Detailed knowledge about tree species composition is of great importance for forest management. The two identical European Space Agency (ESA) Sentinel-2 (S2) satellites provide data with unprecedented spectral, spatial and temporal resolution. Here, we investigated the potential benefits of using high temporal resolution data for classification of five coniferous and seven broadleaved tree species in a diverse Central European Forest. To run the classification, 18 cloud-free S2 acquisitions were analyzed in a two-step approach. The available scenes were first used to stratify the study area into six broad land-cover classes. Subsequently, additional classification models were created separately for the coniferous and the broadleaved forest strata. To permit a deeper analytical insight in the benefits of multi-temporal datasets for species identification, classification models were developed taking into account all 262,143 possible permutations of the 18 S2 scenes. Each model was fine-tuned using a stepwise recursive feature reduction. The additional use of vegetation indices improved the model performances by around 5 percentage points. Individual mono-temporal tree species accuracies range from 48.1% (January 2017) to 78.6% (June 2017). Compared to the best mono-temporal results, the multi-temporal analysis approach improves the out-of-bag overall accuracy from 72.9% to 85.7% for the broadleaved and from 83.8% to 95.3% for the coniferous tree species, respectively. Remarkably, a combination of six–seven scenes achieves a model quality equally high as the model based on all data; images from April until August proved most important. The classes European Beech and European Larch attain the highest user’s accuracies of 96.3% and 95.9%, respectively. The most important spectral variables to distinguish between tree species are located in the Red (coniferous) and short wave infrared (SWIR) bands (broadleaved), respectively. Overall, the study highlights the high potential of multi-temporal S2 data for species-level classifications in Central European forests.
In this paper a new approach for polyphonic piano note onset transcription is presented. It is based on a recurrent neural network to simultaneously detect the onsets and the pitches of the notes from spectral features. Long Short-Term Memory units are used in a bidirectional neural network to model the context of the notes. The use of a single regression output layer instead of the often used one-versus-all classification approach enables the system to significantly lower the number of erroneous note detections. Evaluation is based on common test sets and shows exceptional temporal precision combined with a significant boost in note transcription performance compared to current state-of-the-art approaches. The system is trained jointly with various synthesized piano instruments and real piano recordings and thus generalizes much better than existing systems.
Higgs couplings can be affected by physics beyond the Standard Model. We study modifications through interactions with a hidden sector and in specific composite Higgs models accessible at the LHC. Both scenarios give rise to congruent patterns of universal, or partially universal, shifts. In addition, Higgs decays to the hidden sector may lead to invisible decay modes which we also exploit. Experimental bounds on such potential modifications will measure the concordance of an observed Higgs boson with the Standard Model.
With climate change, extreme storms are expected to occur more frequently. These storms can cause severe forest damage, provoking direct and indirect economic losses for forestry. To minimize economic losses, the windthrow areas need to be detected fast to prevent subsequent biotic damage, for example, related to beetle infestations. Remote sensing is an efficient tool with high potential to cost-efficiently map large storm affected regions. Storm Niklas hit South Germany in March 2015 and caused widespread forest cover loss. We present a two-step change detection approach applying commercial very high-resolution optical Earth Observation data to spot forest damage. First, an object-based bi-temporal change analysis is carried out to identify windthrow areas larger than 0.5 ha. For this purpose, a supervised Random Forest classifier is used, including a semi-automatic feature selection procedure; for image segmentation, the large-scale mean shift algorithm was chosen. Input features include spectral characteristics, texture, vegetation indices, layer combinations and spectral transformations. A hybrid-change detection approach at pixel-level subsequently identifies small groups of fallen trees, combining the most important features of the previous processing step with Spectral Angle Mapper and Multivariate Alteration Detection. The methodology was evaluated on two test sites in Bavaria with RapidEye data at 5 m pixel resolution. The results regarding windthrow areas larger than 0.5 ha were validated with reference data from field visits and acquired through orthophoto interpretation. For the two test sites, the novel object-based change detection approach identified over 90% of the windthrow areas (≥0.5 ha). The red edge channel was the most important for windthrow identification. Accuracy levels of the change detection at tree level could not be calculated, as it was not possible to collect field data for single trees, nor was it possible to perform an orthophoto validation. Nevertheless, the plausibility and applicability of the pixel-based approach is demonstrated on a second test site.
Increases in extreme weather events associated with climate change have the potential to put currently healthy forests at risk. One option to minimize this risk is the application of forest management measures aimed at generating species mixtures predicted to be more resilient to these threats. In order to apply such measures appropriately, forest managers need up-to-date, accurate and consistent forest maps at relatively fine spatial resolutions. Cost efficiency is a major factor when creating such maps. Taking European spruce (Picea abies) and Scots pine (Pinus sylvestris) as an example, this paper describes an innovative approach for mapping two tree species using a combination of commercial very high resolution WorldView-2 (WV2) images and Landsat time series data. As a first step, this study used a supervised object-based classification of WV2 images covering relatively small test sites distributed across the region of interest. Using these classification maps as training data, wall-to-wall mapping of fractional coverages of spruce and pine was achieved using multi-temporal Landsat data and Random Forests (RF) regression. The method was applied for the entire state of Bavaria (Germany), which comprises a total forested area of approximately 26,000 km 2. As applied here, this two-step approach yields consistent and accurate maps of fractional tree cover estimates with a spatial resolution of 1 ha. Independent validation of the fractional cover estimates using 3780 reference samples collected through visual interpretation of orthophotos produced root-mean-square errors (RMSE) of 11% (for spruce) and 14% (for pine) with almost no bias, and R 2 values of 0.74 and 0.79 for spruce and pine, respectively. The majority of the validation samples (75% (spruce) and 84% (pine)) were modeled within the assumed uncertainty of ± 15% of the reference sample. Accuracies were significantly better compared to those achieved using a single-step classification of Landsat time series data at the pixel level (30 m), because the two-step approach better captures regional variation in the spectral signatures of target classes. Moreover, the increased number of available reference cells mitigates the impact of occasional errors in the reference data set. This two-step approach has great potential for cost-effective operational mapping of dominant forest types over large areas. 1. Introduction Climate change is expected to have an important influence on future growing conditions that will likely have a great impact on tree species. Depending on the location, some trees species will benefit, for example, from increasing temperatures and thus, extended vegetation periods. However, at other locations, increased temperatures are likely to lead to water stress, and hence, greater vulnerability of some tree species to abiotic and biotic disturbances (Lindner et al., 2010). In Central Europe, several coniferous tree species are of particular concern: the vulnerability of tree species such as European spruce and Scots pine is particularly hig...
We investigate a late-fusion approach to piano transcription, combined with a strong temporal prior in the form of a handcrafted Hidden Markov Model (HMM). The network architecture under consideration is compact in terms of its number of parameters and easy to train with gradient descent. The network outputs are fused over time in the final stage to obtain note segmentations, with an HMM whose transition probabilities are chosen based on a model of attack, decay, sustain, release (ADSR) envelopes, commonly used for sound synthesis. The note segments are then subject to a final binary decision rule to reject too weak note segment hypotheses. We obtain state-of-the-art results on the MAPS dataset, and are able to outperform other approaches by a large margin, when predicting complete note regions from onsets to offsets.
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.