Effective monitoring of agricultural lands requires accurate spatial information about the locations and boundaries of agricultural fields. Through satellite imagery, such information can be mapped on a large scale at a high temporal frequency. Various methods exist in the literature for segmenting agricultural fields from satellite images. Edge-based, region-based, or hybrid segmentation methods are traditional methods that have widely been used for segmenting agricultural fields. Lately, the use of deep neural networks (DNNs) for various tasks in remote sensing has been gaining traction. Therefore, to identify the optimal method for segmenting agricultural fields from satellite images, we evaluated three state-of-the-art DNNs, namely Mask R-CNN, U-Net, and FracTAL ResUNet against the multiresolution segmentation (MRS) algorithm, which is a region-based and a more traditional segmentation method. Given that the DNNs are supervised methods, we used an optimised version of the MRS algorithm based on supervised Bayesian optimisation. Monotemporal Sentinel-2 (S2) images acquired in Lower Saxony, Germany were used in this study. Based on the agricultural parcels declared by farmers within the European Common Agricultural Policy (CAP) framework, the segmentation results of each method were evaluated using the F-score and intersection over union (IoU) metrics. The respective average F-score and IoU obtained by each method are 0.682 and 0.524 for Mask R-CNN, 0.781 and 0.646 for U-Net, 0.808 and 0.683 for FracTAL ResUNet, and 0.805 and 0.678 for the optimised MRS approach. This study shows that DNNs, particularly FracTAL ResUNet, can be effectively used for large-scale segmentation of agricultural fields from satellite images.

The agricultural sector has the potential to contribute to reaching both global and national climate targets. Lately, frequent discussions emerge among academics as well as policymakers regarding whether the agricultural sector should be subject to carbon pricing under different emission trading systems. Germany has set ambitious climate targets envisaging to reach carbon neutrality by 2045, and the EU plans reaching carbon neutrality by 2050. However, the current GHG emission mitigation trends are not in line with this goal. In this study, we quantitatively analyze the environmental and economic effects of the possible inclusion of the agricultural sector into a carbon pricing scheme, once for Germany only, and second for the EU. Moreover, we evaluate the role of already existing and novel technological mitigation options in the GHG emissions mitigation quest. Our findings demonstrate that even the unilateral action by Germany leads to net agricultural emissions reduction, although, the effect obtained by the EU-wide implementation of carbon pricing in agriculture is fivefold larger. The results also highlight the importance of stimulating the use and transferability of the technological options not only in mitigating GHG emissions but also in alleviating the emission leakage to third countries and easing the economic consequences of such a policy.

The Group on Earth Observations Global Agricultural Monitoring Initiative (GEOGLAM) considers agricultural fields as one of the essential variables that can be derived from satellite data. We evaluated the accuracy at which agricultural fields can be delineated from Sentinel-1 (S1) and Sentinel-2 (S2) images in different agricultural landscapes throughout the growing season. We used supervised segmentation based on the multiresolution segmentation (MRS) algorithm to first identify the optimal feature set from S1 and S2 images for field delineation. Based on this optimal feature set, we analyzed the segmentation accuracy of the fields delineated with increasing data availability between March and October of 2018. From the S1 feature sets, the combination of the two polarizations and two radar indices attained the best segmentation results. For S2, the best results were achieved using a combination of all bands (coastal aerosol, water vapor, and cirrus bands were excluded) and six spectral indices. Combining the radar and spectral indices further improved the results. Compared to the single-period dataset in March, using the dataset covering the whole season led to a significant increase in the segmentation accuracy. For very small fields (< 0.5 ha), the segmentation accuracy obtained was 27.02%, for small fields (0.5 – 1.5 ha), the accuracy was 57.65%, for medium fields (1.5 ha – 15 ha), the accuracy was 75.71%, and for large fields (>15 ha), the accuracy stood at 68.31%. As a use case, the segmentation result was used to aggregate and improve a pixel-based crop type map in Lower Saxony, Germany.

Recent disruptions in international trade have had significant impacts on consumers and producers worldwide and stemmed from various reasons. This study aims to identify key vulnerabilities in EU agriculture by examining an import stop on food and feed products. By conducting this stylised simulation using a global PE model (CAPRI), the authors analyse the adjustment mechanisms within the sector, investigate regional differences within the EU and test the model's ability to depict such a comprehensive scenario. The findings suggest that oilseeds are most affected by an import stop due to their high import share. Meat is indirectly impacted as it relies on imported soy for animal feed, whereas other products with high self‐sufficiency levels are hardly affected. In response to the import stop, EU production expands, increasing nitrogen surpluses, particularly in regions already facing critical levels. Meat production partially moves out of the EU, increasing global GHG emissions. EU consumers are negatively affected by increased prices, leading to an overall welfare decrease in the EU with exceptions for few member states. Alongside EU imports, exports decrease, affecting prices and welfare outside the EU. In the least developed countries, prices increase especially for products that are already consumed less than recommended.

Genome-edited crops are on the verge of being placed on the market and their agricultural and food products will thus be internationally traded soon. National regulations, however, diverge regarding the classification of genome-edited crops. Major countries such as the US and Brazil do not specifically regulate genome-edited crops, while in the European Union, they fall under GMO legislation, according to the European Court of Justice (ECJ). As it is in some cases impossible to analytically distinguish between products from genome-edited plants and those from non-genome-edited plants, EU importers may fear the risk of violating EU legislation. They may choose not to import any agricultural and food products based on crops for which genome-edited varieties are available. Therefore, crop products of which the EU is currently a net importer would become more expensive in the EU, and production would intensify. Furthermore, an intense substitution of products covered and not covered by genome editing would occur in consumption, production, and trade. We analyzed the effects of such a cease of EU imports for cereals and soy in the EU agricultural sector with the comparative static agricultural sector equilibrium model CAPRI. Our results indicate dramatic effects on agricultural and food prices as well as on farm income. The intensification of EU agriculture may result in negative net environmental effects in the EU as well as in an increase in global greenhouse gas (GHG) emissions. This suggests that trade effects should be considered when developing domestic regulation for genome-edited crops.