Search Results (52)

Agriculture in India supports millions of livelihoods and is a major force behind economic expansion. Challenges in modern agriculture depend on environmental factors (such as soil quality and climate variability) and biotic factors (such as pests and diseases). These challenges can be addressed by advancements in technology (such as sensors, internet of things, communication, etc.) and data-driven approaches (such as machine learning (ML) and deep learning (DL)), which can help with crop yield and sustainability in agriculture. This study introduces an innovative deep neural network (DNN) approach for identifying leaf diseases in paddy crops at an early stage. The proposed neural network is a hybrid DL model comprising feature extraction, channel attention, inception with residual, and classification blocks. Channel attention and inception with residual help extract comprehensive information about the crops and potential diseases. The classification module uses softmax to obtain the score for different classes. The importance of each block is analyzed via an ablation study. To understand the feature extraction ability of the modules, extracted features at different stages are fed to the SVM classifier to obtain the classification accuracy. This technique was experimented on eight classes with 7857 paddy crop images, which were obtained from local paddy fields and freely available open sources. The classification performance of the proposed technique is evaluated according to accuracy, sensitivity, specificity, F1 score, MCC, area under curve (AUC), and receiver operating characteristic (ROC). The model was fine-tuned by setting the hyperparameters (such as batch size, learning rate, optimizer, epoch, and train and test ratio). Training, validation, and testing accuracies of 99.91%, 99.87%, and 99.49%, respectively, were obtained for 20 epochs with a learning rate of 0.001 and sgdm optimizer. The proposed network robustness was studied via an ablation study and with noisy data. The model’s classification performance was evaluated for other agricultural data (such as mango, maize, and wheat diseases). These research outcomes can empower farmers with smarter agricultural practices and contribute to economic growth. Full article

The conversion of tropical forests into urban and agriculture landscapes may alter insect populations through habitat disturbance and impact the diets of aerial insectivores. Most dietary studies on aerial insectivores have limitation on identifying prey at higher taxonomic levels in broad landscapes, restricting species-level identification and thus making a detailed dietary comparison impossible. This study examines the dietary changes through adaptation of house-farm swiftlets (Aerodramus sp.) and Pacific swallows (Hirundo tahitica) across three distinct habitats in Peninsular Malaysia: mixed-use landscapes, oil palm plantations, and paddy fields. High-throughput DNA metabarcoding with ANML primers targeting mitochondrial CO1 gene, identified 245 arthropod prey species, with six dominant orders: Coleoptera, Diptera, Blattodea, Hemiptera, Hymenoptera, and Lepidoptera. Mixed-use landscapes supported the highest dietary diversity and niche breadth, reflecting their ecological complexity. Paddy fields exhibited moderate diversity, while oil palm plantations demonstrated the lowest diversity, influenced by simplified vegetation structures and limited prey availability. The consumption of agricultural pests and vector species highlights the critical ecological role of aerial insectivorous birds in natural pest management and mitigating vector-borne disease risks. This research emphasizes the importance of conserving habitat heterogeneity to sustain the ecological services provided by these birds, benefiting both agricultural productivity and public health. Full article

Barnyard grass is one of the most serious rice weeds, often growing near paddy fields and therefore potentially serving as a bridging host for the rice blast fungus. In this study, we isolated three fungal strains from diseased barnyard grass leaves in a rice field. Using a pathogenicity assay, we confirmed that they were capable of causing blast symptoms on barnyard grass and rice leaves to various extents. Based on morphology characterization and genome sequence analyses, we confirmed that these three strains were Epicoccum sorghinum (SCAU-1), Pyricularia grisea (SCAU-2), and Exserohilum rostratum (SCAU-6). The established Avirulence (Avr) genes Avr-Pia, Avr-Pita2, and ACE1 were detected by PCR amplification in SCAU-2, but not in SCAU-1 or SCAU-6. Furthermore, the whole-genome sequence analysis helped to reveal the genetic variations and potential virulence factors relating to the host specificity of these three fungal pathogens. Based on the evolutionary analysis of single-copy orthologous proteins, we found that the genes encoding glycoside hydrolases, carbohydrate esterases, oxidoreductase, and multidrug transporters in SCAU-1 and SCAU-6 were expanded, while expansion in SCAU-2 was mainly related to carbohydrate esterases. In summary, our study provides clues to understand the pathogenic mechanisms of fungal isolates from barnyard grass with the potential to cause rice blast. Full article

Weeds in paddy fields compete with rice for nutrients and cause pests and diseases, greatly affecting rice yield. Accurate weed detection is vital for implementing variable spraying with unmanned aerial vehicles (UAV) for weed control. Therefore, this paper presents an improved weed detection algorithm, YOLOv10n-FCDS (YOLOv10n with FasterNet, CGBlock, Dysample, and Structure of Lightweight Detection Head), using UAV images of Sagittaria trifolia in rice fields as the research object, to address challenges like the detection of small targets, obscured weeds and weeds similar to rice. We enhanced the YOLOv10n model by incorporating FasterNet as the backbone for better small target detection. CGBlock replaced standard convolution and SCDown modules to improve the detection ability of obscured weeds, while DySample enhanced discrimination between weeds and rice. Additionally, we proposed a lightweight detection head based on shared convolution and scale scaling, maintaining accuracy while reducing model parameters. Ablation studies revealed that YOLOv10n-FCDS achieved a 2.6% increase in mean average precision at intersection over union 50% for weed detection, reaching 87.4%. The model also improved small target detection (increasing mAP50 by 2.5%), obscured weed detection (increasing mAP50 by 2.8%), and similar weed detection (increasing mAP50 by 3.0%). In conclusion, YOLOv10n-FCDS enables effective weed detection, supporting variable spraying applications by UAVs in rice fields. Full article

Rodents are reservoirs for zoonotic pathogens, making it essential to study both rodents and their ectoparasites. In 2022 and 2023, we investigated the spatial distribution of rodents and their mites across Korea, focusing on three vector-borne diseases (VBDs): Anaplasma, Ehrlichia, and Rickettsia. A total of 835 wild rodents were collected from 16 locations, each consisting of five distinct environmental settings (mountains, waterways, reservoirs, fields, and paddy fields), with 20 traps per setting, totaling 100 Sherman live folding traps per site. Each rodent was identified using a taxonomic key, and post-mortem examinations led to the collection of 7971 mites (498 pools), followed by PCR analysis. Among the rodents, Anaplasma phagocytophilum was detected in 10.3%, Ehrlichia muris in 0.5%, Ehrlichia ruminantium in 0.2%, and Rickettsia raoultii in 2.9%. In mites, A. phagocytophilum was found in 8.8%, E. muris in 0.2%, R. raoultii in 0.2%, R. endosymbiont in 1.6%, and R. australis in 1.2%. This study marks the first detection of E. muris and R. raoultii in Korean rodents and the first global discovery of E. ruminantium in rodents. The detection of multiple pathogens in mites worldwide highlights the importance of continuous VBD monitoring to mitigate public health risks. Full article

The growth environment significantly influences the intestinal microbiota of aquatic organisms. We investigated the composition and functional differences in the intestinal microbiota of red claw crayfish (Cherax quadricarinatus) in rice fields (RB) and ponds (PB) by 16S rDNA high-throughput sequencing technology. The results indicate that the Shannon, Simpson, Sobs, Chao1, and ACE indices of PB are all higher than those of RB, demonstrating greater diversity and richness of intestinal microbiota. The dominant phyla in the intestinal microbiota of the Cherax quadricarinatus were Proteobacteria, Tenericutes, and Firmicutes. Tenericutes and Proteobacteria were significantly more abundant in the RB than in the PB, while Planctomycetes and Firmicutes were significantly more abundant in the PB than in the RB. The results of network correlation analysis indicate that Proteobacteria and Firmicutes exhibit strong connectivity with other microbial groups in the gut microbiota of Cherax quadricarinatus, showing significant centrality. They play an important role in the interactions within the gut microbiota community. The dominant bacterial genera in the Cherax quadricarinatus’s gut were Citrobacter, Candidatus_Bacilloplasma, and Clostridium_sensu_stricto_1. The abundance of the genus Clostridium was significantly higher in the PB than in the RB, whereas the abundance of Candidatus_Hepatoplasma and Vibrio was significantly lower in the PB than in the RB. The prediction function of KEGG enrichment showed that the abundance of Amino acid metabolism, Biosynthesis of Other Secondary Metabolites, Transport and Catabolism, Cancers, and Nervous System, Substance Dependence were significantly higher in the PB, while the infectious diseases pathway was enriched in the RB. In summary, our results revealed significant differences in the composition and diversity of intestinal microbiota in the Cherax quadricarinatus between rice paddy and pond farming environments. The intestinal microbiota of the Cherax quadricarinatus grown in pond environments exhibit higher diversity and stability, manifested by an increase in beneficial bacteria abundance and a decrease in opportunistic pathogens. These findings significantly improve understanding of the complex relationship among Cherax quadricarinatus, intestinal microbiota, and the environment. Full article

In Asia, rice is the most consumed grain by humans, serving as a staple food in India. The yield of rice paddies is easily affected by nutrient deficiencies and leaf diseases. To overcome this problem and improve the yield productivity of rice, nutrient deficiency and leaf disease identification are essential. The main nutrient elements in paddies are potassium, phosphorus, and nitrogen (PPN), the deficiency of any of which strongly affects the rice plants. When multiple nutrient elements are deficient, the leaf color of the rice plants is altered. To overcome this problem, optimal nutrient delivery is required. Hence, the present study proposes the use of Fuzzy C Means clustering (FCM) with Improved Tunicate Swarm Optimization (ITSO) to segment the lesions in rice plant leaves and identify the deficient nutrients. The proposed ITSO integrates the Tunicate Swarm Optimization (TSO) and Bacterial Foraging Optimization (BFO) approaches. The Hybrid Convolutional Neural Network (HCNN), a deep learning model, is used with ITSO to classify the rice leaf diseases, as well as nutrient deficiencies in the leaves. Two datasets, namely, a field work dataset and a Kaggle dataset, were used for the present study. The proposed HCNN-ITSO classified Bacterial Leaf Bright (BLB), Narrow Brown Leaf Spot (NBLS), Sheath Rot (SR), Brown Spot (BS), and Leaf Smut (LS) in the field work dataset. Furthermore, the potassium-, phosphorus-, and nitrogen-deficiency-presenting leaves were classified using the proposed HCNN-ITSO in the Kaggle dataset. The MATLAB platform was used for experimental analysis in the field work and Kaggle datasets in terms of various performance measures. When compared to previous methods, the proposed method achieved the best accuracies of 98.8% and 99.01% in the field work and Kaggle datasets, respectively. Full article

In Indonesia, where the agricultural insurance system has been in full operation since 2016, a new damage assessment estimation formula for rice diseases was created through integrating the current damage assessment method and unmanned aerial vehicle (UAV) multispectral remote sensing data to improve the efficiency and precision of damage assessment work performed for the payments of insurance claims. The new method can quickly and efficiently output objective assessment results. In this study, UAV images and bacterial leaf blight (BLB) rice damage assessment data were acquired during the rainy and dry seasons of 2021 and 2022 in West Java, Indonesia, where serious BLB damage occurs every year. The six-level BLB score (0, 1, 3, 5, 7, and 9) and damage intensity calculated from the score were used as the BLB damage assessment data. The relationship between normalized UAV data, normalized difference vegetation index (NDVI), and BLB score showed significant correlations at the 1% level. The analysis of damage intensities and UAV data for paddy plots in all cropping seasons showed high correlation coefficients with the normalized red band, normalized near-infrared band, and NDVI, similar to the results of the BLB score analysis. However, for paddy plots with damage intensities of 70% or higher, the biased numbering of the BLB score data may have affected the evaluation results. Therefore, we conducted an analysis using an average of 1090 survey points for each BLB score and confirmed a strong relationship, with correlation coefficients exceeding 0.9 for the normalized red band, normalized near-infrared band, and NDVI. Through comparing the time required by the current assessment method with that required by the assessment method integrating UAV data, it was demonstrated that the evaluation time was reduced by more than 60% on average. We are able to propose a new assessment method for the Indonesian government to achieve complete objective enumeration. Full article

Rice straw is not easy to decompose, it takes a long time to compost, and the anaerobic bacteria involved in the decomposition process produce a large amount of carbon dioxide (CO₂), indicating that applications for rice straw need to be developed. Recycling rice straw in agricultural crops is an opportunity to increase the sustainability of grain production. Several studies have shown that the probiotic population gradually decreases in the soil, leading to an increased risk of plant diseases and decreased biomass yield. Because the microorganisms in the soil are related to the growth of plants, when the soil microbial community is imbalanced it seriously affects plant growth. We investigated the feasibility of using composted rice stalks to artificially cultivate microorganisms obtained from the Oryza sativa-planted environment for analyzing the mycobiota and evaluating applications for sustainable agriculture. Microbes obtained from the water-submerged part (group-A) and soil part (group-B) of O. sativa were cultured in an artificial medium, and the microbial diversity was analyzed with internal transcribed spacer sequencing. Paddy field soil was mixed with fermented paddy straw compost, and the microbes obtained from the soil used for O. sativa planting were designated as group-C. The paddy fields transplanted with artificially cultured microbes from group-A were designated as group-D and those from group-B were designated as group-E. We found that fungi and yeasts can be cultured in groups-A and -B. These microbes altered the soil mycobiota in the paddy fields after transplantation in groups-D and -E compared to groups-A and -B. Development in O. sativa post treatment with microbial transplantation was observed in the groups-D and -E compared to group-C. These results showed that artificially cultured microorganisms could be efficiently transplanted into the soil and improve the mycobiota. Phytohormones were involved in improving O. sativa growth and rice yield via the submerged part-derived microbial medium (group-D) or the soil part-derived microbial medium (group-E) treatments. Collectively, these fungi and yeasts may be applied in microbial transplantation via rice straw fermentation to repair soil mycobiota imbalances, facilitating plant growth and sustainable agriculture. These fungi and yeasts may be applied in microbial transplantation to repair soil mycobiota imbalances and sustainable agriculture. Full article

Radix pseudostellariae is one of the well-known genuine medicinal herbs in Fujian province, China. However, the continuous cropping obstacles with respect to R. pseudostellariae have seriously affected the sustainable utilization of medicinal resources and the development of related industrial systems. The occurrence of continuous cropping obstacles is a comprehensive effect of multiple deteriorating biological and abiotic factors in the rhizosphere soil. Therefore, intensive ecological methods have been the key to abating such obstacles. In this study, four treatments were set up, i.e., fallow (RP-F), fallow + bacterial fertilizer (RP-F-BF), rice-paddy-upland rotation (RP-R), and rice-paddy-upland rotation + bacterial fertilizer (RP-R-BF), during the interval between two plantings of R. pseudostellariae, with a newly planted (NP) treatment as the control. The results show that the yield of R. pseudostellariae under the RP-F treatment decreased by 46.25% compared to the NP treatment. Compared with the RP-F treatment, the yields of the RP-F-BF, RP-R, and RP-R-BF treatments significantly increased by 14.11%, 27.79%, and 62.51%, respectively. The medicinal quality of R. pseudostellariae treated with RP-R-BF was superior to that achieved with the other treatments, with the total saponin and polysaccharide contents increasing by 8.54% and 27.23%, respectively, compared to the RP-F treatment. The ecological intensive treatment of RP-R-BF significantly increased the soil pH, content of organic matter, abundance of beneficial microbial populations, and soil enzyme activity, thus remediating the deteriorating environment of continuous cropping soil. On this basis, the ecological intensive treatment RP-R-BF significantly increased the activity of protective enzymes and the expression levels of genes related to disease and stress resistance in leaves and root tubers. Redundancy and Pearson correlation analyses indicated that rice-paddy-upland rotation improved the soil structure, promoted the growth of eutrophic r-strategy bacterial communities, enhanced compound oxidation and reduction, broke the relationship between the deteriorating environment and harmful biological factors, and eventually weakened the intensity of harmful factors. The subsequent application of bacterial fertilizer improved the beneficial biological and abiotic factors, activated various ecological functions of the soil, enhanced the ecological relationship between various biological and abiotic factors, and reduced the stress intensity of R. pseudostellariae, thereby improving its disease and stress resistance, and ultimately reflecting the recovery of yield and quality. The results indirectly prove that the intensive ecological amelioration of the soil environment was the main factor for the yield recovery of R. pseudostellariae under continuous cropping. Full article

Paddy leaf diseases encompass a range of ailments affecting rice plants’ leaves, arising from factors like bacteria, fungi, viruses, and environmental stress. Precision agriculture leverages technologies for enhanced crop production, with disease detection being a vital element. Prompt identification of diseases in paddy leaves is critical for curtailing their propagation and reducing crop damage. However, manually diagnosing paddy diseases in regions with vast agricultural areas and limited experts proves immensely difficult. The utilization of machine learning (ML) and deep learning (DL) for diagnosing diseases in agricultural crops appears to be effective and well-suited for widespread application. These ML/DL methods cannot ensure data privacy, as they involve sharing training data with a central server, overlooking competitive and regulatory considerations. As a solution, federated learning (FL) aims to facilitate decentralized training to tackle the identified limitations of centralized training. This paper utilizes the FL approach for the classification of rice-leaf diseases. The manuscript presents an effective approach for rice-leaf disease classification with a federated architecture, ensuring data privacy. We have compiled an unbalanced dataset of rice-leaf disease images, categorized into four diseases with their respective image counts: bacterial blight (1584), brown spot (1440), blast (1600), and tungro (1308). The proposed method, called federated transfer learning (F-TL), maintains privacy for all connected devices using a decentralized client-server setup. Both IID (independent and identically distributed) and non-IID datasets were utilized for testing the F-TL framework after preprocessing. Initially, we conducted an effectiveness analysis of CNN and eight transfer learning models for rice-leaf disease classification. Among them, MobileNetV2 and EfficientNetB3 outperformed the other transfer-learned models. Subsequently, we trained these models using both IID and non-IID datasets in a federated learning environment. The framework’s performance was assessed through diverse scenarios, comparing it with traditional and federated learning models. The evaluation considered metrics like validation accuracy, loss as well as resource utilization such as CPU and RAM. EfficientNetB3 excelled in training, achieving 99% accuracy with 0.1 loss for both IID and non-IID datasets. MobilenetV2 showed slightly lower training accuracy at 98% (IID) and 90% (non-IID) with losses of 0.4 and 0.6, respectively. In evaluation, EfficientNetB3 maintained 99% accuracy with 0.1 loss for both datasets, while MobilenetV2 achieved 90% (IID) and 97% (non-IID) accuracy with losses of 0.6 and 0.2, respectively. Results indicated the F-TL framework’s superiority over traditional distributed deep-learning classifiers, demonstrating its effectiveness in both single and multiclient instances. Notably, the framework’s strengths lie in its cost-effectiveness and data-privacy assurance for resource-constrained edge devices, positioning it as a valuable alternative for rice-leaf disease classification compared to existing tools. Full article

Rice paddy diseases significantly reduce the quantity and quality of crops, so it is essential to recognize them quickly and accurately for prevention and control. Deep learning (DL)-based computer-assisted expert systems are encouraging approaches to solving this issue and dealing with the dearth of subject-matter specialists in this area. Nonetheless, a major generalization obstacle is posed by the existence of small discrepancies between various classes of paddy diseases. Numerous studies have used features taken from a single deep layer of an individual complex DL construction with many deep layers and parameters. All of them have relied on spatial knowledge only to learn their recognition models trained with a large number of features. This study suggests a pipeline called “RiPa-Net” based on three lightweight CNNs that can identify and categorize nine paddy diseases as well as healthy paddy. The suggested pipeline gathers features from two different layers of each of the CNNs. Moreover, the suggested method additionally applies the dual-tree complex wavelet transform (DTCWT) to the deep features of the first layer to obtain spectral–temporal information. Additionally, it incorporates the deep features of the first layer of the three CNNs using principal component analysis (PCA) and discrete cosine transform (DCT) transformation methods, which reduce the dimension of the first layer features. The second layer’s spatial deep features are then combined with these fused time-frequency deep features. After that, a feature selection process is introduced to reduce the size of the feature vector and choose only those features that have a significant impact on the recognition process, thereby further reducing recognition complexity. According to the results, combining deep features from two layers of different lightweight CNNs can improve recognition accuracy. Performance also improves as a result of the acquired spatial–spectral–temporal information used to learn models. Using 300 features, the cubic support vector machine (SVM) achieves an outstanding accuracy of 97.5%. The competitive ability of the suggested pipeline is confirmed by a comparison of the experimental results with findings from previously conducted research on the recognition of paddy diseases. Full article

Chlorpyrifos has been used extensively for decades to control crop pests and disease-transmitting insects; its contribution to increasing food security and minimizing the spread of diseases has been well documented. Pymetrozine and Avermectin (also known as abamectin) have been used to replace the toxic organophosphate insecticides (e.g., Chlorpyrifos) applied to rice crops in China, where the overuse of pesticides has occurred. In addition, climate change has exacerbated pesticide use and pollution. Thus, farmers and communities are at risk of exposure to pesticide pollution. This study reviews the contamination, exposure, and health risks through environmental and biological monitoring of the legacy pesticide Chlorpyrifos and currently used insecticides Pymetrozine and Avermectin in China; it investigates whether changes in pesticide usage from Chlorpyrifos to Pymetrozine and Avermectin reduce pesticide contamination and health hazards to communities and residents. In addition, this review discusses whether Pymetrozine and Avermectin applications could be recommended in other countries where farmers largely use Chlorpyrifos and are exposed to high health risks under climate change scenarios. Although Chlorpyrifos is now banned in China, farmers and residents exposed to Chlorpyrifos are still experiencing adverse health effects. Local farmers still consider Chlorpyrifos an effective pesticide and continue to use it illegally in some areas. As a result, the concentration levels of Chlorpyrifos still exceed risk-based thresholds, and the occurrence of Chlorpyrifos with high toxicity in multiple environmental routes causes serious health effects owing to its long-term and wide application. The bioaccumulation of the currently used insecticides Pymetrozine and Avermectin in the environment is unlikely. Pymetrozine and Avermectin used in paddy water and soil for crop growth do not pose a significant hazard to public health. A change in pesticide use from Chlorpyrifos to Pymetrozine and Avermectin can reduce the pesticide contamination of the environment and health hazards to communities and residents. Finally, we recommend Pymetrozine and Avermectin in other countries, such as Vietnam, and countries in Africa, such as Ghana, where farmers still largely use Chlorpyrifos. Full article

The primary purpose of our study is to clarify the differences in physicochemical properties and microbial community composition with the continuous evolution of soil utilization types. Here, we used natural forest soil (NS), healthy banana garden soil (HS), diseased banana garden soil (DS), and paddy soil (PS) in tropical areas of Hainan Province to conduct this study. According to our research, the abundance and diversity of soil bacteria (HS/DS and PS) decrease significantly as soil utilization types evolve. In healthy banana soil, the amount of Actinobacteria and Firmicutes at the bacterial phylum level is more significant than in other soil utilization types. It was observed that the bacterial community structure in NS was notably distinct from that in HS and PS. Apart from paddy soil, the bacterial makeup of the other two soil utilization types mainly remained consistent. Pathogenic soil (DS) undergoes significant changes in its chemical properties. These changes are primarily seen as decreased pH and organic carbon content and increased C/N and inorganic nitrogen content (NH₄⁺, NO₃⁻). This suggests that a specific type of microorganism (Fusarium oxysporum f. sp. cubense) can cause a significant shift in the soil environment, leading to an unexpected change in soil type. Therefore, to ensure that the soil is healthy, we must balance the soil microbial community composition, promote the increase of the beneficial microbial species and quantity, and create an environment suitable for microbial growth. Full article

Wild waterbirds, and especially wild waterfowl, are considered to be a reservoir for avian influenza viruses, with transmission likely occurring at the agricultural-wildlife interface. In the past few decades, avian influenza has repeatedly emerged in China along the East Asian-Australasian Flyway (EAAF), where extensive habitat conversion has occurred. Rapid environmental changes in the EAAF, especially distributional changes in rice paddy agriculture, have the potential to affect both the movements of wild migratory birds and the likelihood of spillover at the agricultural-wildlife interface. To begin to understand the potential implications such changes may have on waterfowl and disease transmission risk, we created dynamic Brownian Bridge Movement Models (dBBMM) based on waterfowl telemetry data. We used these dBBMM models to create hypothetical scenarios that would predict likely changes in waterfowl distribution relative to recent changes in rice distribution quantified through remote sensing. Our models examined a range of responses in which increased availability of rice paddies would drive increased use by waterfowl and decreased availability would result in decreased use, predicted from empirical data. Results from our scenarios suggested that in southeast China, relatively small decreases in rice agriculture could lead to dramatic loss of stopover habitat, and in northeast China, increases in rice paddies should provide new areas that can be used by waterfowl. Finally, we explored the implications of how such scenarios of changing waterfowl distribution may affect the potential for avian influenza transmission. Our results provide advance understanding of changing disease transmission threats by incorporating real-world data that predicts differences in habitat utilization by migratory birds over time. Full article