Refine
Has Fulltext
- no (4) (remove)
Document Type
- Article (4)
Language
- English (4) (remove)
Is part of the Bibliography
- yes (4)
Keywords
- machine (4) (remove)
The accelerating climatic changes and new infrastructure development across the Arctic require more robust risk and environmental assessment, but thus far there is no consistent record of human impact. We provide a first panarctic satellite-based record of expanding infrastructure and anthropogenic impacts along all permafrost affected coasts (100 km buffer, approximate to 6.2 Mio km(2)), named the Sentinel-1/2 derived Arctic Coastal Human Impact (SACHI) dataset. The completeness and thematic content goes beyond traditional satellite based approaches as well as other publicly accessible data sources. Three classes are considered: linear transport infrastructure (roads and railways), buildings, and other impacted area. C-band synthetic aperture radar and multi-spectral information (2016-2020) is exploited within a machine learning framework (gradient boosting machines and deep learning) and combined for retrieval with 10 m nominal resolution. In total, an area of 1243 km(2) constitutes human-built infrastructure as of 2016-2020. Depending on region, SACHI contains 8%-48% more information (human presence) than in OpenStreetMap. 221 (78%) more settlements are identified than in a recently published dataset for this region. 47% is not covered in a global night-time light dataset from 2016. At least 15% (180 km(2)) correspond to new or increased detectable human impact since 2000 according to a Landsat-based normalized difference vegetation index trend comparison within the analysis extent. Most of the expanded presence occurred in Russia, but also some in Canada and US. 31% and 5% of impacted area associated predominantly with oil/gas and mining industry respectively has appeared after 2000. 55% of the identified human impacted area will be shifting to above 0 C-circle ground temperature at two meter depth by 2050 if current permafrost warming trends continue at the pace of the last two decades, highlighting the critical importance to better understand how much and where Arctic infrastructure may become threatened by permafrost thaw.
Provisioning a sufficient stable source of food requires sound knowledge about current and upcoming threats to agricultural production. To that end machine learning approaches were used to identify the prevailing climatic and soil hydrological drivers of spatial and temporal yield variability of four crops, comprising 40 years yield data each from 351 counties in Germany. Effects of progress in agricultural management and breeding were subtracted from the data prior the machine learning modelling by fitting smooth non-linear trends to the 95th percentiles of observed yield data. An extensive feature selection approach was followed then to identify the most relevant predictors out of a large set of candidate predictors, comprising various soil and meteorological data. Particular emphasis was placed on studying the uniqueness of identified key predictors. Random Forest and Support Vector Machine models yielded similar although not identical results, capturing between 50% and 70% of the spatial and temporal variance of silage maize, winter barley, winter rapeseed and winter wheat yield. Equally good performance could be achieved with different sets of predictors. Thus identification of the most reliable models could not be based on the outcome of the model study only but required expert's judgement. Relationships between drivers and response often exhibited optimum curves, especially for summer air temperature and precipitation. In contrast, soil moisture clearly proved less relevant compared to meteorological drivers. In view of the expected climate change both excess precipitation and the excess heat effect deserve more attention in breeding as well as in crop modelling.
Social networking sites (SNS) are a rich source of latent information about individual characteristics. Crawling and analyzing this content provides a new approach for enterprises to personalize services and put forward product recommendations. In the past few years, commercial brands made a gradual appearance on social media platforms for advertisement, customers support and public relation purposes and by now it became a necessity throughout all branches. This online identity can be represented as a brand personality that reflects how a brand is perceived by its customers. We exploited recent research in text analysis and personality detection to build an automatic brand personality prediction model on top of the (Five-Factor Model) and (Linguistic Inquiry and Word Count) features extracted from publicly available benchmarks. Predictive evaluation on brands' accounts reveals that Facebook platform provides a slight advantage over Twitter platform in offering more self-disclosure for users' to express their emotions especially their demographic and psychological traits. Results also confirm the wider perspective that the same social media account carry a quite similar and comparable personality scores over different social media platforms. For evaluating our prediction results on actual brands' accounts, we crawled the Facebook API and Twitter API respectively for 100k posts from the most valuable brands' pages in the USA and we visualize exemplars of comparison results and present suggestions for future directions.
Optical flow models as an open benchmark for radar-based precipitation nowcasting (rainymotion v0.1)
(2019)
Quantitative precipitation nowcasting (QPN) has become an essential technique in various application contexts, such as early warning or urban sewage control. A common heuristic prediction approach is to track the motion of precipitation features from a sequence of weather radar images and then to displace the precipitation field to the imminent future (minutes to hours) based on that motion, assuming that the intensity of the features remains constant (“Lagrangian persistence”). In that context, “optical flow” has become one of the most popular tracking techniques. Yet the present landscape of computational QPN models still struggles with producing open software implementations. Focusing on this gap, we have developed and extensively benchmarked a stack of models based on different optical flow algorithms for the tracking step and a set of parsimonious extrapolation procedures based on image warping and advection. We demonstrate that these models provide skillful predictions comparable with or even superior to state-of-the-art operational software. Our software library (“rainymotion”) for precipitation nowcasting is written in the Python programming language and openly available at GitHub (https://github.com/hydrogo/rainymotion, Ayzel et al., 2019). That way, the library may serve as a tool for providing fast, free, and transparent solutions that could serve as a benchmark for further model development and hypothesis testing – a benchmark that is far more advanced than the conventional benchmark of Eulerian persistence commonly used in QPN verification experiments.