Glycoprotein hormones serve as critical regulators of diverse physiological processes in both vertebrates and invertebrates, yet their functional roles in insect reproduction remain poorly understood. Here, we identified two glycoprotein hormone subunits, SfLFT1 and SfLFT2, and their cognate receptor SfLFTR (a leucine-rich-repeat-containing GPCR) in Spodoptera frugiperda. Liposome-encapsulated siRNA-mediated knockdown of these genes severely disrupted ovarian development as evidenced by suppressed vitellogenin biosynthesis and reduced mature follicle formation. Coimmunoprecipitation and molecular docking analysis further demonstrated that SfLFT1 and SfLFT2 form a functional heterodimer that engages SfLFTR predominantly via SfLFT2. This interaction elevated intracellular cAMP levels, activating second-messenger signaling. RNAi-mediated silencing of the GnRH-related neuropeptides AKH, Crz, and ACP resulted in the downregulation of SfLFT1 and SfLFT2, collectively implying that these neuropeptides are upstream modulators of the thyrostimulin-like GPA2/GPB5 pathway. Our findings reveal a neuroendocrine cascade governing vitellogenesis and ovarian maturation in S. frugiperda, offering potential novel targets for pest management.

The rice leaf roller (RLR), Cnaphalocrocis medinalis (Guenée), is a major migratory pest that threatens rice production across East Asia. Effective management of migratory pests relies fundamentally on accurately identifying their source areas, population dynamics, and key environmental drivers. Western Hunan is a critical rice-growing region characterized by unique topography and varied climates, making it a principal pathway for RLR migration. Based on 14-year (2011-2024) monitoring datasets, we identified substantial interannual variability in July RLR abundance in Western Hunan, when the population typically peaks, highlighting the episodic and unstable nature of regional infestations. Back-trajectory simulations reveal that heavy occurrence years of RLR feature clear northward migration pathways from the Indo-China Peninsula and South China to Western Hunan in July, supported by strong southerly winds along the route. Multiple linear regression analysis further shows that spring warmth initially facilitates high population accumulation in source regions, and the synergistic effect of source-region precipitation deficits and abundant local rainfall triggers large-scale immigration into Western Hunan. These meteorological factors collectively account for up to 66% of the interannual variability in RLR population fluctuations, confirming that climatic conditions largely determine outbreak severity. This provides a robust quantitative framework for regional early-warning systems and sustainable pest management in migratory corridors.

The pine shoot beetle, Tomicus yunnanensis (Curculionidae: Scolytinae), is a significant trunk-boring pest of Pinus yunnanensis forests, causing extensive ecological degradation through direct feeding and its role as a vector for destructive pathogenic fungi. The scarcity of a high-quality reference genome has hindered in-depth studies of its biology, particularly the mechanisms underlying its pathogen transmission and host adaptation. Here, we report a chromosome-level genome assembly of T. yunnanensis. Using a combination of PacBio long-read sequencing, Illumina short-read sequencing, and Hi-C chromatin interaction mapping, we generated a final genome assembly of 379.3 Mb, which was anchored into 14 linkage pseudo-chromosomes, with scaffold N50 value of 21.6 Mb. A total of 12, 941 protein coding genes were predicted and annotated. BUSCO completeness assessment indicated that the completeness of the assembly and annotation reached 96.4% and 95.3%, respectively. This high-quality genome provides a critical resource for future research on the pest's biology, ecological adaptation, management and will ultimately support the development of targeted strategies to control its damage and disrupt its role in pathogen dissemination.

The mechanisms guiding nocturnal insect migration remain poorly understood. Although many species are thought to use the geomagnetic field, the sensory basis of magnetic orientation in insects has yet to be clarified. We developed an indoor experimental system to investigate the integration of geomagnetic and visual cues in the seasonal orientation of a globally distributed pest moth, the fall armyworm (Spodoptera frugiperda), a highly invasive species which in the past decade has colonized almost all potentially habitable regions of the globe. Our results demonstrate that fall armyworms require both geomagnetic and visual cues for accurate migratory orientation, with visual cues being indispensable for magnetic orientation. When visual and geomagnetic cues are placed in conflict, moths become disoriented, although not immediately, indicating that sensory recognition of the conflict requires time to process. We also show that the absence of visual cues leads to a significant loss of flight stability, which likely explains the disruption in orientation. Our findings highlight that visual cues are critical for stable magnetic orientation in the fall armyworm, offering a basis for future investigations of visual-magnetic integration in noctuid migrants.

Migratory insects, due to the vast scale of their migration, have a significant impact on both natural ecosystems and human societies. In recent years, increasing attention has been given to the effects of global climate change on insect migration patterns. This review focuses on how altered regional climate patterns affect seasonal prevailing winds and regional precipitation, which then reshape the spatiotemporal patterns and population dynamics of insect migration. However, direct monitoring of these aerial migratory processes is challenged by the small size of insects and the high altitudes at which migration often occurs (hundreds to thousands of meters above ground). There is still a lack of long-term, systematic monitoring data on a global scale, and the impact of climate change on insect migration has not been comprehensively evaluated. How migratory insects respond to climate change and the underlying mechanisms remain to be further studied.

The larvae and damage symptoms of Cnaphalocrocis medinalis and Cnaphalocrocis patnalis exhibit a high degree of similarity, which often leads to confusion between the two species. This has posed challenges for research on their population dynamics and the development of effective control measures. To better understand their morphological and damage characteristics, population dynamics, species identification based on COI gene fragments, and potential future distribution, a searchlight trap monitoring program was conducted for C. medinalis and its closely related species C. patnalis across four sites in Longhua, Haitang, and Yazhou districts in Hainan Province from 2021 to 2023. The MaxEnt model was utilized to predict the potential global distribution of both species, incorporating known occurrence points and climate variables. The trapping results revealed that both species reached peak abundance between April and June, with a maximum of 1500 individuals captured in May at Beishan Village, Haitang District. Interannual population fluctuations of both species generally followed a unimodal pattern. Genetic analyses revealed distinct differences in the mitochondrial COI gene fragment, confirming that C. medinalis and C. patnalis are closely related yet distinct species. The population peak of C. patnalis occurred slightly earlier than that of C. medinalis, and its field damage was more severe. Infestations during the booting to heading stages of rice significantly reduced seed-setting rates and overall yield. Model predictions indicated that large areas of southern Eurasia are suitable for the survival of both species, with precipitation during the wettest month identified as the primary environmental factor shaping their potential distributions. At present, moderately and highly suitable habitats for C. medinalis account for 2.50% and 2.27% of the global land area, respectively, whereas those for C. patnalis account for 2.85% and 1.19%. These results highlight that climate change is likely to exacerbate the damage caused by both rice leaf-roller pests, particularly the emerging threat posed by C. patnalis. Overall, this study provides a scientific basis for invasion risk assessment and the development of integrated management strategies targeting the combined impacts of C. medinalis and C. patnalis.

BACKGROUND:The migratory invasive species fall armyworm (Spodoptera frugiperda, FAW) has established year-round populations in several West African countries following its initial invasion of Africa in early 2016. However, its seasonal migratory dynamics within West Africa remain poorly understood. If FAW populations in West Africa were able to successfully cross the Sahara Desert and serve as a major source population in North Africa, this could increase the risk of further invasion into southern Europe. In this study, we used atmospheric data to perform trajectory simulations, predicting the seasonal migratory pathways of short-distance migratory FAW individuals within West African breeding habitats and assessing the monthly probabilities of long-distance migrants departing from West Africa successfully crossing the Sahara Desert. RESULTS:The results indicate that from May to September, the vast majority of short-distance migrants (>70%) remained within West African breeding habitats, whereas in other months, a larger proportion of individuals were blown into the Atlantic Ocean. Moreover, short-distance migrants exhibited clear seasonal movement patterns within West Africa: shifting southwestward from January to May, turning northeastward in June and July, and returning southwestward from August to December. Long-distance migrants had an extremely low success rate (≤0.3%) of crossing the Sahara Desert, which occurred only between February and April each year. CONCLUSION:This study revealed the seasonal migration patterns of FAW within West Africa, providing important insights for predicting regional outbreak risks and optimizing management strategies in the region. © 2026 The Author(s). Pest Management Science published by John Wiley & Sons Ltd on behalf of Society of Chemical Industry.

Insect migration is an energetically costly process often involving a trade-off with reproduction. However, how adult nutritional stress regulates resource allocation between these two life-history traits remains unclear. Here, we compared morphological traits, flight performance, ovarian development, fecundity, and energy reserves between migrants and residents of Cnaphalocrocis medinalis under fed and starved conditions. Morphological analyses showed no significant differences in body weight, body length or forewing length between migrants and residents, regardless of nutritional status. Under starvation, migrants exhibited significantly greater flight distances and speeds than residents, and their flight distance and duration were also higher than those of fed migrants. Starved migrants showed a higher proportion of immature ovaries and higher fecundity, accompanied by a prolonged pre-oviposition period, indicating reproductive delay. Under fed conditions, ovarian development and fecundity were similar between migrants and residents. Energy reserve assays revealed that starved migrants accumulated more abdominal triglycerides but had lower thoracic glycogen than residents, suggesting preferentially triglyceride storage in the abdomen for long-distance flight. Under fed conditions, residents possessed higher thoracic glycogen levels than migrants, whereas no differences were observed in triglyceride levels. These results indicate that C. medinalis prioritizes energy allocation to migration over reproduction under energy shortage, but switches to a strategy that simultaneously meets the demands of both when nutrition is sufficient. Our findings underscore the role of adult nutrition in mediating the energy allocation between migration and reproduction, offering a scientific basis for the precise monitoring and management of this pest.

Karst landscapes are characterized by extreme topographic heterogeneity, which limits the capacity of conventional coarse-resolution climate data to resolve local microclimates, thereby introducing uncertainty into biological invasion risk assessments. This study developed a high-resolution climate downscaling framework integrating dynamic temperature lapse rates and error correction to reconstruct a 30-m climate dataset for the Southwest China Karst. Using both the downscaled 30-m dataset and the original 1-km dataset, optimized MaxEnt models were applied to predict the potential distributions of two invasive pests, Bactrocera dorsalis and Tuta absoluta. The downscaling framework outperformed conventional interpolation, improving accuracy for maximum temperature, minimum temperature, and precipitation by 12.5% (R2 = 0.984), 15.1% (R2 = 0.989), and 4.4% (R2 = 0.918), respectively. The optimized MaxEnt models showed stable discriminatory performance for both species, with final training AUC values of 0.803–0.835 and ENMeval cross-validated validation AUC values of 0.778–0.809. Relative to the 30-m model, the 1-km model showed broader suitability patterns on steep valley walls for B. dorsalis and expansive basin floors for T. absoluta due to spatial averaging. At the 30-m scale, B. dorsalis exhibited dendritic distributions along dry–hot karst river valleys, driven primarily by Annual Mean Temperature (37.2% contribution) and NDVI (23.9%). Conversely, T. absoluta displayed patchy distributions concentrated in flat plateau basins and depressions, associated with Annual Mean Temperature (27.9%) and Tree Canopy Density (23.5%). Differentiated management strategies are proposed, including linear interception at valley gateways for B. dorsalis and grid-based monitoring in flat agricultural zones for T. absoluta. These findings indicate that high-resolution climate data can refine the spatial interpretation of invasion risk in complex terrains and provide a more detailed spatial basis for precision pest management in karst ecosystems.

Reports of serious and widespread insect declines have been a source of concern for years, but long-term changes in migratory insect communities-which are important components of large-scale ecosystem functioning-are still little understood. Most migratory insects fly at high altitudes, making quantitative investigation problematic. Aerial trapping is the oldest sampling method, and generally still the only one that can provide information on species identity and adequately sample the smaller species. However, aerial sampling is laborious, and thus sampling periods are usually not continuous and sampling sites are sparsely scattered worldwide. To address these issues, we integrated existing data obtained by sampling from aerial platforms (and some high-mountain netting in East Asia) in a comprehensive analysis. We found that, between 1926 and 2017, the aerial density of high-flying migratory insects from samples taken about 200 m above Europe (eastern United Kingdom), North America (southern and central United States), and Asia (east-central China, India, and the Philippines), remained relatively stable overall. Additionally, some key migratory agricultural pests have significantly increased over this period, indicating that the non-pest portion of the aerial migrant community may have declined. Changes in the community structure of high-altitude migratory insects will be closely associated with large-scale ecosystem changes. Thus, apart from continued long-term monitoring of agricultural insect pests and the development of diversified prevention and control methods, there is a need to protect the diversity of non-pest and beneficial migratory insects.

The navigational mechanisms employed by nocturnal insect migrants remain to be elucidated in most species. Nocturnal insect migrants are often considered to use the Earth’s geomagnetic field for navigation, yet the underlying mechanisms of magnetoreception in insects remain elusive. We developed an indoor experimental system to investigate the integration of geomagnetic and visual cues in the seasonal orientation of a globally distributed pest moth, the fall armyworm (Spodoptera frugiperda), a highly invasive species which in the past decade has colonized almost all potentially habitable regions of the globe. Our results demonstrate that fall armyworms require both geomagnetic and visual cues for accurate migratory orientation, with visual cues being indispensable for magnetic orientation. When visual and geomagnetic cues are placed in conflict moths become disoriented, although not immediately, indicating that sensory recognition of the conflict requires time to process. We also show that the absence of visual cues leads to a significant loss of flight stability, which likely explains the disruption in orientation. Our findings highlight the essential and conserved role of visual cues in maintaining stable magnetic orientation in nocturnal migratory moths.

The fall armyworm (FAW), an important migratory pest native to the Americas, was first detected in a nonnative region (West Africa) in 2016. In the following years, it quickly spread to multiple regions worldwide. FAW exhibits long-distance seasonal migration in both the Americas and Asia, primarily to take advantage of suitable seasonal habitats as they appear along the migratory pathways. Tropical West Africa experiences minimal annual temperature variation and has widely distributed potential year-round habitats, leading us to hypothesize that the migration capacity of FAW populations in this region may be substantially reduced. To test our hypothesis, we assessed the flight performance of FAW collected from Ghana in West Africa with tethered flight mills and compared it to that of a FAW population from southern China. Additionally, we quantified the relationships between morphological characteristics and flight performance of the FAW from Ghana. Based on observed flight behaviors, we categorized FAW into migratory and non-migratory types. The flight capabilities of first-generation Ghanaian FAW bred in the laboratory were similar to that of the field population from Yunnan, Southwest China, with migrants making up the majority. However, after several generations of laboratory rearing, the flight capability of the Ghanaian population significantly declined, primarily due to a marked increase in the proportion of non-migratory individuals. The low correlation between morphological variables and flight duration suggests that genetic factors likely determine most variations in flight propensity. The results of this study indicate that FAW with high migratory capacity in West Africa is likely to pose a threat to crops in eradication zones and neighboring uninvaded areas and may possibly be capable of crossing the Sahara Desert and invading Europe. Therefore, it is crucial to establish comprehensive pest early warning and management systems.

The brown planthopper (BPH), Nilaparvata lugens (Stål), is the most important rice pest in China and other East Asian countries. Identifying their source areas and predicting their population dynamics are crucial for managing migratory pests. Northern South China (NSC) is one of the key regions for northward BPH migration and a direct source of BPH in the key rice‐growing area of the Lower Yangtze River Valley (LYRV). Hence, this study aimed to explore the environmental drivers affecting the population dynamics of BPH in NSC, and develop models for predicting the immigration levels in the LYRV. Initially, the BPH immigrants in NSC were identified to have mostly originated from northern and north‐central Vietnam, Laos, and northeastern Thailand (15°–22° N) in May by using a trajectory analysis approach. The population model showed that immigration size of BPH in NSC in May can be predicted by the temperature observed in February over these source areas combined with the probability of BPH from south‐central Vietnam (their principal overwintering region) immigrating to these source areas in March. Subsequently, the immigration size of BPH in NSC in May combined with the onset time of the South China Sea Summer Monsoon (a sign of rain belt movement and arrival of the flood season in China), can be used to predict the immigration level of BPH in the LYRV in July. These 2 prediction models could forecast nearly 2 months in advance, allowing time for effective control measures to be implemented.

Many insect migrants rely on favorable seasonal winds to carry out long-range latitudinal migrations. In East China, the annual advance and retreat of the East Asian summer monsoon produces ideal conditions for seasonal range expansion and contraction of many migratory crop pests. However, climate-induced changes in the strength, timing, and location of the monsoon are impacting wind systems which may, in turn, affect migration patterns. We investigated these questions in the rice leafroller (RLR) moth, a severe pest of rice that annually invades the Lower Yangtze River Valley (LYRV) of China from winter-breeding areas further south. Using a 24-y dataset of RLR population dynamics from 31 monitoring stations across Southeast China, we investigated the impact of changes in monsoon wind regimes on fall migration patterns of the pest. Historically, RLR emigrated from the LYRV to South China on the favorably directed winds produced by the retreat of the monsoon at the end of the outbreak season (from mid-August onward). We show that in the recent 12-y period, prevailing late-season winds remain northward for longer than previously, preventing locally produced moths from emigrating southward. Additionally, winds now facilitate mass late-season immigrations into the LYRV, creating an ecological trap, as immigrants do not have time to produce another generation. As a consequence of the changing wind patterns, pest pressure is declining, and climate-induced changes to the East Asian summer monsoon result in seasonal migration becoming a riskier strategy. Such changes in insect migration patterns have severe implications for the population dynamics of windborne migrants, ecosystem functioning, and pest management strategies.

As a migratory agricultural pest, the fall armyworm has been in the spotlight since it invaded Africa in 2016. Invasive populations have now colonized much of the Eastern Hemisphere, causing severe damage to a wide range of crops. However, there is still disagreement internationally on the origin and mode of invasion of fall armyworm populations, especially from the Americas to China. In this study, we provided an in-depth insight into the invasion of the fall armyworm in the Eastern hemisphere based on genome-wide data from 124 fall armyworm individuals collected from 14 sites across three continents and trajectory simulation. First, based on 770,423 high-quality SNPs, the PCA and ADMIXTURE analyses clearly distinguished the geographical populations of the Eastern and Western hemispheres. Second, the genetic diversity results revealed that the invasive populations exhibited higher heterozygosity than the native populations. Third, the results of integrated individual assignment tests and migration path simulations showed that the W1 (Florida, Texas, and Puerto Rico) population may be the potential source of the invasive populations in Africa, and a low possibility of trans-sea migration between the Americas and Africa suggested that fall armyworms may have spread through trade in goods. Fourth, our results indicate that the Indian population is a genetically admixed group derived from the E1 (Benin, Ethiopia, and South Africa) population, which subsequently migrated to the Indo-China Peninsula through natural trans-sea dispersal and to Yunnan via Myanmar. These findings not only provide new insights into the invasion of the fall armyworm in the Eastern Hemisphere but also present a method to improve the prediction accuracy of migratory pests.

The circadian clock orchestrates essential behavioral and molecular processes, including the timing of eclosion, one of the most tractable and ecologically relevant outputs of the circadian system. Understanding eclosion timing may offer insights into the circadian clock mechanisms that underlie migratory timing. Here, we characterize the diel and circadian patterns of eclosion and core clock gene expression in the fall armyworm (FAW), Spodoptera frugiperda , a globally distributed migratory moth. Using a custom-designed eclosion monitoring system under both 14 hours light-10 hours dark (L14: D10) and constant darkness (DD) conditions, we observed clear diel eclosion rhythms, peaking shortly after lights-off under L14: D10. Under DD, these rhythms became delayed and damped over three consecutive days, consistent with circadian control. Males exhibited more dispersed emergence patterns and distinct eclosion distributions than females under L14: D10 and DD, suggesting sexually dimorphic timing. Gene expression profiling revealed rhythmic oscillations of five canonical clock genes, cyc , clk , tim , per , cry2 , with sex-dimorphic differences in mesor, amplitude, or phase, particularly the mesors of males are higher than those of females in five clock genes under L14: D10. These results provide strong evidence for sexually dimorphic circadian regulation at both behavioral and molecular levels in a migratory insect that recently invaded China, suggesting that sex-dimorphic circadian architecture may contribute to allochronic speciation and ecological strategies such as eclosion and migratory timing in a novel environment. Leveraging the established circadian eclosion rhythm assay, which captures core features of clockwork mechanisms, further investigation may reveal how these sex-based differences contribute to the evolution of circadian function and adaptive traits. ### Competing Interest Statement The authors have declared no competing interest. National Natural Science Foundation of China, , 32172414, 32472547 Natural Science Foundation of Jiangsu Province, , BK20221510

Artificial light at night (ALAN) is altering nocturnal ecosystems. While the effects of direct light sources on insect behavior are well studied, the influence of large-scale skyglow on migratory orientation remains unclear. Here, we tested how skyglow-induced luminance gradients influence the flight orientation of the fall armyworm, Spodoptera frugiperda, a globally invasive nocturnal migrant that performs seasonal migration in China, using controlled indoor simulations and field assays. Surprisingly, individuals consistently oriented toward darker regions, suggesting that luminance gradients may influence their heading away from the expected seasonal migratory direction. This response was highly consistent across both settings, indicating that skyglow-generated luminance gradients can function as directional cues and potentially interfere with seasonal orientation processes. Such gradients may thus function as ecological traps and represent an underrecognized factor in nocturnal insect navigation. Our findings point to a previously overlooked pathway through which skyglow may affect long-distance orientation in nocturnal migrants, underscoring the need for further work to evaluate its ecological significance within light-polluted environments.

Corn rootworms of Diabrotica virgifera virgifera Le Conte, 1868; Diabrotica undecimpunctata howardi Barber, 1947, and Diabrotica barberi R.F. Smith & Lawrence, 1967 are important pests of corn crops that natively occur in America and have a potential risk of spreading into China through natural spreading or anthropogenic invasion. In this study, the potential geographic distribution and suitable area of these three Diabrotica species based on their global distribution samples and relevant bioclimatic variables were estimated, and an overlay analysis was further carried out in combination with the actual distribution of corn-growing regions, especially in China, in order to assess the potential invasion risks of these Diabrotica beetles, especially in the corn-planting regions of China. The results indicated that six bioclimatic variables (i.e., bio2 (mean diurnal range), bio4 (temperature seasonality), bio5 (max temperature of the warmest month), bio6 (min temperature of coldest month), bio13 (precipitation of wettest month), and bio14 (precipitation of driest month)) were selected for the analysis of the potential geographic distribution and suitable areas of these Diabrotica beetles. The suitable area ranges of D. undecimpunctata and D. virgifera virgifera are relatively large in China, i.e., 21.01–48.46° N and 74.01–131.26° E for D. undecimpunctata and 21.58–41.42° N and 78.71–124.43° E for D. virgifera virgifera, respectively, while D. barberi occupies only a small area in China, i.e., 34.21–46.81° N and 108.80–133.75° E. Based on the overlay analysis of the potential geographic distribution of these three Diabrotica species and the actual distribution of corn-growing regions in China, D. undecimpunctata and D. virgifera virgifera have the largest potential geographic distribution areas, totaling 2.618 × 107 ha and 1.814 × 107 ha in 22 and 20 provinces respectively, while D. barberi has the lowest potential geographic distribution area just in 8 provinces, totaling 44.37 × 104 ha, indicating a low-suitability area. Moreover, under the four climate scenarios (i.e., SSP1_2.6, SSP2_4.5, SSP3_7.0, and SSP5_8.5) in the 2030s and 2050s, these Diabrotica beetles have the potential for sporadic increases or decreases surrounding the potential suitable areas under the current scenario. However, it is worth noting that the high-suitability areas of D. undecimpunctata and D. virgifera virgifera decreased, and their medium- and low-suitability areas increased accordingly. It is presumed that Diabrotica beetles, especially D. virgifera virgifera and D. undecimpunctata, have a high risk of potential invasion into China because there is a large potentially suitable area distribution for their possible occurrence in the maize-planting regions of China.

The East Asian Insect Flyway serves as a critical migration corridor for major agricultural pests including the highly destructive fall armyworm (FAW) (Spodoptera frugiperda), which poses severe threats to crop security worldwide. Two primary migratory routes—eastern and western—extend from the Indochina Peninsula to northern China, enabling its widespread dispersal and enhancing its potential for damage. However, whether the population structure differs between populations from the eastern and western pathways and whether molecular markers can be used to distinguish the insect sources of these two migratory pathways remain largely unknown. Herein, FAW samples from the Indochina Peninsula to northern China collected over 2 years (2019 and 2023) were used to screen 176 key genomic loci (124 single nucleotide polymorphisms (SNPs) and 52 insertions and deletions (InDels)) through genome resequencing and genome-wide association studies (GWAS) analysis. Principal component analysis and phylogenetic trees based on these genomic loci clearly distinguished the eastern and western lineage, grouping all samples into two corresponding clusters. LASSO-regularized logistic regression identified eight stable features (6 SNPs and 2 InDels). Accordingly, machine learning models were constructed to accurately distinguish FAW ofrom the eastern and western migratory pathways. The Multi-Layer Perceptron model achieved the highest performance, with precision (90.00 %), F1-score (0.8730), accuracy (87.50 %), ROC-AUC (89.60 %) and PR-AUC (87.00 %). Using those eight stable features, six UDP-glycosyltransferase (UGT) genes were identified which were enriched in several detoxification-related pathways. Our findings establish a robust molecular toolkit for accurate source identification of FAW individuals, which can significantly enhance the monitoring and early warning systems against this migratory pest. These results also provide a new method for elucidating the migration pathways of other migratory insects worldwide.