,Source Insects and Microbes,Sitophilus oryzae that were 4–8-week-old and collected from a food facility in eastern Kansas in 2012 were used. Adults were reared continuously in the laboratory at CGAHR and subcultured on tempered whole organic wheat, with 75 mixed-sex adults added to 300 g of wheat. Adults were sieved off after a 1-week oviposition period. Colonies were maintained in a chamber set at 27.5˚C, 65% RH, and 14:10 (L:D) h photoperiod. The fungus, Aspergillus flavus, was isolated from field-collected S. oryzae after allowing adults to forage on potato dextrose agar dishes (100 × 15 mm) for 5 d. From the initial dish, A. flavus was re-plated on a new dish in multiple successive rounds until it was a pure isolate. This was used to create A. flavus-inoculated grain, which was then used for the treatments below.,Treatments and Preparation of Grain Masses,At the outset of the experiment, the grain moisture of the wheat for the experiments was determined to be 10.8% using a moisture meter (DICKEY-john, GAC2100, Auburn, IL, USA). A total of 300 g of organic, whole untampered organic wheat (Heartland Mills, Marienthal, KS, USA) was added to each pint mason jar (950 mL; 8.5 D × 17 cm H). In order to assess the effect of singly or multiply infested grain by insects and microbes on the microclimate and fitness outcomes, each grain mass was assigned to one of our treatments: control (no insects or added microbes; Ctrl), the addition of 75 mixed-sex S. oryzae adults only (SO), inoculation with 11.6 g of A. flavus inoculated grain only (AF, details below), and finally the addition of both S. oryzae (75 adults) and A. flavus (11.6 g of inoculated grain; SO + AF). In each grain mass, a datalogger (Hobo® U10-003 Temp/RH Data Logger, Onset, Bourne, MA, USA) was attached below the lid and recorded temperature and relative humidity every 5 min. The experiment was allowed to run for 60 d in an environmental chamber set to 30°C, 60% RH, and 14:10 L:D photoperiod. At the end of the period, all jars were immediately frozen to stop halt reproduction and microbial activity. There were n = 5 replicate grain masses per treatment. For the purposes of looking at changes in abiotic variables, the 60 d period was divided into equal 20 d increments, and labeled early (first 20 d), mid (second 20 d), and late (final 20 d).,Preparation of A. flavus-inoculated grain,In order to inoculate treatments with A. flavus, an inoculum was prepared from wheat that had already undergone a complete colonization process. Briefly, 600 g of grain was added to a stainless-steel pot filled with water and placed on a hot plate at 500°C. It was allowed to boil for 15 min, then the water was drained, and the grain was evenly spread out on sterile wipes (38.1 × 42.5 cm, 3 ply, Tech wipes, Skilcraft, NIB, Alexandria, VA). The grain was allowed to dry inside a laminar fume hood (for ca. 3 h). Subsequently, the grain was divided (in 300 g lots) and placed in two separate sterile mason jars (950-mL capacity). A single hole was drilled through each lid and lined with a cotton ball. The jars were then sealed with aluminum foil and were autoclaved (533LS, Getinge, Rochester, NY, USA) for 30 min. To inoculate with A. flavus, a 3-inch strip of agar containing a pure culture of A. flavus grown on PDA for 7 days at 30°C, 60% RH, and 14:10 L:D photoperiod as above (Ponce et al., 2023; Ponce et al., 2024) was placed into each jar containing the grain. The jars were maintained at room temperature for roughly 10 days or until the A. flavus evenly covered as much of the grain as possible. Inoculated grain was used within 10–15 days of preparation. A total of 11.6 g of this inoculated grain was then added to 300 g for the A. flavus treatments above.,Grain Moisture & Progeny Production,At the end of 60 d, grain moisture readings were taken from 20 g of every replicate and each treatment after allowing grain masses to reach room temperature by using a moisture meter (DICKEY-john, GAC2100,

,Our goals were to 1) isolate, and culture two fungal morphotypes, 2) characterize the volatile emissions from grain inoculated by each fungal morphotype (Aspergillus flavus or Fusarium spp.) compared to uninoculated and sanitized grain, and 3) understand how MVOCs from each morphotype affects mobility, attraction, and preference by L. serricorne. Headspace collection revealed that the Fusarium- and A. flavus-inoculated grain produced significantly different volatiles compared to sanitized grain or the positive control. Changes in MVOC emissions affected close-range foraging during an Ethovision assay, with a greater frequency of entering and spending time in a small zone with kernels inoculated with A. flavus compared to other treatments. In the release-recapture assay, MVOCs were found to be attractive to L. serricorne at a longer distances in commercial pitfall traps. While there was no preference shown among semiochemical stimuli in a still-air, four-way olfactometer, it is possible that methodological limitations prevented robust interpretation from this assay. Overall, our study suggests that MVOCs are important for close- and long-range orientation of L.serricorne during foraging, and that MVOCs may have the potential for inclusion in behaviorally-based tactics for this species.,

,Insects,Beetles used in this study were obtained from stock colonies maintained at the USDA Agricultural Research Service’s (ARS) Center for Grain and Animal Health Research (CGAHR) in Manhattan, KS, USA. Colonies of R. dominica and S. oryzae were reared on organic whole wheat kernels that had been tempered to 15% grain moisture. To subculture, a total of 50 adult individuals were placed on 200 mL of grain in a mason jar (capacity: 473 mL) and given 14 d to mate and lay eggs. At the end of that period, adult hosts were removed by sieving with a #10 sieve (2.00 mm; W.S Tyler Inc., Mentor, Ohio), and colonies were allowed to age for 3-weeks prior to using beetles as hosts for parasitoid rearing. Theocolax elegans were maintained separately on two different hosts, either R. dominica or S. oryzae for at least three full generations. Freshly emerged, healthy T. elegans were used for the experiments below. All colonies of parasitoids were maintained in a separate environmental chamber than host-only colonies to prevent cross-contamination. Colonies were maintained in mason jars and stored in an environmental chamber under constant conditions (27.5°C, 60% RH, 14:10 L:D).,Interactions with Predators,Laboratory studies were performed in 2022 and 2023 at the USDA Center for Grain and Animal Health Research (Manhattan, KS, USA). From July–October of each year, predators were collected weekly from local post-harvest food facilities, including the Kansas State Agronomy Farm (GPS: 39.2062227, -96.5951959), where S. oryzae and other stored product pests are abundantly found (Morrison et al. 2025[1] ). Most predators used in trials were collected by sweep netting (Bioquip Products, Inc., Rancho Dominguez, CA) sampling vegetation adjacent to grain bins or by hand collection and held temporarily in 1-gal (=3.98 L) Ziplocks, then immediately brought back to the lab in a cooler on insulated ice packs. In the lab, insects were processed by individually placing predators into a 950-mL mason jar with 10 S. oryzae from colonies. The predators were identified to family (Marshall 2006, Paquin et al. 2017). Mason jars with predators and S. oryzae were then placed on shelves in an environmental chamber set to constant conditions (27.5°C, 60% RH, 14:10 L:D). After 24 h, the jars were checked, and the number of S. oryzae consumed was recorded as well as the presence of any self-aggregation behavior of S. oryzae together and away from the predator, which was taken to be evidence for non-consumptive effects in the presence of the predator. The results of predators were only included when there were n = 3 or greater number of replicates.,Ethovision,Video-tracking coupled with Ethovision software v.14.0 (Noldus, Inc., Leesburg, VA: Noldus et al. 2002) was used to investigate the impact of natural enemy kairomones on the mobility and orientation of R. dominica and S. oryzae over short distances. This system has previously been used for analyzing the mobility and foraging behaviors of stored product insects (Wilkins et al. 2020; Ponce et al. 2022). Six arenas consisting of Petri dishes (VWR Petri dishes, 100 × 15 mm) with an 85-mm filter paper (Grade 1, Whatman, GE Healthcare, Chicago, IL) adhered to the bottom using double-sided sticky tape were arranged 80 cm below a network video camera (GigE, Basler AG, Ahrensburg, Germany). The movement of individual insects within each arena was simultaneously recorded on an adjacent computer. Four zones were monitored in Ethovision, including the two halves of the Petri dish (i.e. treatment half vs control half) and two 1 cm diameter zones nested in the middle of each half where stimuli were applied (treatment stimulus zone and control stimulus zone). The position of treatments was randomized between replicates and a total of n = 12 replicate assays were conducted for each treatment. For each assay, a single insect was introduced into the center of an arena and its movement was tracked for a total of 10 min. Several

,Insect Sources,Insect colonies of R. dominica and T. castaneum maintained continuously at the USDA-ARS Center for Grain and Animal Health Research were used. This included T. castaneum collected in Eastern KS (USA) from 2012, and R. dominica collected from Eastern KS in 2019. Tribolium castaneum and had been reared on a mixture of 95% unbleached, organic flour and 5% brewer’s yeast, while R. dominica was reared on tempered organic whole wheat. Adults that were 4–6-week-old were used for experiments. Colonies were maintained at 27.5°C, 65% RH, and 14:10 (L:D) h photoperiod.,Treatments,The following netting treatments were used: negative control (e.g., no netting), positive control (netting identical to LLIN but without insecticide; Item#1721-9668, Casa Mesh White, Casa Solid, Joann’s Fabrics, Hudson, OH, USA), 0.34% w/w alpha-cypermethrin LLIN (Carifend, BASF Corps, Ludwigshafen, Germany), and a 0.4% w/w deltamethrin LLIN (D-Terrence, Vestergaard Inc., Lausanne, Switzerland).,Laboratory food dust assay,To evaluate the effect of food dust on the efficacy of LLIN, there were two food dust regimes. Netting was either used as is or fully dipped into organic flour (Heartland Mills, Marienthal, KS, USA) that filled a 9 × 9 cm square Petri dish. After exposure to food dust, the netting was used to line a new, clean 9 × 9 cm Petri dish. Rhyzopertha dominica and T. castaneum adults were tested in cohorts of 20 and exposed on the netting for 10 min continuously in the Petri dishes, then their conditions were checked at 1, 24, 48 h, and 168 h after exposure. Insects were held in an environmental chamber set to 27.5°C, 65% RH, and 14:10 L:D. Conditions were classified as the percentage that were alive (normally moving around unimpeded), affected (showing abnormal or sluggish movements, but movement still present, even if just twitching of extremities), or dead (completely immobile; full definitions in Morrison et al. 2018). This was performed under a stereomicroscope (SMZ18, Nikon Inc., Tokyo, Japan). A total of n = 5 replicate cohorts were tested per combination of treatments (dust regime, netting type, exposure time, post-exposure holding duration, and species).,Spillage assay,To evaluate whether netting could be used to protect sites of spillage, we performed a spillage assay in the laboratory. For this assay, only netting without insecticide but identical to LLIN and 0.34% alpha-cypermethrin LLIN (BASF) was used. Netting was placed covering a single layer of 35 g of whole organic hard winter wheat (Heartland Mills, Marienthal, KS, USA) in a 9 × 9 cm square Petri dish. A control treatment included a single layer of positive control or alpha-cypermethrin LLIN placed in a Petri dish without food. Cohorts of 20 mixed-sex R. dominica or T. castaneum adults were exposed continuously to the netting for 48 h. After that period, the conditions of the adults were recorded as alive (moving normally), affected (sluggish movements, unable to right themselves when fallen, or twitching body parts), or dead (completely immobile) according to established definitions in (Morrison et al., 2018). After sieving adults, we placed the grain from the Petri dish in a separate vial (11 × 4.9 cm H:D) for six weeks to check for progeny production, including the number of larvae, pupae, and adults. A total of n = 7 replicate cohorts were tested per combination of treatments.,Interception assay,To determine whether LLIN can prevent horizontal dispersal of stored product insects to sites of spillage, we performed an interception assay. A single layer of organic, whole wheat (Heartland Mills, Marienthal, KS, USA) was placed in a 245 × 245 mm large square Petri dish (Item# 431111, Corning Inc., Corning, NY, USA). In the center of the dish, a 2.5 x 24.5 cm (W × L) strip of netting was added on top of the wheat. A total of 50 mixed-sex R. dominica or T. castaneum adults were added to the middle of zone 1 (e.g., release zone; Figure 1). The remainder of the dish was

,Experimental Insects,The field strains of T. castaneum and R. dominica (F.) were used in this study. The former originates from Eastern Kansas in 2012, and the latter is also from Eastern Kansas but from 2019. For all species, four to eight-week-old adults were used. Rearings were kept at the USDA Center for Grain Animal Health Research in Manhattan, KS. Tribolium castaneum was reared on a mixture of 95% unbleached, organic flour and 5% brewer’s yeast, while R. dominica was reared on tempered organic whole wheat. Colonies were maintained at 27.5°C, 65% RH, and 14:10 for maintenance or 16:8 (L:D) h photoperiod for the experiment.,Treatments,Treatments included exposure to three different types of long-lasting insecticide-incorporated netting (LLIN). These consisted of 1) Carifend®, LLIN with 0.34% alpha-cypermethrin (40 deniers, BASF, Ludwigshafen, Germany), 2) D-Terrence, LLIN with 0.4% deltamethrin (2 × 2 mm mesh, Vestergaard SA., Lausanne, Switzerland), and 3) 8% etofenprox LLIN (AgBio, Inc, CO, USA), and for control, we used netting identical to the Carifend or Vestergaard netting but lacking insecticide.,Direct Lethality Assessments,Cohort of 20 mixed-sex adult beetles were exposed for 5, 60, or 120-min intervals on netting affixed to a 9 × 9 cm2 petri dish in the laboratory. After exposure, we took the evaluated condition after 0, 24, 72, or 168 h as alive, affected, or dead condition (Figure 1), according to the definitions described in Ranabhat et al. (2022) in Petri dishes without netting containing 8.5 cm D filter paper. Briefly, living adults were defined as moving with normal speed and activity and able to right themselves if flipped. By contrast, affected adults exhibited sluggish or drunken movements, could not right themselves if flipped, and some or all of their limbs exhibited twitching. Dead adults were completely immobile. For post-exposure treatment, adults were held under the same environmental chamber conditions as the colonies but without supplemental food after exposure. We performed a total of n = 4 replications per treatment combination for each species.,Baseline Mobility Assay after Exposure to LLINs,Based on the observation of the lethality assay, we focused our baseline mobility assay on Carifend® and D-Terrence LLIN. Using only alive adults, we assessed their movement in six individual Petri dishes (100 × 15 mm D: H) that consisted of a filter paper (85 mm D, Grade 1, GE Healthcare, Buckinghamshire, United Kingdom) lining. Treatments included a negative control (e.g., filter paper only), one of the two LLINS, or an identical netting to the Carifend or Vestergaard netting but without insecticide (e.g., as a positive control). Their movement was tracked for 60-min using a network camera (GigE, Basler AG, Ehrenburg, Germany) affixed 80 cm above the dishes. The Petri dishes were backlit using a LED light box (42 × 30 cm W: L, LPB3, Litup, Shenzhen, China) to increase contrast and affixed in place with white foam board. The video was streamed to a computer and processed in Ethovision (v.14.0, Noldus Inc., Leesburg, VA). The program automatically calculated the total distance moved (cm) and the instantaneous velocity (cm/s) over the 60-min period for each adult. Each adult was considered a replicate and was never used more than once. In total, n = 18 replicates were performed per treatment combination.,Comparison of Sublethal Effects among LLINs,For the sublethal movement assay, mixed-sex adult beetles were exposed to the Carifend®, D-Terrence LLIN, or control net as mentioned above. Cohorts of 5–10 adults were exposed for 5- or 60-min intervals on LLINs affixed to a 9 × 9 cm2 Petri dish in the laboratory. After exposure, the effects of the LLINs on adult movement were assessed either immediately or after 72 h in Petri dishes under the same environmental chamber conditions as the colonies but without supplemental food and then assayed using the video-tracking system described above by using Ethovision

,Insecticide Netting In this study, we focused on two types of long-lasting insecticide netting (LLIN) that have been found to be effective for managing various stored product insect pests. One is an LLIN consisting of a polyethylene netting (2 × 2 mm mesh, D-Terrence, Vestergaard, Inc., Lausanne, Switzerland) with 0.4% deltamethrin active ingredient (a.i.), while the second one is Carifend® net (40 deniers with mesh size 97 knots/cm2; BASF AG, Ludwigshafen, Germany) containing 0.34% α-cypermethrin (a.i.).,Foundational Model We used a standard Lefkovitch matrix model to project population growth for Tribolium castaneum, with four life stages (e.g., egg, larva, pupa, and adult;(Lefkovitch,1965). In equation (1), the Leftkovitch matrix L matrix (4 × 4) represents the life-stage structure of T. castaneum which has an egg, larvae, pupae, and an adult, where only the adults contribute to the fecundity, F. By multiplying L with the population vector ni(t), where t is time step (e.g., generation) and i is a life stage, we obtain the resultant vector ni(t + 1), which reveals the distribution of individuals across different life stages in the subsequent time period. In equation (1), P1 represents the probability of staying in the egg stage and G1 is the probability of moving from the egg to the larval stage, P2 is the probability of staying in the larval stage, G2 is probability of moving from the larval stage to pupal stage, P3 is the probability of staying in the pupal stage, G3 is probability of moving from the pupal stage to adult, while P4 is the probability of staying in the adult stage (Figure 1).,Model Parameterization and Scenarios We simulated population outcomes for up to 15 generations by using the life table data for T. castaneum using the R package popbio. Survivorship, fecundity, and transition information for each stage were derived from the literature (summarized in Table 1). The developmental duration of eggs, larvae, and pupae were 3.82 ± 0.005, 22.81 ± 0.67, and 6.24 ± 0.071 days (Kollros,1944). The average life duration of the adult used in this study was 221.16 days (Park et al., 1961). We used 94 offspring for fertility from the study Park et al.,(1965) and 99% rate of eclosion from pupae to adult. In order to explore the sensitivity of the base model to changes in mortality and fecundity, both of these parameters were systematically varied from near zero to their maximum value given in the base model (e.g., F = 94, P4 = 0.871). The parameters were varied alone or in combination and the resulting population growth was plotted. All plots were created using ggplot2 (Wickham, 2016) in R software (R Core Team, 2022). Three empirical scenarios from the literature were modeled containing estimates of fecundity reduction only, survivorship reduction only, or both fecundity and survivorship reduction when using LLIN (R.V. Wilkins et al., 2021; Gerken et al., 2021;Scheff et al., 2021, Scheff et al., 2023; Table 2). An individual projection matrix was constructed for each of the three scenarios and combinations of the reductions in fecundity, survivorship, or both. Population growth and proportion in each life stage was projected for 15 generations for each case, including the base model. Overall variation and oscillation were calculated to compare trends among proportion of life stages in each case. In order to compare differences in population sizes between cases for all generations and for generation 15 only, population sizes for each generation were bootstrapped 1000 times to provide iterative replication. The bootstrapped data were then compared one case to another using proc ttest in SAS (Version 9.4) for all generations and for generation 15 only. In addition, a sensitivity analysis was performed to determine which stage should be targeted to most greatly affect the population growth after exposure to the netting. Moreover, a mortality function based on empirical data with LLIN exposure collected in the laboratory

,Trapping in 2023 with a linear set of dosages of (E)-8-dodecenyl acetate,Field trapping was done according to the methodology in Ruiz et al. 2022. The fields were located in North-Central Kansas at the Land Institute near Salina, KS. No pesticides were applied to these fields during the experiment in 2023. Starting the first week of June, six transects were set out, two in each Silphium integrifolium field. Each transect contained seven 30.4 cm x 30.4 cm sticky card traps (Alpha Scents, Canby, OR, USA) affixed to the top of a 1.27 cm diameter, three foot in length PVC pole that was hammered into the ground until sturdy. The cards were affixed using a 271 cm long sticky card ring holder (Olson Products Inc., Medina, OH, USA) that was bent to a 90° angle and placed inside the PVC pipe. Two large binder clips were also used to anchor the sticky card to its card holder.,The sticky traps in each transect were spaced 10 meters apart around the perimeter of the field. Within each transect, traps were baited with a linear increase in concentrations in 2023, including either a control (50 µl of acetone), a low concentration (50 µl of a solution made by mixing 5.75 µl of (E)-8-dodecenyl acetate in 5 ml of acetone), or a doubled concentration (11.5 µl of (E)-8-dodecenyl acetate diluted in 5 ml of acetone) of (E)-8-dodecenyl acetate (Alfa Chemistry, Ronkonkoma, NY, USA). All lures were added to a 3-ml LDPE dropping bottle (Wheaton, DWK Life Sciences, Millville, NJ, USA). The clear sticky card traps were collected and replaced biweekly until the first E. giganteana adult was caught, then traps were changed weekly. The lures and control bottles were replaced once every two weeks (with lure emissions confirmed out to 14 d in Ruiz et al. 2022) and their position in the field rotated at each change. Each lure was in each position twice over the course of the season.,When collected, the sticky cards were held in a 7.6 L (=2 gal) labeled Ziploc© bag transported back to USDA-ARS. All collected sticky traps were placed in a freezer for approximately 24 h. The total number of E. giganteana per trap and their distance from the lure in millimeters was recorded. In addition, the number of nontarget lepidoptera was recorded on each trap. Individual E. giganteana and non-target lepidoptera were only counted if more than half of the specimen was remaining on the sticky trap at the time of counting to ensure positive identification.,Trapping in 2024 with an exponential set of concentrations of (E)-8-dodecenyl acetate,Field trapping in 2024 was conducted similarly to that in 2023 with the following modifications. Three different fields located at the Land Institute were used (Table 1). [HS1] Pesticides were applied once to one of the fields and adjacent to one of the others. Three transects were deployed in each of the three fields. Each transect contained four traps for a total of 36 traps. The traps were assembled similarly to those used in 2023, but a hand-made sticky card was used instead of a manufactured one to improve captures. These sticky cards were made of a laminated 21.6 × 27.9 cm (=8.5 by 11 in) piece of white cardstock paper (Astrobright, Neenah, WI, USA) coated on both sides with TADⓇ all-weather adhesive (Trécé Adhesives Division, Adair, OK, USA). The sticky sides were covered with wax paper for ease of travel. Additionally, the sticky cards had a chicken wire cage placed over them in the field to try to prevent the capture of birds and other nontargets on the traps. Traps in 2024 were baited with an exponential set of concentrations of (E)-8-dodecenyl acetate. In each transect, there was a solvent only control (50 µl of acetone), a low concentration equivalent to the 2023 treatment (50 µl of a solution made of 5.75 µl of (E)-8-dodecenyl acetate diluted in 5 ml of acetone), a medium concentration (50 µl of a solution made of 78.5 µl of (E)-8-dodecenyl acetate diluted in 5 ml of acetone), and a high concentration (50 µl of a solution made

,A systematic search of the literature using Google Scholar, (https://scholar.google.com/) and Web of Science was used to identify studies that examined the effects of individual compounds or mixtures of MVOCs on the behavioral responses of stored-product arthropods. Stored-product arthropods were defined as those insects and arachnids attacking stored, durable commodities in the post-harvest supply chain at any of the successive links, including storage, transportation, processing, and marketing. Where applicable, we parsed studies into component experiments where behavioral responses or other factors such as type of assays or measured variables may have differed (e.g. dosage, compound, etc.). We classified each test as resulting in statistically significant attraction (+), repellence (−), or neither (○) compared to a negative or positive control. We excluded any studies lacking appropriate negative or positive controls, lacking replication, or lacking sufficient details on the identity of tested substrates to enable appropriate interpretation. Terms used to search databases included the following singly and/or in combination: “fungal”, “volatiles”, “stored products”, “insect behavior”, “insect-microbe”, “interactions”, “semiochemicals”, “mycotoxin”, “behavioral response”, “attraction”, and “postharvest”, and combinations thereof. In addition, we kept track of methodology used for tests, response variables, target insect, insect stage, and microbial taxon. We split our analysis up between tests with complex (but usually uncharacterized) blends of MVOCs, and those with known individual or known component mixtures of MVOCs.,,

,Real-time, image-based monitoring for stored product insect pests could increase timely treatments and protection for postharvest products throughout the supply chain. Artificial intelligence (AI) and machine learning can provide the models necessary for accurate identification and population-counting within a trap-based system. This study presents the development of a smart vision-based monitoring system for moth population estimation using sticky traps with automated camera imaging. The proposed system integrates advanced image processing techniques with a Convolutional Neural Network (CNN) to accurately detect and classify moths and non-moth insects captured on sticky traps. Sticky traps, widely employed in integrated pest management (IPM) systems, often require manual inspection, which is labor-intensive and prone to human error. To address this, the developed system automates the detection process, reducing reliance on manual counting while improving classification precision. The dataset, consisting of 1,739 high-resolution images, was divided into training and testing subsets with a 70–30% split. Each image was preprocessed and annotated with ground-truth labels for accurate performance evaluation. The model demonstrated a high overall classification accuracy of 95.8%, with precision, recall, and F1-scores consistently exceeding 90%. These results highlight the effectiveness of the CNN in managing complex scenarios such as insect overlap, varied environmental conditions, and trap orientations, offering a scalable and efficient solution for real-time insect population monitoring in storage environments. The findings suggest that the proposed system provides a reliable and automated alternative for pest management, significantly reducing labor and enhancing decision-making in storage facilities and postharvest agriculture. In addition, field validation demonstrated the system’s feasibility in real-world storage environments, offering an effective and scalable alternative to traditional inspection practices while minimizing labor and enhancing precision pest control decisions.,This dataset features a subset of the images captured every hour in a sticky trap baited with a Plodia interpunctella pheromone lure. The images were processed for classificaiton of Indian meal moths and for population counting over time. A read me on image file naming convention, meta data, and conversion code for MatLab are included in the data files.,This research used resources provided by the SCINet project and/or the AI Center of Excellence of the USDA Agricultural Research Service, ARS project numbers 0201-88888-003-000D and 0201-88888-002-000D.,