High-resolution Output Research Articles

Intensification of the hydrological cycle expected in West Africa over the 21st century

Abstract. This study uses the high-resolution outputs of the recent CORDEX-Africa climate projections to investigate the future changes in different aspects of the hydrological cycle over West Africa. Over the twenty-first century, temperatures in West Africa are expected to increase at a faster rate (+0.5 ∘C per decade) than the global average (+0.3 ∘C per decade), and mean precipitation is expected to increase over the Guinea Coast (+0.03 mm d−1 per decade) but decrease over the Sahel (−0.005 mm d−1 per decade). In addition, precipitation is expected to become more intense (+0.2 mm d−1 per decade) and less frequent (−1.5 d per decade) over all of West Africa as a result of increasing regional temperature (precipitation intensity increases on average by +0.35 mm d−1 ∘C−1 and precipitation frequency decreases on average by −2.2 d ∘C−1). Over the Sahel, the average length of dry spells is also expected to increase with temperature (+4 % d ∘C−1), which increases the likelihood for droughts with warming in this subregion. Hence, the hydrological cycle is expected to increase throughout the twenty-first century over all of West Africa, on average by +11 % ∘C−1 over the Sahel as a result of increasing precipitation intensity and lengthening of dry spells, and on average by +3 % ∘C−1 over the Guinea Coast as a result of increasing precipitation intensity only.

A Markov-chain Activity-based Model for Pedestrians in Office Buildings

As the number of people working in office buildings increases, there is an urgent need to improve building services, such as lighting and temperature control, within these buildings to increase energy efficiency and well-being of occupants. A pedestrian behaviour model that simulates office occupants’ movements and locations can provide the high spatial and temporal resolution data required for the testing, evaluation, and optimization of these control systems. However, since most studies in pedestrian research focus on modelling specific actions at the operational level or target situations where movement schedules do not have to modelled, a pedestrian behaviour model that can simulate complex situations over long time periods is missing. Therefore, this paper proposes a tactical level model to generate occupant movement patterns in office buildings. The Markov-chain activity-based model proposed here is data parsimonious, flexible in accepting different levels of information, and can produce high resolution output. The mathematical properties of the methodology are analyzed to understand their impact on the final results. Finally, the tactical level pedestrian behaviour model is face validated using a case study of an imaginary office with a simple layout.

Pan-European hydrodynamic models and their ability to identify compound floods

The interaction between storm surges and inland run-off has been gaining increasing attention recently, as they have the potential to result in compound floods. In Europe, several flood events of this type have been recorded in the past century in Belgium, France, Ireland, Italy and UK. First projections of compound flood hazard under climate change have been made, but no study has so far analysed whether existing, independent climate and hydrodynamic models are able to reproduce the co-occurrence of storm surges, precipitation, river discharges or waves. Here, we investigate the dependence between the different drivers in different observational and modelled data set, utilizing gauge records and high-resolution outputs of climate reanalyses and hindcasts, hydrodynamic models of European coasts and rivers. The results show considerable regional differences in strength of the dependence in surge–precipitation and surge–discharge pairs. The models reproduce those dependencies, and the time lags between the flood drivers, rather well in north-western Europe, but less successfully in the southern part. Further, we identified several compound flood events in the reanalysis data. We were able to link most of those modelled events with historical reports of flood or storm losses. However, false positives and false negatives were also present in the reanalysis and several large compound floods were missed by the reanalysis. All in all, the study still shows that accurate representation of compound floods by independent models of each driver is possible, even if not yet achievable at every location.

Computed Tomography 3D Super-Resolution with Generative Adversarial Neural Networks: Implications on Unsaturated and Two-Phase Fluid Flow.

Fluid flow characteristics are important to assess reservoir performance. Unfortunately, laboratory techniques are inadequate to know these characteristics, which is why numerical methods were developed. Such methods often use computed tomography (CT) scans as input but this technique is plagued by a resolution versus sample size trade-off. Therefore, a super-resolution method using generative adversarial neural networks (GANs) was used to artificially improve the resolution. Firstly, the influence of resolution on pore network properties and single-phase, unsaturated, and two-phase flow was analysed to verify that pores and pore throats become larger on average and surface area decreases with worsening resolution. These observations are reflected in increasingly overestimated single-phase permeability, less moisture uptake at lower capillary pressures, and high residual oil fraction after waterflooding. Therefore, the super-resolution GANs were developed which take low (12 µm) resolution input and increase the resolution to 4 µm, which is compared to the expected high-resolution output. These results better predicted pore network properties and fluid flow properties despite the overestimation of porosity. Relevant small pores and pore surfaces are better resolved thus providing better estimates of unsaturated and two-phase flow which can be heavily influenced by flow along pore boundaries and through smaller pores. This study presents the second case in which GANs were applied to a super-resolution problem on geological materials, but it is the first one to apply it directly on raw CT images and to determine the actual impact of a super-resolution method on fluid predictions.

Preserving details in semantics-aware context for scene parsing

Great success of scene parsing (also known as, semantic segmentation) has been achieved with the pipeline of fully convolutional networks (FCNs). Nevertheless, there are a lot of segmentation failures caused by large similarities between local appearances. To alleviate the problem, most of existing methods attempt to improve the global view of FCNs by introducing different contextual modules. Though the reconstructed high resolution output of these methods is of rich semantics, it cannot faithfully recover the fine image details owing to lack of desired precise low-level information. To overcome the problem, we propose to improve the spatial decoding process through embedding possibly lost low-level information in a principled way. To this end, we make the following three contributions. First, we propose a semantics conformity module to make low-level features variations agnostic. Second, we introduce semantics into the conformed low level features through guidance from semantically aware features. Finally, we institute the availability of various possible contextual features at feature fusion to enrich context information. The proposed approach demonstrates competitive performance on challenging PASCAL VOC 2012, Cityscapes, and ADE20K benchmarks in comparison to the state-of-the-art methods.

Точностные характеристики выходной продукции высокого разрешения КА «Ресурс-П»

Точностные характеристики выходной продукции высокого разрешения КА «Ресурс-П»

Multimodal Deep Unfolding for Guided Image Super-Resolution.

The reconstruction of a high resolution image given a low resolution observation is an ill-posed inverse problem in imaging. Deep learning methods rely on training data to learn an end-to-end mapping from a low-resolution input to a highresolution output. Unlike existing deep multimodal models that do not incorporate domain knowledge about the problem, we propose a multimodal deep learning design that incorporates sparse priors and allows the effective integration of information from another image modality into the network architecture. Our solution relies on a novel deep unfolding operator, performing steps similar to an iterative algorithm for convolutional sparse coding with side information; therefore, the proposed neural network is interpretable by design. The deep unfolding architecture is used as a core component of a multimodal framework for guided image super-resolution. An alternative multimodal design is investigated by employing residual learning to improve the training efficiency. The presented multimodal approach is applied to super-resolution of near-infrared and multi-spectral images as well as depth upsampling using RGB images as side information. Experimental results show that our model outperforms state-ofthe-art methods.

Super-Resolution with compressively sensed MR/PET signals at its input

Abstract The aim of this paper is to present a highly effective Magnetic Resonance Imaging- Positron Emission Tomography (MR/PET) image reconstruction strategy allowing for simultaneous resolution enhancing and scanning time minimisation. The presented algorithm employs the combined sparsity, compressed sensing (CS) theory and super resolution to achieve high-resolution output maintaining data collecting steps at the lowest possible levels. This paper presents a very promising application of super-resolution of highly sensitively compressed MR/PET raw data. The presented algorithm nests image priors, deblurring, and a discrete dense displacement sampling for the deformable registration of high-resolution images at its core. Data from preliminary trials can also be valuable in providing background information useful in reducing examinations times. In accordance with expectations, the presented algorithm can enhance image resolution without any hardware modifications. However, the motion estimation algorithm can drastically eliminate diagnostic image artifacts that increase the chances of a correct diagnosis. The robustness of the suggested algorithm was subjected to state-of-the art image resolution enhancement algorithms: 3D kernel regression, Enhanced Deep Residual Networks for Single Image Super-Resolution, Image Super-Resolution Using Very Deep Residual Channel Attention Networks, Residual Dense Network for Image Super-Resolution. It is worth underlining that combining Compressed Sensing with its conjugate symmetry, as well as Partial Fourier methodology leads to data acquisition acceleration when compared to the different and unmodified k-space sampling patterns. It can be clearly seen that the obtained improvements have led to much better sharpness, edge interpretations, and contrast. Moreover, the accomplishments have been validated by PSNR. In accordance with expectations, the presented algorithm is able to enhance image resolution without any hardware adjustments. Besides the resolution tradeoffs, this method is able to minimise motion artifacts what is especially important for effective physician-to-physician communication and unbiased diagnosis.

Guidance Based Improved Depth Upsampling With Better Initial Estimate

Like optical images, depth images are also gaining popularity because of its use in many applications like robot navigation, augmented reality, 3DTV and more. The commercially available depth cameras generate depth images which suffer from low spatial resolution, corrupted with noise, and missing regions. Such images need to be super-resolved, denoised and inpainted before using them to have better accuracy. Super-resolution (SR) techniques can be used to produce a high-resolution output. Since SR is an ill-posed inverse problem, a good initial estimate is always a good regulariser to find the optimal solution. We propose an initial estimate as part of our SR pipeline, esp. ×8, which will helps in quick convergence and accurate output. We propose a cascade approach by combining residual interpolation (RI) method with anisotropic total generalised variation (ATGV) method, both uses HR guidance image. The improvements are shown qualitative and quantitative with different levels of noise.

Deep Learning for Single Image Super-Resolution: A Brief Review

Single image super-resolution (SISR) is a notoriously challenging ill-posed problem, which aims to obtain a high-resolution (HR) output from one of its low-resolution (LR) versions. To solve the SISR problem, recently powerful deep learning algorithms have been employed and achieved the state-of-the-art performance. In this survey, we review representative deep learning-based SISR methods, and group them into two categories according to their major contributions to two essential aspects of SISR: the exploration of efficient neural network architectures for SISR, and the development of effective optimization objectives for deep SISR learning. For each category, a baseline is firstly established and several critical limitations of the baseline are summarized. Then representative works on overcoming these limitations are presented based on their original contents as well as our critical understandings and analyses, and relevant comparisons are conducted from a variety of perspectives. Finally we conclude this review with some vital current challenges and future trends in SISR leveraging deep learning algorithms.

Initial Development and Testing of a Convection-Allowing Model Scorecard

AbstractEvaluation of numerical weather prediction (NWP) is critical for both forecasters and researchers. Through such evaluation, forecasters can understand the strengths and weaknesses of NWP guidance, and researchers can work to improve NWP models. However, evaluating high-resolution convection-allowing models (CAMs) requires unique verification metrics tailored to high-resolution output, particularly when considering extreme events. Metrics used and fields evaluated often differ between verification studies, hindering the effort to broadly compare CAMs. The purpose of this article is to summarize the development and initial testing of a CAM-based scorecard, which is intended for broad use across research and operational communities and is similar to scorecards currently available within the enhanced Model Evaluation Tools package (METplus) for evaluating coarser models. Scorecards visualize many verification metrics and attributes simultaneously, providing a broad overview of model performance. A preliminary CAM scorecard was developed and tested during the 2018 Spring Forecasting Experiment using METplus, focused on metrics and attributes relevant to severe convective forecasting. The scorecard compared attributes specific to convection-allowing scales such as reflectivity and surrogate severe fields, using metrics like the critical success index (CSI) and fractions skill score (FSS). While this preliminary scorecard focuses on attributes relevant to severe convective storms, the scorecard framework allows for the inclusion of further metrics relevant to other applications. Development of a CAM scorecard allows for evidence-based decision-making regarding future operational CAM systems as the National Weather Service transitions to a Unified Forecast system as part of the Next-Generation Global Prediction System initiative.

Development of Downscaled Climate Projections: A Case Study of the Red River Basin, South-Central U.S.

Climate models provide information that resource managers, policy makers, and researchers can use when planning for the future. While this information is valuable in the broad sense, the low spatial-resolution often lacks local details that resource managers and decision makers need to plan for their communities. Therefore, statistically downscaled climate projections provide a high-resolution output and offer local information that is more beneficial than coarse-resolution global climate model output. In the Red River Basin, located in the south-central U.S., this detailed information is used to develop long-term water plans. This area is prone to drought conditions and heavy precipitation events, and studies have consistently estimated that this will continue in the future. This paper introduces a dataset of statistically downscaled climate projections of daily minimum and maximum temperature and daily precipitation that is a useful tool for studies regarding climatological and hydrological aspects in the region. The dataset was created using two quantile mapping techniques to downscale the CCSM4, MPI-ESM-LR, and MIROC5 model outputs to a 0.1-degree spatial resolution. Furthermore, we describe the added value of coproduction of knowledge between climate scientists and end users, or in this case impacts modelers and decision makers, for creating climate projections that can be used for climate risk assessments. A case study of the data’s development and application is provided, detecting the mean daily changes in temperature and precipitation through the end of the century in the Red River Basin for two representative concentration pathways. After applying the users’ inputs to develop the datasets, results for this example estimate an increase in mean daily precipitation in the eastern portion of the basin and as much as a 15% decline in the west by the end of the century. Furthermore, mean daily temperature is expected to rise across the entire basin in all scenarios by up to 6–7°C.

Documenting Archaeological Sites on Mountains and Slopes with Drones

ABSTRACTThe addition of drones to the archaeologist's toolbox has brought about exciting new possibilities, particularly for field research and the conservation and protection of our built heritage. As drones become more widely available and effective, the challenge of precision becomes more important. Better georeferencing and higher-resolution outputs are the current thresholds. In order to achieve the second objective with our current equipment, drones have to fly closer to the ground and, ideally, follow the elevation of the surface. This task can be extremely complicated along the steep surfaces and mountains typical to the Andean region where we work. In this article, we present a recording (flying and photographing) methodology that achieves a higher ground resolution by dividing up the sites into several altitudinal sections, which are flown independently yet processed photogrammetrically as a single set. We have named this methodology “Flying Slopes in Multiple Stepped Polygons.”

DATA AUGMENTATION APPROACHES FOR SATELLITE IMAGE SUPER-RESOLUTION

Abstract. Data augmentation is a well known technique that is frequently used in machine learning tasks to increase the number of training instances and hence decrease model over-fitting. In this paper we propose a data augmentation technique that can further boost the performance of satellite image super resolution tasks. A super-resolution convolutional neural network (SRCNN) was adopted as a state-of-the-art deep learning model to test the proposed data augmentation technique. Different augmentation techniques were studied to investigate their relative importance and accuracy gains. We categorized the augmentation methods into instance based and channel based augmentation methods. The former refers to the standard approach of creating new data instances through applying image transformations to the original images such as adding artificial noise, rotations and translations to training samples, while in the latter we fuse auxiliary channels (or custom bands) with each training instance, which helps the model learn useful representations. Fusing auxiliary derived channels to a satellite image RGB combination can be seen as a spectral-spatial fusion process as we explain later. Several experiments were carried out to evaluate the efficacy of the proposed fusion-based augmentation method compared with traditional data augmentation techniques such as rotation, flip and noisy training inputs. The reconstruction quality of the high resolution output was quantitatively evaluated using Peak-Signal-To-Noise-Ratio (PSNR) and qualitatively through visualisation of test samples before and after super-resolving.

Land Cover Maps Production with High Resolution Satellite Image Time Series and Convolutional Neural Networks: Adaptations and Limits for Operational Systems

The Sentinel-2 satellite mission offers high resolution multispectral time-series image data, enabling the production of detailed land cover maps globally. When mapping large territories, the trade-off between processing time and result quality is a central design decision. Currently, this machine learning task is usually performed using pixel-wise classification methods. However, the radical shift of the computer vision field away from hand-engineered image features and towards more automation by representation learning comes with many promises, including higher quality results and less engineering effort. In particular, convolutional neural networks learn features which take into account the context of the pixels and, therefore, a better representation of the data can be obtained. In this paper, we assess fully convolutional neural network architectures as replacements for a Random Forest classifier in an operational context for the production of high resolution land cover maps with Sentinel-2 time-series at the country scale. Our contributions include a framework for working with Sentinel-2 L2A time-series image data, an adaptation of the U-Net model (a fully convolutional neural network) for dealing with sparse annotation data while maintaining high resolution output, and an analysis of those results in the context of operational production of land cover maps. We conclude that fully convolutional neural networks can yield improved results with respect to pixel-wise Random Forest classifiers for classes where texture and context are pertinent. However, this new approach shows higher variability in quality across different landscapes and comes with a computational cost which could be to high for operational systems.

Antarctic ice shelf thickness change from multimission lidar mapping

Abstract. We calculate rates of ice thickness change and bottom melt for ice shelves in West Antarctica and the Antarctic Peninsula from a combination of elevation measurements from NASA–CECS Antarctic ice mapping campaigns and NASA Operation IceBridge corrected for oceanic processes from measurements and models, surface velocity measurements from synthetic aperture radar, and high-resolution outputs from regional climate models. The ice thickness change rates are calculated in a Lagrangian reference frame to reduce the effects from advection of sharp vertical features, such as cracks and crevasses, that can saturate Eulerian-derived estimates. We use our method over different ice shelves in Antarctica, which vary in terms of size, repeat coverage from airborne altimetry, and dominant processes governing their recent changes. We find that the Larsen-C Ice Shelf is close to steady state over our observation period with spatial variations in ice thickness largely due to the flux divergence of the shelf. Firn and surface processes are responsible for some short-term variability in ice thickness of the Larsen-C Ice Shelf over the time period. The Wilkins Ice Shelf is sensitive to short-timescale coastal and upper-ocean processes, and basal melt is the dominant contributor to the ice thickness change over the period. At the Pine Island Ice Shelf in the critical region near the grounding zone, we find that ice shelf thickness change rates exceed 40 m yr−1, with the change dominated by strong submarine melting. Regions near the grounding zones of the Dotson and Crosson ice shelves are decreasing in thickness at rates greater than 40 m yr−1, also due to intense basal melt. NASA–CECS Antarctic ice mapping and NASA Operation IceBridge campaigns provide validation datasets for floating ice shelves at moderately high resolution when coregistered using Lagrangian methods.

Image enhancement algorithm based on generative adversarial network in combination of improved game adversarial loss mechanism

The feed-forward architectures of recently proposed generative adversarial network can learn the non-linear mapping from low-resolution output to high-resolution output. However, this approach does not fully address the mutual dependencies of different resolution images. By analyzing the zero-sum game, the paper proposes an image enhancement algorithm by using conditional generative adversarial networks based on improved non-saturating game. Firstly, the enhancement image obtained by the GAN model is adopted as a condition against the network object image, making the original image learning the network structure of the object image with dim-small. Our proposed generative adversarial networks can obtain a clearer image through improved non-saturating game, and it can still get a large gradient and sufficient learning, which makes up for the deficiencies in the mini-maximum game. In addition, the loss function of the network adds the loss of discriminator to guide discriminator to generate high quality images. We compared the proposed method (SRG) with other methods including SC, SRCNN, VESPCN and ESPCN, and the proposed method resulted in obvious improvements in the peak signal-to-noise ratio (PSNR) by 2.348 dB and in structural similarity index measurement (SSIM) by 1.89% to enhance the visual effects of nature images.

Using the evaporative stress index to monitor flash drought in Australia

Flash drought is a term and concept that has gained increasing attention in the research literature and media since it was first coined in the United States in the early 2000s to describe a drought that has undergone rapid intensification. In Australia the term has recently been used in reference to the 2017/18 drought in eastern Australia. Due to its rapid intensification, the impacts of flash droughts will likely occur too quickly for many of the usual drought-coping mechanisms to be deployed. This study proposes the use of the evaporative stress index (ESI), the standardized anomaly of the actual evapotranspiration to potential evapotranspiration ratio, to identify flash droughts in Australia computed using daily outputs from the Bureau of Meteorology’s land surface water balance model AWRA-L. The case study of the January 2018 flash drought in eastern Australia is used to assess and demonstrate the suitability of the ESI. Results show that the ESI accurately highlighted the event and offered potential for flash drought pre-warning by a few weeks. In addition, the availability of long term high-resolution outputs from AWRA-L offers the ability to investigate multiple flash drought events in detail for greater understanding and to inform stakeholders.

Across-scale process similarity based interpolation for image super-resolution

A pivotal step in image super-resolution techniques is interpolation, which aims at generating high resolution images without introducing artifacts such as blurring and ringing. In this paper, we propose a technique that performs interpolation through an infusion of high frequency signal components computed by exploiting ‘process similarity’. By ‘process similarity’, we refer to the resemblance between a decomposition of the image at a resolution to the decomposition of the image at another resolution. In our approach, the decompositions generating image details and approximations are obtained through the discrete wavelet (DWT) and stationary wavelet (SWT) transforms. The complementary nature of DWT and SWT is leveraged to get the structural relation between the input image and its low resolution approximation. The structural relation is represented by optimal model parameters obtained through particle swarm optimization (PSO). Owing to process similarity, these parameters are used to generate the high resolution output image from the input image. The proposed approach is compared with six existing techniques qualitatively and in terms of PSNR, SSIM, and FSIM measures, along with computation time (CPU time). It is found that our approach is the fastest in terms of CPU time and produces comparable results.

A Universal Optical Flow Based Real-Time Low-Latency Omnidirectional Stereo Video System

Omnidirectional stereoscopic video (ODSV) is a key element of creating an immersive experience for virtual reality that has attracted extensive interest while presenting many technical challenges. Two such key challenges are real-time, low-latency high-quality seamless video stitching from multiple cameras, and faithful reconstruction of 3-D information. Even though various attempts have been made to achieve different combinations of real-time, low-latency, automation, and high output resolution in stereoscopic panoramic video communication, achieving these characteristics simultaneously remains a challenge to be tackled. In this paper, we present a universally applicable and practical end-to-end system based on a novel real-time optical flow algorithm to produce high-quality real-time ODSV with reconstructed 3-D depth information at low latency. Through a configurable process, various camera systems can be calibrated and seamlessly stitched together using the proposed system. The stitched 3-D panoramic video is encoded with a standard compliant video encoder that is optimized for panoramic video. Thanks to various optimizations introduced in this paper, the proposed system is capable of producing real-time ODSV of ultra High definition resolution with a glass to glass latency of 2.2 s using a desktop computer with a single Nvidia graphic card. Experiments show that the proposed system achieves an encoding performance superior to existing open-source HEVC implementations and an optical flow estimation performance better than the Facebook algorithm while running two orders of magnitudes faster.