EAMNet: a dual-decoder network with edge-semantics synergy for agricultural parcel extraction from remote sensing images

E2EVAP: End-to-end vectorization of smallholder agricultural parcel boundaries from high-resolution remote sensing imagery

This paper uses a logit model to estimate whether and to what extent Maryland’s Priority Funding Area (PFA) program steers urban growth to locations inside targeted growth area boundaries of an ex-urban county in the outer suburbs of the Washington, D.C. region. The results of our model indicate that the size of an agricultural parcel, its distance from urban parcels, its proximity to highways, the quality of the land for agriculture, and the location in or outside of PFAs influence the probability an agricultural parcel will remain in agriculture or be converted to urban use. We find that some of the areas experiencing the greatest market pressure for development are located outside PFAs and, although Maryland’s incentive-based strategy reduces the likelihood a parcel outside a PFA will transition to urban use, this policy is not one hundred percent effective.

The Corona spy programme was a series of reconnaissance satellites which delivered more than 860000 images between 1960 and 1972. Since 1995, the data are declassified and a large historic earth observation archive is made accessible to the scientific community. Despite the large volume of information and the high spatial resolution of the satellite imagery, little has been done in the last 25 years in the context of image processing of this data source, a fact which perhaps can be attributed to the technical difficulties of these primitive images such as the lack of metadata, intense spatial and radiometric distortions, low Signal-to-Noise Ratio (SNR) and a single panchromatic band. Hence, the photogrammetric challenges to extract useful information are paramount. In this study, we present recent developments arising from our efforts to map settlements and agricultural parcels over the Plovdiv region, Bulgaria from a Corona image acquired in 1968. We, overall, present initial findings from the integration of earth observation into the ERC-StG project UrbanOccupationsOETR and evaluate the usability of such primitive images in feature extraction. We compare the areas corresponding to settlements and correlate them with concurrent population census. Based on the findings, we suggest that settlements and agricultural parcels can be mapped from a Corona KH-4B image with fine radiometric quality.

The accurate acquisition of agricultural parcels from remote sensing images is crucial for agricultural management and crop production monitoring. Most of the existing agricultural parcel extraction methods comprise semantic segmentation through remote sensing images, pixel-level classification, and then vectorized raster data. However, this approach faces challenges such as internal cavities, unclosed boundaries, and fuzzy edges, which hinder the accurate extraction of complete agricultural parcels. Therefore, this paper proposes a vector contour segmentation network based on the hybrid backbone and multiscale edge feature extraction module (HEVNet). We use the extraction of vector polygons of agricultural parcels by predicting the location of contour points, which avoids the above problems that may occur when raster data is converted to vector data. Simultaneously, this paper proposes a hybrid backbone for feature extraction. A hybrid backbone combines the respective advantages of the Resnet and Transformer backbone networks to balance local features and global features in feature extraction. In addition, we propose a multiscale edge feature extraction module, which can extract and enhance the edge features of different scales to prevent the possible loss of edge details in down sampling. This paper uses the datasets of Denmark, the Netherlands, iFLYTEK, and Hengyang in China to evaluate our model. The obtained IOU indexes were 67.92%, 81.35%, 78.02%, and 66.35%, which are higher than previous IOU indexes based on the optimal model (DBBANet). The results demonstrate that the proposed model significantly enhances the integrity and edge accuracy of agricultural parcel extraction.

The accurate extraction of agricultural parcels from remote sensing images is crucial for advanced agricultural management and monitoring systems. Existing methods primarily emphasize regional accuracy over boundary quality, often resulting in fragmented outputs due to uniform crop types, diverse agricultural practices, and environmental variations. To address these issues, this paper proposes DSTBA-Net, an end-to-end encoder–decoder architecture. Initially, we introduce a Dual-Stream Feature Extraction (DSFE) mechanism within the encoder, which consists of Residual Blocks and Boundary Feature Guidance (BFG) to separately process image and boundary data. The extracted features are then fused in the Global Feature Fusion Module (GFFM), utilizing Transformer technology to further integrate global and detailed information. In the decoder, we employ Feature Compensation Recovery (FCR) to restore critical information lost during the encoding process. Additionally, the network is optimized using a boundary-aware weighted loss strategy. DSTBA-Net aims to achieve high precision in agricultural parcel segmentation and accurate boundary extraction. To evaluate the model’s effectiveness, we conducted experiments on agricultural parcel extraction in Denmark (Europe) and Shandong (Asia). Both quantitative and qualitative analyses show that DSTBA-Net outperforms comparative methods, offering significant advantages in agricultural parcel extraction.

The growing and multiple interests in land as a resource has led to an increase in locally or regionally clashing land use interests on agricultural land which may result in conflicts or open up possibilities for synergies. Urbanization, food production, renewable energy production, environmental protection, and climate protection are known as key land use interests in many regions. The objective of our study is to identify and map land use conflicts, land use synergies, and areas with land use synergy potentials in the federal state of Brandenburg, Germany. We have combined different methods: an analysis of statistical data, an online survey with farmers, a primary document analysis (articles, court documents, policy documents, position papers), and a GIS-based spatial analysis. In our Brandenburg case study, we have identified the use of agricultural land for renewable energy production and environmental protection as the most relevant land use interests leading to conflict situations. We show that land use synergies can make a significant contribution to achieving environmental and climate protection goals, as well as sustainable development. Through the site-adapted and targeted establishment of agroforestry systems, agricultural areas with agri-photovoltaic systems and agricultural parcels with integrated nonproductive areas may lead to land use synergies. Our study contributes to a better understanding of the occurrence of land use conflicts and land use synergies. We highlight the potential for targeted and sustainable environmental and climate protection through the promotion of land use synergies as a result of establishing agroforestry systems and agricultural parcels with agri-photovoltaic systems and integrated nonproductive areas. Our results provide a basis for agricultural policy to promote land use systems that contribute to environmental and climate protection.

ABSTRACTA correct delineation of agricultural parcels is a primary requirement for any parcel-based application such as the estimate of agricultural subsidies. Currently, high-resolution remote-sensing images provide useful spatial information to delineate parcels; however, their manual processing is highly time consuming. Thus, it is necessary to create methods which allow performing this task automatically. In this work, the use of a machine-learning algorithm to delineate agricultural parcels is explored through a novel methodology. The proposed methodology combines superpixels and supervised classification in order to determine which adjacent superpixels should be merged, transforming the segmentation issue into a machine learning matter. A visual evaluation of results obtained by the methodology applied to two areas of a high-resolution satellite image of fragmented agricultural landscape points out that the use of machine-learning algorithm for this task is promising.

It is necessary to monitor the crop pattern in parcel level and to obtain the data having agricultural statistic value to ensure that the national agricultural policies are implemented in a more rational and effective way. It is known that the most common means used to apply agricultural policies are premium - support systems. However, inaccuracies in crop pattern statements of producer, deviations in the amount of cultivated area and erroneous the yield declarations prevent to apply the premium support system in an effective way. Therefore, monitoring of agricultural crop pattern in parcel level is of a vital importance. The effective monitoring of agricultural crop pattern can only be possible by means of using in conjunction withGeographic Information System (GIS) and Remote Sensing (RS) data. In this project that is a pilot study, cotton production, one of the most common of agricultural products in the Aegean Region, is selected as crop pattern example. In this project, the agricultural parcels digitized by General Directorate of Agricultural Reform (GDAR) are used as a basis. Information system of agricultural parcels are integrated with Farmer Registration System (FRS) data containing statement information to gain the farmer statement information belonging to each agricultural parcel as an attribute data. Rapid Eye and SPOT satellite images covering an area of 11.179 km2 are used to monitor the crop pattern in parcel level and perform the farmer statement checks. Shooting of satellite images was made in August when land cover ratio of the cotton plant is the highest stage. The results obtained from this pilot project are shown that applied method may be used to monitor other common agricultural products and to control the farmer statements.

Optimal parameters for delineating agricultural parcels from satellite images based on supervised Bayesian optimization

Within the scope of establishing Agricultural Parcel Database work item, all agricultural parcels within the cadastral parcels and the parcels used for agricultural purposes as well as raw soils were digitized. With the completion of agricultural parcels digitization, parcel based crop production yield values have been calculated. Digital elevation model, slope map and soil data are used to extract yield coefficient. By means of this yield model, agricultural subsidies are being paid according to geographical features of the parcels. This new payment system provides true and accurate data which prevents objections and payments with fake or duplicated deeds. Quality of agricultural statistics is also improved by the means of the study.

Using a semantic edge-aware multi-task neural network to delineate agricultural parcels from remote sensing images

Monitoring of soil organic carbon (SOC) and pH is needed to manage soil protection and tackle possible degradation in support of, i.e, the upcoming European Soil Framework Directive. Harmonized monitoring procedures and protocols produced under the auspices of the International Organization for Standardization (ISO) and the European Committee for Standardization (CEN) will be recommended. The uncertainty contributions of sampling, sample pretreatment, and analysis in the monitoring of soil pH and organic carbon in agricultural parcels using these harmonized monitoring procedures have been studied.A within-laboratory comparison between the different analytical methods and sample pretreatments was made on 451 soil samples for SOC and 150 samples for soil acidity. Thereafter, a field study was performed to evaluate the contribution of the sampling method. Finally, an interlaboratory trial (including sampling) was organized to assess the overall monitoring uncertainty.The results indicate that the influence of different sample pretreatments (e.g., milling) in combination with different analytical methods (elemental combustion versus chemical oxidation) are the main contributions to the observed uncertainty in the monitoring of SOC. For the monitoring of soil acidity, a similar observation was made, showing that differences in the practical implementation of the analytical method (e.g., mechanical shaking) are the main contributions to the monitoring uncertainty. The monitoring uncertainties derived from an interlaboratory trial (including sampling) amounted to ±20% (95% confidence interval, CI) for SOC and ±0.3 pH units (95% CI) for soil acidity on an agricultural parcel.

The relationship between cropland suitability and the surrounding environmental factors has an important role in understanding and adjusting agricultural land management systems to natural cropland suitability. In this study, the relationship between soybean cropland suitability, determined by a novel machine learningbased approach, and three major environmental factors in continental Croatia was evaluated. These constituted of two major land cover classes (forests and urban areas), utilized soybean growth seasons per agricultural parcels during a 2017–2020 study period and soil types. The sensitivity analysis in geographic information system (GIS) using a raster overlay method, along with auxiliary spatial processing, was performed. The proximity of soybean agricultural parcels to forests showed a high correlation with suitability values, indicating a potential benefit of implementing agroforestry in land management plans. A notable amount of suitable agricultural parcels for soybean cultivation, which were previously not utilized for soybean cultivation was observed. A disregard of crop rotations was also noted, with the same soybean parcels within the study period in three and four years. This analysis showed considerable potential in understanding the effects of environmental factors on cropland suitability values, leading to more efficient land management policies and future suitability studies.

Within the scope of TARBIL Project, digitization of agricultural parcels have become a prior duty. In order to achieve agricultural parcels, a protocol had been signed both with General Directorate of Land Registry and Cadastre for acquisition of existing cadastral parcels and ITU UHUZAM for SPOT 5 images (2,5 m resolution). All agricultural parcels within the boundaries of cadastral parcels were digitized based on SPOT 5 Images and orthophotos. Digitization of agricultural parcels involves following procedures;

We present a software system for automated projection of situational knowledge for disease outbreak in agriculture. The system supports farmers and agricultural advisers in obtaining and maintaining awareness of present and future disease outbreaks in crops grown at agricultural parcels. It models objects such as plant pathogens and agricultural parcel crops, and their relations, as entities in situations observed by an environmental monitoring system. It utilizes a mechanistic disease pressure model to obtain knowledge about observed situations from forecast data for various weather parameters. It represents obtained situational knowledge explicitly and manages represented knowledge in a knowledge base. We evaluate the system for 3 fungal plant pathogens, 2 cereal crops, and 17 agricultural parcels located in Finland, for a growing season. We underscore how the explicit representation of situational knowledge is useful toward various purposes, including reasoning, query and visualization, and is, thus, vastly superior to having situational knowledge only implicit in high-level data products such as maps.