As part of the Common Agricultural Policy (CAP) of the European Union (EU), farmers make annual declarations of the agricultural activities for which they receive subsidies. The declarations include the crops they grow at parcel level, referred to as Geo-Spatial Application (GSA) data. Paying Agencies (PA) of every EU Member State MS) use specific crop classifications in their native language, and not all provide access to the GSA data. In the past, the EuroCrops initiative harmonized openly available GSA data for a single year (2021) using the Hierarchical Crop and Agriculture Taxonomy (HCAT), but multiple years are available depending on the country. Harmonizing a time series of farmers' crop declarations at parcel level would allow for comparative spatiotemporal analysis across the EU, the development of indicators that can be used for CAP and other policy monitoring purposes, and would provide data for training and validation of remotely sensed products. Here we have collected the GSA crop type declarations and parcel geometries that are publicly available from 18 PAs, the administrative bodies managing GSA data, for a minimum of three years, but covering the period 2008-2023, where available. We have then harmonized the GSA data using HCAT4, a new version developed as part of this work. The data set includes nearly 47 million parcels covering 21 Mha. To facilitate integration and interoperability of the GSA data with other EU data sets containing spatial information on crops, we harmonized the crop classes used in the following data sets with HCAT4: (1) LUCAS, (2) the Integrated Farm Statistics/Farm Structure Survey, (3) the Farm Accountancy Data Network (FADN), and (4) the classification systems of the Copernicus High Resolution Layer on Crop Types. To demonstrate the potential of the multiannual, harmonised dataset presented in this paper, the GSA data were aggregated to NUTS 2 regions and compared with statistics on crop areas from Eurostat, showing good correspondence for many crops but also highlighting those crops and countries where the agreement is less good, providing possible reasons why. The data can also be used for mapping crop rotations, and a map showing maize monoculture illustrates this application. Farmers' declarations will increasingly become available as MS are required to publish these under the High-Value Dataset regulation. The EuroCrops v2.0 data set is registered and publicly available under 10.2905/b9fb9e67-78a9-4327-9d59-39a928d812d3 .

This paper presents a Europe-wide agricultural land use systems map produced by the integration and harmonization of grasslands and croplands layers from the Copernicus Land Monitoring Service High Resolution Layers (HRL) in Europe. By utilizing high-resolution spatial data from the Copernicus Sentinel missions, the study applies a predefined set of logical rules to identify crop-grass sequences by combining the HRL products. The resulting maps provide detailed classifications of permanent grasslands, permanent crops, arable systems, and land use changes across 38 countries in the European Environment Agency network (EEA38) from 2017 to 2021. European agriculture is dominated by permanent grasslands (45.5%), followed by arable systems including temporary grassland (33.5%), permanent crops (3.8%), and land use change (1.6%). While the study is based on HRL products with substantial accuracy, some discrepancies (<3% of classified areas), such as disagreements in land use classifications across years and data gaps, present opportunities for further refinement and improvement. The derived harmonized agricultural land use systems data is a step forward for assessments in land and soil management, nature restoration, and climate mitigation targets.

Quantifying grassland biomass is essential for monitoring forage availability in livestock-based agricultural systems and for supporting sustainable land management and policy decisions across Europe. Remote sensing offers extensive capabilities for monitoring grasslands, but the lack of adequate in-situ data for training and validation constrains the evaluation of regression models at a continental scale. The dedicated grassland module in the 2022/23 rollout of the Land Use/ Cover Area frame Survey (LUCAS) constitutes a unique, large-scale and geographically comprehensive data source covering the European Union (EU). This study investigates the suitability of the LUCAS variables average grass height and vigour of vegetation for remote sensing-based analysis by conducting machine learning regression and classification on more than 4000 transects with a cloud-free Sentinel-2 scene available. The EU-wide grass height Support Vector Regression model, based on Sentinel-2 bands and vegetation indices, delivers a root mean square error (RMSE) of approximately 19 cm and an R2 of 0.25. Predicting the height of tall grassland presents greater challenges due to increased saturation of vegetation indices and the onset of plant senescence. The vigour of vegetation-a visual assessment on an ordinal scale-only allows for classification analysis that leads to frequent misclassification despite class aggregation. In conclusion, the average grass height is the preferred variable within the LUCAS database for biomass-related and remote sensing-based modelling. Rigorous filtering using ground images and metadata is strongly recommended to account for the environmental and management heterogeneity across the EU.

Meta-analyses (MAs) are needed to inform agricultural policies on sustainable farming practices (FPs). This study assesses the quality against established criteria of 570 MAs published from 2000-2023 and included in the recently published "JRC-Farming Practices Evidence Library". We find that average MA quality significantly improved (p < 0.001) over time. However, about two-thirds of the assessments showed deficiencies in at least four areas, notably study selection and publication bias reporting. MAs related to animal husbandry, manure management, and those synthesizing modelling-derived outcomes demonstrated particularly low quality. Less than 40% of MAs provided accessible original data, limiting reproducibility and re-use. These shortcomings may hinder the full potential of MAs to support evidence-based policy. We propose recommendations to promote FAIR data sharing, enhance awareness, and encourage greater transparency in reporting, which a needed to strengthen the role of MAs in agricultural sustainability.

European grasslands are among the world’s most species-rich ecosystems, yet they are increasingly shaped by two contrasting land-use trajectories: agricultural intensification and abandonment. Using 161,070 vegetation plots from the European Vegetation Archive covering all EU Member States and the United Kingdom, we quantified how landscape, environmental conditions, and nitrogen inputs jointly determine grassland plant diversity at continental scale. Applying a spatially explicit Bayesian modelling framework, we show that surrounding land use exerts a strong and consistent influence on local diversity. Landscapes dominated by low-intensity grasslands and heterogeneous farmland support approximately 8% higher plant diversity, whereas arable, urban, or woody-encroached landscapes reduce it. Diversity peaks at mid-elevation, in mildly acidic soils, and under moderately wet conditions, reflecting long-recognised gradients and providing a consistent, continent-wide estimate of their magnitude. Nitrogen inputs have a pronounced negative effect, with enrichment favouring nitrophilous, fast-growing species that outcompete slower-growing taxa. Spatial projection further indicates that, undercurrent nitrogen loads, grassland diversity is markedly reduced relative to a zero-input baseline, with national-level losses exceeding 10% in all EU Member States and reaching 29% in the Netherlands. These results highlight the considerable potential for biodiversity recovery if nitrogen inputs were reduced, particularly in intensively farmed regions. To complement this field-based analysis, we examined contemporary land-cover transitions using remotely sensed data from the Google-Dynamic-World dataset. Time-series classification allowed us to quantify the dominant processes driving ongoing grassland change across Europe. We found that succession linked to land abandonment, compounded by improving climatic conditions at higher elevations, is the prevailing process in montane and subalpine regions, where grasslands are increasingly transitioning towards woody vegetation. By contrast, intensification, conversion to cropland, and soil sealing are the most common pathways in flat, accessible lowlands, reflecting ongoing pressures from agriculture, infrastructure expansion, and urban development. This dual-pattern underscores how socio-economic drivers, accessibility, and biophysical gradients jointly structure grassland dynamics. Together, these two complementary lines of evidence show that sustaining Europe’s grassland biodiversity requires coordinated action across scales. Effective conservation and restoration will depend on integrating field-level mitigation with landscape-scale policies that internalise agricultural externalities and balance productivity, abandonment, and recovery within multifunctional rural systems.

The impacts of agricultural, environmental and climate change policies in Europe are investigated using the CAPRI (Common Agricultural Policy Regionalised Impact) model. Although the model runs at a regional level, primarily NUTS2, the underlying data have been spatially disaggregated to finer scale units called 'Farm Structure Units'. In this study we present these spatially disaggregated layers of agri-environmental variables for a time series from 2000 to 2018. This harmonized and spatially consistent data set includes crop types (area, yield), livestock types (totals and densities) and various parameters associated with nitrogen application and losses. These data can be used to calculate nitrogen budgets as well as providing inputs to biogeochemical or land management models.

The global increase in pesticide use has raised concerns about its impact on biodiversity, ecosystems, and human health, in particular of people living near agricultural areas. This study explores the assessment of pesticide exposure and risks to residents at a high spatial granularity using plant protection product data. Our objective was to develop an indicator to monitor pesticide risk levels faced by residents in France by integrating spatial datasets and exposure assessment methodologies. Using spatialized pesticide sales data based on crop authorizations, we mapped potential pesticide loads at the parcel level. This map, combined with population distribution data, allowed us to develop an indicator for monitoring residential pesticide exposures. Our findings indicate that, on average, 13% of people in France may be exposed to various levels of pesticides due to their proximity to treated crops. This indicator demonstrates the usefulness of granular pesticide sales data in monitoring exposure and can support risk reduction strategies, helping to identify regions where efforts towards sustainable farming should concentrate.

Context or problem In recent decades, compounding weather extremes and plant diseases have increased wheat yield variability in France, the largest wheat producer in the European Union. Objective or research question How these extremes might affect future wheat production remains unclear. Methods Based on department level wheat yields, disease, and climate indices from 1980 to 2019 in France, we combined an existing disease model with machine learning algorithms to estimate future grain yields. Results This approach explains about 59% of historical yield variability. Projections from five CMIP6 climate models suggest that extreme low wheat yields, which used to occur once every 20 years, could occur every decade by the end of this century, but elevated CO2 levels might lessen these events. Conclusions Heatwave-related yield losses are expected to double, while flooding-related yield losses will potentially decline by one third, depending on the representative concentration pathway. Ear blight disease is projected to contribute to 20% of the expected 400 kg ha-1 average yield losses by the end of the century, compared with 12% in the historical baseline period. These projections depend on the timing of anthesis, currently between late May and early June in most departments. Anthesis advancing to early May would shift losses primarily to heavy rainfall and low solar radiation. Implications or significance French wheat production must adapt to these emerging threats, such as heat stress, which until recently had little impact but may become the primary cause of future yield losses.

Due to confidentiality restrictions in releasing census and survey data, such as agricultural data from the European farm structure survey (9 million records), the data are aggregated to a coarse resolution (NUTS2 administrative regions) before public release. Even when other types of census data are released as grids, grid cells may be suppressed in locations where confidentiality rules have not been respected. Here, we present a method, implemented in the R package MRG, for creating multi-resolution grids that respect restrictions while maximizing the spatial resolution at which the data are disseminated. The method can be adjusted for different restrictions, it can create the same grid structure for a set of variables, and it allows for a contextual suppression of some grid cells (i.e., suppress if all neighbors are non-confidential, merge if several others are also confidential) if this results in a generally higher information content, a combination of features that has not previously been available. The method is exemplified with a synthetic data set.

Improving the sustainability of agriculture requires an advanced assessment of the ecological impacts of pesticides at both policy and scientific levels. This can be achieved by integrating ecological considerations into the assessments of plant protection products beyond plot or experimental sites. Among plant protection products, pesticides are often the most harmful and toxic due to the chemical properties of their active substances (AS), which can range from non- to extremely toxic depending on the organism affected. Our study applies the Pesticide Load Index (PLI), as applied in Denmark and in the United Kingdom , to quantify pesticide risks to environmental health and biodiversity across the European Union. The PLI is defined as the sum of the application rate (AR) for each applied AS (k) divided by the toxicity (TOX) for a number of non-target taxa such as birds, mammals, fish, algae and agricultural beneficial insects like bees and natural enemies of pests, using the formula: PLI = Σ (ARk / TOXk,i).Our methodology bridges the gap between ecological health and pesticide risk assessment using three extensive data sets (Figure 1). The first includes EU-wide estimations of AS emissions, as geospatial layers at 1km resolution, representing the most extensive data collection available for the entire European Union. The second dataset provides unparalleled granularity in AS use, capturing field-level information across France for the year 2018, including details on crop type distribution. The third dataset, sourced from the Pesticide Properties DataBase, assesses the ecological impacts of pesticide use by linking usage to ecotoxicological endpoints.Figure 1: Overview of the methodology for the Pesticide Load Index (PLI) Study. By integrating acute toxicity, chronic toxicity, and environmental fate, our approach moves towards a thorough understanding of pesticide impacts. Acute toxicity, indicative of short-term exposure, highlights immediate and potentially severe effects, while chronic toxicity addresses the long-term consequences of prolonged and continuous exposure. The environmental fate sheds light on the pesticides' behaviour and transformation in the environment, considering their distribution, degradation, accumulation, and transport across air, water, and soil.The outcomes of this study provide a new perspective on pesticide use within the EU. The highly granular nature of the PLI maps makes them key tools for identifying areas with high ecotoxic levels, and therefore informing where additional risk mitigation measures are necessary. Detailed analyses are done by i) identifying predicted hotspots of pesticide use across the EU, ii) analysing variations in bio-climatic regions, and iii) breaking down the results by crop type and region. The role of this approach in monitoring the progress towards the European Union Farm to Fork and Biodiversity strategies targets is therefore clear, particularly in relation to the ambitious target of reducing pesticide use and toxicity by 50% by 2030. Our framework provides essential ecological insights for biodiversity conservation and ecosystem preservation, providing policy-makers with spatially explicit data for better-tailored strategies. Additionally, by enabling comparisons between crops, regions, and EU Member States it can contribute as to developing protective, realistic, and scientifically sound regulatory frameworks.

The European agricultural census in 2020 collected a large number of variables from the major share of all the farms within the European Union. There are many potential applications of such a data set, from direct estimates of agricultural indicators to use as input in more complex analytical models. However, the individual responses in the data set cannot be shared directly, as they are regarded as confidential information. Instead, the data must be aggregated to a level where individual responses cannot be identified, typically NUTS regions or grid cells. As a minimum, each aggregated value must be estimated from at least 10 farms (frequency rule). Additionally, a dominance rule requires an aggregated value to be treated as confidential if the 2 largest farms are responsible for more than 85% of the value within a grid cell.Whereas such requirements are clear, there are many methods for creating grids that respect them. The distribution of data is usually not homogeneous, and different methods have varying effects on the result. We will outline the advantages and drawbacks of certain methods and present the most promising one that involves grid cells of varying sizes. Whereas there are some examples of this method in the past, it will be the first time it is applied on a continental scale and high-resolution data set such as the European agricultural census data.

This study presents an operational and robust method for detecting and dating cereal harvest events using temporal stacks of Copernicus Sentinel-2 imagery and crop and fields border information from ancillary records. The proposed approach is exempt from training data, thereby enabling its application across diverse geographical contexts. The method was used to generate 10 m resolution maps of harvest dates for all wheat and barley fields in 2021, 2022, and 2023 in Castilla y León, a major cereal-producing region of Spain. This work also investigates the use of a reference dataset derived from real time kinematic records (RTK) in agricultural machinery as an alternative source of large-scale in situ data reference as for Earth observation-based agricultural products. The initial comparison of annual harvest date maps with the RTK-based reference datasets revealed that the temporal lag in the detection of harvest events between Earth observation-derived maps and reference harvest dates was less than 10 days for 65.7% of fields, while the temporal lag was between 10 and 30 days for 26.1% of the fields. The 3-year average root mean square error of the lag between harvest dates in the reference dataset and maps was 16.1 days. An in-depth visual analysis of the Sentinel-2 temporal series was carried out to understand and evaluate the potential and limitations of the RTK-based reference dataset. The visual inspection of a representative sample of 668 fields with large temporal lags revealed that the date of harvest of 41.11% of these fields had been correctly identified in the Sentinel-2 based maps and 16.43% of them had been incorrectly identified. The visual inspection could not find evidence of harvest in 10.52% of the analyzed fields. Monte Carlo simulations were parameterized using the findings of the visual inspection to build a series of synthetic reference datasets. Accuracy metrics calculated from synthetic datasets revealed that the quality of the harvest maps was higher than what the initial comparison against the RTK-based reference dataset suggested. The date of harvest was registered within 10 days in both the maps and the synthetic reference datasets for 90.5% of the fields, the root mean squared error of the comparison was 9.5 days, and harvest dates were registered in the Sentinel-2 based maps 2 days (median) after the dates registered in the reference dataset. These results highlight the feasibility of mapping harvest dates in cereal fields with time series of high-resolution satellite imagery and expose the potential use of alternative sources of calibration and validation datasets for Earth observation products. More generally, these results contribute to defining plausible targets for monitoring of agricultural practices with Earth observation data.

In the context of climate change, high expectations have been put on the agricultural sector for reducing greenhouse gas (GHG) emissions and enhance carbon sequestration. Consequently, a large and growing number of studies have evaluated the efficacy of various agricultural practices for climate change mitigation. However, the scientific evidence is often heterogeneous and frequently contradictory, making it difficult to use to support policy decisions. Meta-analyses synthesise large data sets and have become the gold standard for providing scientific evidence to inform environmental and agricultural policies. However, a growing number of meta-analyses are now available on a specific topic, occasionally with conflicting conclusions, requiring a further level of synthesis to consolidate the findings. We present the results of a systematic review of 693 published meta-analyses on the effect of farming practices on climate change mitigation. After a systematic search and review of the literature, we extracted data assessing the climate impacts of 34 farming practices and 123 comparisons of sub-practices with corresponding control practices, for a wide range of cropping and livestock systems around the world. From this dataset, we selected the farming practices that showed overall significantly positive effects on the reduction of GHG emission and/or on the increase of carbon sequestration. For cropland and grassland, we were able to identify a set of 35 mitigation sub-practices , including cover and catch crops, intercropping, leguminous crops, the use of enhanced efficiency fertilisers, soil amendment with lime and gypsum, different crop residue management techniques, water management practices, different conservation, restoration and management measures in grasslands, conservation and restoration of peatlands and wetlands, the conservation and creation of landscape features, as well as organic farming systems. For livestock, we identified seven effective mitigation practices, including livestock feeding techniques, manure land application techniques, manure storage techniques. A limited number meta-analyses reported the effect of a given practice on more than one GHG or on GHGs coupled with carbon sequestration together, limiting the exploration of interacting effects. The systematic evidence map provides robust and encompassing literature based evidence on farming practices with established positive effect on climate change mitigation to support a wide community of inventory compilers, modellers and policymakers. Our review also identifies farming practices with remaining knowledge gaps and research priorities.

Most crop simulation models do not consider the effect of waterlogging despite its importance for crop performance. Here, we reviewed the impact of waterlogging during different wheat phenological stages on grain number per unit area, average grain size, and grain yield. Episodes of waterlogging from the onset of tillering to anthesis result in fewer, and during grain filling in lighter grains. To simulate such impacts, we implemented a new waterlogging module into the wheat crop simulation model DSSAT-NWheat, accounting for the effects of waterlogging on wheat root growth, biomass growth, and potential average grain size. The model incorporating the new waterlogging routine was tested using data from a controlled experiment, and it reasonably reproduced wheat yield responses to pre-anthesis waterlogging. A sensitivity analysis showed that the simulated impact of waterlogging on above ground biomass and roots, as well as leaf area index, grain number, and grain yield varied with phenological stages. The simulated crop was most sensitive to pre-anthesis waterlogging, consistent with experimental studies. The new waterlogging-enabled crop model is an initial attempt to consider the impact of excess rainfall and waterlogging on crop growth and final grain yield to reduce model uncertainties when projecting climate change impacts with increasing rainfall intensity.

The agricultural sector holds the greatest reduction potential to limit adverse effects of reactive nitrogen in the environment. Assessing the negative impacts of excessive release of reactive nitrogen into the biosphere requires spatially explicit information to capture e.g. hot spots of nitrogen surplus, nitrogen use efficiency, the impact on sensitive ecosystems or on ground/drinking water quality.The agricultural economic model CAPRI is one of the main tools applied by the European Commission for the ex-ante analysis of the impact of agricultural policies and agro-environmental legislation at regional level (NUTS2) in Europe. CAPRI builds on long-term time series of regional, national and international agricultural statistics (e.g. crop and livestock production, fertilizer use), market and trade data. Inputs (e.g. inorganic fertilizer) in CAPRI are explicitly linked to production which delivers the basis for connecting environmental indicators (e.g. nitrogen surplus) directly to individual activities.To provide the link between the agro-economic model CAPRI and the impact assessment of nitrogen use in agriculture on the environment at higher spatial resolution, we developed a procedure to disaggregate CAPRI regional data and provide maps of nitrogen input/output, crop and livestock production for the time series 2000 – 2018 at the level of Farm Structure Units (FSU) for 26 EU member states and the UK. The FSU are built by the spatial intersection of a 10 x 10 km2 INSPIRE compliant grid, the CAPRI NUTS2 region borders and the soil mapping units of the Harmonized World Soil Data Base (FAO/IIASA/ISRIC/ISS-CAS/JRC, 2009), having a median area of 12 km2 (minimum 1 km2, maximum 100 km2).The disaggregation procedure for 36 crop types and 18 livestock categories from the regional level to the FSU is driven by information from the gridded Farm Structure Survey (FSS, 2010) crop and livestock data at 10 x 10 km2 resolution, CORINE (2018) non-agricultural land cover shares, altitude and slope constraints for individual crops / crop classes derived from LUCAS survey data (https://ec.europa.eu/eurostat/web/lucas).Nitrogen inputs from mineral fertilizer and manure are disaggregated from the regional level to the FSU following the crops’ requirements. N input from atmospheric deposition and N supply by biological fixation is taken into account at FSU level. N from mineralization of soil organic matter could not be taken into account due to lack of data. N losses from volatilization and surface run-off, N removal by harvest, N in crop residues complete the N flow data set in agricultural areas at FSU level.

This study conducts a comprehensive comparison of landscape feature data derived from different sources — Small Woody Features (SWF) product from Copernicus Land Monitoring system, LUCAS Landscape Feature (LF) Module, and LUCAS Transect Module — in EU agricultural landscapes. Additionally, we consider the European Monitoring of Biodiversity in Agricultural Landscapes (EMBAL) project's approach of in-situ data collection for land cover, landscape elements, and biodiversity. This approach offers a promising avenue for integrating detailed field survey data with broad-scale remote sensing observations. Furthermore the EMBAL project has the potential to enhance the previously mentioned datasets by incorporating additional information, such as the nature value of all surveyed land units, habitat types or pollination potential among others. This inclusion could contribute to having better insights into the ecological significance and monitoring of agricultural landscapes. Our analysis further explores the potential of incorporating cutting-edge datasets for enhanced monitoring of landscape features. Specifically, we consider the high-resolution (3-meter) dataset from Liu et al. (2023), which presents a detailed canopy height map and quantifies tree cover and woody biomass across Europe. We critically assess the strengths and limitations of each source: SWF's remote sensing foundation provides broad coverage but focuses only on woody features, the LUCAS LF Module combines photo-interpretation with field survey for a more detailed typology, and the LUCAS Transect, though discontinued, offered valuable field data for linear features. Strategies for monitoring landscape features have been considered for a long time, but are continually updated with the latest available data and methods. A comprehensive comparison and evaluation of the new data sources has not yet been carried out. Our study aims to identify complementarities between the different datasets to improve both quantitative and qualitative monitoring of landscape features informing sustainable agricultural practices and biodiversity conservation strategies.

Comprehensive, wall-to-wall, evaluation of cropping systems and therefore crop diversity using Earth Observation (EO) data is becoming reality. Agricultural policies such as the Common Agricultural Policy (CAP) in the European Union (EU) stimulate more diverse crop-mixes. We compute a new EU-wide overview of crop diversification for 2018 using the Shannon diversity index based on 10 m resolution EO crop map. For the EU as a whole, the effective number of species broadly ranges from 2.6 (p10) to 5.3 (p90) with a median of 3.9. The EO-based map allows identifying how crop diversity varies at an informative spatial resolution, e.g. in areas dominated by mono-cropping or with extensive forest cover. Here we compare the crop diversity calculated from top-down EO-data and bottom-up farmers' declarations in the Netherlands using the EO-based map (more than 84 millions 10 m pixels) and 2018 Dutch farmers declarations (more than 323 thousands parcels). After accounting for differences in thematic and spatial detail we show agreement in spatial patterns and calculated crop diversification (R2 = 0.62). Furthermore, we track changes in crop diversity over time using the Dutch farmers' declarations from 2009 to 2021, which suggest a positive response to the 2014 CAP greening policy. Combining the forthcoming Copernicus High Resolution Layers on Crop Types with increasingly available parcel data will enhance spatial targeting of agricultural policies and facilitate the monitoring of policy impact at farm to regional level.

The InsectAI COST action will support insect monitoring and conservation at the national and continental scale in order to understand and counteract widespread insect declines. The Action will bring together a critical mass of researchers and stakeholders in image-based insect AI technologies to direct and drive the research agenda, build research capacity across Europe and support innovation and application.There is mounting evidence that populations of insects around the world are in sharp decline. Understanding trends in species and their drivers is key to knowing the size of the challenge, its causes and how to address it. To identify solutions that lead to sustainable biodiversity alongside economic prosperity, insect monitoring should be efficient and provide standardised and frequently updated status indicators to guide conservation actions.The EU Biodiversity Strategy 2030 identifies the critical challenge of delivering standardised information about the state of nature and image-based insect AI can contribute to this. Specifically, the EU Nature Restoration Law will likely set binding targets for the high resolution data that cameras can provide. Thus, outputs of the Action will contribute directly to EU policies implementation, where biodiversity monitoring is considered a key component.The InsectAI COST Action will organise workshops, conferences, short-term scientific missions, hackathons, design-sprints and much more, across four Working Groups. These groups will address how image-based insect AI technologies can best address Societal Needs, support innovation in Image Collection hardware, create standardised approaches for Image Processing and develop novel Data Analysis and Integration methods for turning data into actionable insights.

Natural pest control is a crucial regulating ecosystem service for sustaining crop yields while lowering pesticide use. Its effectiveness depends on landscape complexity, particularly the amount and spatial arrangement of semi-natural habitats, in and around fields, that support natural enemies. We provide a 50 m-resolution, pan-European map of NPC potential that updates and refines the model of Rega et al. (2018). The workflow merges Copernicus High-Resolution Layers for 2018 - Tree Cover Density, Grasslands and Woody Vegetation Mask (5–10 m source grids) - with empirical coefficients from extensive field surveys. Morphological spatial pattern analysis distinguishes linear from areal habitat elements, capturing their contrasting ecological functions: linear features improve connectivity for enemy movement, whereas areal patches offer stable refugia and resources. All scripts and configuration files are openly released, allowing straightforward reruns with future Copernicus updates or with analogous land-cover products outside Europe. The resulting NPC index maps spatial variation in habitat composition, abundance and proximity to cropland, providing an indicator for planning and management from continental to local scales.