Textural classification of land cover using support vector machines: an empirical comparison with parametric, non parametric and hybrid classifiers in the Bolivian Amazon

Land cover classification is a key research field in remote sensing and land change science as thematic maps derived from remotely sensed data have become the basis for analyzing many socio-ecological issues. However, land cover classification remains a difficult task and it is especially challenging in heterogeneous tropical landscapes where nonetheless such maps are of great importance. The present study aims to establish an efficient classification approach to accurately map all broad land cover classes in a large, heterogeneous tropical area of Bolivia, as a basis for further studies (e.g., land cover-land use change). Specifically, we compare the performance of parametric (maximum likelihood), non-parametric (k-nearest neighbour and four different support vector machines - SVM), and hybrid classifiers, using both hard and soft (fuzzy) accuracy assessments. In addition, we test whether the inclusion of a textural index (homogeneity) in the classifications improves their performance. We classified Landsat imagery for two dates corresponding to dry and wet seasons and found that non-parametric, and particularly SVM classifiers, outperformed both parametric and hybrid classifiers. We also found that the use of the homogeneity index along with reflectance bands significantly increased the overall accuracy of all the classifications, but particularly of SVM algorithms. We observed that improvements in producer’s and user’s accuracies through the inclusion of the homogeneity index were different depending on land cover classes. Earlygrowth/degraded forests, pastures, grasslands and savanna were the classes most improved, especially with the SVM radial basis function and SVM sigmoid classifiers, though with both classifiers all land cover classes were mapped with producer’s and user’s accuracies of around 90%. Our approach seems very well suited to accurately map land cover in tropical regions, thus having the potential to contribute to conservation initiatives, climate change mitigation schemes such as REDD+, and rural development policies.

Cross recurrence quantification for cover song identification

There is growing evidence that nonlinear time series analysis techniques can be used to successfully characterize, classify, or process signals derived from realworld dynamics even though these are not necessarily deterministic and stationary. In the present study we proceed in this direction by addressing an important problem our modern society is facing, the automatic classification of digital information. In particular, we address the automatic identification of cover songs, i.e. alternative renditions of a previously recorded musical piece. For this purpose we here propose a recurrence quantification analysis measure that allows tracking potentially curved and disrupted traces in cross recurrence plots. We apply this measure to cross recurrence plots constructed from the state space representation of musical descriptor time series extracted from the raw audio signal. We show that our method identifies cover songs with a higher accuracy as compared to previously published techniques. Beyond the particular application proposed here, we discuss how our approach can be useful for the characterization of a variety of signals from different scientific disciplines. We study coupled Rössler dynamics with stochastically modulated mean frequencies as one concrete example to illustrate this point.

Predictability of music descriptor time series and its application to cover song detection

Intuitively, music has both predictable and unpredictable components. In this work we assess this qualitative statement in a quantitative way using common time series models fitted to state-of-the-art music descriptors. These descriptors cover different musical facets and are extracted from a large collection of real audio recordings comprising a variety of musical genres. Our findings show that music descriptor time series exhibit a certain predictability not only for short time intervals, but also for mid-term and relatively long intervals. This fact is observed independently of the descriptor, musical facet and time series model we consider. Moreover, we show that our findings are not only of theoretical relevance but can also have practical impact. To this end we demonstrate that music predictability at relatively long time intervals can be exploited in a real-world application, namely the automatic identification of cover songs (i.e. different renditions or versions of the same musical piece). Importantly, this prediction strategy yields a parameter-free approach for cover song identification that is substantially faster, allows for reduced computational storage and still maintains highly competitive accuracies when compared to state-of-the-art systems.

Chroma binary similarity and local alignment applied to cover song identification

We present a new technique for audio signal comparison based on tonal subsequence alignment and its application to detect cover versions (i.e., different performances of the same underlying musical piece). Cover song identification is a task whose popularity has increased in the Music Information Retrieval (MIR) community along in the past, as it provides a direct and objective way to evaluate music similarity algorithms.This article first presents a series of experiments carried outwith two state-of-the-art methods for cover song identification.We have studied several components of these (such as chroma resolution and similarity, transposition, beat tracking or Dynamic Time Warping constraints), in order to discover which characteristics would be desirable for a competitive cover song identifier. After analyzing many cross-validated results, the importance of these characteristics is discussed, and the best-performing ones are finally applied to the newly proposed method. Multipleevaluations of this one confirm a large increase in identificationaccuracy when comparing it with alternative state-of-the-artapproaches.

Reconstructing snow avalanches in the Southeastern Pyrenees

A regional study of snow avalanche processes was undertaken in the SE Pyrenees. Dendrogeomorphology was used to date and reconstruct large-scale snow avalanche events that occurred in the last four decades. Dendrochronological analyses yielded the dates of nine winters when avalanches occurred in the recent past in six studied avalanche paths. Some of these avalanches were already known, but others had not been documented. In one case, the existing avalanche path map was improved with the dendrogeomorphological information of a larger past event. As a result of the dendrogeomorphological analyses, evidence for three regional-scale major avalanche years was identified in the SE Pyrenees from 1971 to 2004: 1971¿1972, 1995¿1996 and 2002¿2003. The specific synoptic atmospheric situations and the most likely nivometeorological and snowpack conditions that released these major avalanches were determined using weather data for the seasons of major avalanche releases. In 1971¿1972 the snow avalanche episode was characterized by a deep trough crossing the Pyrenees. In 1995¿1996 a variety of meteorological situations produced several episodes of major avalanches. In 2002¿2003 the more significant of two episodes was attributed to a north advection pumping an arctic air mass over the Pyrenees. The 1995¿1996 avalanche season proved to be the most notable in the four past decades in the Pyrenees.

On the complementariness of infrasound and seismic sensors for monitoring snow avalanches

The paper analyses and compares infrasonic and seismic data from snow avalanches monitored at the Vallée de la Sionne test site in Switzerland from 2009 to 2010. Using a combination of seismic and infrasound sensors, it is possible not only to detect a snow avalanche but also to distinguish between the different flow regimes and to analyse duration, average speed (for sections of the avalanche path) and avalanche size. Different sensitiveness of the seismic and infrasound sensors to the avalanche regimes is shown. Furthermore, the high amplitudes observed in the infrasound signal for one avalanche were modelled assuming that the suspension layer of the avalanche acts as a moving turbulent sound source. Our results show reproducibility for similar avalanches on the same avalanche path.

Influence of emergence timing of weeds on the establishment of woody natives and ground cover species

Les invasions biològiques són produïdes per espècies transportades per l'home fora de la regió d'origen a altres regions on s'estableixen i expandeixen. Són actualment de les majors causes de perduda de biodiversitat, amb el canvi d'usos del sòl, tret rellevant en zones insulars. Comprendre mecanismes de competència amb les espècies autòctones és clau per gestionar el problema. L’experiment evidencia diferències de creixement de 7 plantes natives australianes (3 espècies d’eucaliptus, 3 espècies d’acàcia, 1 pasturatge natiu), competint intraespecífica (entre mateixa espècie) i interespecíficament (acàcies o eucaliptus convivint amb pasturatge natiu) plantejant tres tractaments (sense males herbes, males herbes i males herbes a posteriori) per definir la naturalesa de la interacció dels diferents tipus funcionals d'espècies. S’analitzen tendències temporals de creixement de plàntules, així com la supervivència. S’ha detectat una moderada correlació entre taxes de creixement d’espècies i mida de la llavor, (p ≈ 0.6), així com una correlació entre la supervivència i la humitat del sòl (p ≈ 0.5); efectes estacionals. A curt termini i en escenari de primavera la convivència amb males herbes reporta creixement nul. Tractaments sense males herbes, presenten major supervivència en escenaris en competència interespecífica. A llarg termini les espècies amb major supervivència són les que conviuen amb pasturatge natiu i sense males herbes, indicant un efecte beneficiós en espècies millor adaptades a la sequera (E. loxophleba).

The snow storm of the 8th of March 2010 in Barcelona: a paradigmatic case

A heavy precipitation event swept over Catalonia (NE Spain) on 8 March 2010, with a total amount that ex- ceeded 100mm locally and snowfall of more than 60cm near the coast. Unusual for this region and at this time of the year, this snowfall event affected mainly the coastal region and was accompanied by thunderstorms and strong wind gusts in some areas. Most of the damage was due to"wet snow", a kind of snow that favours accretion on power lines and causes line-breaking and subsequent interruption of the electricity supply. This paper conducts an interdisciplinary analysis of the event to show its great societal impact and the role played by the recently developed social networks (it has been called the first"Snowfall 2.0"), as well to analyse the meteorologi- cal factors associated with the major damage, and to propose an indicator that could summarise them. With this aim, the paper introduces the event and its societal impact and com- pares it with other important snowfalls that have affected the Catalan coast, using the PRESSGAMA database. The sec- ond part of the paper shows the event"s main meteorological features and analyses the near-surface atmospheric variables responsible for the major damage through the application of the SAFRAN (Système d"analyse fournissant des renseigne- ments atmosphériques à la neige) mesoscale analysis, which, together with the proposed"wind, wet-snow index" (WWSI), allows to estimate the severity of the event. This snow storm provides further evidence of our vulnerability to natural haz- ards and highlights the importance of a multidisciplinary ap- proach in analysing societal impact and the meteorological factors responsible for this kind of event.

Evaluation of a snow avalanche possibly triggered by a local earthquake at Vallée de la Sionne, Switzerland

Snow avalanches are moving sources of infrasonic and seismic energy. They can be triggered by many different mechanisms that include the shaking produced by earthquakes. The forces induced by an earthquake can cause an increase in the load down the slope and can also decrease the shear strength and both effects can cause the release of an avalanche. This phenomenon represents an important hazard associated with earthquakes in snow-covered mountain areas with high seismicity.