Afghanistans annual opium survey relies upon time-consuming human interpretation of satellite images to map the area of potential poppy cultivation for statistical sample design. Deep Convolutional Neural Networks (CNNs) have shown groundbreaking performance for image classification tasks by encoding local contextual information, in some cases outperforming trained analysts. In this study, we investigate the development of a CNN to automate the classification of agriculture from medium resolution satellite imagery as an alternative to manual interpretation. The residual network (ResNet50) CNN architecture was trained and validated for delineating the agricultural area using labelled multi-seasonal Disaster Monitoring Constellation (DMC) satellite imagery (32 m) of Helmand and Kandahar provinces. The effect of input image chip size, training sampling strategy, elevation data and multi-seasonal imagery were investigated. The best performing single year classification used an input chip size of 33 × 33 pixels, a targeted sampling strategy and transfer learning, resulting in high overall accuracy (94%). The inclusion of elevation data marginally lowered performance (93%). Multi-seasonal classification achieved an overall accuracy of 89% using the previous two years' data. Only 25% of the target year's training samples were necessary to update the model to achieve > 94% overall accuracy. A data-driven approach to automate agricultural mask production using CNNs is proposed to reduce the burden of human interpretation. The ability to continually update CNN models with new data has the potential to significantly improve automatic classification of vegetation across years.
The approaches that have been used for regulation of biological pesticides in the UK to date are discussed in relation to the expected European system. Biological pesticides are defined under the Control of Pesticides Regulations 1986 as 'bacteria, protozoa, fungi, viruses and mycoplasmas used for destroying or controlling pests'. The data requirements for biological pesticides are simpler than those for chemical pesticides but take into account special factors such as infectivity, sensitization of users and toxin production. The Plant Protection Products Regulations (1995) implement Directive 91/414/EEC in the UK.
<p>The world&#8217;s peatlands are our largest terrestrial carbon store whilst also providing a sustainable source of drinking water, a haven for wildlife and storing a record of our past. The England Peat Map aims to provide baseline maps for the extent, depth, and condition of peaty soils in England by 2024. This will enable targeting of future restoration, support nature recovery, improve greenhouse emissions reporting and natural capital accounting.</p><p>The maps will be created using a combination of multi-scale Earth observation imagery (satellite and airborne), existing and new ecological field survey data and machine/deep learning. Extent and depth mapping is implemented with random forest models and uses Sentinel satellite imagery and airborne LiDAR in combination with other ancillary datasets (e.g., geology and climate) for prediction. Assessment of peatland condition requires looking at these landscapes in different ways. Land cover mapping is used as a proxy for condition by targeting reflective classes for condition (e.g., Sphagnum, heather, and bare peat). Random forest and convolutional neural network (CNN) models are used in combination with Sentinel satellite imagery, aerial photography, and airborne LiDAR to produce national outputs. Mapping erosion/drainage features (grips, gullies and haggs) across the landscape is essential in understanding the underlying hydrological condition of the peatland and promising results have been achieved using CNNs with LiDAR and aerial photography. The final aspect of assessed condition is the movement of peat, also termed bog breathing, and is measured using Sentinel-1 Interferometric Synthetic Aperture Radar (InSAR). This opportunity is a result of novel in-situ peat movement cameras being installed across pilot sites to provide ground truth data.</p><p>The final maps will be released free of charge under an open UK government license, allowing wider application and new opportunities for use compared with currently available datasets. For example, these baseline maps have the potential to contribute towards national peatland monitoring to address further decline of peatland habitats and target restoration interventions to achieve cost effective results. Several challenges have occurred during the initial phase of the project such as the difficulty in licensing suitable training data and in defining what we are mapping when features lack a globally agreed definition (e.g., surface features). The talk will discuss these challenges as well as the future direction of the project and how these challenges can be overcome.</p>
Though the reasons may not yet be fully understood, all the evidence points to the fact that the world's climate is changing. It is a risk civil engineers can no longer afford to ignore, say Alex Hamer and Caroline Peters of law firm Reynolds Porter Chamberlain.
<p>Accurate mapping of agricultural area is essential for Afghanistan&#8217;s annual opium poppy monitoring programme. Access to labelled data remains the main barrier for utilising deep learning from satellite imagery to automate the process of land cover classification. In this study, we aim to transfer knowledge from historical labelled data of agricultural land, from work on poppy cultivation estimates undertaken between 2007 and 2010, to classify imagery from a range of sensors using deep learning. Fully Convolutional Networks (FCNs) have been used to learn the complex features of agriculture in southern Afghanistan using their inherent spatial and spectral characteristics from satellite imagery. FCNs are trained and validated using labelled Disaster Monitoring Constellation (DMC) data (32 m) to transfer knowledge of agricultural land to classify other imagery, such as Landsat (30 m). The dependency on spatial and spectral characteristics are explored using intensity, Normalised Difference Vegetation Index (NDVI), top of atmosphere reflectance and tasselled cap transformation. The underlying spatial features associated with agriculture are found to play a significant role in agriculture discrimination. High classification performance has been achieved with over 92% overall accuracy and 0.58 intersection over union. The ability to transfer knowledge from historical datasets to new satellite sensors is an exciting prospect for future automated agricultural land discrimination in the United Nations Office on Drugs and Crime annual opium survey.</p>
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.