Design of a Forest Fire Early Alert System through a Deep 3D-CNN Structure and a WRF-CNN Bias Correction.

Throughout the years, wildfires have negatively impacted ecological systems and urban areas. Hence, reinforcing territorial risk management strategies against wildfires is essential. In this study, we built an early alert system (EAS) with two different Machine Learning (ML) techniques to calculate the meteorological conditions of two Colombian areas: (i) A 3D convolutional neural net capable of learning from satellite data and (ii) a convolutional network to bias-correct the Weather Research and Forecasting (WRF) model output. The results were used to quantify the daily Fire Weather Index and were coupled with the outcomes from a land cover analysis conducted through a Naïve-Bayes classifier to estimate the probability of wildfire occurrence. These results, combined with an assessment of global vulnerability in both locations, allow the construction of daily risk maps in both areas. On the other hand, a set of short-term preventive and corrective measures were suggested to public authorities to implement, after an early alert prediction of a possible future wildfire. Finally, Soil Management Practices are proposed to tackle the medium- and long-term causes of wildfire development, with the aim of reducing vulnerability and promoting soil protection. In conclusion, this paper creates an EAS for wildfires, based on novel ML techniques and risk maps.

Validation of PM10 and PM2.5 early alert in Bogotá, Colombia, through the modeling software WRF-CHEM.

Air quality data from Bogotá, Colombia, show high levels of particulate matter (PM), which often generate respiratory problems to the population and a high economic cost to the government. Since 2016, air quality in the city of Bogotá has been measured through the Bogota Air Quality Index (IBOCA) which works as an indicator of environmental risk due to air pollution. However, available technological tools in Bogotá are not enough to generate early alerts due to PM10 and PM2.5. Currently, alerts are only announced once the measured PM values exceed a certain standard (e.g., 37 µ g/m3), but not with enough anticipation to efficiently protect the population. It is necessary to develop an early air quality alert in Bogotá, in order to provide information that improves risk management protocols in the capital district. The purpose of this investigation is to validate the corrective alert presented on the 14th and 15th of February of 2019, through the WRF-Chem model under different weather conditions, using three different setups of the model to simulate PM10 and PM2.5 concentrations during two different climatic seasons and different resolutions. The results of this article generate a validation of two configurations of the model that can be used for the Environmental Secretary of the District (SDA) forecasts in Bogotá, Colombia, in order to contribute to the prediction of pollution events produced by PM10 and PM2.5 as a tool for an early alert system (EAS) at least 24 h in advance.

Compassion-focused imagery reduces shame and is moderated by shame, self-reassurance and multisensory imagery vividness.

Compassion-focused imagery (CFI) is an emotion-regulation technique involving visualization of a person, animal or object offering one compassion, to generate feelings of safeness. It is proven to increase self-compassion and reduce negative affect. This study explores two hypotheses not previously investigated: i) which sensory modalities can stimulate compassionate affect; and ii) whether presentation of pictorial stimuli can enhance CFI. Additionally, we examine iii) whether CFI can reduce shame and iv) whether self-criticism inhibits CFI, since previous studies have involved small samples or methodological limitations. After completing measures of self-criticism, selfreassurance and imagery abilities in five sensory modalities, participants (n=160) were randomly assigned to look at compassionate images during CFI (visual input), compassionate images before CFI (priming), or abstract images (control). Participants trialled CFI then rated compassionate affect and completed open-response questions. Before and after CFI, participants recalled a shame-based memory and rated state shame. Correlational analyses explored whether self-criticism, self-reassurance, and multisensory imagery abilities moderated outcomes. CFI significantly reduced shame regarding a recalled memory, particularly for those high in shame. Compassionate affect was predicted by imagery vividness in visual and bodily-sensation modalities. Self-criticism predicted poorer CFI In multiple regressions, self-reassurance predicted poorer CFI outcomes but self-criticism did not. Between-group effects did not emerge. Qualitative data suggested that pictures helped some participants but hindered others. CFI is a promising technique for shame-prone clients, but may be challenging for those with low imagery abilities or unfamiliar with self-reassurance. Multiple senses should be engaged.