Scanner Data Research Articles

The Impact of Private Label Introduction on Assortment, Prices, and Profits of Retailers*

We study how introducing private‐label brands (PLs) affects retail prices and profits, accounting for assortment adjustments of national brands (NBs). We employ an event‐study framework and scanner data on the US beef market. When a PL is added to the low‐priced market segment, we find that retail stores further differentiate NBs from the PL and remove same‐segment NBs. When a PL is added to the high‐priced segment, however, NB assortment changes are limited. PL introduction and PL‐driven NB assortment changes impose small price effects on NB, but strongly cannibalize NB demand and steer consumers toward PLs, likely increasing store profits.

Willingness-to-Pay for Energy Efficiency: Evidence from the European Common Market

This paper explores the willingness-to-pay for energy efficiency by exploiting variation across products and countries within the EU market for household appliances. Based on scanner data at product-level, I use the hedonic method to estimate implicit prices for energy efficiency and derive implicit discount rates. The paper argues that the implicit price will be underestimated when energy consumption is not only a determinant of operating cost but also is positively associated with other features of a product. The empirical analysis confirms that estimates of the willingness-to-pay are higher when this effect is accounted for in the estimation. This is especially true of product types for which the heterogeneity of usage intensity is low. The results thus indicate that the energy efficiency gap is smaller than found in earlier studies.

A Patchy Prohibition: Product and Flavor Substitution After the Food and Drug Administration's Prioritized Enforcement Policy on Flavored E-cigarettes.

E-cigarettes have rapidly grown in use among U.S. adolescents; in response, the Food and Drug Administration (FDA) engaged in an "enforcement policy on banned e-cigarette flavors" ("enforcement action") for pod-based e-cigarettes in January 2020, which accounted for most U.S. e-cigarette sales. No literature has yet examined long-term changes in e-cigarette sales patterns changed in relation to the FDA enforcement action. We analyzed U.S. e-cigarette sales using Nielsen retail scanner data between March 2017 and December 2021, describing e-cigarette sales trends overall, by device type, and by flavor category. We also performed joinpoint regression analysis on the sales trends to detect significant changes in the rate of change of sales over time. The FDA enforcement action was associated with a sharp initial decrease in prefilled pod dollar sales, followed by a steady increase from April 2020 through the end of 2021, growing beyond the previous maximum in August 2019. We also observed a dramatic change in the composition of flavors sold: A large decline in mint-flavored pod sales was offset by a similar increase in menthol-flavored sales. Simultaneously, disposable product sales increased nearly ten-fold from July 2019 to July 2020 before stabilizing, dominated by fruit-flavored products. Our findings suggest rapid product substitution without a long-term decline in e-cigarette sales in association with the enforcement action, along with a growing dominance of youth-friendly flavors, contrasting against FDA policy goals. Our study revealed the weakness of the "patchy" enforcement action, raising concern about its unintended consequences as consumption simply shifted to other e-cigarette products. This is the first detailed longitudinal study on e-cigarette sales trends in the United States following the FDA flavor enforcement action, with novel findings on flavor trends and their relation to policy events. We report sales overall, by product type, and by flavor category, and highlight several important trends following the action, such as the rise and persistence of disposable e-cigarettes increasingly and overwhelmingly dominated by youth-friendly flavors, and likely substitution of prefilled e-cigarette flavors without any long-term decline in sales. Our results highlight the weaknesses of "patchy" regulation and suggest the need for a more comprehensive approach to flavor regulation.

Neural network spectral relationship to improve an inherent optical properties data processing system for residual error correction.

The residual error was a critical indicator to measure the data quality of ocean color products, which allows a user to decide the valuable envisioned application of these data. To effectively remove the residual errors from satellite remote sensing reflectance (Rrs) using the inherent optical data processing system (IDAS), we expressed the residual error spectrum as an exponential plus linear function, and then we developed neural network models to derive the corresponding spectral slope coefficients from satellite Rrs data. Coupled with the neural network models-based spectral relationship, the IDAS algorithm (IDASnn) was more effective than an invariant spectral relationship-based IDAS algorithm (IDAScw) in reducing the effects of residual errors in Rrs on IOPs retrieval for our synthetic, field, and Chinese Ocean Color and Temperature Scanner (COCTS) data. Particularly, due to the improved spectral relationship of the residual errors, the IDASnn algorithm provided more accurate and smoother spatiotemporal ocean color product than the IDAScw algorithm for the open ocean. Furthermore, we could monitor the data quality with the IDASnn algorithm, suggesting that the residual error was exceptionally large for COCTS images with low effective coverage. The product effective coverage should be rigorously controlled, or the residual error should be accurately corrected before temporal and spatial analysis of the COCTS data. Our results suggest that an accurate spectral relationship of residual errors is critical to determine how well the IDAS algorithm corrects for residual error.

Grocery Shopping for America: Mitigation Strategies for Threats to National Identity

People demonstrate indirect support for a nation's identity by consuming products representing their nationality. In such context, this article focuses on how people react toward brands with national associations when the nation faces threats perpetrated by institutions. Institutions are important as they are one of the core elements defining national identity. Institutional threats to national identity can come from within the nation (internal threat) and from outside (external threat). Weekly supermarket scanner data from 2004 showed that sales of American-sounding brands declined in counties that saw higher coverage of the Abu Ghraib prison torture scandal (internal threat), and sales of American-sounding brands increased in counties with more war casualties (external threat). Seven additional experiments demonstrated that (1) self-enhancement derived from national identity mediates these main effects, (2) advertisements that refocus attention on how the brand helps cope with external threats mitigate the negative effects of internal threats for American brands, and (3) such advertisements do not mitigate the negative effects of internal threats for non-American brands. Qualitative surveys (N = 218), surveys (N = 1,603), experiments (N = 3,123), and secondary data analyses (encompassing sales of over 8,000 brands across more than 1,100 U.S. stores) were used to triangulate the results.

Early evidence of flavored tobacco product restrictions in Massachusetts and New York State.

With many US states and localities enacting policies that restrict flavored e-cigarette sales, evaluation of these restrictions is critical to inform future efforts. This study analyzed both survey and retail scanner data to assess early-stage impacts of flavored tobacco sales restrictions in Massachusetts and New York State on e-cigarettes sales and product use among young people. This study uses state-level e-cigarette retail sales data and survey data from youth and young adults (aged 13-24 years). Cross-sectional surveys were conducted at two time points in Massachusetts (both post policy implementation) and New York (pre and post policy implementation); retail sales data in both states were analyzed from 2019 through 2020 and compared to sales in control states. E-cigarette unit sales decreased significantly following the implementation of statewide restrictions on flavored e-cigarettes in both Massachusetts and New York State (p<0.001). Survey data showed a decrease in mint flavored e-cigarette use in Massachusetts and an increase in tobacco flavored e-cigarette use in New York State over time (p=0.001). In both states, a greater proportion of respondents reported using disposable e-cigarettes at Time 2 compared to Time 1 (p=0.001). Among those who reported using fruit-flavored e-cigarettes in New York State, a significantly greater proportion reported disposable device use at Time 2 compared to Time 1 (p=0.004). Findings from these case studies from two US states suggest that statewide policies reduce the availability of e-cigarettes and have the potential to reduce use of many youth-appealing flavors. The increase in use of disposable e-cigarettes likely reflects existing loopholes in federal policy, which may be attenuating the potential impact of strong state-level policies.

Application of optical scanning systems and 3D modeling algorithms as a method to control the depth of teeth preparation for fixed orthopedic structures

Background. In orthopedic dentistry at the present stage of its development, a chemical technique for preparing teeth for fixed structures of dentures has been developed; however, the state of the pulp in response to preparation is not taken into account. As a result, medical tactics for preserving or extirpating the pulp of abutment teeth, depending on the clinical case, are unreasonable. Given the generally accepted rules for preparing teeth for fixed orthopedic structures, there is a significant percentage of complications. Controlling the depth of tooth preparation makes it possible to carry out this manipulation as rationally as possible, and as a result to ensure the effectiveness of procedure, based on the state of vitality of the prepared teeth. The aim of the study is to determine and control the depth of the studied teeth preparation using digital volumetric scanning technology and algorithms of a digital graphic 3D editor in the CAD/CAM system. Materials and methods. The article presents the results of using digital volumetric scanning of the CAD/CAM system and an integrated algorithm for digital 3D modeling to determine and control the depth of teeth preparation for fixed orthopedic structures. Results. Based on the results of digital volumetric scanning, the working thickness of the tooth preparation in the area of the tooth neck was determined with the formation of various types of chamfer in different study groups. In order to determine the depth of the preparation of hard dental tissues, an artificial crown was modeled in the CAD system — digital volumetric scanner NeWay (Open Technologies) and data on its thickness in the area of the ledge were obtained. Conclusions. Method of digital volumetric scanning to determine and control the depth of preparation of hard dental tissues makes it possible to prevent the development of irreversible morpho-functional changes in the tissues of teeth caused by odontoreparation.

An Integrated Approach between Multispectral Satellite Images and Geophysical and Morpho-Topographic Surveys for the Detection of Water Stress Associated with Coastal Dune Erosion

Coastal erosion occurs due to different processes involving physical and ecological systems. One of these factors is the degree of water stress experienced by dune vegetation. While healthy dune vegetation can help to stabilize the dune systems, water-stressed vegetation can instead enhance dune erosion. In this study, remote sensing techniques were used to monitor the water stress affecting the dune vegetation in dune systems along the alluvial plain of the Chiatona coast (Apulia, Southern Italy) located on the Ionian Arc. Multispectral satellite data from Landsat 8/9 and Sentinel-2 were used to assess the water stress at different spatial scales over a 4-year monitoring period from 2019 to 2023. The normalized difference vegetation index (NDVI) and the normalized difference moisture index (NDMI) were used to identify dune surfaces that were experiencing water stress. Furthermore, a terrestrial laser scanner and LiDAR data were acquired at different temporal ranges in areas affected by water stress to highlight coastal changes in areas associated with unhealthy dune vegetation. A large drop in NDVI values was observed in May 2020 due to the occurrence of coastal fires in some parts of the Chiatona coast. Geoelectrical surveys were conducted to investigate if coastal fires were capable of saline groundwater contamination, potentially enhancing dune erosion in these areas. The joint analysis of remote sensing, topographical, and geoelectric data showed that water stress reduced the amount of healthy dune vegetation, triggering dune deflation processes that resulted in increased coastal erosion rates, while also leading to the saline contamination of groundwater.

Light Absorption by Optically Active Components in the Arctic Region (August 2020) and the Possibility of Application to Satellite Products for Water Quality Assessment

In August 2020, during the 80th cruise of the R/V “Akademik Mstislav Keldysh”, the chlorophyll a concentration (Chl-a) and spectral coefficients of light absorption by phytoplankton pigments, non-algal particles (NAP) and colored dissolved organic matter (CDOM) were measured in the Norwegian Sea, the Barents Sea and the adjacent area of the Arctic Ocean. It was shown that the spatial distribution of the three light-absorbing components in the explored Arctic region was non-homogenous. It was revealed that CDOM contributed largely to the total non-water light absorption (atot(λ) = aph(λ) + aNAP(λ) + aCDOM(λ)) in the blue spectral range in the Arctic Ocean and the Barents Sea. The fraction of NAP in the total non-water absorption was low (less than 20%). The depth of the euphotic zone depended on atot(λ) in the surface water layer, which was described by a power equation. The Arctic Ocean, the Norwegian Sea and the Barents Sea did not differ in the Chl-a-specific light absorption coefficients of phytoplankton. In the blue maximum of phytoplankton absorption spectra, Chl-a-specific light absorption coefficients of phytoplankton in the upper mixed layer (UML) were higher than those below the UML. Relationships between phytoplankton absorption coefficients and Chl-a were derived by least squares fitting to power functions for the whole visible domain with a 1 nm interval. The OCI, OC3 and GIOP algorithms were validated using a database of co-located results (day-to-day) of in situ measurements (n = 63) and the ocean color scanner data: the Moderate Resolution Imaging Spectroradiometer (MODIS) onboard the Terra (EOS AM) and Aqua (EOS PM) satellites, the Visible and Infrared Imager/Radiometer Suite (VIIRS) onboard the Suomi National Polar-orbiting Partnership (S-NPP) and JPSS-1 satellites (also known as NOAA-20), and the Ocean and the Land Color Imager (OLCI) onboard the Sentinel-3A and Sentinel-3B satellites. The comparison showed that despite the technological progress in optical scanners and the algorithms refinement, the considered standard products (chlor_a, chl_ocx, aph_443, adg_443) carried little information about inherent optical properties in Arctic waters. Based on the statistic metrics (Bias, MdAD, MAE and RMSE), it was concluded that refinement of the algorithm for retrieval of water bio-optical properties based on remote sensing data was required for the Arctic region.

DEPART: Decomposing prices using atheoretical regression trees

Regular prices and temporary discounts are important elements for retailers’ and brands’ pricing decisions. These two variables need to be considered separately because consumer sensitivities to their changes typically differ. Although the scope and richness of retail datasets have grown rapidly in recent years, most of them only record actual prices paid by customers and lack direct information about regular prices and discounts. A systematic review involving close to five hundred publications that investigated pricing variables using retail scanner data confirms this, as 63% of them only observed actual prices. To solve this missing data problem, these studies often adopted heuristics to decompose actual prices into regular prices and discount depths. However, there are many such heuristics and their accuracies have not been assessed. This research introduces DEPART, a new machine learning approach based on regression trees with a publicly available R package and benchmarks it against previously used heuristics in two different datasets. The results show that on average the proposed method outperforms previously used heuristics by 26.5% or more. Additional analyses illustrate the potential economic benefits of adopting DEPART to improve pricing decisions.

Changes in Sales of Vaping Products and Cigarettes Associated With the New York State Flavored Vaping Product Sales Restriction.

New York (NY) implemented a statewide restriction on the retail sale of flavored vaping products to reduce availability of vaping products having youth-appealing flavors in 2020. We assessed the intended effects of the NY law on sales of flavored vaping products and explored whether policy implementation had unintended effects on consumer behavior by evaluating policy-associated changes in sales of combusted cigarettes, which could serve as more harmful substitute products for NY consumers of flavored vaping products. We analyzed custom product-level weekly retail tobacco sales scanner data for NY and a comparison state (California [CA]) for convenience stores and other outlets from June 2018 through June 2021. We categorized flavor descriptors for vaping products as flavored or as tobacco or unflavored and categorized cigarettes as menthol or non-menthol. We used a difference-in-difference model to assess the effect of the sales restriction on unit sales of flavored and unflavored vaping products and menthol and non-menthol cigarettes in NY compared with CA. Following NY policy implementation, flavored and total vaping product sales decreased in NY relative to CA. Unflavored vaping product sales increased in NY, while menthol cigarette sales did not change significantly relative to CA sales. The NY flavored vaping product policy was associated with fewer sales of flavored and total vaping products. The increase in sales of unflavored vaping products did not suggest complete substitution, and sales data suggest that consumers did not turn to cigarettes after flavored vaping products became unavailable. This study provides evidence that NY's flavored vaping product policy is associated with reduced flavored vaping product access and sales. Our analyses of potential unintended consequences indicate that some consumers switched from flavored to unflavored vaping products, but that cigarette sales did not change concurrent with the policy which means that decreased availability of flavored vaping products did not result in vapers switching to cigarettes. NY's policy had its intended effect with limited unintended consequences.

The Computer and the Statistician. Computerization and the Mobilization of Scanner Data by National Statistical Institutes for the Construction of Price Indexes

The Computer and the Statistician. Computerization and the Mobilization of Scanner Data by National Statistical Institutes for the Construction of Price Indexes

Assessing Precision and Dependability of Reconstructed Three-Dimensional Modeling for Vehicles at Crash Scenes using Unmanned Aircraft System

This study focuses on the accuracy assessment of 3D reconstructions of crime scenes using Unmanned Aircraft Systems (UAS) and Terrestrial Laser Scanners (TLS) data for forensic crash investigation. Forensic crash investigation involves meticulously analyzing physical evidence, vehicles, and human factors in road collisions to determine the sequence of events. Preserving the original state of the crash scene before cleaning is essential for accurate forensic analysis. However, this preservation process can disrupt normal activities and demand considerable time. Geomatic technology, specifically UAS or drones, offers a potential solution for efficient and precise forensic mapping. The application of UAS technology enables swift data collection, leading to cost savings, enhanced safety, and data utilization. This study aims to assess the suitability of UAS techniques for forensic mapping, encompassing both relative and absolute accuracy. This research uses a UAS to rapidly and comprehensively capture evidence from a simulated crash site using predefined flight paths. The acquired image data is then processed utilizing Agisoft Metashape software, generating a detailed 3D model of the crash scene. This model can be enriched with annotations, measurements, and pertinent information. A comparative analysis is performed by preparing a table that contrasts the absolute and relative accuracy of UAS-collected data with that obtained from TLS, which serves as a benchmark. The results reveal that the UAS demonstrates a relative accuracy Root Mean Square Error (RMSE) of approximately ±4.1 cm compared to TLS. Concerning absolute precision, the UAS-produced RMSE values are determined as ±0.20719 for the X coordinate, ±0.164 for the Y coordinate, and ±0.001584 for the Z coordinate compared to GNSS data, which functions as the benchmark. The utilization of UAS technology offers a non-invasive measurement approach that eliminates direct physical contact between the operator and the documented object. This non-intrusive method ensures the preservation of the original scene characteristics and has shown its superiority over conventional approaches in managing crash scenes. Overall, this study underscores the potential of UAS technology in accurately reconstructing crime scenes for forensic investigation purposes.

Characteristics Associated With Purchasing Sugar-Sweetened Beverages and Bottled Water Among US Households, 2015

BackgroundFrequent intake of sugar-sweetened beverages (SSBs) among US adults is a public health concern because it has been associated with increased risks for adverse health outcomes such as obesity, type 2 diabetes, and cardiovascular disease. In contrast, drinking plain water (such as tap, bottled, or unsweetened sparkling water) instead of drinking SSBs might provide health benefits by improving diet quality and helping prevent chronic diseases. However, there is limited information on estimated expenditures on SSBs or bottled water among US households. ObjectiveThis study examined differences in SSB and bottled water purchasing according to household and geographic area characteristics and estimated costs spent on purchasing SSB and bottled water from retail stores among a nationally representative sample of US households. DesignThis study is a secondary analysis of the 2015 Circana (formerly Information Resources Inc) Consumer Network Panel data, which were merged with the US Department of Agriculture nutrition data using the US Department of Agriculture Purchase-to-Plate Crosswalk-2015 dataset (the latest available version of the Purchase-to-Plate Crosswalk at the time the study began), and the Child Opportunity Index 2.0 data. Participants/settingsA total of 63,610 households, representative of the contiguous US population, consistently provided food and beverage purchase scanner data from retail stores throughout 2015. Explanatory variablesThe included demographic and socioeconomic variables were household head’s age, marital status, highest education level, race and ethnicity of the primary shopper in the household, family income relative to the federal poverty level, and presence of children in the household. In addition, descriptors of households’ residential areas were included, such as the county-level poverty prevalence, urbanization, census region, and census tract level Child Opportunity Index. Main outcome measuresAnnual per capita spending on SSB and bottled water and daily per capita SSB calories purchased. Statistical analysisUnadjusted and multivariable adjusted mean values of the main outcome measures were compared by household demographic, socioeconomic, and geographic characteristics using linear regression analysis including Circana’s household projection factors. ResultsNearly all households reported purchasing SSBs at least once during 2015 and spent on average $47 (interquartile range = $20) per person per year on SSBs, which corresponded to 211 kcal (interquartile range = 125 kcal) of SSBs per person per day. About seven in 10 households reported purchasing bottled water at least once during 2015 and spent $11 (interquartile range = $5) per person on bottled water per year. Both annual per capita SSB and bottled water spending, and daily per capita SSB calories purchased was highest for households whose heads were between 40 and 59 years of age, had low household income, or lived in poor counties, or counties with a low Child Opportunity Index. Annual per capita spending was also higher for households with never married/widowed/divorced head, or at least 1 non-Hispanic Black head, and households without children, or those living in the South. Daily per capita SSB calorie purchases were highest for households where at least 1 head had less than a high school degree, households with at least 1 Hispanic or married head, and households with children or those living in the Midwest. ConclusionsThese findings suggest that households that had lower socioeconomic status had higher annual per capita spending on SSBs and bottled water and higher daily per capita total SSB calories purchased than households with higher socioeconomic status.

Estimating the vertical direction in a photogrammetric 3D model, with application to visualization

The process of building a Virtual Reality (VR) environment from images involves several steps: choose experimental conditions (scene, camera, trajectory, weather), take the images, reconstruct a textured 3D model thanks to a photogrammetry software, and import the 3D model into a game engine. This paper focuses on a postprocessing technique for the photogrammetry step, mostly for outdoor environments that cannot be reconstructed using an unmanned aerial vehicle. As visualization applications (including VR) need a 3D model with a known vertical direction, a method is introduced to compute it. The method is based on 3D principal component analysis and a 2D Hough transform. In the experiments, we first reconstruct both man-made and natural immersive environments using a helmet-held 360 camera, then we import the 3D models in good coordinate systems (i.e. with a vertical axis and a plausible scale) into Unity, and finally we use VR headsets to explore the scenes like a pedestrian. We also experiment on scanner data and show that our method is competitive with previous work.

Changes in Sales of Tobacco and Nicotine Replacement Therapy Products Before and During the COVID-19 Pandemic.

The COVID-19 pandemic and its associated social distancing policies such as lockdowns and quarantine influenced people's lives and health behaviors. We comprehensively assessed national trends in sales of cigarettes, cigars, e-cigarettes, and over-the-counter nicotine replacement therapy (NRT) products before and during the pandemic, allowing for cross-product comparisons. Stockpiling behavior was also assessed. We used US national tobacco and over-the-counter NRT retail store scanner data (excluding internet, specialty/vape store, and prescription sales) collected at 4-week intervals by NielsenIQ from December 2018 to June 2021. We applied an interrupted time-series model to assess differences in tobacco product and NRT unit sales before and during the pandemic. We defined the prepandemic period as December 16, 2018, through April 4, 2020, pandemic as starting on April 5, 2020, through June 26, 2021, and the stockpiling period as one 4-week period before the pandemic started. Four-week cigarette, e-cigarette, and cigar unit sales on average increased by 11.5% (P = .006), 37.1% (P < .001), and 26.1% (P < .001) respectively, while 4-week NRT unit sales decreased on average by 13.1% (P < .001), during the pandemic compared with the prepandemic period. Stockpiling was associated with increases in sales of all tobacco products and NRT products. Unit sales of assessed tobacco products increased while NRT unit sales decreased during the COVID-19 pandemic, compared with the prepandemic period. These changes may suggest an increase in the intensity of tobacco product use or stockpiling of tobacco products among people who use tobacco.

Strategy for HBIM implementation using high-resolution 3D architectural documentation based on laser scanning and photogrammetry of the José de Alencar theatre

Cultural heritage (CH) relevant importance to society leads to the need for historical, architectural, historical, and structural documentation. Such documents are necessary for the effective conservation and restoration of heritage buildings. Digitalization and documentation have been challenging and multidisciplinary topics for cultural heritage (CH) involving new technologies for information capture. 3D architectural documentation of existing heritage buildings is possible due to digital survey technologies joined with BIM methodology. The José de Alencar Theatre was surveyed with an integrated approach using a laser scanner and photogrammetry. BIM methodology based on digital scanning and image-based data was applied to generate a 3D model and extensive BIM library. The results indicate that a reliable BIM model of the José de Alencar theatre can be done, generating useful documentation and information on the historical construction based on the laser scanner and photogrammetry data with architectural geometry well-detailed.

Bigger, stronger and cheaper: growth in e-cigarette market driven by disposable devices with more e-liquid, higher nicotine concentration and declining prices

ObjectiveGiven the evolving changes in the disposable e-cigarette market, we explore patterns of sales in the USA by e-liquid volume capacity, nicotine strength and real sales-weighted average prices by both...

Automatic labelling for semantic segmentation of VHR satellite images: Application of airborne laser scanner data and object-based image analysis

The application of deep learning methods to remote sensing data has produced good results in recent studies. A promising application area is automatic land cover classification (semantic segmentation) from very high-resolution satellite imagery. However, the deep learning methods require large, labelled training datasets that are suitable for the study area. Map data can be used as training data, but it is often insufficiently detailed for very high-resolution satellite imagery. National airborne laser scanner (lidar) datasets provide additional details and are available in many countries. Successful land cover classifications from lidar datasets have been reached, e.g., by object-based image analysis. In the present study, we investigated the feasibility of using airborne laser scanner data and object-based image analysis to automatically generate labelled training data for a deep neural network -based land cover classification of a VHR satellite image. Input data for the object-based classification included digital surface models, intensity and pulse information derived from the lidar data. The resulting land cover classification was then utilized as training data for deep learning. A state-of-the-art deep learning architecture, UnetFormer, was trained and applied to the land cover classification of a WorldView-3 stereo dataset. For the semantic segmentation, three different input data composites were produced using the red, green, blue, NIR and digital surface model bands derived from the satellite data. The quality of the generated training data and the semantic segmentation results was estimated using an independent test set of ground truth points. The results show that final satellite image classification accuracy (94–96%) close to the training data accuracy (97%) was obtained. It was also demonstrated that the resulting maps could be used for land cover change detection.

Agri-food importing firms amid a global health crisis

This paper exploits daily customs transaction data on the universe of Swiss agri-food importing firms to assess the response of firms to a global shock. Estimating a linear model that regresses product-level import margins on daily COVID19 shocks and a host of fixed effects, we find that the pandemic had a substantial trade-reducing effect on imports. The trade effects were driven mainly by a reduction in the number of importing firms (i.e., 63% of the total effect), and much less by the number of products imported and the average import value per product per firm. We explore several sources of heterogeneity and show, among others, that larger and incumbent firms were affected more by the trade adjustments. Our results also reveal that the relative contribution of each import margin to the decline in aggregate imports depends on the level of data aggregation (i.e., daily, weekly or monthly). Finally, we validate and confirm our main findings by testing two mechanisms: (i) third-country supply-side effects using insights from structural gravity models and (ii) changes to consumer demand using consumer mobility, and retailer and consumer scanner data.