg found during the construction of a new International Airport 'Felipe Angeles', Santa Lucía, State of México. This egg is the first Pleistocene fossil egg record for the family Phoenicopteridae, the first fossil egg record of this family in the Americas and the second record of a phoenicopterid fossil egg in the world. We re-identified the fossil eggs described by Martin del Campo in the 1940s, suggesting that they are also flamingo eggs. Using biogeographical and climate niche data for family Phoenicopteridae in North America, we infer the presence of a salinity and shallow palaeolake during the Late Pleistocene, with climatic condition being warmest and wetter than at present. [ABSTRACT FROM AUTHOR]

Based on the species‐rich avifaunas from Early Neolithic sites across Upper Mesopotamia (southeast Türkiye, northern Syria, northern Iraq), we compared seven species' Early Holocene distribution patterns with that of their modern species ranges. The avifaunal remains from four sites were analysed by the authors and bird identifications from 10 additional sites were extracted from published reports. In the case of the Common Crane Grus grus, Grey Partridge Perdix perdix and Black Francolin Francolinus francolinus, shifts in distributions relate to significant changes in climate marking the transition from the Pleistocene to the Holocene. In contrast, the massive decline of the Griffon Vulture Gyps fulvus represents a more recent phenomenon related to anthropogenic impact on their habitats and food sources. For the Black‐bellied Sandgrouse Pterocles orientalis and the Pin‐tailed Sandgrouse P. alchata, changes in distributional range from the Early Holocene to the present could not be detected. Finally, a single bone of Macqueen's Bustard Chlamydotis macqueenii at Göbekli Tepe is unexpected and conceivably we are dealing with the remains of a rare vagrant, more likely to be found in dry steppe and desert habitats, which were located south of the study area at that time. This study highlights the value of archaeozoological finds in helping to understand how species distributional ranges have changed over time. Similarly, our work suggests that authors studying archaeozoological data should not assume that present‐day distributional ranges of taxa of interest represent the ranges of these species in the past. [ABSTRACT FROM AUTHOR]

Utilizing time-series data from ship trajectories to forecast their subsequent movement is crucial for enhancing the safety within maritime traffic environments. The application of deep learning techniques, leveraging Automatic Identification System (AIS) data, has emerged as a pivotal area in maritime traffic studies. Within this domain, the precise forecasting of ship trajectories stands as a central challenge. In this study, we propose the multi-gated attention encoder decoder (MGAED) network, a model based on an encoder–decoder structure specialized for predicting ship trajectories in canals. The model employs a long short-term memory network (LSTM) as an encoder, combined with multiple Gated Recurrent Units (GRUs) and an attention mechanism for the decoder. Long-term dependencies in time-series data are captured through GRUs, while the attention mechanism is used to strengthen the model's ability to capture key information, and a soft threshold residual structure is introduced to handle sparse features, thus enhancing the model's generalization ability and robustness. The efficacy of our model is substantiated by an extensive evaluation against current deep learning benchmarks. Through comprehensive comparison experiments with existing deep learning methods, our model shows significant improvements in prediction accuracy, with an at least 9.63% reduction in the mean error (MAE) and an at least 20.0% reduction in the mean square error (MSE), providing a new solution to improve the accuracy and efficiency of ship trajectory prediction. [ABSTRACT FROM AUTHOR]

Malware remains a major threat to computer systems, with a vast number of new samples being identified and documented regularly. Windows systems are particularly vulnerable to malicious programs like viruses, worms, and trojans. Dynamic analysis, which involves observing malware behavior during execution in a controlled environment, has emerged as a powerful technique for detection. This approach often focuses on analyzing Application Programming Interface (API) calls, which represent the interactions between the malware and the operating system. Recent advances in deep learning have shown promise in improving malware detection accuracy using API call sequence data. However, the potential of Generative Adversarial Networks (GANs) for this purpose remains largely unexplored. This paper proposes a novel hybrid deep learning model combining Gated Recurrent Units (GRUs) and GANs to enhance malware detection based on API call sequences from Windows portable executable files. We evaluate our GRU–GAN model against other approaches like Bidirectional Long Short-Term Memory (BiLSTM) and Bidirectional Gated Recurrent Unit (BiGRU) on multiple datasets. Results demonstrated the superior performance of our hybrid model, achieving 98.9% accuracy on the most challenging dataset. It outperformed existing models in resource utilization, with faster training and testing times and low memory usage. [ABSTRACT FROM AUTHOR]

Accurate predictions of parking occupancy are vital for navigation and autonomous transport systems. This research introduces a deep learning mode, AGCRU, which integrates Adaptive Graph Convolutional Networks (GCNs) with Gated Recurrent Units (GRUs) for predicting on-street parking occupancy. By leveraging real-world data from Melbourne, the proposed model utilizes on-street parking sensors to capture both temporal and spatial dynamics of parking behaviors. The AGCRU model is enhanced with the inclusion of Points of Interest (POIs) and housing data to refine its predictive accuracy based on spatial relationships and parking habits. Notably, the model demonstrates a mean absolute error (MAE) of 0.0156 at 15 min, 0.0330 at 30 min, and 0.0558 at 60 min; root mean square error (RMSE) values are 0.0244, 0.0665, and 0.1003 for these intervals, respectively. The mean absolute percentage error (MAPE) for these intervals is 1.5561%, 3.3071%, and 5.5810%. These metrics, considerably lower than those from traditional and competing models, indicate the high efficiency and accuracy of the AGCRU model in an urban setting. This demonstrates the model as a tool for enhancing urban parking management and planning strategies. [ABSTRACT FROM AUTHOR]

This study focuses on the problem of the supply prediction of logistics transportation vehicles in road transportation. Aiming at the problem that the supply data of logistics transportation has the characteristics of long sequential data, numerous influencing factors, and a significant spatiotemporal evolution law, which leads to the lack of accuracy of supply predictions, this paper proposes a supply prediction method for logistics transportation based on an improved Informer model. Firstly, multidimensional feature engineering is applied to historical supply data to enhance the interpretability of labeled data. Secondly, a spatiotemporal convolutional network is designed to extract the spatiotemporal features of the supply volume. Lastly, a long short-term memory (LSTM) model is introduced to capture the supply volume's long- and short-term dependencies, and the predicted value is derived through a multilayer perceptron. The experimental results show that mean square error (MSE) is reduced by 73.8%, 79.36%, 82.24%, 78.58%, 77.02%, 53.96%, and 40.38%, and mean absolute error (MAE) is reduced by 52%, 59.5%, 60.36%, 57.52%, 53.9%, 31.21%, and 36.58%, respectively, when compared to the auto-regressive integrated moving average (ARIMA), support vector regression (SVR), LSTM, gated recurrent units (GRUs), a back propagation neural network (BPNN), and Informer and InformerStack single models; compared with the ARIMA + BPNN, ARIMA + GRU and ARIMA + LSTM integrated models, the MSE is reduced by 74.88%, 71.56%, and 74.07%, respectively, and the MAE is reduced by 51.31%, 50%, and 52.02%; it effectively reduces the supply prediction error and improves the prediction accuracy. [ABSTRACT FROM AUTHOR]

Objective Animals Studied Procedures Results Conclusions To establish baseline ophthalmic parameters for an endangered, semi‐wild population of healthy whooping cranes (Grus americana) (WHCR) and Mississippi sandhill cranes (Grus canadensis pulla) (SACR).Eighteen WHCR and 16 SACR.Ophthalmic examination was performed by a single observer, followed by conjunctival swab collection for aerobic bacterial culture and measurement of tear production (phenol red thread test, PRTT) and corneal diameter (CD) as tolerated. Measurement of the axial globe (AG) length, anterior chamber (AC) depth, lens thickness, vitreous chamber (VC) depth, and pecten length was performed via ocular ultrasound (OUS) as tolerated.Eyelid cicatrization (n = 1 WHCR), keratitis (n = 2 WHCR), incipient cataracts (n = 1 WHCR, n = 4 SACR), and uveal cysts (n = 1 SACR) were identified. Twenty‐one bacterial species were cultured from SACR, while 18 bacterial species were cultured from WHCR. SACR under 6 months old had increased PRTT values compared to older SACR (p = .0432). AG length and VC depth of male WHCR were greater than in female WHCR (p = .0045 and p = .0008, respectively). WHCR less than 6 months old had greater AC depth and lens thickness than WHCR over 6 months (p < .001 and p = .0013, respectively). SACR less than 6 months old had greater AC depth and lens thickness than WHCR over 6 months (p < .0001 and p < .0001, respectively).WHCR and SACR are amenable to complete ophthalmic examination. Age‐related differences in PRTT in SACR, sexual dimorphism in WHCR, and age‐related differences in AC depth and lens thickness in WHCR and SACR were identified. [ABSTRACT FROM AUTHOR]

The Korean demilitarised zone (DMZ) has traditionally been understood as an alienated borderland consistent with ideas of no-man's lands as abandoned and enclosed spaces. However, far from being an empty space or geopolitical vacuum, the withdrawal of human bodies and activity from the DMZ has (inadvertently) established an ecological haven where non-human life thrives. The near complete inaccessibility of the space poses significant obstacles to researching the species thriving within and, indeed, to how we envision, sense, and engage with the DMZ to begin with. Yet, the difficulties and challenges associated with researching such spaces also provide stimulating ways of thinking with and through the subfield of animal geographies. Drawing upon fieldwork experiences with birds at and along the DMZ, with a particular focus on the red-crowned crane (Grus japonensis), this paper explores how the subfield of animal geographies can itself become a means of exploring, interacting, and engaging with (de)limited spaces. In doing so, it considers how we might push animal geographies beyond its current limits whilst also expanding both the conceptual and methodological toolboxes through which we approach less accessible spaces of study. [ABSTRACT FROM AUTHOR]

Objective: To assess intraocular pressure (IOP) development in cranes and determine the impact of age, weight, species, head position, and sex. Animals Studied: Whooping cranes (WC) (Grus americana), and Mississippi‐sandhill cranes (MSC) (Grus canadensis pulla). Procedures: Chicks were manually restrained on days 1–3, 7, 21, 35, 60, 75, and 120 for routine examinations. IOP was opportunistically measured utilizing the Tonovet Plus® in D setting with the head above the heart (AH) and below the heart (BH). Values were also obtained longitudinally in adults (>120 days old) upon presentation in 1 year. Results: Intraocular pressure was highly correlated with age and weight in chicks. For every kilogram gained, IOP increased 2.46 ± 0.08 mmHg in WC and 2.66 ± 0.11 mmHg in MSC. Once hatched, IOP increased 1.13 ± 0.04 mmHg in WC and 0.87 ± 0.04 mmHg in MSC every 10 days. IOP was similar to adults at 120 days of age. In adult WC, mean IOP AH was 24.0 ± 0.4 mmHg, and BH was 27.9 ± 0.4 mmHg, there was a significant difference regarding head positioning and sex, females (25.3 ± 0.4 mm Hg) had lower IOP than males (26.5 ± 0.4 mmHg). In adult MSC, mean IOP AH was 20.7 ± 0.4 mmHg, and BH was 24.6 ± 0.4 mmHg. The difference between head positioning was significant. Conclusions: This study documents the correlation between IOP and weight or age during early development in cranes, as well as the importance of head positioning. [ABSTRACT FROM AUTHOR]

Simple Summary: The morphological designs and the behavior (rhythmic brushing, vibrating, scraping, and tapping) of the male genitalia in two species of crane flies indicate that male genital structures in both species function to stimulate the female during copulation. These observations are used to test current theoretical explanations of the rapid divergent evolution of male genitalia of animals with internal insemination. Male genitalia have been hypothesized to function as courtship devices during copulation, but it is difficult to use behavioral observations to test this hypothesis because male genitalia are usually hidden inside the female during copulation. In tipuloid flies, however, nearly all of the male's complex genital structures remain outside the female. Copulation behavior and genital morphology in Tipula (Triplicitipula) colei and T. (Lunatipula) translucida suggest that some male genital structures function to stimulate the female: male structures that contact the female bear tufts or dense arrays of modified setae on precisely the surfaces that contact the female; contact involves repeated, stereotyped rhythmic movements that include brushing, vibrating, scraping, and tapping; the movements are appropriately designed to utilize the morphology of the modified setae to stimulate the female; and the movements have little or no other perceptible mechanical effects on the female. The female structures contacted by these male genital movements fail to show the defensive designs predicted by the theories of genital evolution that are based on morphological species isolation or male–female morphological conflicts of interest; also unexplained by the conflict of interest hypothesis are female movements that seem designed to increase rather than avoid stimulation by the male. [ABSTRACT FROM AUTHOR]

This paper presents a comparative analysis of deep learning techniques for anomaly detection and failure prediction. We explore various deep learning architectures on an IoT dataset, including recurrent neural networks (RNNs, LSTMs and GRUs), convolutional neural networks (CNNs) and transformers, to assess their effectiveness in anomaly detection and failure prediction. It was found that the hybrid transformer-GRU configuration delivers the highest accuracy, albeit at the cost of requiring the longest computational time for training. Furthermore, we employ explainability techniques to elucidate the decision-making processes of these black box models and evaluate their behaviour. By analysing the inner workings of the models, we aim at providing insights into the factors influencing failure predictions. Through comprehensive experimentation and analysis on sensor data collected from a water pump, this study contributes to the understanding of deep learning methodologies for anomaly detection and failure prediction and underscores the importance of model interpretability in critical applications such as prognostics and health management. Additionally, we specify the architecture for deploying these models in a real environment using the RAI4.0 metamodel, meant for designing, configuring and automatically deploying distributed stream-based industrial applications. Our findings will offer valuable guidance for practitioners seeking to deploy deep learning techniques effectively in predictive maintenance systems, facilitating informed decision-making and enhancing reliability and efficiency in industrial operations. [ABSTRACT FROM AUTHOR]

Invertebrates greatly support the growth, development, and reproduction of insectivorous birds. However, the influence of human activity (e.g., pesticide use, deforestation, and urbanization) inevitably leads to a decrease in global arthropods. The diversity and variation in invertebrate diet influence the food composition of birds, especially species living in rapidly changing environments, such as the Tibetan Plateau. However, little is known of the seasonal variation in invertebrate diet in response to environmental changes. Here, we characterized the invertebrate diet composition in pre‐ and post‐breeding black‐necked crane (Grus nigricollis) using fecal metabarcoding. We identified 38 invertebrate genera; the top three were Tipula (82.1% of relative abundance), Ceramica (3.0%), and unclassified_Hymenoptera (2.5%), with Tipula predominated the diet in both seasons. We also observed 20 and 16 unique genera in the pre‐ and post‐breeding periods, and the genera composition was distinct between seasons (R =.036, p =.024). In pre‐breeding, black‐necked cranes tended to consume more diverse foods, and individual cranes exhibited greater heterogeneity at the genus level. At the genera and species level, pre‐breeding black‐necked cranes showed a wider dietary niche than post‐breeding cranes. We observed season‐specific features, with Tipula (common crane fly) and Stethophyma (grasshoppers) being enriched in the post‐breeding period and Ceramica (moth) being more abundant in the pre‐breeding period. Three Tipula species had the greatest importance in discriminating between seasonal diets. This study demonstrated a seasonal pattern of invertebrate diet in the black‐necked crane, suggesting diet composition in response to resource and species availability. These results elaborate on the foraging ecology of highland birds and can inform the management of black‐necked crane conservation. [ABSTRACT FROM AUTHOR]

Migratory connectivity describes the degree to which migratory populations are mixed across space and time. Unlike adults, subadult birds often exhibit distinct migratory patterns and continually refine their migratory behaviour and destinations as they mature. Consequently, the influence of subadult movements on overall migratory connectivity might be different from that of adults. However, current studies on migratory connectivity often overlook population age structures, predominantly focusing on adults. In this study, we investigated the role of subadult movements in shaping population level connectivity by using satellite tracking data from 214 black-necked cranes, Grus nigricollis , in western China. We first assessed the variances in spatial separation in different age cohorts using the continuous temporal Mantel correlation coefficient with data from 17 juveniles tracked in the same year for 3 consecutive years. We then calculated the continuous temporal migratory connectivity for the entire population (comprising various age groups) from 15 September to 15 November and compared the result to that of the family group (consisting of juveniles and adults only). Our results revealed a positive correlation between temporal variation in spatial separation and age after the juveniles separated from the adults, suggesting that subadults may have fine-tuned their migration paths. Moreover, the migratory connectivity of the all-age cohort was moderate (below 0.6) in the winter season, and notably lower than that of the family group during the autumn period. Given the considerable impact of subadults on migratory connectivity, we recommend using data collected from birds across all age categories to improve the precision of population level migratory connectivity estimates. • Black-necked cranes have moderate migratory connectivity. • Spatial separation between individuals varied between age groups. • Individuals of all ages should be included when calculating migratory connectivity. [ABSTRACT FROM AUTHOR]

Copyright of ANIAV: Revista de Investigación en Artes Visuales is the property of Universidad Politecnica de Valencia and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Power consumption in the home has grown in recent years as a consequence of the use of varied residential applications. On the other hand, many families are beginning to use renewable energy, such as energy production, energy storage devices, and electric vehicles. As a result, estimating household power demand is necessary for energy consumption monitoring and planning. Power consumption forecasting is a challenging time series prediction topic. Furthermore, conventional forecasting approaches make it difficult to anticipate electric power consumption since it comprises irregular trend components, such as regular seasonal fluctuations. To address this issue, algorithms combining stationary wavelet transform (SWT) with deep learning models have been proposed. The denoised series is fitted with various benchmark models, including Long Short-Term Memory (LSTM), Gated Recurrent Units (GRUs), Bidirectional Gated Recurrent Units (Bi-GRUs), Bidirectional Long Short-Term Memory (Bi-LSTM), and Bidirectional Gated Recurrent Units Long Short-Term Memory (Bi-GRU LSTM) models. The performance of the SWT approach is evaluated using power consumption data at three different time intervals (1 min, 15 min, and 1 h). The performance of these models is evaluated using metrics such as Root Mean Square Error (RMSE), Mean Absolute Percentage Error (MAPE), and Mean Absolute Error (MAE). The SWT/GRU model, utilizing the bior2.4 filter at level 1, has emerged as a highly reliable option for precise power consumption forecasting across various time intervals. It is observed that the bior2.4/GRU model has enhanced accuracy by over 60% compared to the deep learning model alone across all accuracy measures. The findings clearly highlight the success of the SWT denoising technique with the bior2.4 filter in improving the power consumption prediction accuracy. [ABSTRACT FROM AUTHOR]

Accurate detection and segmentation of brain cancer in MRI scans are critical for effective diagnosis and treatment planning. Traditional methods often struggle with the complexities of tumor morphology and variations in scan quality. Existing detection systems can be slow and may not effectively handle the variability in tumor appearances, leading to potential delays in diagnosis and treatment. To address these challenges, we propose an enhanced detection framework using a Siamese Regional Proposed Network (SRPN). The SRPN integrates template branch and bounding box regression to expedite detection processes. The system utilizes an extended Siamese network to learn the distance between tracklet pairs, capturing the local and global features of tumors. These features are transferred to bidirectional gated recurrent units (GRUs), which generate tracklets and segment them into shorter sub-tracklets based on local distances. The segmented subtracklets are then reconnected into longer trajectories using similarities derived from temporal pooling global features. Additionally, fuzzy logic fusion is employed to combine segmented regions for improved accuracy. The SRPN-based framework demonstrated a significant improvement in detection speed and accuracy. Experimental results show an accuracy increase of 12% over traditional methods, achieving 94% accuracy with a detection time reduction of 30%. The system also improved segmentation precision, with a mean Intersection over Union (IoU) score of 85%, compared to 75% in conventional approaches. [ABSTRACT FROM AUTHOR]

To address the limitations in predictive capabilities of thermal error models built from single-source, single-structure data, this paper proposes a thermal error prediction model based on decision-level fusion of multi-source heterogeneous information to enhance prediction accuracy. First, an experimental platform for multi-source heterogeneous information acquisition was constructed to collect thermal error data from different signal sources (multi-source) and different structures (heterogeneous). Next, based on the characteristics of the multi-source and heterogeneous data, relevant features were extracted to construct the feature set. Then, using the feature information set of the multi-source and heterogeneous data, thermal error prediction sub-models were established using Nonlinear Autoregressive models with exogenous inputs (NARX) and Gated Recurrent Units (GRUs) for a vertical machining center spindle. Finally, the entropy weight method was employed to assign the weights for the linear-weighted fusion rule, achieving decision-level fusion of multi-source heterogeneous information to obtain the final prediction result. This result was then compared with experimental results and the prediction results of single-source models. The findings indicate that the proposed thermal error prediction model closely matches the actual results and outperforms the single-source and single-structure data models in terms of Root-Mean-Square Error (RMSE), Coefficient of Determination (R2), and Mean Absolute Error (MAE). [ABSTRACT FROM AUTHOR]

Improving the accuracy of short-term wind speed predictions is crucial for mitigating the impact on power systems when integrating wind power into an electricity grid. This study developed a hybrid short-term wind speed prediction method, termed VMD–SSA–GRU, by combining variational mode decomposition (VMD) with gated recurrent units (GRUs) and optimizing it using a sparrow search algorithm (SSA). Initially, VMD was used to decompose the wind speed time series into subtime series. After reconstructing these subtime series, a GRU model was employed to establish separate prediction models for each series. Furthermore, an enhanced SSA was proposed to optimize the hyperparameters of the GRU model, which improved the prediction accuracy. Ultimately, the sub-series predictions were aggregated to produce the final wind speed prediction values. The predictive accuracy of this model was validated using the wind speed data measured at a meteorological station near a bridge site. The performance of the VMD–SSA–GRU model was compared with several other hybrid models, including those using wavelet transform, long short-term memory, and other neural networks. Comparably, the RMSE value of the VMD-SSA-GRU model was lower by 25.3%, 60.2%, and 61.7% in comparison to the VMD–SSA–LSTM, VMD–GRU, and VMD–LSTM models, respectively. The experimental results demonstrated that the proposed method achieved higher prediction accuracy than traditional methods. [ABSTRACT FROM AUTHOR]

We estimated the annual harvest of waterfowl and Sandhill Crane Grus canadensis and their eggs by Alaska's rural residents and described seasonal and geographic patterns. Subsistence in Alaska refers to patterns of resource use typical of rural, remote regions where Indigenous people are a high proportion of the population. Rural communities in Alaska rely on the legally-allowed spring-summer harvest of migratory birds for food and socio-cultural wellbeing, in addition to harvests in the fall-winter general hunting season. We based harvest estimates on a large dataset (637 community-years) composed from multiple sources. The estimated annual average harvest of waterfowl and Sandhill Crane by rural residents was 270,641 birds/year (68% in spring-summer, 32% in fall-winter) and 36,692 eggs/year in the 2004–2015 reference period. Harvest estimates for ducks, swans, and Sandhill Crane were lower than in the 1980s–1990s. Harvest amounts, seasonality, and species composition distinguished regional patterns for the Pacific-Aleutian mainland and islands, Bering Sea mainland, St. Lawrence-Diomede islands, North Slope, and Interior Alaska-Upper Copper River. Rural residents accounted for 79% of the total waterfowl harvest in Alaska and high proportions of the total Pacific Flyway harvest for several species of sea ducks, geese, swans, and Sandhill Crane. Alaska's Indigenous people are important partners in harvest management and conservation of migratory birds. Harvest data are needed to inform efficient and appropriate decisions to achieve management goals. This study can facilitate collaboration for harvest management and conservation across Alaska and the flyways by helping diverse users to understand their contributions to the total harvest. [ABSTRACT FROM AUTHOR]

Genes, expressed as sequences of nucleotides, are susceptible to mutations, some of which can lead to cancer. Machine learning and deep learning methods have emerged as vital tools in identifying mutations associated with cancer. Thyroid cancer ranks as the 5th most prevalent cancer in the USA, with thousands diagnosed annually. This paper presents an ensemble learning model leveraging deep learning techniques such as Long Short-Term Memory (LSTM), Gated Recurrent Units (GRUs), and Bi-directional LSTM (Bi-LSTM) to detect thyroid cancer mutations early. The model is trained on a dataset sourced from asia.ensembl.org and IntOGen.org, consisting of 633 samples with 969 mutations across 41 genes, collected from individuals of various demographics. Feature extraction encompasses techniques including Hahn moments, central moments, raw moments, and various matrix-based methods. Evaluation employs three testing methods: self-consistency test (SCT), independent set test (IST), and 10-fold cross-validation test (10-FCVT). The proposed ensemble learning model demonstrates promising performance, achieving 96% accuracy in the independent set test (IST). Statistical measures such as training accuracy, testing accuracy, recall, sensitivity, specificity, Mathew's Correlation Coefficient (MCC), loss, training accuracy, F1 Score, and Cohen's kappa are utilized for comprehensive evaluation. [ABSTRACT FROM AUTHOR]

Introduction: The H9N2 subtype is a predominant avian influenza virus (AIV) circulating in Chinese poultry, forming various genotypes (A-W) based on gene segment origins. This study aims to investigate the genotypic distribution and pathogenic characteristics of H9N2 isolates from wild birds and domestic poultry in Yunnan Province, China. Methods: Eleven H9N2 strains were isolated from fecal samples of overwintering wild birds and proximate domestic poultry in Yunnan, including four from common cranes (Grus g rus), two from bar-headed geese (Anserindicus), and five from domestic poultry (Gallus gallus). Phylogenetic analysis was conducted to determine the genotypes, and representative strains were inoculated into Yunnan mallard ducks to assess pathogenicity. Results: Phylogenetic analysis revealed that five isolates from domestic birds and one from a bar-headed goose belong to genotype S, while the remaining five isolates from wild birds belong to genotype A. These bird-derived strains possess deletions in the stalk domain of NA protein and the N166D mutation of HA protein, typical of poultry strains. Genotype S H9N2 demonstrated oropharyngeal shedding, while genotype A H9N2 exhibited cloacal shedding and high viral loads in the duodenum. Both strains caused significant pathological injuries, with genotype S inducing more severe damage to the thymus and spleen, while genotype A caused duodenal muscle layer rupture. Discussion: These findings suggest that at least two genotypes of H9N2 are currently circulating in Yunnan, and Yunnan mallard ducks potentially act as intermediaries in interspecies transmission. These insights highlight the importance of analyzing the current epidemiological transmission characteristics of H9N2 among wild and domestic birds in China. [ABSTRACT FROM AUTHOR]

With the increasing demand for multi-variety and small-batch products, it's necessary to frequently dispatch and replace the progressive press dies on the stamping production lines to ensure the diversity of processed automobile covering parts. This paper formulates a die scheduling problem with twin-crane transportation (DSP-TCT) encountered in the stamping production line, which concentrates on the scheduling of transporting dies between the production line and warehouse by twin cranes with satisfying crane distance constraint, die position constraint, and precedence constraint. To solve DSP-TCT, this paper proposes a node sequence-based ant colony optimisation algorithm (NS-ACO). In this algorithm, each node represents a single die transportation task with action and time information executed by the twin cranes. The combination of adjacent nodes with a high time utilisation rate can be accumulated as heuristic priority knowledge for guiding optimisation. To demonstrate the effectiveness of the NS-ACO algorithm, numerical experiments with three different die stacking strategies are executed. [ABSTRACT FROM AUTHOR]

Background: Migratory birds exhibit heterogeneity in foraging strategies during wintering to cope with environmental and migratory pressures, and gut bacteria respond to changes in host diet. However, less is known about the dynamics of diet and gut fungi during the wintering period in black-necked cranes (Grus nigricollis). Results: In this work, we performed amplicon sequencing of the trnL-P6 loop and ITS1 regions to characterize the dietary composition and gut fungal composition of black-necked cranes during wintering. Results indicated that during the wintering period, the plant-based diet of black-necked cranes mainly consisted of families Poaceae, Solanaceae, and Polygonaceae. Among them, the abundance of Solanaceae, Polygonaceae, Fabaceae, and Caryophyllaceae was significantly higher in the late wintering period, which also led to a more even consumption of various food types by black-necked cranes during this period. The diversity of gut fungal communities and the abundance of core fungi were more conserved during the wintering period, primarily dominated by Ascomycota and Basidiomycota. LEfSe analysis (P < 0.05, LDA > 2) found that Pyxidiophora, Pseudopeziza, Sporormiella, Geotrichum, and Papiliotrema were significantly enriched in early winter, Ramularia and Dendryphion were significantly enriched in mid-winter, Barnettozyma was significantly abundant in late winter, and Pleuroascus was significantly abundant in late winter. Finally, mantel test revealed a significant correlation between winter diet and gut fungal. Conclusions: This study revealed the dynamic changes in the food composition and gut fungal community of black-necked cranes during wintering in Dashanbao. In the late wintering period, their response to environmental and migratory pressures was to broaden their diet, increase the intake of non-preferred foods, and promote a more balanced consumption ratio of various foods. Balanced food composition played an important role in stabilizing the structure of the gut fungal community. While gut fungal effectively enhanced the host's food utilization rate, they may also faced potential risks of introducing pathogenic fungi. Additionally, we recongnized the limitations of fecal testing in studying the composition of animal gut fungal, as it cannot effectively distinguished between fungal taxa from food or soil inadvertently ingested and intestines. Future research on functions such as cultivation and metagenomics may further elucidate the role of fungi in the gut ecosystem. [ABSTRACT FROM AUTHOR]

Human activity recognition (HAR) has gained significant attention in computer vision and human‐computer interaction. This paper investigates the difficulties encountered in human activity recognition (HAR), precisely differentiating between various activities by extracting spatial and temporal features from sequential data. Traditional machine learning approaches necessitate manual feature extraction, hindering their effectiveness. For temporal features, RNNs have been widely used for HAR; however, they need help processing long sequences, leading to information bottlenecks. This work introduces a framework that effectively integrates spatial and temporal features by utilizing a series of layers that incorporate a self‐attention mechanism to overcome these problems. Here, spatial characteristics are derived using 1D convolutions coupled with pooling layers to capture essential spatial information. After that, GRUs are used to make it possible to effectively represent the temporal dynamics that are inherent in sequential data. Furthermore, the utilization of an attention mechanism serves the purpose of dynamically selecting the significant segments within the sequence, thereby improving the model's comprehension of context and enhancing the efficacy of deep neural networks (DNNs) in the domain of human activity recognition (HAR). Three different optimizers, namely, Adam, SGD, and RMSprop, were employed to train the model. Each optimizer was tested with three distinct learning rates of 0.1, 0.001, and 0.0001. Experiments on the UCI‐HAR dataset have shown that the model works well, with an impressive 97% accuracy rate when using the Adam optimizer with a learning rate of 0.001. [ABSTRACT FROM AUTHOR]

During the early 21st century, the Carpathian Basin was recognised as one of the world's most important migratory area for the Common Crane, but it is not completely clear, what was its status during the late 19th and early 20th centuries. Between 1897 and 1916, a total of 1487 field observation data were published in the journal Aquila from the Carpathian Basin. Our work analysed the timing of the spring migration, how it differed between years and geographical regions, and how the temperature and geographical variables reported above influenced the timing of the migration. The results show that the migration routes of the species have changed significantly over the last century. During the study period, the migration concentrated in the eastern part of the Carpathian Basin, and was particularly rare in the Great Hungarian Plain. There was on average a two-week difference in the timing of migration between the western and eastern parts and between different years. The start and peak of migration were weeks later than today, and this change is mainly due to the effects of climate change. Geographical factors did not influence the migration of the species, whereas higher air temperatures advanced the timing of the migration. [ABSTRACT FROM AUTHOR]

Grus americana (Whooping Crane) are particularly susceptible to colliding with power lines due to their wing loading, size, and flight behavior, often resulting in fatal collisions. This is the first study assessing the specific biological (sex, age, flock size), environmental (time of year, time of day), and structural (line type, line direction) circumstances associated with Whooping Crane collisions with power lines in all 4 reintroduced populations. We documented 65 instances of mortality from power lines and found that both migratory and nonmigratory reintroduced populations were at risk. In migratory populations, collisions seemed more likely to occur during migration. Significantly more males collided with power lines than females in nonmigratory populations. Both transmission and distribution lines posed threats for collisions in all populations. We documented more collisions of juvenile and sub-adult cranes than adults. This study aims to provide insight into the circumstances in which power lines pose a threat to cranes, which will inform efforts to mark power lines and guide decisions on release locations for captive-reared cranes, in hopes of ultimately reducing mortalities and improving population growth for reintroduced Whooping Cranes. [ABSTRACT FROM AUTHOR]

Simple Summary: The gut microbiota plays important roles for maintaining the health of the host. In this study, the results revealed significant differences in the gut bacterial communities among bean geese, hooded cranes, and domestic geese. In comparison to domestic geese, the gut bacterial community of bean geese and hooded cranes had a greater capacity for energy metabolism, suggesting that wild birds may rely more on their gut microbiota to survive in cold conditions. Furthermore, pathogens were discovered to overlap among the three hosts, reminding us to monitor the potential for pathogen transmission between poultry and wild birds. Hooded cranes showed the highest diversity and relative abundance of pathogens compared to the other two species. Due to its vulnerable status, more focus should be paid to the protection of the hooded crane species. These findings could help us gain a deeper understanding of the structure of gut bacterial and pathogenic communities in poultry and wild birds. The host's physiological well-being is intricately associated with the gut microbiota. However, previous studies regarding the intestinal microbiota have focused on domesticated or captive birds. This study used high-throughput sequencing technology to identify the gut bacterial communities of sympatric bean geese, hooded cranes, and domestic geese. The results indicated that the gut bacterial diversity in domestic geese and hooded cranes showed considerably higher diversity than bean geese. The gut bacterial community compositions varied significantly among the three hosts (p < 0.05). Compared to the hooded crane, the bean goose and domestic goose were more similar in their genotype and evolutionary history, with less difference in the bacterial community composition and assembly processes between the two species. Thus, the results might support the crucial role of host genotypes on their gut microbiota. The gut bacteria of wild hooded cranes and bean geese had a greater capacity for energy metabolism compared to domestic geese, suggesting that wild birds may rely more on their gut microbiota to survive in cold conditions. Moreover, the intestines of the three hosts were identified as harboring potential pathogens. The relative abundance of pathogens was higher in the hooded crane compared to the other two species. The hooded crane gut bacterial community assemblage revealed the least deterministic process with the lowest filtering/selection on the gut microbiota, which might have been a reason for the highest number of pathogens result. Compared to the hooded crane, the sympatric bean goose showed the least diversity and relative abundance of pathogens. The intestinal bacterial co-occurrence network showed the highest stability in the bean goose, potentially enhancing host resistance to adverse environments and reducing the susceptibility to pathogen invasion. In this study, the pathogens were also discovered to overlap among the three hosts, reminding us to monitor the potential for pathogen transmission between poultry and wild birds. Overall, the current findings have the potential to enhance the understanding of gut bacterial and pathogenic community structures in poultry and wild birds. [ABSTRACT FROM AUTHOR]

Simple Summary: The red-crowned cranes consist of two populations: continental (Far East Eurasia) and island (Hokkaido, Japan) cranes. It was once thought that these two populations lived independently. Having recovered from near extinction more than a century ago, the island population in Hokkaido, Japan, now exhibits very low genetic diversity, raising concerns about potentially devastating effects from infectious diseases. In 2018, a possible mating between a continental male and an island female was observed in northern Hokkaido. This study investigates their offspring or their blood relatives by examining the major histocompatibility complex (MHC) in cranes from northern and southeastern Hokkaido between 2008 and 2022. We identified 58 MHC types based on nucleotide sequences. MHC types from the possible continental male were predominantly found in cranes from northern Hokkaido. Genetic analysis also suggested clear population differentiation between northern and southeastern Hokkaido. The results suggest that genetic traits from the continental population have been integrated into the Hokkaido cranes, particularly in the northern population. This genetic exchange may improve the disease resistance and environmental adaptability of the Hokkaido crane population, providing valuable insights for conservation efforts. Red-crowned cranes (Grus japonensis) consist of two distinct groups: the continental population and the island population. The island population, localized in Hokkaido, Japan, exhibits very low genetic diversity due to its rapid recovery from the brink of extinction. Our previous research in 2018 highlighted a possible mating between a male from the continental population, with the Gj5 haplotype, and a female from the island population, with the Gj2 haplotype, at Hitominuma Sawmp shore in northern Hokkaido. The present study attempted to unravel the distribution of their offspring by examining the major histocompatibility complex (MHC) of this mixed breeding pair compared with samples collected from cranes in northern and southeastern Hokkaido between 2008 and 2022. The analysis identified 55 MHC types, including 10 known types in a dataset of 89 crane samples, based on amino acid sequences. A total of 58 MHC types were recognized, based on nucleotide sequences, as there were many cases in which the same amino acid sequence had different nucleotide sequences. The five DNA types of MHC in the Hitominuma Swamp male were predominantly identified in eight cranes from northern Hokkaido and one chick from southeastern Hokkaido. In addition, population genetic analysis, based on insertion/deletion (InDel) polymorphisms, indicates distinct population differentiation between the northern and southeastern regions of Hokkaido. These results suggest that genetic contributions from the continental red-crowned crane population have already been integrated into the Hokkaido populations, with a more pronounced influence in northern Hokkaido. [ABSTRACT FROM AUTHOR]

Simple Summary: The fecal microbiome of common cranes (Grus grus) in Tianjin Tuanbo Bird Natural Reserve (wild group) and Beijing Wildlife Park (semi-captive group) in China were analyzed and compared in this study, and the results showed that Firmicutes and Proteobacteria are the dominant phyla. The Sobs and Chao1 indexes revealed that the richness of gut microbiota in the semi-captive group was higher than in the wild group. Among the analysis of the relationship between plants and intestinal bacteria, Zea mays, Glycine max, and Phragmites australia had a significant correlation with the intestinal bacteria of G. grus. Beta diversity data highlighted the significant differences between the two groups and that the gut microbial taxa of the G. grus were associated with the main functions to adapt the dietary compositions. Taken together, these data will help us evaluate the influence of diet on animal microbiomes and improve our ability to enhance the conservation of this species. The gut microbiota of wild animals can regulate host physical health to adapt to the environment. High-throughput sequencing from fecal samples was used to analyze the gut microbiota communities in common cranes (Grus grus) without harming them. Herein, we compared the fecal microbiome of fifteen G. grus in Tianjin Tuanbo Bird Natural Reserve (wild group) and six G. grus sampled from Beijing Wildlife Park (semi-captive group) in China, using 16S amplicon sequencing and bioinformatic analysis. The results showed that microbiota diversity and composition varied in different groups, suggesting that the gut microbiota was interactively influenced by diet and the environment. A total of 38 phyla and 776 genera were analyzed in this study. The dominant phyla of the G. grus were Firmicutes and Proteobacteria. Meanwhile, the microbiota richness of the semi-captive group was higher than the wild group. Data on beta diversity highlighted significant differences based on different dietary compositions. Zea mays, Glycine max, and Phragmites australia showed a significant correlation with intestinal bacteria of G. grus. This study provides a comprehensive analysis of diet and microbiomes in semi-captive and wild G. grus living in different environments, thus helping us to evaluate the influence on animal microbiomes and improve conservation efforts for this species. [ABSTRACT FROM AUTHOR]

This study introduces a deep-learning-based automatic sleep scoring system to detect sleep apnea using a single-lead electrocardiography (ECG) signal, focusing on accurately estimating the apnea–hypopnea index (AHI). Unlike other research, this work emphasizes AHI estimation, crucial for the diagnosis and severity evaluation of sleep apnea. The suggested model, trained on 1465 ECG recordings, combines the deep-shallow fusion network for sleep apnea detection network (DSF-SANet) and gated recurrent units (GRUs) to analyze ECG signals at 1-min intervals, capturing sleep-related respiratory disturbances. Achieving a 0.87 correlation coefficient with actual AHI values, an accuracy of 0.82, an F1 score of 0.71, and an area under the receiver operating characteristic curve of 0.88 for per-segment classification, our model was effective in identifying sleep-breathing events and estimating the AHI, offering a promising tool for medical professionals. [ABSTRACT FROM AUTHOR]

Peatlands represent an important part of the landscape of boreal western Canada, occupying some 365,157 km2. Sixty-three percent of these are minerogenous fens. Scattered among these fens are landscape features that have unique and distinctive patterns—pools and carpets (flarks) separated by raised linear 'strings'. These patterned fens harbor rare and uncommon species and serve as habitats for endangered wildlife (e.g., woodland caribou, whooping cranes). In this study, utilizing Google Earth Pro (1) we documented 1083 ribbed fens and 250 reticulate fens in the province of Alberta, Canada; (2) determined the regional variation in patterned fen occurrences; (3) described the various morphological forms of patterned fens; and (4) recognized these as six distinctive peatland site-types. Patterned fens are not randomly arranged on the landscape. Ribbed fens are concentrated on regional high elevational uplands and montane benchlands with morainal deposits, while reticulate fens are more numerous on low elevation plains with glacial-fluvial and glacial-lacustrine deposits. Patterned fens vary along minerotrophic vegetation and chemical gradients and have a complex set of morphological types. To our knowledge, this is the first study that provides base line information on the abundance and distribution of patterned fens in Alberta and associates morphological patterned fen types with environmental or geological characteristics. The digital files and maps provide a permanent record against which future change can be compared. [ABSTRACT FROM AUTHOR]

Simple Summary: Climate change and global warming have effects on every ecosystem and have caused huge losses in global biodiversity. This study identified that currently, the study area explored in this work provides a good quantity (around 35%) of suitable habitat for the Demoiselle Crane. The most influential factors determining Demoiselle Crane habitat suitability included the temperature seasonality, annual mean temperature, terrain ruggedness index, and human population density as significant contributors. Under changing climate scenarios, the study predicted a major loss of species current suitable habitat, with shrinkage and movement towards western–central areas along the Pakistan–Afghanistan boarder. The inevitable impacts of climate change have reverberated across ecosystems and caused substantial global biodiversity loss. Climate-induced habitat loss has contributed to range shifts at both species and community levels. Given the importance of identifying suitable habitats for at-risk species, it is imperative to assess potential current and future distributions, and to understand influential environmental factors. Like many species, the Demoiselle crane is not immune to climatic pressures. Khyber Pakhtunkhwa and Balochistan provinces in Pakistan are known wintering grounds for this species. Given that Pakistan is among the top five countries facing devastating effects of climate change, this study sought to conduct species distribution modeling under climate change using data collected during 4 years of field surveys. We developed a Maximum Entropy distribution model to predict the current and projected future distribution of the species across the study area. Future habitat projections for 2050 and 2070 were carried out using two representative concentration pathways (RCP 4.5 and RCP 8.5) under three global circulation models, including HADGEM2-AO, BCC-CSM1-1, and CCSM4. The most influential factors shaping Demoiselle Crane habitat suitability included the temperature seasonality, annual mean temperature, terrain ruggedness index, and human population density, all of which contributed significantly to the suitability (81.3%). The model identified 35% of the study area as moderately suitable (134,068 km2) and highly suitable (27,911 km2) habitat for the species under current climatic conditions. Under changing climate scenarios, our model predicted a major loss of the species' current suitable habitat, with shrinkage and shift towards western–central areas along the Pakistan–Afghanistan boarder. The RCP 8.5, which is the extreme climate change scenario, portrays particularly severe consequences, with habitat losses reaching 65% in 2050 and 85% in 2070. This comprehensive study provides useful insights into the Demoiselle Crane habitat's current and future dynamics in Pakistan. [ABSTRACT FROM AUTHOR]

Copyright of Fire Ecology is the property of Springer Nature and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Wildlife species confront threats from climate and land use change, exacerbating the influence of extreme climatic events on populations and biodiversity. Migratory waterbirds are especially vulnerable to hydrological drought via reduced availability of surface water habitats. We assessed how whooping cranes (Grus americana) modified habitat use and migration strategies during drought to evaluate their resilience to changing conditions and adaptive capacity. We categorized >8000 night‐roost sites used by 146 cranes from 2010 to 2022 and examined relative use during non‐drought, moderate drought, and extreme drought conditions. We found cultivated and uncultivated palustrine and lacustrine wetlands were generally used less during droughts than non‐drought conditions. Conversely, impounded palustrine and lacustrine systems and rivers served more frequently as drought refugia (i.e., used more during drought than non‐drought conditions). Night roosts occurred primarily on private lands (86% overall); public land use decreased with latitude and increased with drought severity, with greatest use (56%) occurring during severe autumn drought in the southern Great Plains. Quantifying use of identified critical habitats in the United States indicated that Cheyenne Bottoms State Waterfowl Management Area and Quivira National Wildlife Refuge were used less during drought, and the Central Platte River and Salt Plains National Wildlife Refuge received similar use during drought compared to non‐drought conditions. Our findings provide insights into compensatory use of habitats, where impounded surface water may function in a complementary fashion with natural wetlands. Collectively, these and other types of wetlands distributed across the migration corridor provided a reliable network of habitat available across the Great Plains. A diversity of wetlands available during variable environmental conditions would be useful in supporting continued recovery of whooping cranes and likely have benefits for a wide array of migratory birds. [ABSTRACT FROM AUTHOR]

We consider the problem of extracting a deterministic finite automaton (DFA) from a trained recurrent neural network (RNN). We present a novel algorithm that uses exact learning and abstract interpretation to perform efficient extraction of a minimal DFA describing the state dynamics of a given RNN. We use Angluin's L ∗ algorithm as a learner and the given RNN as an oracle, refining the abstraction of the RNN only as much as necessary for answering equivalence queries. Our technique allows DFA-extraction from the RNN while avoiding state explosion, even when the state vectors are large and fine differentiation is required between RNN states. We experiment on multi-layer GRUs and LSTMs with state-vector dimensions, alphabet sizes, and underlying DFA which are significantly larger than in previous DFA-extraction work. Aditionally, we discuss when it may be relevant to apply the technique to RNNs trained as language models rather than binary classifiers, and present experiments on some such examples. In some of our experiments, the underlying target language can be described with a succinct DFA, yet we find that the extracted DFA is large and complex. These are cases in which the RNN has failed to learn the intended generalisation, and our extraction procedure highlights words which are misclassified by the seemingly "perfect" RNN. [ABSTRACT FROM AUTHOR]

Background: The genus Helius Lepeletier & Serville, 1828 is globally distributed with 232 species and subspecies, of which 25 have been known to occur in China. Amongst the Chinese Helius crane flies, 24 species are distributed in southern China. The species diversity of Helius in other Chinese regions may be severely underestimated due to a lack of investigation. Some investigations on crane flies in Inner Mongolia, China have been initiated by the authors together with other entomologists, with Helius being one of the key targets of attention. New information: Two Helius species, H. (Helius)flavus (Walker, 1856) and H. (H.) gracillimus Alexander, 1938, are added to the Chinese fauna. The two newly-recorded species also represent the first records of the crane fly tribe Elephantomyiini in Inner Mongolia. Re-descriptions and illustrations of the two newly-recorded species are presented. [ABSTRACT FROM AUTHOR]

The western population of the red‐crowned crane Grus japonensis in mainland China has been decreasing in the past few decades and wild population enhancement programmes have been launched in this country. First, 14 captive‐bred red‐crowned cranes were released into the core area of Yancheng National Nature Reserve for Rare Birds (YNNR), one of the most important wintering areas of this species, in 2013 (seven individuals) and 2015 (seven individuals) and then 8 more captive‐bred cranes were released into YNNR from February 2022 to February 2023. We used satellite positioning and drone monitoring to study the status of released cranes. The results showed that two individuals (No. BJZ001 and BJZ008) from the first group of released cranes were found breeding in 6 of 7 years in the YNNR from 2017 to 2023. Three individuals (No. WNNR022, WNNR025 and WNNR026) from the second group of released cranes were recorded breeding in YNNR in 2023. All released cranes lived in the YNNR year round and did not migrate with wild cranes. Raccoon dogs, Nyctereutes procyonoides, were first recorded as red‐crowned crane nest predators in the YNNR. Although these released cranes breed successfully in the YNNR, nestlings might face the threat of predators in non‐traditional breeding areas. Further research is needed to determine whether offsprings of released individuals migrate with wild cranes and if breeding in their original wintering grounds is truly beneficial for population growth. [ABSTRACT FROM AUTHOR]

Urbanization, industrialization, and intensification of agriculture have led to considerable heavy metal pollution across the globe, harming our ecosystems. Concentrations of arsenic (As), cadmium (Cd), copper (Cu), and lead (Pb) have been analysed in 249 eggshells collected between 2006 and 2021 from 83 female Common Cranes (Grus grus) nesting within north-eastern Germany. Information on the presence of trace elements in cranes from Europe and their potential adverse effects on the reproduction are largely missing. Only Cu and Pb were found to be present in eggshell samples. Levels of both metals did not exceed concentrations considered potentially toxic in birds and unhatched eggs did not contain higher metal concentrations compared to eggshell residues from hatched eggs. Statistical analysis revealed that trace element concentrations decreased significantly over the course of the study period. The ban of leaded gasoline in the early twenty-first century and strict limitations of heavy metal-based biocontrol products are likely responsible for this decrease over the years. However, as Cu levels gradually increase with increasing proportions of agricultural areas within the cranes' home ranges, we suggest that considerable amounts of Cu originating from agricultural practises are still being released into the environment. We found no increase in metal concentrations in eggshells with increasing female age, suggesting that heavy metals do not accumulate in the circulatory systems of the adults over time. This study is the first to assess heavy metal contamination in Common Cranes and indicates the suitability of crane's eggshells as bioindicator for monitoring environmental pollution. [ABSTRACT FROM AUTHOR]