The amount of real-time communication between agents in an information system has increased rapidly since the beginning of the decade. This is because the use of these systems, e.g. social media, ...has become commonplace in today’s society. This requires analytical algorithms to learn and predict this stream of information in real-time. The nature of these systems is non-static and can be explained, among other things, by the fast pace of trends. This creates an environment in which algorithms must recognize changes and adapt. Recent work shows vital research in the field, but mainly lack stable performance during model adaptation. In this work, a concept drift detection strategy followed by a prototype-based adaptation strategy is proposed. Validated through experimental results on a variety of typical non-static data, our solution provides stable and quick adjustments in times of change.
Semi‐natural grasslands represent ecosystems with high biodiversity. Their conservation depends on the removal of biomass, for example, through grazing by livestock or wildlife. For this, spatially ...explicit information about grassland forage quantity and quality is a prerequisite for efficient management. The recent advancements of the Sentinel satellite mission offer new possibilities to support the conservation of semi‐natural grasslands. In this study, the combined use of radar (Sentinel‐1) and multispectral (Sentinel‐2) data to predict forage quantity and quality indicators of semi‐natural grassland in Germany was investigated. Field data for organic acid detergent fibre concentration (oADF), crude protein concentration (CP), compressed sward height (CSH) and standing biomass dry weight (DM) collected between 2015 and 2017 were related to remote sensing data using the random forest regression algorithm. In total, 102 optical‐ and radar‐based predictor variables were used to derive an optimized dataset, maximizing the predictive power of the respective model. High R2 values were obtained for the grassland quality indicators oADF (R2 = 0.79, RMSE = 2.29%) and CP (R2 = 0.72, RMSE = 1.70%) using 15 and 8 predictor variables respectively. Lower R2 values were achieved for the quantity indicators CSH (R2 = 0.60, RMSE = 2.77 cm) and DM (R2 = 0.45, RMSE = 90.84 g/m²). A permutation‐based variable importance measure indicated a strong contribution of simple ratio‐based optical indices to the model performance. In particular, the ratios between the narrow near‐infrared and red‐edge region were among the most important variables. The model performance for oADF, CP and CSH was only marginally increased by adding Sentinel‐1 data. For DM, no positive effect on the model performance was observed by combining Sentinel‐1 and Sentinel‐2 data. Thus, optical Sentinel‐2 data might be sufficient to accurately predict forage quality, and to some extent also quantity indicators of semi‐natural grassland.
Radar (Sentinel‐1) and multispectral (Sentinel‐2) data were evaluated for mapping semi‐natural grassland forage quantity and quality indicators in Germany. The predictor dataset was optimized using permutation‐based variable importance, maximizing the predictive power of the random forest regression models. Simple ratios between the narrow near‐infrared and red‐edge region were among the most important variables. The model performance was only marginally increased by including Sentinel‐1 data.
Life science data are often encoded in a non-standard way by means of alpha-numeric sequences, graph representations, numerical vectors of variable length, or other formats. Domain-specific or ...data-driven similarity measures like alignment functions have been employed with great success. The vast majority of more complex data analysis algorithms require fixed-length vectorial input data, asking for substantial preprocessing of life science data. Data-driven measures are widely ignored in favor of simple encodings. These preprocessing steps are not always easy to perform nor particularly effective, with a potential loss of information and interpretability. We present some strategies and concepts of how to employ data-driven similarity measures in the life science context and other complex biological systems. In particular, we show how to use data-driven similarity measures effectively in standard learning algorithms.
Following the dissolution of the Soviet Union, agricultural reforms in Central Asia often translated into the fragmentation of large fields into smaller shares. Most remote-sensing-based land use ...classification approaches are categorical in nature, and thus they are unable to capture these changes. We have developed an approach to detecting the timing of land fragmentation based on textural information from a time series of Landsat images for four Central Asian countries (Uzbekistan, Turkmenistan, Kyrgyzstan and Tajikistan) between 1990 and 2019. Our results showed that detected fragmentation events correspond well with documented agrarian reform processes in the different countries, and validation yielded maximum overall accuracies between 67 and 73%. In a case study of a former collective farm in Kyrgyzstan, we demonstrate how our method can accurately detect changes on the local scale. Texture time series data have great potential for analysing the trajectories of cropland fragmentation, in particular in regions where additional information on land use is limited.
•First time cropland fragmentation analysis for Central Asia using Landsat data.•New approach to detect the timing of land fragmentation based on textural information.•Degree and timing of cropland fragmentation resulting from national land reforms can vary considerably within a country.
Blazars have long been considered as accelerator candidates for cosmic rays. In such a scenario, hadronic interactions in the jet would produce neutrinos and gamma rays. Correlating the astrophysical ...neutrinos detected by IceCube with the gamma-ray emission from blazars could therefore help elucidate the origin of cosmic rays. In our method we focus on periods where blazars show an enhanced gamma-ray flux, as measured by Fermi-LAT, thereby reducing the background of the search. We present results for TXS 0506+056, using nearly 10 years of IceCube data and discuss them in the context of other recent analyses on this source. In addition, we give an outlook on applying this method in a stacked search for the combined emission from a selection of variable Fermi blazars.
Land cover mapping can be seen as a key element to understand the spatial distribution of habitats and thus to sustainable management of natural resources. Multi-temporal remote sensing data are a ...valuable data source for land cover mapping. However, the increased amount of data requires effective machine learning algorithms and data compression approaches. In this study, the Random Forest and C 5.0 classification algorithms were applied to (1) a multi-temporal Tasselled-Cap-transformed, (2) top of atmosphere and (3) surface reflectance RapidEye time-series. The overall accuracies ranged from 91.44% to 91.80%, with only minor differences between algorithms and datasets. The McNemar test showed, however, significant differences between the Tasselled-Cap-transformed and untransformed mapping results in most cases. The temporal profiles for the Tasselled-Cap-transformed RapidEye data indicated a good separability between considered classes. The phenological profiles of vegetated surfaces followed a typical green-up curve for the Greenness Tasselled-Cap-index. A permutation-based variable importance measure indicated that late autumn should be considered as most important phenological phase contributing to the classification model performance. The results suggested that the RapidEye Tasselled Cap Transformation, which was designed for agricultural applications, can be an effective data compression tool, suitable to map heterogeneous landscapes with no measurable negative impact on classification accuracy.
We present a simple method for narrowing the intrinsic Lorentzian linewidth of a commercial ultraviolet grating extended-cavity diode laser (TOPTICA DL Pro) using weak optical feedback from a long ...external cavity. We achieve a suppression in frequency noise spectral density of 20 dB measured at frequencies around 1 MHz, corresponding to the narrowing of the intrinsic Lorentzian linewidth from 200 kHz to 2 kHz. Provided additional active low-frequency noise suppression and long-term drift compensation, the system is suitable for experiments requiring a tunable ultraviolet laser with narrow linewidth and low high-frequency noise, such as precision spectroscopy, optical clocks, and quantum information science experiments.
Under extensive grazing, a mosaic pattern of frequently defoliated short patches and rarely defoliated tall patches is often formed. The agronomic and ecological consequences of this patch‐grazing ...pattern strongly depend on its stability between successive years. We assessed patch structure and temporal stability under three intensities of cattle stocking (moderate, lenient and very lenient) in a cattle grazing experiment established in 2002. Aerial images of the whole area taken in 2005, 2010, 2013 and 2015 were classified into short and tall patches using random forest classification. These were complemented by annual sward height measurements (2007‐2017) at 10 permanent plots per paddock, which were classified into sward height classes. The mean proportion (0.72, 0.32, 0.19) and size of short patches decreased with stocking intensity, while size of tall patches increased. Inter‐annual stability depended on patch type and stocking intensity and was particularly high for the respective dominant patch type. Of the short patch area in 2015, 0.62, 0.29 and 0.30 were classified as short in all four aerial images under moderate, lenient and very lenient grazing, respectively; the corresponding proportions for tall patches were 0.10, 0.53 and 0.65. Our results imply that short and tall patches experience persistent differences in local grazing intensity over extended periods. The long‐term effects of this heterogeneity on soil properties and vegetation composition need to be monitored to assess agronomic sustainability and ecological potential of patch‐grazed pastures.
•Adopting Invariant Kernel Transfer Learning for sparse models.•Nyström based Basis Transfer for performance improvements by means of prediction and computational time.•A variety of experimental ...results is provided showing the efficiency of the proposed approach.
Transfer learning is focused on the reuse of supervised learning models in a new context. Prominent applications can be found in robotics, image processing or web mining. In these fields, the learning scenarios are naturally changing but often remain related to each other motivating the reuse of existing supervised models. Current transfer learning models are neither sparse nor interpretable. Sparsity is very desirable if the methods have to be used in technically limited environments and interpretability is getting more critical due to privacy regulations. In this work, we propose two transfer learning extensions integrated into the sparse and interpretable probabilistic classification vector machine. They are compared to standard benchmarks in the field and show their relevance either by sparsity or performance improvements.