Relational Part-Aware Learning for Complex Composite Object Detection in High-Resolution Remote Sensing Images.

In high-resolution remote sensing images (RSIs), complex composite object detection (e.g., coal-fired power plant detection and harbor detection) is challenging due to multiple discrete parts with variable layouts leading to complex weak inter-relationship and blurred boundaries, instead of a clearly defined single object. To address this issue, this article proposes an end-to-end framework, i.e., relational part-aware network (REPAN), to explore the semantic correlation and extract discriminative features among multiple parts. Specifically, we first design a part region proposal network (P-RPN) to locate discriminative yet subtle regions. With butterfly units (BFUs) embedded, feature-scale confusion problems stemming from aliasing effects can be largely alleviated. Second, a feature relation Transformer (FRT) plumbs the depths of the spatial relationships by part-and-global joint learning, exploring correlations between various parts to enhance significant part representation. Finally, a contextual detector (CD) classifies and detects parts and the whole composite object through multirelation-aware features, where part information guides to locate the whole object. We collect three remote sensing object detection datasets with four categories to evaluate our method. Consistently surpassing the performance of state-of-the-art methods, the results of extensive experiments underscore the effectiveness and superiority of our proposed method.

A Prolonged Artificial Nighttime-light Dataset of China (1984-2020).

Nighttime light remote sensing has been an increasingly important proxy for human activities. Despite an urgent need for long-term products and pilot explorations in synthesizing them, the publicly available long-term products are limited. A Night-Time Light convolutional LSTM network is proposed and applied the network to produce a 1-km annual Prolonged Artificial Nighttime-light DAtaset of China (PANDA-China) from 1984 to 2020. Assessments between modeled and original images show that on average the RMSE reaches 0.73, the coefficient of determination (R2) reaches 0.95, and the linear slope is 0.99 at the pixel level, indicating a high confidence in the quality of generated data products. Quantitative and visual comparisons witness PANDA-China's superiority against other NTL datasets in its significantly longer NTL dynamics, higher temporal consistency, and better correlations with socioeconomics (built-up areas, gross domestic product, population) characterizing the most relevant indicator in different development phases. The PANDA-China product provides an unprecedented opportunity to trace nighttime light dynamics in the past four decades.

Verifying Quantum Advantage Experiments with Multiple Amplitude Tensor Network Contraction.

The quantum supremacy experiment, such as Google Sycamore [F. Arute et al., Nature (London) 574, 505 (2019).NATUAS0028-083610.1038/s41586-019-1666-5], poses a great challenge for classical verification due to the exponentially increasing compute cost. Using a new-generation Sunway supercomputer within 8.5 d, we provide a direct verification by computing 3×10^{6} exact amplitudes for the experimentally generated bitstrings, obtaining a cross-entropy benchmarking fidelity of 0.191% (the estimated value is 0.224%). The leap of simulation capability is built on a multiple-amplitude tensor network contraction algorithm which systematically exploits the "classical advantage" (the inherent "store-and-compute" operation mode of von Neumann machines) of current supercomputers, and a fused tensor network contraction algorithm which drastically increases the compute efficiency on heterogeneous architectures. Our method has a far-reaching impact in solving quantum many-body problems, statistical problems, as well as combinatorial optimization problems.

Spatially heterogeneous shifts in vegetation phenology induced by climate change threaten the integrity of the avian migration network.

Phenological responses to climate change frequently vary among trophic levels, which can result in increasing asynchrony between the peak energy requirements of consumers and the availability of resources. Migratory birds use multiple habitats with seasonal food resources along migration flyways. Spatially heterogeneous climate change could cause the phenology of food availability along the migration flyway to become desynchronized. Such heterogeneous shifts in food phenology could pose a challenge to migratory birds by reducing their opportunity for food availability along the migration path and consequently influencing their survival and reproduction. We develop a novel graph-based approach to quantify this problem and deploy it to evaluate the condition of the heterogeneous shifts in vegetation phenology for 16 migratory herbivorous waterfowl species in Asia. We show that climate change-induced heterogeneous shifts in vegetation phenology could cause a 12% loss of migration network integrity on average across all study species. Species that winter at relatively lower latitudes are subjected to a higher loss of integrity in their migration network. These findings highlight the susceptibility of migratory species to climate change. Our proposed methodological framework could be applied to migratory species in general to yield an accurate assessment of the exposure under climate change and help to identify actions for biodiversity conservation in the face of climate-related risks.

Toward Earth system modeling with resolved clouds and ocean submesoscales on heterogeneous many-core HPCs.

With the aid of the newly developed 'Sunway' heterogeneous-architecture supercomputer, which has world-leading HPC (high-performance computer) capability, a series of high-resolution coupled Earth system models (SW-HRESMs) with up to 5 km of atmosphere and 3 km of ocean have been developed. These models can meet the needs of multiscale interaction studies with different computational costs. Here we describe the progress of SW-HRESMs development, with an overview of the major advancements made by the international Earth science community in HR-ESMs. We also show the preliminary results of SW-HRESMs with regard to capturing major weather-climate extremes in the atmosphere and ocean, stressing the importance of permitted clouds and ocean submesoscale eddies in modeling tropical cyclones and eddy-mean flow interactions, and paving the way for further model development to resolve finer scales with even higher resolution and more realistic physics. Finally, in addition to increasing model resolution, the development procedure for a non-hydrostatic cloud and ocean submesoscale resolved ESM is discussed, laying out the major scientific directions of such a huge modeling advancement.

A global map of planting years of plantations.

Plantation is an important land use type that differs from natural forests and affects the economy and the environment. Tree age is one of the key factors used to quantify the impact of plantations. However, there is a lack of datasets explicitly documenting the planting years of global plantations. Here we used time-series Landsat archive from 1982 to 2020 and the LandTrendr algorithm to generate global maps of planting years based on the global plantation extent products in Google Earth Engine (GEE) platform. The datasets developed in this study are in a GeoTIFF format with 30-meter spatial resolution by recording gridded specie types and planting years of global plantations. The derived dataset could be used for yield prediction of tree crops and social and ecological cost-benefit analysis of plantations.

Annual dynamic dataset of global cropping intensity from 2001 to 2019.

The cropping intensity has received growing concern in the agriculture field in applications such as harvest area research. Notwithstanding the significant amount of existing literature on local cropping intensities, research considering global datasets appears to be limited in spatial resolution and precision. In this paper, we present an annual dynamic global cropping intensity dataset covering the period from 2001 to 2019 at a 250-m resolution with an average overall accuracy of 89%, exceeding the accuracy of the current annual dynamic global cropping intensity data at a 500-m resolution. We used the enhanced vegetation index (EVI) of MOD13Q1 as the database via a sixth-order polynomial function to calculate the cropping intensity. The global cropping intensity dataset was packaged in the GeoTIFF file type, with the quality control band in the same format. The dataset fills the vacancy of medium-resolution, global-scale annual cropping intensity data and provides an improved map for further global yield estimations and food security analyses.

Climatechange vs. Globalwarming: Characterizing Two Competing Climate Discourses on Twitter with Semantic Network and Temporal Analyses#.

Distinct perceptions of the global climate is one of the factors preventing society from achieving consensus or taking collaborative actions on this issue. The public has not even reached an agreement on the naming of the global concern, showing preference for either "climate change" or "global warming", and few previous studies have addressed these two competing discourses resulting from distinct climate concerns by differently linking numerous climate concepts. Based on the 6,662,478 tweets containing #climatechange or #globalwarming generated between 1 January 2009 and 31 December 2018, we constructed the semantic networks of the two discourses and examined their evolution over the decade. The findings indicate that climate change demonstrated a more scientific perspective and showed an attempt to condense climate discussions rather than diffuse the topic by frequently addressing sub-topics simultaneously. Global warming triggered more political responses and showed a greater connection with phenomena. Temporal analysis suggests that traditional political discussions were gradually fading in both discourses but more recently started to revive in the form of discourse alliance in the climate change discourse. The associations between global warming and weather abnormalitiessuddenly strengthened around 2012. Climate change is becoming more dominant than global warming in public discussions. Although two discourses have shown more similarities in the rank order of important climate concepts, apparent disagreements continue about how these concepts are associated. These findings lay the groundwork for researchers and communicators to narrow the discrepancy between diverse climate perceptions.

Managing nitrogen to restore water quality in China.

The nitrogen cycle has been radically changed by human activities1. China consumes nearly one third of the world's nitrogen fertilizers. The excessive application of fertilizers2,3 and increased nitrogen discharge from livestock, domestic and industrial sources have resulted in pervasive water pollution. Quantifying a nitrogen 'boundary'4 in heterogeneous environments is important for the effective management of local water quality. Here we use a combination of water-quality observations and simulated nitrogen discharge from agricultural and other sources to estimate spatial patterns of nitrogen discharge into water bodies across China from 1955 to 2014. We find that the critical surface-water quality standard (1.0 milligrams of nitrogen per litre) was being exceeded in most provinces by the mid-1980s, and that current rates of anthropogenic nitrogen discharge (14.5 ± 3.1 megatonnes of nitrogen per year) to fresh water are about 2.7 times the estimated 'safe' nitrogen discharge threshold (5.2 ± 0.7 megatonnes of nitrogen per year). Current efforts to reduce pollution through wastewater treatment and by improving cropland nitrogen management can partially remedy this situation. Domestic wastewater treatment has helped to reduce net discharge by 0.7 ± 0.1 megatonnes in 2014, but at high monetary and energy costs. Improved cropland nitrogen management could remove another 2.3 ± 0.3 megatonnes of nitrogen per year-about 25 per cent of the excess discharge to fresh water. Successfully restoring a clean water environment in China will further require transformational changes to boost the national nutrient recycling rate from its current average of 36 per cent to about 87 per cent, which is a level typical of traditional Chinese agriculture. Although ambitious, such a high level of nitrogen recycling is technologically achievable at an estimated capital cost of approximately 100 billion US dollars and operating costs of 18-29 billion US dollars per year, and could provide co-benefits such as recycled wastewater for crop irrigation and improved environmental quality and ecosystem services.

PGAP-X: extension on pan-genome analysis pipeline.

BACKGROUND: Since PGAP (pan-genome analysis pipeline) was published in 2012, it has been widely employed in bacterial genomics research. Though PGAP has integrated several modules for pan-genomics analysis, how to properly and effectively interpret and visualize the results data is still a challenge. RESULT: To well present bacterial genomic characteristics, a novel cross-platform software was developed, named PGAP-X. Four kinds of data analysis modules were developed and integrated: whole genome sequences alignment, orthologous genes clustering, pan-genome profile analysis, and genetic variants analysis. The results from these analyses can be directly visualized in PGAP-X. The modules for data visualization in PGAP-X include: comparison of genome structure, gene distribution by conservation, pan-genome profile curve and variation on genic and genomic region. Meanwhile, result data produced by other programs with similar function can be imported to be further analyzed and visualized in PGAP-X. To test the performance of PGAP-X, we comprehensively analyzed 14 Streptococcus pneumonia strains and 14 Chlamydia trachomatis. The results show that, S. pneumonia strains have higher diversity on genome structure and gene contents than C. trachomatis strains. In addition, S. pneumonia strains might have suffered many evolutionary events, such genomic rearrangements, frequent horizontal gene transfer, homologous recombination, and other evolutionary process. CONCLUSION: Briefly, PGAP-X directly presents the characteristics of bacterial genomic diversity with different visualization methods, which could help us to intuitively understand dynamics and evolution in bacterial genomes. The source code and the pre-complied executable programs are freely available from http://pgapx.ybzhao.com .

Solving global shallow water equations on heterogeneous supercomputers.

The scientific demand for more accurate modeling of the climate system calls for more computing power to support higher resolutions, inclusion of more component models, more complicated physics schemes, and larger ensembles. As the recent improvements in computing power mostly come from the increasing number of nodes in a system and the integration of heterogeneous accelerators, how to scale the computing problems onto more nodes and various kinds of accelerators has become a challenge for the model development. This paper describes our efforts on developing a highly scalable framework for performing global atmospheric modeling on heterogeneous supercomputers equipped with various accelerators, such as GPU (Graphic Processing Unit), MIC (Many Integrated Core), and FPGA (Field Programmable Gate Arrays) cards. We propose a generalized partition scheme of the problem domain, so as to keep a balanced utilization of both CPU resources and accelerator resources. With optimizations on both computing and memory access patterns, we manage to achieve around 8 to 20 times speedup when comparing one hybrid GPU or MIC node with one CPU node with 12 cores. Using a customized FPGA-based data-flow engines, we see the potential to gain another 5 to 8 times improvement on performance. On heterogeneous supercomputers, such as Tianhe-1A and Tianhe-2, our framework is capable of achieving ideally linear scaling efficiency, and sustained double-precision performances of 581 Tflops on Tianhe-1A (using 3750 nodes) and 3.74 Pflops on Tianhe-2 (using 8644 nodes). Our study also provides an evaluation on the programming paradigm of various accelerator architectures (GPU, MIC, FPGA) for performing global atmospheric simulation, to form a picture about both the potential performance benefits and the programming efforts involved.