Abstract
<p>The Dansgaard-Oeschger (DO) events are one of the most striking examples of abrupt climate change in the Earth's history, representing temperature oscillations of about 8 to 16 degrees Celsius within a few decades. DO events have been studied extensively in paleoclimatic records, particularly in ice core proxies. Examples include the Greenland NGRIP record of oxygen isotopic composition.<br>This work addresses the anticipation of DO events using machine learning algorithms. We consider the NGRIP time series from 20 to 60 kyr b2k with the GICC05 timescale and 20-year temporal resolution. Forecasting horizons range from 0 (nowcasting) to 400 years. We adopt three different machine learning algorithms (random forests, support vector machines, and logistic regression) in training windows of 5 kyr. We perform validation on subsequent test windows of 5 kyr, based on timestamps of previous DO events' classification in Greenland by Rasmussen et al. (2014). We perform experiments with both sliding and growing windows.<br>Results show that predictions on sliding windows are better overall, indicating that modelling is affected by non-stationary characteristics of the time series. The three algorithms' predictive performance is similar, with a slightly better performance of random forest models for shorter forecast horizons. The prediction models' predictive capability decreases as the forecasting horizon grows more extensive but remains reasonable up to 120 years. Model performance deprecation is mostly related to imprecision in accurately determining the start and end time of events and identifying some periods as DO events when such is not valid.</p>

Abstract

Abstract
The technological revolution that we have been witnessing recently has allowed components miniaturization and made electronic components accessible. Hyperspectral sensors benefited from these advances and could be mounted on unmanned aerial vehicles, which was unthinkable until recently. This fact significantly increased the applications of hyperspectral data, namely in agriculture, especially in the detection of diseases at an early stage. The vineyard is one of the agricultural sectors that has the most to gain from the use of this type of data, both by the economic value and by the number of diseases the plants are exposed to. The Flavescense dorée is a disease that attacks vineyards and may conduct to a significant loss. Nowadays, the detection of this disease is based on the visual identification of symptoms performed by experts who cover the entire area. However, this work remains tedious and relies only on the human eye, which is a problem since sometimes healthy plants are torn out, while diseased ones are left. If the experts think they have found symptoms, they take samples to send to the laboratory for further analysis. If the test is positive, then the whole vine is uprooted, to limit the spread of the disease. In this context, the use of hyperspectral data will allow the development of new disease detection methods. However, it will be necessary to reduce the volume of data used to make them usable by conventional resources. Fortunately, the advent of machine learning techniques empowered the development of systems that allow better decisions to be made, and consequently save time and money. In this article, a machine learning approach, which is based on an Autoencoder to automatically detect wine disease, is proposed.

Abstract
Engagement plays a key role for most organizations. Establishing close relationships with consumers and other stakeholders - thus promoting their loyalty and participation in the value creation process - has become an element of competitive advantage. Extant literature has focused consumer-brands relationships in commercial contexts; yet, when it comes to non-commercial or non-profit contexts - where communities of decidedly engaged individuals voluntarily invest their time and energy to a cause - research is still in its infancy. This study sets out to understand how non-profit organizations (NPO) can generate a sense of engagement among volunteers and which volunteers' behaviours - associated with that psychological state - entice value co-creation with NPO. Group interviews were carried out with volunteers to gain insights on drivers and outcomes of Volunteer Engagement (VE). Value congruence between volunteers and NPO, a sense of community, as well as perceptions of competence and autonomy, were identified as drivers of VE. The study further validated the impact of VE not only on somewhat predictable outcomes, such as NPO loyalty and advocacy, but also on the co-creation of value with NPO through the recruitment of new volunteers and the development of new ideas for service innovation.

Abstract
<p>Air ions are ubiquitous in the atmosphere. These charge carriers can be found in various forms as charged molecules, nanoclusters as well as aerosol particles. The population of air ions normally concentrates in the cluster size range (0.8 – 1.7 nm in mobility equivalent diameters) in the absence of particle formation processes. A concentration burst in the intermediate size range (1.7 – 7 nm) can be typically observed during atmospheric new particle formation (NPF) and in precipitation episodes <sup>1</sup>. Contrary to the intermediate ions formed during NPF that favour growth to larger sizes, intermediate ion bursts resulting from precipitation tend to shrink <sup>2,3</sup>. The production of intermediate ions during precipitation has been attributed to the Lenard effect and they are usually referred to as the balloelectric ions <sup>3</sup>.</p><p>During precipitation the rain-out and wash-out of radon progeny increase the gamma dose at ground level <sup>4</sup>. Being a type of ionising radiation, gamma creates positive and negative charges in the air. These charges are either lost in recombination or transformed into air ions. It is therefore interesting to understand whether the precipitation-associated elevation in gamma radiation plays any role in forming or neutralising the balloelectric ions. At SMEAR II station in Hyytiälä, Finland <sup>5</sup>, we have conducted measurements of air ions, gamma radiation, precipitation together with other meteorological parameters. A similar establishment of the measurement set stands also at SMEAR Estonia station in Jarvseljä, Estonia <sup>6</sup>. The data collected at Hyytiälä from 2017.7 to 2018.8 show that the intermediate ion concentration correlates with rainfall only when the precipitation intensity is greater than 1 mm/h. For milder rainfall with the precipitation intensity being 0.1-1 mm/h, the intermediate ion concentration increases with an increase in the gamma counts. The work is under progress and we intend to extend the analysis to Jarvseljä data for a comprehensive understanding of the observations.</p><p>Acknowledgements: This work received financial supports from European Regional Development Fund (project MOBTT42) under the Mobilitas Pluss programme and from Estonian Research Council project PRG714.</p><p>References:</p><p>1. Tammet, H., Komsaare, K. & Hõrrak, U. Intermediate ions in the atmosphere. Atmospheric Research <strong>135-136</strong>, 263-273, doi:10.1016/j.atmosres.2012.09.009 (2014).</p><p>2. Hõrrak, U. et al. Formation of Charged Nanometer Aerosol Particles Associated with Rainfall: Atmospheric Measurements and Lab Experiment. Report Series in Aerosol Science <strong>80</strong>, 180-185 (2006).</p><p>3. Tammet, H., Hõrrak, U. & Kulmala, M. Negatively charged nanoparticles produced by splashing of water. Atmos. Chem. Phys. <strong>9</strong>, 357–367 (2009).</p><p>4. Paatero, J. & Hatakka, J. Wet deposition efficiency of short-lived radon-222 progeny in central Finland. Boreal Env. Res. <strong>4</strong>, 285-293 (1999).</p><p>5. Hari, P. & Kulmala, M. Station for measuring ecosystem-atmosphere relations (SMEAR II). Boreal Environ. Res. <strong>10</strong>, 315-322 (2005).</p><p>6. Noe, S. M. et al. SMEAR Estonia: Perspectives of a large-scale forest ecosystem – atmosphere research infrastructure. Forestry Studies <strong>63</strong>, doi:10.1515/fsmu-2015-0009 (2015).</p>

Abstract